US20010001851A1 - Database wizard - Google Patents
Database wizard Download PDFInfo
- Publication number
- US20010001851A1 US20010001851A1 US09/753,595 US75359501A US2001001851A1 US 20010001851 A1 US20010001851 A1 US 20010001851A1 US 75359501 A US75359501 A US 75359501A US 2001001851 A1 US2001001851 A1 US 2001001851A1
- Authority
- US
- United States
- Prior art keywords
- component
- information
- user
- predictive maintenance
- database
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Abandoned
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
Definitions
- the present invention relates generally to predictive maintenance of machines. More particularly, it relates to establishing and executing predictive maintenance programs for machines.
- a highly specialized art commonly referred to as “predictive maintenance”, has evolved in an effort to predict when a machine will fail or requires maintenance so that corrective measures can be taken on an “as needed” basis.
- predictive maintenance In a typical predictive maintenance program, periodic inspections of the machinery are made in order to assess the current operating condition of the machine. Data collected during the periodic inspections is typically stored and trended over time as an additional measure of the machine's operational health.
- the periodic inspections often involve multiple technologies including oil sampling and analysis, infrared thermography analysis, and vibrational analysis. For example, vibrational analysis is usually accomplished with the aid of a portable instrument which senses and processes vibration generated by the machine.
- These portable instruments typically include a vibration transducer attached to what is essentially a highly specialized hand-held computer.
- the maintenance technician places the vibration transducer against a predefined test point of the machine.
- the resultant machine vibration signal produced by the transducer is provided to the data collector where the data is processed (and perhaps analyzed) according to predefined conditions and stored for later downloading to a machine database which has been previously set up on a host computer.
- the host computer analyzes the vibration data for faults or other anomalous conditions and machine data is stored in the database.
- Machines within a facility are typically monitored according to a route which is generated by a maintenance technician and programmed into the data collector with the aid of the host computer.
- the route typically includes a list of machines, measurement test points, and setup conditions for each test point.
- the hand held instrument In response to commands from the user, the hand held instrument prompts the user for the identity of the machine and the test point to be monitored, and it automatically sets up the instrument, for example, to accept the specified frequency range for the test point, perform the specified analysis and store the specified type or set of data.
- a Fast Fourier Transform analysis may be performed on a pre-selected frequency range of the data and all or part of the resulting frequency spectrum may be stored and displayed.
- the user progresses through the many machines and the corresponding test points, he collects and stores measured data which is subsequently transferred to the host computer for long term storage and further analysis.
- the user or maintenance technician defines each test point for each machine, including the location for each test point, analysis parameters sets including the type and quantity of data to take for each test point, the type of analysis to be performed on the data, frequency ranges, alarm levels, and the like.
- the locations of the test points and the parameters or settings chosen for each test point vary depending on the type, size and combinations of machines. For example, a motor driving a fan may have different test points and settings than the same motor driving a pump. Defining a predictive maintenance program of this type for such a large number of different machines requires a great deal of expertise on the part of the maintenance technician.
- Such expertise is typically gained only through years of experience and/or extensive training including training on how to select a probe/sensor, which parameters to measure for a particular machine, locations corresponding to the most data rich points for measuring particular parameters, frequency ranges, analysis alarm limits, and other such information.
- the maintenance technician must define the measurements points, analysis parameter sets, and alarm limit sets, and he must integrate these items into a useable database setup. Further complicating the maintenance technician's task is the fact that knowledge and expertise gained through the experience of engineers and technicians is too often not shared among users and others skilled in the art. More common is the situation where expertise is lost as a result of job changes and the like. Even when expertise is documented in user's manuals or lab notebooks, a great deal of studying and understanding is required in order for the information to be put to proper use.
- the solution should include the integration of machine database setup with the use of multiple measurement technologies, and it should be capable of pooling the scattered expertise of predictive maintenance modelers and significantly reducing the level of skill and expertise needed to establish an adequate predictive maintenance program.
- the invention in one aspect provides a method for establishing a predictive maintenance database that defines information needed to monitor components in accordance with a predictive maintenance plan.
- a component type corresponding to a particular component to be monitored is identified, and physical characteristic information is also identified which corresponds to the identified component type and the particular component to be monitored.
- a knowledge base in the computer defines relationships between monitoring practices, component types and physical characteristic information for component types, and an inference engine operates in part on the knowledge base to construct predictive maintenance databases.
- Information for a predictive maintenance database is constructed for each component to be monitored using the inference engine operating on the knowledge base, the selected component type and the selected physical characteristic information.
- the database information for the predictive maintenance database may be constructed in a number of ways based on a number of factors.
- the database information may be constructed to correspond in part to a defined type of data to be measured for the identified component type and/or defined measurement points on the component from which data will be measured.
- An analysis parameter set may also be defined by the constructing step, including setup parameters for use by a data collection instrument to collect data in accordance with the predictive maintenance database.
- an alarm limit set may be defined by the constructing step including alarm limits delineating normal and abnormal component operation for data measured in accordance with the database.
- constructing the database information may include recommending a plurality of measurement points for measuring operating characteristics of the component in accordance with the predictive maintenance plan.
- Additional steps in the method may include specifying a recommended type of component operating characteristic to be measured at each of the plurality of measurement points, and specifying a recommended alarm limit delineating normal and abnormal operation for a recommended type of component operating characteristic to be measured at a particular one of the plurality of measurement points.
- An image of the component being monitored may be displayed with locations being designated on the component image corresponding to one or more of the plurality of measurement points.
- An operational significance of the selected component type may be specified.
- the selected component type and the selected physical characteristics may be stored and later used for establishing further predictive maintenance databases. When collecting data in accordance with the predictive maintenance program, a user is prompted to place an appropriate measurement device at a measurement point to measure a component operating characteristic.
- the present invention also provides a programmable apparatus for establishing a predictive maintenance database defining information needed to monitor components in accordance with a predictive maintenance plan.
- a knowledge base defines relationships between monitoring practices, component types and physical characteristic information for component types.
- a data processor is connected to the memory and includes an inference engine for operating in part on the knowledge base to construct database information for a predictive maintenance database. Based on user input provided through a user interface, the data processor is programmed to identify a component type corresponding to a particular component to be monitored, identify physical characteristic information corresponding to the identified component type and the particular component to be monitored, and construct information for a predictive maintenance database for each component to be monitored using the inference engine operating on the knowledge base, the identified component type and the identified physical characteristic information.
- a plurality of component groups are displayed, and a user is prompted to select at least one of the component groups.
- User input identifies a selected component group corresponding to a particular component to be monitored.
- a plurality of component types is displayed corresponding to the selected group, and the user is prompted to select at least one of the component types.
- a user input is received identifying a selected component type corresponding to the particular component to be monitored.
- Physical characteristic types are displayed corresponding to the selected component type, and the user is prompted to provide physical characteristic information corresponding to the physical characteristic types to further define a component to be monitored. Physical characteristic information provided by the user is accepted.
- a knowledge base is provided in the computer and defines relationships between monitoring practices and component types and physical characteristic information for component types.
- An inference engine is also provided in the computer for constructing database information for predictive maintenance databases based in part on the knowledge base.
- the knowledge base is used to select measurement specifications based on the selected component type and the physical characteristic information provided by the user.
- the database information is constructed using the inference engine operating on the knowledge base, the selected component type, the selected physical characteristic information, and the user defined measurement specifications.
- the present invention also provides a method for associating a machine component with physical information in a computer to define a component configuration for use in establishing a predictive maintenance database for the component configuration.
- This method involves identifying a component type corresponding to a particular component to be monitored where the particular component to be monitored has a plurality of physical component parameters.
- Information is specified which corresponds to one or more of the plurality of physical component parameters.
- the specified information may include the operating speed of the particular component to be monitored.
- a component configuration is produced from the identified component type and the specified information.
- the method may further include the steps of associating with the component type at least one of a plurality of measurement technologies.
- Database information for predictive maintenance database is then constructed based on the identified component type, the specified information, and said one or more selected measurement technologies.
- Another method involves graphically associating a plurality of machine components in a computer to define an equipment configuration for use in establishing a predictive maintenance database for the equipment configuration.
- a first component type is identified which corresponds to a first component to be monitored.
- a second component type is likewise identified which corresponds to a second component to be monitored.
- component information is specified which corresponds to physical characteristics of the component.
- Component configurations are produced for each of the first and second components based on the specified component types and component information.
- a physical coupling between the two components is defined, and an equipment configuration is produced from the two equipment configurations and the physical coupling.
- a method for establishing a predictive maintenance database in a computer that defines information needed to monitor components in accordance with a predictive maintenance plan.
- the method includes identifying a component type corresponding to a particular component to be monitored.
- a master file of information is provided in the computer which includes at least component identification information and corresponding predictive maintenance database information that specifies the types of measurements needed by the predictive maintenance plan for each component in the master file.
- the master file is searched for component identification information corresponding to the identified component type to produce at least one set of component identification information, and a set of component identification information is selected from the at least one set of component identification information.
- database information is constructed for a predictive maintenance database for the component to be monitored using the set of selected component identification information and the predictive database information corresponding to the set of selected component identification information.
- the master file of information may include component identification information in the form of the name of component manufacturers, component model numbers, or both.
- the component identification information may also physical criteria corresponding to physical characteristics of components.
- Predictive maintenance database information may include measurement point locations identifying points on components where predictive maintenance data is to be measured in accordance with the predictive maintenance plan. Types of measurement analyses to be performed in accordance with the predictive maintenance plan may also be included as predictive maintenance database information.
- Searching of the master file for component identification information may be accomplished by searching based on manufacturer name and model number.
- the master file may also be searched based on physical criteria of the component.
- FIG. 1 is a functional block diagram of a programmable apparatus for use in establishing a predictive maintenance database in accordance with the present invention
- FIG. 2 is a flow diagram of a program for controlling operation of the apparatus of FIG. 1;
- FIG. 3 is a user interface screen which enables the user to initiate creation of a new predictive maintenance database and to initiate modification of an existing predictive maintenance database in accordance with the present invention
- FIG. 4 is a user interface screen prompting the user to select predefined predictive maintenance technologies to be incorporated into the creation of a new predictive maintenance database
- FIG. 5 is a user interface screen prompting the user to define information corresponding to the location of equipment to be monitored in accordance with the new predictive maintenance database being created;
- FIG. 6 is a user interface screen prompting the user to define information corresponding to the type of equipment to be monitored and the operational significance of the equipment;
- FIG. 7 is a user interface screen prompting the user to define information for use by the program of FIG. 2 in creating vibration monitoring elements of the predictive maintenance database;
- FIG. 8 is a user interface screen prompting the user to define information for use in creating thermography monitoring elements of the predictive maintenance database
- FIG. 9 is a user interface screen of a main program screen which provides a tree structure of database files and enables the user to launch a detailed configuration of equipment represented by a file shown in the tree structure;
- FIG. 10 is a user interface screen from which the user has initiated definition of a new equipment configuration file entitled “Boiler Feed Pump #1” defining physical characteristics of a boiler feed pump to be monitored;
- FIG. 11 is a user interface screen for defining components and component connectivity of the new configuration
- FIG. 12 is a user interface screen prompting the user to define general motor configuration information
- FIG. 13 is a user interface screen prompting the user to define information corresponding to motor type
- FIG. 14 is a user interface screen prompting the user to define physical characteristics of the motor
- FIG. 15 is a user interface screen prompting the user to define bearing types
- FIG. 16 is a user interface screen which enables the user to select bearing information from a list of known bearings
- FIG. 17 is a user interface screen from which known bearings can be looked up and imported into the component definition
- FIG. 18 is a user interface screen showing motor vibration measurement points selected by the program of FIG. 2;
- FIG. 19 is a user interface screen showing that the motor is configured for the vibration technology selected in FIG. 4 and the user is initiating configuration of the motor for another technology;
- FIG. 20 is a user interface screen prompting the user for general motor information
- FIG. 21 is a user interface screen prompting the user for information corresponding to rated operating parameters of the motor
- FIG. 22 is a user interface screen showing motor measurement points selected by the program of FIG. 2;
- FIG. 23 is a user interface screen in which the user initiates configuration of the motor for thermography data collection
- FIG. 24 is a user interface screen which enables the user to provide information for use in selecting thermography measurement points for the motor;
- FIG. 25 is a user interface screen which enables the user to initiate configuration of the pump for vibration technology
- FIG. 26 is a user interface screen prompting the user for general pump information
- FIG. 27 is a user interface screen prompting the user for additional pump information
- FIG. 28 is a user interface screen showing pump vibration measurement points selected by the program of FIG. 2;
- FIG. 29 is a user interface screen showing the pump and motor components as being configured with an unconfigured coupling between the pump and motor;
- FIG. 30 is a user interface screen showing the pump, motor, and coupling as being configured
- FIG. 31 is a user interface screen from which the user may initiate creation of a predictive maintenance database in accordance with the invention
- FIG. 32 is a user interface screen showing the progress of the program of FIG. 2 while creating a predictive maintenance database
- FIG. 33 is a user interface screen of a main program screen for a database viewing program which enables viewing and editing of information contained in predictive maintenance database files created in accordance with the present invention
- FIG. 34 is a user interface screen of the database viewing program which displays measurement points created by the main program
- FIG. 35 is a user interface screen of the database viewing program showing detailed measurement point information
- FIG. 36 is a user interface screen of the database viewing program showing additional detailed measurement point information
- FIG. 37 is a user interface screen of the database viewing program showing a list of analysis parameters created by the main program
- FIG. 38 is a user interface screen of the database viewing program showing analysis parameter details for time waveform and frequency spectrum data collection
- FIG. 39 is a user interface screen of the database viewing program showing additional analysis parameter details for frequency ranges in which measurements are taken;
- FIG. 40 is a user interface screen of the database viewing program showing a list of alarm limits which correspond to the analysis parameters of FIG. 37;
- FIG. 41 is a user interface screen of the database viewing program showing amplitude limits defining multiple levels of alarming
- FIG. 42 is a user interface screen from which the user has initiated definition of a new equipment configuration file entitled “Condensate Pump #1” defining physical characteristics of a condensate pump to be monitored;
- FIG. 43 is a user interface screen prompting the user to specify whether existing configuration information will be used to configure the condensate pump;
- FIG. 44 is a user interface screen which enables the user to select from a list of known motor types for use in configuring the condensate pump;
- FIG. 45 is a user interface screen prompting the user for general information corresponding to the condensate pump motor
- FIG. 46 is a user interface screen for displaying motor construction information
- FIG. 47 is a user interface screen for displaying motor bearing information
- FIG. 48 is a user interface screen for displaying additional bearing information
- FIG. 49 is a user interface screen showing motor measurement points
- FIG. 50 is a user interface screen showing configured and unconfigured components of the condensate pump
- FIG. 51 is a user interface screen showing information corresponding to a component of the condensate pump
- FIG. 52 is a user interface screen showing a completely configured condensate pump
- FIG. 53 is a table of candidate measurement points for an AC induction motor showing how operational significance relates to measurement point selection.
- FIG. 54 is a user interface screen showing a master component/database file and related data fields for constructing a predictive maintenance database using a lookup technique.
- FIG. 1 shows in block diagram form a programmable apparatus 10 for establishing a predictive maintenance database defining information needed to monitor equipment (such as electric motors, pumps, bearings, and the like) for anomalous or faulty operation in accordance with a predictive maintenance plan.
- the apparatus 10 includes a computer 20 having a data processor 22 and associated memory 28 , a display 26 , and a user interface 24 (such as a mouse and/or keyboard) for inputting user information and commands to the data processor 22 .
- a communications port 30 such as a serial infrared data port, is provided to enable the computer 20 to communicate with a peripheral device.
- a digital camera 32 may be provided for capturing digital images of equipment which are provided to the data processor 22 for processing and display on the display 26 .
- the data processor 22 is a PentiumTM processor running WindowsTM 95 or WindowsTM NT Workstation as the operating system.
- the computer 20 provides a straightforward, user-friendly environment in which users, including inexperienced maintenance technicians, can quickly and efficiently create a predictive maintenance database or create an area or component that may be incorporated into an existing predictive maintenance database.
- a site is a grouping of areas. A site is usually equated with a plant.
- a “component” is an item to be monitored in accordance with appropriate predictive maintenance principles. Motors, engines, gearboxes, pumps, fans, and like items are examples of components.
- a “configuration” is a detailed definition of one component or of two or more interconnected components, such as a motor driving a pump. “Equipment” is rather broadly defined as including components, groups of components, and configurations.
- Equipment For rotating machinery, the term “equipment” may be used to refer to a machine train consisting of components connected via a coupling. “Operational Significance” is a general rating that indicates the relative criticality of proper operation of equipment to the activities of the site. Values for operational significance include “critical”, “essential”, “important”, “secondary”, and “non-essential”.
- FIG. 2 Operation of the computer 20 to establish a predictive maintenance database in accordance with a preferred embodiment of the invention is illustrated in the flow diagram of FIG. 2 (hereinafter referred to as the “program 40 ”).
- the program 40 combines user input with stored information to create new predictive maintenance database files, or to modify or edit an existing predictive maintenance database file, in a fraction of the time and effort previously required with conventional approaches.
- the program includes three major subsystems—a main program 42 , a component design studio 44 , and an inference engine 46 .
- the main program 42 accepts site information from the user 48 and assists the user 48 in describing the site information. It leads the user 48 through the creation of areas and equipment that match the topology of the site to be monitored.
- the user 48 may also provide information relative to the monitoring technologies to be applied and the monitoring hardware to be used as part of the predictive maintenance plan implemented by the predictive maintenance database.
- the component design studio 44 is a drag-and-drop graphical user interface tool that enables the user 48 to define new equipment and edit existing equipment, including components and configurations, for predictive maintenance databases. It enables the user 48 to graphically associate machine components, such as a pump being driven by a motor. Component and configuration definitions can be stored and reused for further equipment definitions.
- the component design studio 44 also prompts the user 48 for information relating to physical characteristics of the equipment to be monitored. For example, if the equipment to be monitored is an electric motor, physical characteristic information would preferably include the spatial orientation of the motor (i.e., vertical or horizontal), number of poles, number of stator bars, rated running speed, and other information. The physical characteristics information may also be stored and reused for further equipment definitions.
- GUI graphical user interface
- SDI Microsoft WindowsTM Single Document Interface
- the application includes a main window that may contain one or more data views.
- One of these views is a tree that shows the hierarchy of items created by the user.
- Other views based on the currently selected tree item, show the properties of the selected item and provide access to other user interfaces which aid the user 48 in creating and modifying equipment definitions and databases.
- Common configurations and component definitions may be stored in one or more component warehouse databases 64 which can be accessed by the component design studio 44 , thus eliminating the need for the user 48 to create configuration and component definitions for equipment that has been previously defined and stored in a component warehouse database 64 .
- component identifiers and connectivity information are stored in the warehouse 64 .
- the physical characteristics are stored in the warehouse 64 .
- two types of warehouses are available to the user 48 .
- One type of warehouse is a read-only warehouse containing a large number of ready to use component and/or configuration definitions and is provided by the program supplier as an integral part of the program 40 .
- a second type of warehouse is one that is created by the user 48 for storing configurations and components not included in the read-only warehouse.
- the main program 42 and component design studio 44 produce a single program data file 50 that includes information entered by the user 48 including site information and equipment definition information. This information may be modified by the user 48 until the user 48 is satisfied with its completeness and accuracy. At that time, the user 48 may request that the program data file 50 be passed on to the inference engine 46 .
- the inference engine 46 performs the task of taking user input relating to the physical characteristics of components and combining it with predictive maintenance knowledge to determine the best monitoring setup for those components.
- the inference engine 46 receives the program data file 50 and creates a predictive maintenance database file by operating on data contained in the program data file 50 in conjunction with data and information contained in a knowledge base 52 .
- Information contained in the predictive maintenance database file may be viewed and edited by a database program 54 , which in a preferred embodiment is an RBMwareTM predictive maintenance database program available from Computational Systems, Inc. of Knoxville, Tenn.
- the inference engine 46 also enables the user to edit existing predictive maintenance database files 54 .
- the knowledge base 52 contains empirical knowledge and information gained through years of experience in monitoring equipment.
- the primary references which had the most significant impact on the contents of the knowledge base 52 include observations of “best practices” by engineers experienced in the art of predictive maintenance.
- the various teachings of numerous text books and industry periodicals also shaped the contents of the knowledge base 52 , including that portion of the knowledge base 52 which generates analysis parameter sets and alarm limit sets. Accordingly, predictive maintenance databases created by the program 40 will far exceed the quality of databases created by a novice, and will likewise deliver the experienced user 48 quality databases which have been standardized across equipment types.
- the information contained in the knowledge base 52 defines a relationship between physical characteristics of a component type and optimal monitoring practices as determined from experience.
- information in the knowledge base 52 includes measurement points for placement of sensors, types of sensors to place at the measurement points, and setup criteria for the measurement instrument (such as number of frequency lines, frequency filtering of sensor signals, frequency bands of interest, alarm limits, and the like).
- the number and types of measurement points created depends on the component's type and operational significance. For equipment which includes bearings, there will typically be three vibration measurement points per bearing located in each of the three directions (horizontal, vertical, and axial).
- Information contained in the knowledge base 52 may be edited to reflect advances in predictive maintenance know-how.
- Analysis parameter sets defining the types and amounts of data to be measured, setup criteria, and the like, are partially predefined in the knowledge base.
- the analysis parameter sets are different for different types of components and are used to setup a data collection instrument to collect data in an optimal way.
- the predefined analysis parameter sets are applicable for most components of a given type (motors, turbines, pumps, fans, and the like) and are organized into families of similar components.
- a core group of sleeve and rolling element bearing analysis parameter sets exist. These analysis parameter sets are somewhat dependent on turning speed. The selection of a specific analysis parameter set is based on component type, measurement point RPM, bearing type, and similar information. The analysis parameter sets typically are unaffected by adjacent components and coupling information.
- the number of lines of resolution for frequency analysis is variable based on the reference turning speed of the equipment. This enables the user 48 to have good frequency resolution over a wide range of operating speeds.
- Alarm limit sets defining criteria for generating fault alarms for parameters contained in the analysis parameter sets, are grouped by components similar to the analysis parameter sets. They are based on the type of equipment being monitored and the type of environment in which the equipment is operated. Each component type includes a family of alarm limit sets with each alarm limit family having a plurality of alarm grades, and some families may be accessed by multiple components. For example, in one embodiment, a family of alarm limit sets for AC induction motors is also used by AC synchronous motors. In addition, some alarm values are based on several factors such as driven component type, component RPM, and component weight and horsepower. Different levels of alarm severity are also assigned for some component types.
- alarm criteria is preferably based on the operating environment of the equipment. Values for alarm criteria include “smooth”, “moderate”, and “rough” where a “smooth” alarm criteria represents a low threshold for alarming and “rough” represents a high threshold for alarming.
- the inference engine 46 provides the capability for integration of multiple measurement technologies including vibration monitoring technology, motor monitoring technology, oil monitoring technology 56 and thermography 60 .
- the program 40 prompts the user 48 to specify a particular type of measurement technology to be applied.
- the user 48 provides information relative to the specified measurement technology, and the program 40 creates a predictive maintenance database file applying the measurement technology to a specified piece of equipment to be monitored. Multiple measurement technologies may be applied to each piece of equipment.
- the present invention provides a user interface to the program 40 which enables the user 48 to easily answer questions and to provide information used by the program 40 in constructing predictive maintenance database files.
- the program 40 is designed to “fail safe” in the sense that, no matter how much or how little information the user 48 knows about the equipment, the program 40 is able to create meaningful analysis parameter sets and alarm limit sets for quality data collection.
- a computer 20 running a program 40 in accordance with the invention receives the user inputs and creates a predictive maintenance database complete with equipment definition information, measurement points, analysis parameter sets, alarm limit sets, and equipment configuration information needed for expert analysis systems to perform detailed analysis on data that is collected.
- the following Example 1 describes a typical process for creating a predictive maintenance database for a boiler feed pump located within a site. Typically, a separate predictive maintenance database file is created for each site and each piece of equipment to be monitored within the site is included in the database file.
- Example 2 describes how the program enables the user 48 to reuse previously configured components when adding new equipment configurations to the database or editing existing equipment configurations in the database.
- Example 3 provides a detailed explanation of how the inference engine 46 creates analysis parameter sets, alarm limit sets, and measurement points based on rules defined in the knowledge base 52 and/or the inference engine 46 .
- the program 40 enables the user 48 to successfully create a predictive maintenance database even if the user 48 knows very little about the equipment and needs to select the default answers provided by the program 40 .
- the knowledge base 52 and the inference engine 46 it is important to understand that there is not a unique correct way to monitor equipment. There are many correct ways to monitor a particular piece of equipment or a particular configuration, and there are many incorrect ways to do so. Thus, the knowledge base 52 and the inference engine 46 may vary widely, so long as they operate together to specify one of the correct setups for monitoring the specified equipment. The examples discussed below illustrate a correct knowledge base 52 and inference engine 46 , but the examples should not be construed as limiting the invention to any one knowledge base 52 or inference engine 46 . In particular, rules for defining measurement points, analysis parameter sets, and alarm limit sets may exist in either or both of the knowledge base 52 and inference engine 46 .
- FIGS. 3 - 32 are images of user interface screens, or screen shots, of a typical “run” through the program 40 for creating a predictive maintenance database for a boiler feed pump.
- the screens are displayed to the user 48 at display 26 and generally prompt the user 48 for information which assists the program 40 in creating the database.
- the user 48 is asked whether he wishes to create a new predictive maintenance database or open an existing database for editing.
- Existing database files which the user 48 may select are listed in window 70 .
- the user 48 has opted to create a new database.
- FIG. 4 prompts the user 48 to provide this information.
- window 72 the user 48 is asked to specify measurement technologies and in window 74 the user 48 is asked to specify measurement hardware information.
- the user 48 has selected all measurement technologies including periodic vibration, oil analysis, thermography, MotorViewTM (an electrical motor analysis program available from Computational Systems, Inc. of Knoxville, Tenn.), and corrective analysis (a group of monitoring technologies available from Computational Systems, Inc. under the trade name UltraManageTM).
- window 74 the user 48 has selected “periodic vibration”. This selection takes the user 48 to another screen from which the user 48 selects specific periodic vibration hardware.
- the user 48 is next prompted in FIG. 5 to provide an area name 76 and an area identification 78 .
- the area name 76 is typically a descriptive word name for the facility, such as “powerhouse”, and the area identification 78 is typically a shortened term or group of characters that the user 48 can identify.
- the user 48 has chosen the identification “PH01” to represent powerhouse # 1 .
- the user 48 provides an equipment name 80 , an equipment identification 82 , and an operational significance 84 .
- values for operational significance of equipment include “critical”, “essential”, “important”, “secondary”, and “non-essential”.
- the program 40 adjusts the measurement technique based on this input value. For example, a boiler feed pump which is “essential” to the operation of the powerhouse would be monitored at shorter intervals than one which is “non-essential”. In addition, more measurement points and types of measurement points would be created.
- the user 48 Since the user 48 selected “periodic vibration” in FIG. 4 as the measurement technology, the user 48 is prompted in FIG. 7 to specify various equipment parameters effecting vibration including the equipment or component type 86 , a reference driver speed 88 of the equipment, speed units 90 , a reference load 92 corresponding to the reference operating speed 88 , and an alarm criteria 94 . Alarm levels are adjusted automatically by the program 40 based on the alarm criteria selection 94 .
- a name for the equipment (Boiler feed Pump #1) has now been created within the “powerhouse” area and is ready to go through a more detailed configuration.
- the detailed configuration portion of the program 40 is that portion of the program 40 which asks for information that enables the measurement information to be set up correctly.
- a detailed configuration of the boiler feed pump #1 is being launched from the main program screen shown in FIG. 9. This accomplished by selecting the file entitled “Boiler Feed Pump #1” from the file tree structure shown in box 93 and then selecting the “Configure” button 95 .
- the user 48 has defined a new configuration file title “Boiler Feed Pump #1” shown at window 96 .
- Configuration information including component types, couplings between components, and physical characteristics of components, are stored in the specified file.
- the user 48 may elect to save configuration information in a user-defined warehouse file 98 .
- a read-only warehouse file is also provided as part of the program 40 .
- the user 48 may select a configuration which is already stored in one of the warehouse files, thus avoiding the need to define a configuration when the equipment (or like equipment) has been previously configured.
- the user 48 is asked to identify components of the new configuration. Since the boiler feed pump #1 includes a motor and a pump, each of the components are selected from the list of rotating components and displayed in the lower window 100 as an unconfigured motor 102 and an unconfigured pump 104 . A dashed line 106 connecting the motor 102 and pump 104 represents an unconfigured coupling. These components may be configured for each technology that should be applied to the specific equipment.
- Rotating equipment such as motors posses characteristics that will generate specific vibration frequencies when the equipment is running. The amplitude at these frequencies is used to determine the condition of the equipment.
- the program 40 asks the user 48 to input this information at the screen shown in FIG. 14, if known. For example, the user may input the number of phases, poles, rotor bars and stator slots, if known, for a synchronous motor.
- the inference engine 46 uses this information in part to select appropriate analysis parameter information.
- FIG. 15 shows a screen from which bearings may be looked up from a list of known bearings
- FIG. 17 shows a screen that enables the user 48 to look up bearings from master lists and import them into the component definition.
- the program 40 has processed the motor information entered by the user 48 (including the selected component type and the selected physical characteristics) and determined the best or optimal measurement points 103 for the motor.
- the best or optimal points chosen are those for which a check mark appears in the column titled “Active?”.
- a unique measurement point identifier (PID) 105 is generated and associated each with a measurement point 103 .
- an image of the motor is obtained from stored equipment diagram files 62 (FIG. 2) and the measurement points 103 are indicated on the motor image.
- the user 48 must possess substantial knowledge of predictive maintenance practices in order to identify the best measurement points 103 . As seen in FIG. 18, the program 40 has identified these points for him.
- the motor 102 ′ is now configured for the vibration technology selected back in FIG. 4.
- the user 48 now chooses to configure the motor technology by selecting the motor icon 108 at the bottom of the screen.
- the motor technology requests additional motor information from the user 48 (for example, identification number, frame size, insulation class, rated RPM, rated power, rated voltage, and rated current).
- the information provided in FIG. 20 is used to determine measurement parameters for collecting data while the information provided by the user 48 in FIG. 21 is used for analysis of the data.
- FIG. 22 shows measurement points that are selected for the motor based on the information provided in FIGS. 20 and 21. The measurement methods are also altered based on that information.
- the user 48 may select icon 110 at the bottom of the screen to configure the motor for infrared thermography data collection.
- Thermography measurement points are set up in the predictive maintenance database based on the information provided at the screen shown in FIG. 24.
- the user 48 selects icon 112 shown at the bottom of the screen of FIG. 25 to configure the driven component (i.e., the pump) for the vibration technology.
- This selection takes user 48 to the screen shown in FIG. 26 which prompts the user 48 to provide the requested information.
- a user may not know all of the configuration information that the program 40 requests. In such a case, the user 48 simply needs to answer what is known and the program 40 will create an optimal database from the information that is available. Users who know more information about the equipment details can enter this information into the screen shown in FIG. 26 and by selecting the advanced screen button 114 located in the lower left hand corner of the screen. The additional information will be reflected in the setup of the actual predictive maintenance database as it is built.
- FIG. 27 Information relating to the pump type 116 , pump support 118 , pumped fluid 120 , number of stages 121 and number of inlet/outlet impeller vanes 123 , is used by the program 40 to establish measurement parameters, while information such as inlet type 122 and number of inlet/outlet diffuser vanes 125 are used to determine specific analysis frequencies.
- Measurement points 124 are established by the program 40 based on the information entered in FIGS. 26 and 27, and the measurement points 124 are displayed on the screen shown in FIG. 28. Each measurement point is identified by a unique measurement point identifier (PID) 126 . The measurement points are used by the program 40 to establish the measurement parameters and locations.
- PID measurement point identifier
- the user 48 is taken to the component design studio 44 (FIG. 2) in FIG. 29 where the coupling 106 between the configured motor 102 ′ and the configured pump 104 ′ is defined.
- the coupling 106 attaches the driver, in this case a motor 102 ′, and a driven unit, in this case a pump 104 ′.
- the type of coupling can effect the speed of the driven unit.
- the user 48 simply inputs the type of coupling and any speed ratio information. Coupling types can be found by expanding the menu selection under “Existing” shown at 124 . This information enables the program 40 to calculate the correct measurement point speeds. The speed at each measurement point is an important piece of information used by the program 40 to establish analysis parameters which control how data is measured and subsequently analyzed.
- the “boiler feed pump #1” is now configured in FIG. 30, including a configured coupling 106 ′.
- the user 48 is now ready to instruct the program 40 to create a predictive maintenance database for the configured equipment.
- the user 48 accomplishes this by returning to the main program screen, shown in FIG. 31 (see also FIG. 9), and clicking the hammer icon 128 .
- pop-up progress screen 130 enables the user 48 to monitor the progress of the program 40 as the database is created.
- a predictive maintenance database file is created and can be viewed and edited with a commercially available database program 54 (FIG. 2), such as DBASE, as shown in FIGS. 33 - 41 .
- FIG. 33 provides a view of the main program screen from the DBASE program.
- the screen indicates to the user 48 that two equipment configurations (“Boiler Feed Pump #1” and “Condensate Pump #1”) are included within the PH01 Powerhouse area of the database.
- the user 48 may edit, move, delete, and generally manipulate data contained in the database by use the appropriate buttons shown in the upper right-hand portion of the screen. These buttons are generally indicated at 182 .
- the user 48 selects “Boiler Feed Pump #1” and then clicks the “OK” button 180 located in the lower right-hand portion of the screen.
- a list of measurement points created by the program 40 to monitor the “Boiler Feed Pump #1” is shown in FIG. 34. Included in the list are points for measuring vibrational displacement at the outboard side of the motor 184 , vibrational displacement at the inboard side of the motor 186 , motor leakage flux 188 , temperature 190 , and others. The list also includes points for visual observations made by the user 48 , including observation of motor cleanliness 192 and observation of air flow through the motor 194 .
- FIGS. 35 - 41 illustrate various detailed information which is included in the database for each measurement point. Some of the information is based on data input to the program 40 by the user 48 . As shown in FIG. 35, the user 48 is able to view and edit measurement point information including a measurement point identifier 192 , measurement point description 194 , measurement units and code 196 , motor rpm at the measurement point 198 , monitoring schedule 200 , and number of values in statistical calculations 202 . The screen shown in FIG. 35 also shows that data collection set information 204 (used during actual field data collection) is included in the database. The data collection set information includes an analysis parameter set 206 and an alarm limit set 206 .
- Additional measurement point information shown in FIG. 36 includes probe type 204 , sensor orientation 206 , sensor position 208 , sensitivity of the sensor 210 , highest and lowest acceptable signal levels 212 , and other detailed information.
- the user 48 is provided a descriptive list of analysis parameters which are included in the analysis parameter set 206 created by the program 40 . Included in the list is an AC motor rolling bearing analysis parameter 212 , a peakvue analysis parameter 214 , an electric current-rotor bar condition parameter 216 , motor shaft current and voltage measurement parameters 218 , and others.
- the analysis parameter sets control the manner in which data is collected. These sets control two basic items.
- the first is time waveform and frequency spectrum data collection along with any special signal processing.
- the user 48 may view and edit spectrum and waveform information contained in the database for each of the analysis parameters listed in FIG. 37.
- FIG. 38 the user 48 is able to view detailed information relating to waveform and frequency data collection parameters for analysis parameter number 1 entitled “AC MTR, ROLLING BRG (1600). Included in this information is the spectral frequency setup 220 , low frequency signal conditioning limit 222 (for noise elimination), upper and lower frequency limits 224 , number of spectral lines to be acquired 226 , number of averages 228 , and type of analysis window 230 .
- the second item in the parameter analysis set is the parameter bands (i.e., frequency ranges in which the amplitude is measured) that will be measured and trended by the DBASE database program.
- the analysis parameter sets are scalar values that correspond to waveform characteristics or integrated energies over specified frequency ranges in the spectrum. These may include the maximum peak to peak value 232 in the waveform, crest factor 234 , a narrow frequency interval around on times turning speed (TS) 236 , the amplitude of all frequencies in a wide interval from 3.5 to 10.5 ⁇ TS, and others.
- Each of the parameter bands is displayed in FIG. 39 according to a descriptive title, units type, type of parameter, and lower and upper frequencies. Additionally, each parameter band is selected by the program 40 based on information, including type of equipment and component information, that was input to the program 40 by the user 48 .
- the program 40 also creates alarm limit sets which correspond to the analysis parameter sets.
- Alarm limit sets typically vary between different types of equipment and are generally dependent on expected amplitude levels.
- the DBASE database program has displayed by descriptive title a list of alarm limit parameters. Included in the list is an AC motor rolling bearing (moderate) 242 , Peakvue (moderate) 244 , skin temperature 246 , roller element bearing temperature 248 , shaft current and voltage alarms 250 , and others.
- Each alarm limit set contains amplitude limits which are compared to the trended data in the analysis parameter bands. The amplitude levels are based on the type of equipment input to the program 40 by the user 48 and the unexpected operational conditions.
- FIG. 41 shows the alarm limits for the twelve analysis parameters given in FIG. 40. Included in FIG. 41 is a column specifying for each alarm limit the units code 252 , alarm type 254 , an alarm limit value indicative of a significant failure or fault 256 , an alarm limit value indicative of a less severe failure or alert 258 , and other information.
- a user who knows very few equipment details, or a user who knows all equipment details can use the program 40 to create a predictive maintenance database.
- the program 40 creates a predictive maintenance database that is more than adequate for data collection and analysis purposes, even when few details are known about the equipment. The more information that can be input into the program 40 , the more detailed the measurement points, analysis parameter sets, and alarm limit sets will be.
- the “boiler feed pump #1” configuration may be reused to define other like configurations for the creation of additional configurations in predictive maintenance databases.
- each of the components 102 ′, 104 ′, 106 ′ and their corresponding templates may be reused in defining other equipment configurations, as illustrated in Example 2 given below.
- FIGS. 42 - 52 will be used to illustrate the ability of the program 40 to reuse already configured components when configuring equipment.
- the user 48 is prompted to specify whether existing configuration information will be used.
- Existing information can be recalled from one of three types of stored information, including component information 144 , template information 146 , and configuration information 148 .
- Component information includes the appropriate template information as well as bearing setup information.
- Template information contains detailed machine setup information (excluding bearing setup information) and is stored in a component warehouse 64 (either a read-only warehouse or a user-defined warehouse). Elements of a component that are not changeable are considered as template information.
- Configuration information includes complete equipment train information, which usually consists of at least one driver and one driven component connected by a coupling. The user 48 clicks the template 146 selection and is taken to the screen shown in FIG. 44.
- the template 146 may be selected from a local file 153 , a user-defined component warehouse 154 , or a read-only component warehouse 155 .
- the local file 153 includes templates that the user 48 will reuse only in the present database. Typically, such templates are created for equipment that can be found at only one site.
- the user warehouse 154 includes templates which have been configured and stored by the user 48 and can be edited, and the supplier warehouse 155 includes templates provided by the program 40 supplier and cannot be edited.
- a list of standard motor types contained in the supplier warehouse 155 are displayed in box 152 , and a motor 150 has been selected from the list. Although there is template information present in the component warehouse 155 for the selected motor 150 , the motor 150 is considered to be unconfigured at this point since the physical characteristics have not yet been defined.
- General component definition information is provided by the user 48 in FIG. 45 (see also FIG. 12).
- the motor component will be created based on the information contained in the template identified in box 156 , which is grayed out and not editable since this template is part of a predefined component warehouse that was provided with the program 40 .
- Information corresponding to motor construction and bearing types is grayed out in FIGS. 46 and 47 (see also FIG. 14) as well. Thus, while the information can be displayed, it is not changeable by the user 48 .
- measurement points 160 and corresponding identifiers 162 are created and displayed as shown in FIG. 49.
- the measurement points 160 can be edited by the user 48 .
- FIG. 50 the motor 151 ′ is now configured.
- the user 48 has selected a gearbox 164 from a list of predefined gearbox components displayed in box 166 .
- a popup box 168 prompts the user 48 as to whether the gearbox should be edited. Clicking “Yes” takes the user 48 to the screen shown in FIG. 51. Since all information relating to the gearbox has been predefined in the component warehouse, the user 48 may only examine the information shown in FIG. 51.
- FIG. 52 the “condensate pump #1” configuration has been completed.
- the configuration includes the motor 150 ′, gearbox 164 ′, a pump 170 which was selected from the local file 153 and not edited, a coupling 172 interconnecting the pump 150 ′ and gearbox 164 ′, and a coupling 174 interconnecting the pump 170 and gearbox 164 ′.
- the user 48 is now ready to insert this information into his predictive maintenance database as described above with reference to FIGS. 31 - 33 (note that FIG. 32 includes the “condensate pump #1”) and to view or edit the new database information as described in FIGS. 34 - 41 .
- the knowledge base 52 is a set of information and rules.
- the information is physical data and the rules relate different types of physical data one to the other. For example, a rule could relate a particular motor type of a particular physical description to a set of measurement points.
- the knowledge base 52 does not directly relate anything to a predictive maintenance database.
- the inference engine 46 relates data in the knowledge base 52 and data generated by the knowledge base and its rules, collectively or individually, to a particular set of data in a predictive maintenance database. Since these concepts are somewhat complicated, they may best be understood by reference to a simplified example of a knowledge base 52 and inference engine 46 as given below in Example 3.
- Probe Type casing
- the following steps illustrate how the analysis parameter and alarm limit sets were created by the program 40 . It is worth noting that it is common for a user 48 to not know all of the information given above. As previously described, minimal information is needed for the program 40 to create the analysis parameter sets and alarm limit sets. For rotating equipment such as AC induction motors, the absolute minimum information needed is the specification of an equipment type and the speed of the equipment.
- Step 1 The first rule for an AC induction motor is to create the analysis parameter (AP) set and alarm limit (AL) set based on bearing type and name the sets as follows:
- Step 2 Next, following rules for AC motors, the inference engine 46 will in the measurement details of the analysis parameter set as follows:
- a special time waveform will be collected in acceleration units with the maximum time in the waveform based on a spectral Fmax of 80 orders with 1024 points in the waveform.
- Step 3 The remaining details of the parameter set forth above are default settings for this type of AC induction motor.
- the rules provide that the following parameter bands will be measured for trending:
- Step 4 The following parameters bands will be created based on certain rules:
- the default value will be 60 Hz, which is the line frequency standard in North America.
- the parameter band for 2 ⁇ Line Frequency band will trend the frequency range between 115 Hz to 125 Hz.
- Step 5 Next, the inference engine 46 creates a parameter band to trend the frequency related to the number of rotor bars and a parameter band to trend the frequency related to the number of stator slots.
- Sator Slot pass freq range (#stator slots ⁇ 5) to (#stator slots+5) orders
- the alarm limit set created by the inference engine 46 will include alarm limits appropriate for each of the parameter bands described above.
- the alarm limit values are based on the type of equipment and the alarm criteria specified by the user 48 . For this example, the alarm criteria was set to moderate. If the alarm criteria had been set to “smooth”, the default alarm levels would be set at alarm limits which are lower than those for the “moderate” setting. Conversely, if the alarm criteria had been specified as “rough”, the default alarm levels would be set at alarm limits higher than those for the “moderate” setting.
- FIG. 53 is a table of candidate measurement points which the program 40 uses as rules to determine, based on the operational significance defined by the user 48 , which measurement points will be generated for an AC induction motor.
- the values of 1 - 5 are used in FIG. 53 to indicate operational significance where “critical” corresponds to an operational significance value of “1”, “essential” corresponds to “2”, “important” corresponds to “3”, “secondary” corresponds to “4”, and “non-essential” corresponds to “5”.
- the operational significance of the motor was set as “essential” which equates to an operational significance of “2” in the table shown in FIG. 53. Accordingly, each candidate measurement point for which a check mark appears in column 2 was selected as a measurement point for the motor.
- the above examples and description explain how the analysis parameter sets, alarm limit sets, and measurement points are selected by the program 40 based on information provided to the program 40 by the user 48 .
- the selections are made based on rules known by the program's inference engine 46 .
- the inference engine rules are preferably accepted industry practices which are likely to be unknown to a novice user of the program 40 .
- the rules are designed to produce a predictive maintenance database which will allow the user 48 to collect predictive maintenance data more correctly for each type of equipment that is to be monitored, even when minimal information is known about each piece of equipment, thereby enabling the user 48 to achieve a greater degree of analysis accuracy with significantly less information, experience, and time.
- the invention may be implemented with a more simplistic lookup technique or combination of both the lookup technique and the inference engine technique. In the latter case, the user can choose between the two techniques.
- the lookup technique is selected from the pull-down menu labeled “Options” 218 .
- the lookup technique is preferably implemented by providing a Master Component/Database file 200 that contains at least two fields of data, namely, a component identification field 202 and a database information field 210 , each corresponding to a particular component, such as a motor or a pump. While it would be possible to use a single component identification field and a single database information field, in most applications these two “fields” will actually be a group of related fields.
- the component identification field may include a separate field for the manufacturer's name 204 , the model number 206 , and each physical attribute 208 such as the horsepower rating of a motor or the number of rotor bars in a motor.
- the database information field will normally include many different fields such as those disclosed in FIGS. 34 - 41 .
- the user 48 To build a database using the lookup technique, the user 48 first uses the component identification field 202 to find and select a record in the master component/database file 200 corresponding to the component to be monitored. When the component record is selected, either automatically or by the user 48 , the database information (or record) found in the master component/database file 200 is added to the database that is being built.
- the component identification field 202 may contain a number of fields containing physical attributes or physical descriptions of the component or a manufacturer and model number, and it preferably has both.
- the user 48 first names the component in the same manner as discussed above with reference to FIG. 6.
- the user 48 may also provide an operational significance and alarm information as discussed above, but this is not required.
- a corresponding component record may be found in the master component/database file 200 by two basic techniques.
- the user 48 provides physical criteria describing the physical component.
- the user may provide the following physical criteria of a component such as a motor: 3 phases, 2 poles, 68 rotor bars, 54 stator slots, rated RPM of 3575, rated horsepower of 25, rated voltage of 440 volts and rated current of 200 amps.
- a search such as by clicking on a search button 212 , 214 , and the program 40 searches the physical attributes in the component identification field 202 for the best fit.
- the program 40 may automatically select the best fit component record from the master component/database file 200 and automatically add the selected record to the database being built. However, preferably, the program 40 may also display a best fit group of component records and allow the user 48 to select one record.
- the best fit group would usually include all of the component records that exactly fit the physical criteria provided by the user 48 , plus additional records that had physical attributes that were near the physical criteria provided by the user 48 .
- the best fit group of records is prioritized with the most likely candidate record listed earlier or higher in the best fit group. Priority may be based on the closeness of the fit and/or the prevalence or popularity of the component in the market. For example, a component priority could be proportional to the quantity of the component manufactured or the quantity of the components in use in a particular market.
- the other way of selecting a component record from the master component/database file 200 is by using the manufacturer and model number.
- the user 48 inputs the model number, which preferably includes the manufacturer as shown in block 216 of FIG. 53 (i.e., “GE” represents General Electric as the manufacturer), and the program 40 searches the identification field for a record having the exact model number. If an exact match is found, it is either automatically chosen and the database being created is updated with the chosen record as described above, or the record having the exact match is displayed. Whether the selection is made automatically or manually is preferably determined by a user option.
- the searching capabilities described above provide significant advantages over known predictive database programs. While it was certainly possible to copy portions of databases produced by prior art programs and attach such copies to another database, there was no specialized searching capability for finding what needed to be copied. To the extent that one database was used to make another, it was generally a manual process.
- the searching capability enables the user to build a database systematically using some information about the machine or machines for which the database is being built.
- the searching feature is flexible in that a variety of information may be used to conduct the search, including physical information, model numbers or manufacturers.
- the program provides for building a configuration composed of more than one machine and using the lookup technique for building a database for the overall configuration.
- the lookup technique searches the master component/database file 200 first for the specific combination of machines, such as a particular pump, coupling and pump. If the specific combination is found, it is used to construct the database. If the combination is not found, the master component/database file 200 is searched for the individual machines seperately and the database information for each machine is combined to produce the database for the overall configuration.
- the lookup technique requires the use of a master component/database file 200 that is typically much larger than any file necessary when the inference engine technique is used.
- the master component/database file 200 may actually exist as a number of files. For example, a separate file may be created for different types of components. A separate file may be provided for pumps, gear boxes, motors, etc. Also, separate files may be provided for different sub-categories of components, such as induction motors versus synchronous motors. Also, conventional searching techniques and enhancements would be used for searching and finding data within the files. Preferably, the data in all of the fields would be indexed to enhance searching.
- the database generated by the technique must reflect the operational significance and/or the alarm level provided by the user 48 .
- One way to incorporate operational significance into the lookup technique is to provide multiple entries (records) for the same component, with a separate record for each operational significance. In other words, if there were three levels of operational significance that a user 48 could choose, each component in the master component/database file 200 would require three separate records, one for each operational significance. Likewise, if alarm levels are used, each component must have a separate record for each alarm level. If both operational significance and alarm level is provided, the master component/database file 200 should have a separate record for each combination of operational significance and alarm level. For example, a first record must be provided for alarm level one, operational significance one, and a second record must be provided for alarm level one, operational significance two. It will be appreciated that the use of alarm levels and operational significance can cause the master component/database file 200 to grow dramatically.
- the inference engine technique could be used to produce preliminary database information based solely on the component identity ignoring alarm level and operational significance.
- an inference engine 46 or a set of rules can be used to modify the preliminary database information based upon both the alarm levels and the operational significance provided by the user 48 .
Abstract
Description
- The present invention relates generally to predictive maintenance of machines. More particularly, it relates to establishing and executing predictive maintenance programs for machines.
- A highly specialized art, commonly referred to as “predictive maintenance”, has evolved in an effort to predict when a machine will fail or requires maintenance so that corrective measures can be taken on an “as needed” basis. In a typical predictive maintenance program, periodic inspections of the machinery are made in order to assess the current operating condition of the machine. Data collected during the periodic inspections is typically stored and trended over time as an additional measure of the machine's operational health. The periodic inspections often involve multiple technologies including oil sampling and analysis, infrared thermography analysis, and vibrational analysis. For example, vibrational analysis is usually accomplished with the aid of a portable instrument which senses and processes vibration generated by the machine. These portable instruments, which are often referred to as data collectors or data analyzers, typically include a vibration transducer attached to what is essentially a highly specialized hand-held computer. The maintenance technician places the vibration transducer against a predefined test point of the machine. In a typical application, the resultant machine vibration signal produced by the transducer is provided to the data collector where the data is processed (and perhaps analyzed) according to predefined conditions and stored for later downloading to a machine database which has been previously set up on a host computer. The host computer analyzes the vibration data for faults or other anomalous conditions and machine data is stored in the database.
- Machines within a facility are typically monitored according to a route which is generated by a maintenance technician and programmed into the data collector with the aid of the host computer. The route typically includes a list of machines, measurement test points, and setup conditions for each test point. There are usually many machines in the route with many test points on each machine, and for each test point there may be specified a vibration frequency range to be analyzed, a type of analysis to be performed, a particular type or set of data to be measured and stored, and similar other data collection and analysis parameters. In response to commands from the user, the hand held instrument prompts the user for the identity of the machine and the test point to be monitored, and it automatically sets up the instrument, for example, to accept the specified frequency range for the test point, perform the specified analysis and store the specified type or set of data. A Fast Fourier Transform analysis may be performed on a pre-selected frequency range of the data and all or part of the resulting frequency spectrum may be stored and displayed. As the user progresses through the many machines and the corresponding test points, he collects and stores measured data which is subsequently transferred to the host computer for long term storage and further analysis.
- In a typical predictive maintenance program as described above, the user or maintenance technician defines each test point for each machine, including the location for each test point, analysis parameters sets including the type and quantity of data to take for each test point, the type of analysis to be performed on the data, frequency ranges, alarm levels, and the like. The locations of the test points and the parameters or settings chosen for each test point vary depending on the type, size and combinations of machines. For example, a motor driving a fan may have different test points and settings than the same motor driving a pump. Defining a predictive maintenance program of this type for such a large number of different machines requires a great deal of expertise on the part of the maintenance technician. Such expertise is typically gained only through years of experience and/or extensive training including training on how to select a probe/sensor, which parameters to measure for a particular machine, locations corresponding to the most data rich points for measuring particular parameters, frequency ranges, analysis alarm limits, and other such information. The maintenance technician must define the measurements points, analysis parameter sets, and alarm limit sets, and he must integrate these items into a useable database setup. Further complicating the maintenance technician's task is the fact that knowledge and expertise gained through the experience of engineers and technicians is too often not shared among users and others skilled in the art. More common is the situation where expertise is lost as a result of job changes and the like. Even when expertise is documented in user's manuals or lab notebooks, a great deal of studying and understanding is required in order for the information to be put to proper use.
- The difficulty and complexity of providing the settings for each measurement point may be more fully appreciated by considering the settings disclosed for measurement point examples in the following detailed description. While a relatively small number of examples are discussed herein, it will be understood that a typical predictive maintenance database will have hundreds of measurement points with each measurement point typically having multiple settings. In predictive maintenance databases involving vibration, each measurement point will typically have many settings, often 50 or more.
- Clearly, the proficiency and skill required to define an acceptable predictive maintenance program for a machine is beyond the abilities of a layperson. Because of the complexity involved and the expertise needed to properly set up an adequate predictive maintenance program or model, data technicians have been known to simply use the default settings provided by vendors of data collection/analysis instruments.
- What is needed, therefore, is a simplified method and apparatus for creating a predictive maintenance database. The solution should include the integration of machine database setup with the use of multiple measurement technologies, and it should be capable of pooling the scattered expertise of predictive maintenance modelers and significantly reducing the level of skill and expertise needed to establish an adequate predictive maintenance program.
- With regard to the foregoing and other objects, the invention in one aspect provides a method for establishing a predictive maintenance database that defines information needed to monitor components in accordance with a predictive maintenance plan. In the method, a component type corresponding to a particular component to be monitored is identified, and physical characteristic information is also identified which corresponds to the identified component type and the particular component to be monitored. A knowledge base in the computer defines relationships between monitoring practices, component types and physical characteristic information for component types, and an inference engine operates in part on the knowledge base to construct predictive maintenance databases. Information for a predictive maintenance database is constructed for each component to be monitored using the inference engine operating on the knowledge base, the selected component type and the selected physical characteristic information.
- In accordance with the above method, the database information for the predictive maintenance database may be constructed in a number of ways based on a number of factors. For example, the database information may be constructed to correspond in part to a defined type of data to be measured for the identified component type and/or defined measurement points on the component from which data will be measured. An analysis parameter set may also be defined by the constructing step, including setup parameters for use by a data collection instrument to collect data in accordance with the predictive maintenance database. Additionally, an alarm limit set may be defined by the constructing step including alarm limits delineating normal and abnormal component operation for data measured in accordance with the database.
- Further, constructing the database information may include recommending a plurality of measurement points for measuring operating characteristics of the component in accordance with the predictive maintenance plan.
- Additional steps in the method may include specifying a recommended type of component operating characteristic to be measured at each of the plurality of measurement points, and specifying a recommended alarm limit delineating normal and abnormal operation for a recommended type of component operating characteristic to be measured at a particular one of the plurality of measurement points. An image of the component being monitored may be displayed with locations being designated on the component image corresponding to one or more of the plurality of measurement points. An operational significance of the selected component type may be specified. The selected component type and the selected physical characteristics may be stored and later used for establishing further predictive maintenance databases. When collecting data in accordance with the predictive maintenance program, a user is prompted to place an appropriate measurement device at a measurement point to measure a component operating characteristic.
- The present invention also provides a programmable apparatus for establishing a predictive maintenance database defining information needed to monitor components in accordance with a predictive maintenance plan. In the apparatus, a knowledge base defines relationships between monitoring practices, component types and physical characteristic information for component types. A data processor is connected to the memory and includes an inference engine for operating in part on the knowledge base to construct database information for a predictive maintenance database. Based on user input provided through a user interface, the data processor is programmed to identify a component type corresponding to a particular component to be monitored, identify physical characteristic information corresponding to the identified component type and the particular component to be monitored, and construct information for a predictive maintenance database for each component to be monitored using the inference engine operating on the knowledge base, the identified component type and the identified physical characteristic information.
- In accordance with another aspect of the preferred method, a plurality of component groups are displayed, and a user is prompted to select at least one of the component groups. User input identifies a selected component group corresponding to a particular component to be monitored. A plurality of component types is displayed corresponding to the selected group, and the user is prompted to select at least one of the component types. A user input is received identifying a selected component type corresponding to the particular component to be monitored. Physical characteristic types are displayed corresponding to the selected component type, and the user is prompted to provide physical characteristic information corresponding to the physical characteristic types to further define a component to be monitored. Physical characteristic information provided by the user is accepted. A knowledge base is provided in the computer and defines relationships between monitoring practices and component types and physical characteristic information for component types. An inference engine is also provided in the computer for constructing database information for predictive maintenance databases based in part on the knowledge base. The knowledge base is used to select measurement specifications based on the selected component type and the physical characteristic information provided by the user. The database information is constructed using the inference engine operating on the knowledge base, the selected component type, the selected physical characteristic information, and the user defined measurement specifications.
- The present invention also provides a method for associating a machine component with physical information in a computer to define a component configuration for use in establishing a predictive maintenance database for the component configuration. This method involves identifying a component type corresponding to a particular component to be monitored where the particular component to be monitored has a plurality of physical component parameters. Information is specified which corresponds to one or more of the plurality of physical component parameters. For example, the specified information may include the operating speed of the particular component to be monitored. A component configuration is produced from the identified component type and the specified information.
- The method may further include the steps of associating with the component type at least one of a plurality of measurement technologies. Database information for predictive maintenance database is then constructed based on the identified component type, the specified information, and said one or more selected measurement technologies.
- Another method according to the present invention involves graphically associating a plurality of machine components in a computer to define an equipment configuration for use in establishing a predictive maintenance database for the equipment configuration. In this method, a first component type is identified which corresponds to a first component to be monitored. A second component type is likewise identified which corresponds to a second component to be monitored. For each of the first and second component types, component information is specified which corresponds to physical characteristics of the component. Component configurations are produced for each of the first and second components based on the specified component types and component information. A physical coupling between the two components is defined, and an equipment configuration is produced from the two equipment configurations and the physical coupling.
- In accordance with a further aspect of the invention, there is provided a method for establishing a predictive maintenance database in a computer that defines information needed to monitor components in accordance with a predictive maintenance plan. The method includes identifying a component type corresponding to a particular component to be monitored. A master file of information is provided in the computer which includes at least component identification information and corresponding predictive maintenance database information that specifies the types of measurements needed by the predictive maintenance plan for each component in the master file. The master file is searched for component identification information corresponding to the identified component type to produce at least one set of component identification information, and a set of component identification information is selected from the at least one set of component identification information. Finally, database information is constructed for a predictive maintenance database for the component to be monitored using the set of selected component identification information and the predictive database information corresponding to the set of selected component identification information.
- The master file of information may include component identification information in the form of the name of component manufacturers, component model numbers, or both. The component identification information may also physical criteria corresponding to physical characteristics of components.
- Predictive maintenance database information may include measurement point locations identifying points on components where predictive maintenance data is to be measured in accordance with the predictive maintenance plan. Types of measurement analyses to be performed in accordance with the predictive maintenance plan may also be included as predictive maintenance database information.
- Searching of the master file for component identification information may be accomplished by searching based on manufacturer name and model number. The master file may also be searched based on physical criteria of the component.
- The above and other features, aspects and advantages of the present invention will now be discussed in the following detailed description and appended claims considered in conjunction with the accompanying drawings in which:
- FIG. 1 is a functional block diagram of a programmable apparatus for use in establishing a predictive maintenance database in accordance with the present invention;
- FIG. 2 is a flow diagram of a program for controlling operation of the apparatus of FIG. 1;
- FIG. 3 is a user interface screen which enables the user to initiate creation of a new predictive maintenance database and to initiate modification of an existing predictive maintenance database in accordance with the present invention;
- FIG. 4 is a user interface screen prompting the user to select predefined predictive maintenance technologies to be incorporated into the creation of a new predictive maintenance database;
- FIG. 5 is a user interface screen prompting the user to define information corresponding to the location of equipment to be monitored in accordance with the new predictive maintenance database being created;
- FIG. 6 is a user interface screen prompting the user to define information corresponding to the type of equipment to be monitored and the operational significance of the equipment;
- FIG. 7 is a user interface screen prompting the user to define information for use by the program of FIG. 2 in creating vibration monitoring elements of the predictive maintenance database;
- FIG. 8 is a user interface screen prompting the user to define information for use in creating thermography monitoring elements of the predictive maintenance database;
- FIG. 9 is a user interface screen of a main program screen which provides a tree structure of database files and enables the user to launch a detailed configuration of equipment represented by a file shown in the tree structure;
- FIG. 10 is a user interface screen from which the user has initiated definition of a new equipment configuration file entitled “Boiler
Feed Pump # 1” defining physical characteristics of a boiler feed pump to be monitored; - FIG. 11 is a user interface screen for defining components and component connectivity of the new configuration;
- FIG. 12 is a user interface screen prompting the user to define general motor configuration information;
- FIG. 13 is a user interface screen prompting the user to define information corresponding to motor type;
- FIG. 14 is a user interface screen prompting the user to define physical characteristics of the motor;
- FIG. 15 is a user interface screen prompting the user to define bearing types;
- FIG. 16 is a user interface screen which enables the user to select bearing information from a list of known bearings;
- FIG. 17 is a user interface screen from which known bearings can be looked up and imported into the component definition;
- FIG. 18 is a user interface screen showing motor vibration measurement points selected by the program of FIG. 2;
- FIG. 19 is a user interface screen showing that the motor is configured for the vibration technology selected in FIG. 4 and the user is initiating configuration of the motor for another technology;
- FIG. 20 is a user interface screen prompting the user for general motor information;
- FIG. 21 is a user interface screen prompting the user for information corresponding to rated operating parameters of the motor;
- FIG. 22 is a user interface screen showing motor measurement points selected by the program of FIG. 2;
- FIG. 23 is a user interface screen in which the user initiates configuration of the motor for thermography data collection;
- FIG. 24 is a user interface screen which enables the user to provide information for use in selecting thermography measurement points for the motor;
- FIG. 25 is a user interface screen which enables the user to initiate configuration of the pump for vibration technology;
- FIG. 26 is a user interface screen prompting the user for general pump information;
- FIG. 27 is a user interface screen prompting the user for additional pump information;
- FIG. 28 is a user interface screen showing pump vibration measurement points selected by the program of FIG. 2;
- FIG. 29 is a user interface screen showing the pump and motor components as being configured with an unconfigured coupling between the pump and motor;
- FIG. 30 is a user interface screen showing the pump, motor, and coupling as being configured;
- FIG. 31 is a user interface screen from which the user may initiate creation of a predictive maintenance database in accordance with the invention;
- FIG. 32 is a user interface screen showing the progress of the program of FIG. 2 while creating a predictive maintenance database;
- FIG. 33 is a user interface screen of a main program screen for a database viewing program which enables viewing and editing of information contained in predictive maintenance database files created in accordance with the present invention;
- FIG. 34 is a user interface screen of the database viewing program which displays measurement points created by the main program;
- FIG. 35 is a user interface screen of the database viewing program showing detailed measurement point information;
- FIG. 36 is a user interface screen of the database viewing program showing additional detailed measurement point information;
- FIG. 37 is a user interface screen of the database viewing program showing a list of analysis parameters created by the main program;
- FIG. 38 is a user interface screen of the database viewing program showing analysis parameter details for time waveform and frequency spectrum data collection;
- FIG. 39 is a user interface screen of the database viewing program showing additional analysis parameter details for frequency ranges in which measurements are taken;
- FIG. 40 is a user interface screen of the database viewing program showing a list of alarm limits which correspond to the analysis parameters of FIG. 37;
- FIG. 41 is a user interface screen of the database viewing program showing amplitude limits defining multiple levels of alarming;
- FIG. 42 is a user interface screen from which the user has initiated definition of a new equipment configuration file entitled “
Condensate Pump # 1” defining physical characteristics of a condensate pump to be monitored; - FIG. 43 is a user interface screen prompting the user to specify whether existing configuration information will be used to configure the condensate pump;
- FIG. 44 is a user interface screen which enables the user to select from a list of known motor types for use in configuring the condensate pump;
- FIG. 45 is a user interface screen prompting the user for general information corresponding to the condensate pump motor;
- FIG. 46 is a user interface screen for displaying motor construction information;
- FIG. 47 is a user interface screen for displaying motor bearing information;
- FIG. 48 is a user interface screen for displaying additional bearing information;
- FIG. 49 is a user interface screen showing motor measurement points;
- FIG. 50 is a user interface screen showing configured and unconfigured components of the condensate pump;
- FIG. 51 is a user interface screen showing information corresponding to a component of the condensate pump;
- FIG. 52 is a user interface screen showing a completely configured condensate pump;
- FIG. 53 is a table of candidate measurement points for an AC induction motor showing how operational significance relates to measurement point selection; and
- FIG. 54 is a user interface screen showing a master component/database file and related data fields for constructing a predictive maintenance database using a lookup technique.
- With reference now to the drawings in which like reference characters designate like or similar parts throughout the several views, FIG. 1 shows in block diagram form a
programmable apparatus 10 for establishing a predictive maintenance database defining information needed to monitor equipment (such as electric motors, pumps, bearings, and the like) for anomalous or faulty operation in accordance with a predictive maintenance plan. Theapparatus 10 includes acomputer 20 having adata processor 22 and associatedmemory 28, adisplay 26, and a user interface 24 (such as a mouse and/or keyboard) for inputting user information and commands to thedata processor 22. Acommunications port 30, such as a serial infrared data port, is provided to enable thecomputer 20 to communicate with a peripheral device. When images of monitored equipment are desired, adigital camera 32 may be provided for capturing digital images of equipment which are provided to thedata processor 22 for processing and display on thedisplay 26. - In a preferred embodiment, the
data processor 22 is a Pentium™ processor runningWindows™ 95 or Windows™ NT Workstation as the operating system. When programmed in accordance with the invention, thecomputer 20 provides a straightforward, user-friendly environment in which users, including inexperienced maintenance technicians, can quickly and efficiently create a predictive maintenance database or create an area or component that may be incorporated into an existing predictive maintenance database. - As an initial matter, defining a few terms commonly used herein should be helpful. By use of the term “area” herein, what is meant is a location within a site such as a building. A “site” is a grouping of areas. A site is usually equated with a plant. A “component” is an item to be monitored in accordance with appropriate predictive maintenance principles. Motors, engines, gearboxes, pumps, fans, and like items are examples of components. A “configuration” is a detailed definition of one component or of two or more interconnected components, such as a motor driving a pump. “Equipment” is rather broadly defined as including components, groups of components, and configurations. For rotating machinery, the term “equipment” may be used to refer to a machine train consisting of components connected via a coupling. “Operational Significance” is a general rating that indicates the relative criticality of proper operation of equipment to the activities of the site. Values for operational significance include “critical”, “essential”, “important”, “secondary”, and “non-essential”.
- Operation of the
computer 20 to establish a predictive maintenance database in accordance with a preferred embodiment of the invention is illustrated in the flow diagram of FIG. 2 (hereinafter referred to as the “program 40”). As will be seen, theprogram 40 combines user input with stored information to create new predictive maintenance database files, or to modify or edit an existing predictive maintenance database file, in a fraction of the time and effort previously required with conventional approaches. - The program includes three major subsystems—a
main program 42, acomponent design studio 44, and aninference engine 46. Themain program 42 accepts site information from theuser 48 and assists theuser 48 in describing the site information. It leads theuser 48 through the creation of areas and equipment that match the topology of the site to be monitored. Theuser 48 may also provide information relative to the monitoring technologies to be applied and the monitoring hardware to be used as part of the predictive maintenance plan implemented by the predictive maintenance database. - The
component design studio 44 is a drag-and-drop graphical user interface tool that enables theuser 48 to define new equipment and edit existing equipment, including components and configurations, for predictive maintenance databases. It enables theuser 48 to graphically associate machine components, such as a pump being driven by a motor. Component and configuration definitions can be stored and reused for further equipment definitions. Thecomponent design studio 44 also prompts theuser 48 for information relating to physical characteristics of the equipment to be monitored. For example, if the equipment to be monitored is an electric motor, physical characteristic information would preferably include the spatial orientation of the motor (i.e., vertical or horizontal), number of poles, number of stator bars, rated running speed, and other information. The physical characteristics information may also be stored and reused for further equipment definitions. - In a preferred embodiment, the graphical user interface (GUI) is a standard Microsoft Windows™ Single Document Interface (SDI) application. The application includes a main window that may contain one or more data views. One of these views is a tree that shows the hierarchy of items created by the user. Other views, based on the currently selected tree item, show the properties of the selected item and provide access to other user interfaces which aid the
user 48 in creating and modifying equipment definitions and databases. - Common configurations and component definitions may be stored in one or more
component warehouse databases 64 which can be accessed by thecomponent design studio 44, thus eliminating the need for theuser 48 to create configuration and component definitions for equipment that has been previously defined and stored in acomponent warehouse database 64. For configurations, component identifiers and connectivity information are stored in thewarehouse 64. For components, the physical characteristics are stored in thewarehouse 64. In a preferred embodiment, two types of warehouses are available to theuser 48. One type of warehouse is a read-only warehouse containing a large number of ready to use component and/or configuration definitions and is provided by the program supplier as an integral part of theprogram 40. A second type of warehouse is one that is created by theuser 48 for storing configurations and components not included in the read-only warehouse. - The
main program 42 andcomponent design studio 44 produce a single program data file 50 that includes information entered by theuser 48 including site information and equipment definition information. This information may be modified by theuser 48 until theuser 48 is satisfied with its completeness and accuracy. At that time, theuser 48 may request that the program data file 50 be passed on to theinference engine 46. - The
inference engine 46 performs the task of taking user input relating to the physical characteristics of components and combining it with predictive maintenance knowledge to determine the best monitoring setup for those components. In this regard, theinference engine 46 receives the program data file 50 and creates a predictive maintenance database file by operating on data contained in the program data file 50 in conjunction with data and information contained in aknowledge base 52. Information contained in the predictive maintenance database file may be viewed and edited by adatabase program 54, which in a preferred embodiment is an RBMware™ predictive maintenance database program available from Computational Systems, Inc. of Knoxville, Tenn. Theinference engine 46 also enables the user to edit existing predictive maintenance database files 54. - The
knowledge base 52 contains empirical knowledge and information gained through years of experience in monitoring equipment. The primary references which had the most significant impact on the contents of theknowledge base 52 include observations of “best practices” by engineers experienced in the art of predictive maintenance. The various teachings of numerous text books and industry periodicals also shaped the contents of theknowledge base 52, including that portion of theknowledge base 52 which generates analysis parameter sets and alarm limit sets. Accordingly, predictive maintenance databases created by theprogram 40 will far exceed the quality of databases created by a novice, and will likewise deliver theexperienced user 48 quality databases which have been standardized across equipment types. - The information contained in the
knowledge base 52 defines a relationship between physical characteristics of a component type and optimal monitoring practices as determined from experience. For example, information in theknowledge base 52 includes measurement points for placement of sensors, types of sensors to place at the measurement points, and setup criteria for the measurement instrument (such as number of frequency lines, frequency filtering of sensor signals, frequency bands of interest, alarm limits, and the like). The number and types of measurement points created depends on the component's type and operational significance. For equipment which includes bearings, there will typically be three vibration measurement points per bearing located in each of the three directions (horizontal, vertical, and axial). Information contained in theknowledge base 52 may be edited to reflect advances in predictive maintenance know-how. - Analysis parameter sets, defining the types and amounts of data to be measured, setup criteria, and the like, are partially predefined in the knowledge base. The analysis parameter sets are different for different types of components and are used to setup a data collection instrument to collect data in an optimal way. The predefined analysis parameter sets are applicable for most components of a given type (motors, turbines, pumps, fans, and the like) and are organized into families of similar components.
- For each of the component types, a core group of sleeve and rolling element bearing analysis parameter sets exist. These analysis parameter sets are somewhat dependent on turning speed. The selection of a specific analysis parameter set is based on component type, measurement point RPM, bearing type, and similar information. The analysis parameter sets typically are unaffected by adjacent components and coupling information.
- For rotating equipment, the number of lines of resolution for frequency analysis is variable based on the reference turning speed of the equipment. This enables the
user 48 to have good frequency resolution over a wide range of operating speeds. - Alarm limit sets, defining criteria for generating fault alarms for parameters contained in the analysis parameter sets, are grouped by components similar to the analysis parameter sets. They are based on the type of equipment being monitored and the type of environment in which the equipment is operated. Each component type includes a family of alarm limit sets with each alarm limit family having a plurality of alarm grades, and some families may be accessed by multiple components. For example, in one embodiment, a family of alarm limit sets for AC induction motors is also used by AC synchronous motors. In addition, some alarm values are based on several factors such as driven component type, component RPM, and component weight and horsepower. Different levels of alarm severity are also assigned for some component types.
- The selection of an alarm limit set is also effected by alarm criteria which may be input by the user. Alarm criteria is preferably based on the operating environment of the equipment. Values for alarm criteria include “smooth”, “moderate”, and “rough” where a “smooth” alarm criteria represents a low threshold for alarming and “rough” represents a high threshold for alarming.
- The
inference engine 46 provides the capability for integration of multiple measurement technologies including vibration monitoring technology, motor monitoring technology,oil monitoring technology 56 andthermography 60. In operation, theprogram 40 prompts theuser 48 to specify a particular type of measurement technology to be applied. Theuser 48 provides information relative to the specified measurement technology, and theprogram 40 creates a predictive maintenance database file applying the measurement technology to a specified piece of equipment to be monitored. Multiple measurement technologies may be applied to each piece of equipment. - Data analysis for purposes of predictive maintenance is highly dependent on the quality of the collected data. Unfortunately, many
new users 48 do not have the knowledge and experience needed to properly configure a predictive maintenance database to be able to perform beneficial analysis. The present invention provides a user interface to theprogram 40 which enables theuser 48 to easily answer questions and to provide information used by theprogram 40 in constructing predictive maintenance database files. Theprogram 40 is designed to “fail safe” in the sense that, no matter how much or how little information theuser 48 knows about the equipment, theprogram 40 is able to create meaningful analysis parameter sets and alarm limit sets for quality data collection. - A
computer 20 running aprogram 40 in accordance with the invention receives the user inputs and creates a predictive maintenance database complete with equipment definition information, measurement points, analysis parameter sets, alarm limit sets, and equipment configuration information needed for expert analysis systems to perform detailed analysis on data that is collected. The following Example 1 describes a typical process for creating a predictive maintenance database for a boiler feed pump located within a site. Typically, a separate predictive maintenance database file is created for each site and each piece of equipment to be monitored within the site is included in the database file. Example 2 describes how the program enables theuser 48 to reuse previously configured components when adding new equipment configurations to the database or editing existing equipment configurations in the database. Example 3 provides a detailed explanation of how theinference engine 46 creates analysis parameter sets, alarm limit sets, and measurement points based on rules defined in theknowledge base 52 and/or theinference engine 46. As will be seen from the following examples, theprogram 40 enables theuser 48 to successfully create a predictive maintenance database even if theuser 48 knows very little about the equipment and needs to select the default answers provided by theprogram 40. - In considering the
knowledge base 52 and theinference engine 46, it is important to understand that there is not a unique correct way to monitor equipment. There are many correct ways to monitor a particular piece of equipment or a particular configuration, and there are many incorrect ways to do so. Thus, theknowledge base 52 and theinference engine 46 may vary widely, so long as they operate together to specify one of the correct setups for monitoring the specified equipment. The examples discussed below illustrate acorrect knowledge base 52 andinference engine 46, but the examples should not be construed as limiting the invention to any oneknowledge base 52 orinference engine 46. In particular, rules for defining measurement points, analysis parameter sets, and alarm limit sets may exist in either or both of theknowledge base 52 andinference engine 46. - FIGS.3-32 are images of user interface screens, or screen shots, of a typical “run” through the
program 40 for creating a predictive maintenance database for a boiler feed pump. The screens are displayed to theuser 48 atdisplay 26 and generally prompt theuser 48 for information which assists theprogram 40 in creating the database. - In FIG. 3, the
user 48 is asked whether he wishes to create a new predictive maintenance database or open an existing database for editing. Existing database files which theuser 48 may select are listed inwindow 70. In this example, theuser 48 has opted to create a new database. - To create the new database, the
program 40 will need to know which measurement technologies should be applied and which types of measurement hardware should be used. FIG. 4 prompts theuser 48 to provide this information. Inwindow 72, theuser 48 is asked to specify measurement technologies and inwindow 74 theuser 48 is asked to specify measurement hardware information. In FIG. 4, theuser 48 has selected all measurement technologies including periodic vibration, oil analysis, thermography, MotorView™ (an electrical motor analysis program available from Computational Systems, Inc. of Knoxville, Tenn.), and corrective analysis (a group of monitoring technologies available from Computational Systems, Inc. under the trade name UltraManage™). Inwindow 74, theuser 48 has selected “periodic vibration”. This selection takes theuser 48 to another screen from which theuser 48 selects specific periodic vibration hardware. - The
user 48 is next prompted in FIG. 5 to provide anarea name 76 and anarea identification 78. Thearea name 76 is typically a descriptive word name for the facility, such as “powerhouse”, and thearea identification 78 is typically a shortened term or group of characters that theuser 48 can identify. Here, theuser 48 has chosen the identification “PH01” to representpowerhouse # 1. - In FIG. 6, the
user 48 provides anequipment name 80, anequipment identification 82, and anoperational significance 84. As described above, values for operational significance of equipment include “critical”, “essential”, “important”, “secondary”, and “non-essential”. Theprogram 40 adjusts the measurement technique based on this input value. For example, a boiler feed pump which is “essential” to the operation of the powerhouse would be monitored at shorter intervals than one which is “non-essential”. In addition, more measurement points and types of measurement points would be created. - Since the
user 48 selected “periodic vibration” in FIG. 4 as the measurement technology, theuser 48 is prompted in FIG. 7 to specify various equipment parameters effecting vibration including the equipment orcomponent type 86, areference driver speed 88 of the equipment,speed units 90, areference load 92 corresponding to thereference operating speed 88, and analarm criteria 94. Alarm levels are adjusted automatically by theprogram 40 based on thealarm criteria selection 94. - In FIG. 8, the
user 48 is asked to provide setup information required by the technologies selected in FIG. 4. This information is used later during the detailed component setup. - A name for the equipment (Boiler feed Pump #1) has now been created within the “powerhouse” area and is ready to go through a more detailed configuration. The detailed configuration portion of the
program 40 is that portion of theprogram 40 which asks for information that enables the measurement information to be set up correctly. A detailed configuration of the boilerfeed pump # 1 is being launched from the main program screen shown in FIG. 9. This accomplished by selecting the file entitled “BoilerFeed Pump # 1” from the file tree structure shown inbox 93 and then selecting the “Configure”button 95. - In FIG. 10, the
user 48 has defined a new configuration file title “BoilerFeed Pump # 1” shown atwindow 96. Configuration information, including component types, couplings between components, and physical characteristics of components, are stored in the specified file. If desired, theuser 48 may elect to save configuration information in a user-definedwarehouse file 98. A read-only warehouse file is also provided as part of theprogram 40. At the screen shown in FIG. 10, theuser 48 may select a configuration which is already stored in one of the warehouse files, thus avoiding the need to define a configuration when the equipment (or like equipment) has been previously configured. - At the component design studio shown in FIG. 11, the
user 48 is asked to identify components of the new configuration. Since the boilerfeed pump # 1 includes a motor and a pump, each of the components are selected from the list of rotating components and displayed in thelower window 100 as anunconfigured motor 102 and anunconfigured pump 104. A dashedline 106 connecting themotor 102 and pump 104 represents an unconfigured coupling. These components may be configured for each technology that should be applied to the specific equipment. - A typical procedure for configuring the components shown in FIG. 11 will now be described. The
motor 102 will be configured first, then thepump 104, and last thecoupling 106 between the two. - General information relating to the motor is provided at the screens shown in FIGS. 12 and 13. This information is needed both for use in creating the data collection methods and also for the programs that analyze the data.
- Rotating equipment such as motors posses characteristics that will generate specific vibration frequencies when the equipment is running. The amplitude at these frequencies is used to determine the condition of the equipment. During the detailed configuration of the equipment, the
program 40 asks theuser 48 to input this information at the screen shown in FIG. 14, if known. For example, the user may input the number of phases, poles, rotor bars and stator slots, if known, for a synchronous motor. Theinference engine 46 uses this information in part to select appropriate analysis parameter information. - The
user 48 is next taken to the screen shown in FIG. 15 where theuser 48 is asked to select motor bearing types and thrust load location, if applicable. Bearings are an important element relating to the health of rotating equipment and are treated as such by theprogram 40. Bearing information is important in the setup of the measurement methods as well as the analysis of the data. FIG. 16 shows a screen from which bearings may be looked up from a list of known bearings, and FIG. 17 shows a screen that enables theuser 48 to look up bearings from master lists and import them into the component definition. - In FIG. 18, the
program 40 has processed the motor information entered by the user 48 (including the selected component type and the selected physical characteristics) and determined the best or optimal measurement points 103 for the motor. The best or optimal points chosen are those for which a check mark appears in the column titled “Active?”. A unique measurement point identifier (PID) 105 is generated and associated each with ameasurement point 103. In an alternate embodiment of the user interface screen shown in FIG. 18, an image of the motor is obtained from stored equipment diagram files 62 (FIG. 2) and the measurement points 103 are indicated on the motor image. In typical conventional methods, theuser 48 must possess substantial knowledge of predictive maintenance practices in order to identify the best measurement points 103. As seen in FIG. 18, theprogram 40 has identified these points for him. - In FIG. 19, the
motor 102′ is now configured for the vibration technology selected back in FIG. 4. Theuser 48 now chooses to configure the motor technology by selecting themotor icon 108 at the bottom of the screen. - As seen in FIGS. 20 and 21, the motor technology requests additional motor information from the user48 (for example, identification number, frame size, insulation class, rated RPM, rated power, rated voltage, and rated current). The information provided in FIG. 20 is used to determine measurement parameters for collecting data while the information provided by the
user 48 in FIG. 21 is used for analysis of the data. - FIG. 22 shows measurement points that are selected for the motor based on the information provided in FIGS. 20 and 21. The measurement methods are also altered based on that information.
- In FIG. 23, the
user 48 may select icon 110 at the bottom of the screen to configure the motor for infrared thermography data collection. Thermography measurement points are set up in the predictive maintenance database based on the information provided at the screen shown in FIG. 24. - The
user 48 selectsicon 112 shown at the bottom of the screen of FIG. 25 to configure the driven component (i.e., the pump) for the vibration technology. This selection takesuser 48 to the screen shown in FIG. 26 which prompts theuser 48 to provide the requested information. Often, a user may not know all of the configuration information that theprogram 40 requests. In such a case, theuser 48 simply needs to answer what is known and theprogram 40 will create an optimal database from the information that is available. Users who know more information about the equipment details can enter this information into the screen shown in FIG. 26 and by selecting theadvanced screen button 114 located in the lower left hand corner of the screen. The additional information will be reflected in the setup of the actual predictive maintenance database as it is built. - Additional information is requested in FIG. 27. Information relating to the
pump type 116,pump support 118, pumpedfluid 120, number ofstages 121 and number of inlet/outlet impeller vanes 123, is used by theprogram 40 to establish measurement parameters, while information such asinlet type 122 and number of inlet/outlet diffuser vanes 125 are used to determine specific analysis frequencies. - Measurement points124 (FIG. 28) are established by the
program 40 based on the information entered in FIGS. 26 and 27, and the measurement points 124 are displayed on the screen shown in FIG. 28. Each measurement point is identified by a unique measurement point identifier (PID) 126. The measurement points are used by theprogram 40 to establish the measurement parameters and locations. - The
user 48 is taken to the component design studio 44 (FIG. 2) in FIG. 29 where thecoupling 106 between the configuredmotor 102′ and the configuredpump 104′ is defined. Thecoupling 106 attaches the driver, in this case amotor 102′, and a driven unit, in this case apump 104′. The type of coupling can effect the speed of the driven unit. - In the
program 40, theuser 48 simply inputs the type of coupling and any speed ratio information. Coupling types can be found by expanding the menu selection under “Existing” shown at 124. This information enables theprogram 40 to calculate the correct measurement point speeds. The speed at each measurement point is an important piece of information used by theprogram 40 to establish analysis parameters which control how data is measured and subsequently analyzed. - The “boiler
feed pump # 1” is now configured in FIG. 30, including a configuredcoupling 106′. Theuser 48 is now ready to instruct theprogram 40 to create a predictive maintenance database for the configured equipment. Theuser 48 accomplishes this by returning to the main program screen, shown in FIG. 31 (see also FIG. 9), and clicking thehammer icon 128. As shown in FIG. 32, pop-upprogress screen 130 enables theuser 48 to monitor the progress of theprogram 40 as the database is created. A predictive maintenance database file is created and can be viewed and edited with a commercially available database program 54 (FIG. 2), such as DBASE, as shown in FIGS. 33-41. - FIG. 33 provides a view of the main program screen from the DBASE program. The screen indicates to the
user 48 that two equipment configurations (“BoilerFeed Pump # 1” and “Condensate Pump # 1”) are included within the PH01 Powerhouse area of the database. From the screen shown in FIG. 33, theuser 48 may edit, move, delete, and generally manipulate data contained in the database by use the appropriate buttons shown in the upper right-hand portion of the screen. These buttons are generally indicated at 182. To examine the measurement points output by theprogram 40 for the BoilerFeed Pump # 1, theuser 48 selects “BoilerFeed Pump # 1” and then clicks the “OK”button 180 located in the lower right-hand portion of the screen. - A list of measurement points created by the
program 40 to monitor the “BoilerFeed Pump # 1” is shown in FIG. 34. Included in the list are points for measuring vibrational displacement at the outboard side of themotor 184, vibrational displacement at the inboard side of themotor 186,motor leakage flux 188,temperature 190, and others. The list also includes points for visual observations made by theuser 48, including observation ofmotor cleanliness 192 and observation of air flow through themotor 194. - FIGS.35-41 illustrate various detailed information which is included in the database for each measurement point. Some of the information is based on data input to the
program 40 by theuser 48. As shown in FIG. 35, theuser 48 is able to view and edit measurement point information including ameasurement point identifier 192,measurement point description 194, measurement units andcode 196, motor rpm at themeasurement point 198,monitoring schedule 200, and number of values instatistical calculations 202. The screen shown in FIG. 35 also shows that data collection set information 204 (used during actual field data collection) is included in the database. The data collection set information includes an analysis parameter set 206 and an alarm limit set 206. - Additional measurement point information shown in FIG. 36 includes
probe type 204,sensor orientation 206,sensor position 208, sensitivity of thesensor 210, highest and lowestacceptable signal levels 212, and other detailed information. - At the screen shown in FIG. 37, the
user 48 is provided a descriptive list of analysis parameters which are included in the analysis parameter set 206 created by theprogram 40. Included in the list is an AC motor rollingbearing analysis parameter 212, apeakvue analysis parameter 214, an electric current-rotorbar condition parameter 216, motor shaft current andvoltage measurement parameters 218, and others. - The analysis parameter sets control the manner in which data is collected. These sets control two basic items. The first is time waveform and frequency spectrum data collection along with any special signal processing. The
user 48 may view and edit spectrum and waveform information contained in the database for each of the analysis parameters listed in FIG. 37. For example, in FIG. 38 theuser 48 is able to view detailed information relating to waveform and frequency data collection parameters foranalysis parameter number 1 entitled “AC MTR, ROLLING BRG (1600). Included in this information is thespectral frequency setup 220, low frequency signal conditioning limit 222 (for noise elimination), upper and lower frequency limits 224, number of spectral lines to be acquired 226, number ofaverages 228, and type ofanalysis window 230. - The second item in the parameter analysis set is the parameter bands (i.e., frequency ranges in which the amplitude is measured) that will be measured and trended by the DBASE database program. As shown in FIG. 39, the analysis parameter sets are scalar values that correspond to waveform characteristics or integrated energies over specified frequency ranges in the spectrum. These may include the maximum peak to peak
value 232 in the waveform,crest factor 234, a narrow frequency interval around on times turning speed (TS) 236, the amplitude of all frequencies in a wide interval from 3.5 to 10.5×TS, and others. Each of the parameter bands is displayed in FIG. 39 according to a descriptive title, units type, type of parameter, and lower and upper frequencies. Additionally, each parameter band is selected by theprogram 40 based on information, including type of equipment and component information, that was input to theprogram 40 by theuser 48. - As described above, the
program 40 also creates alarm limit sets which correspond to the analysis parameter sets. Alarm limit sets typically vary between different types of equipment and are generally dependent on expected amplitude levels. In FIG. 40, the DBASE database program has displayed by descriptive title a list of alarm limit parameters. Included in the list is an AC motor rolling bearing (moderate) 242, Peakvue (moderate) 244,skin temperature 246, rollerelement bearing temperature 248, shaft current andvoltage alarms 250, and others. - Each alarm limit set contains amplitude limits which are compared to the trended data in the analysis parameter bands. The amplitude levels are based on the type of equipment input to the
program 40 by theuser 48 and the unexpected operational conditions. FIG. 41 shows the alarm limits for the twelve analysis parameters given in FIG. 40. Included in FIG. 41 is a column specifying for each alarm limit theunits code 252, alarm type 254, an alarm limit value indicative of a significant failure or fault 256, an alarm limit value indicative of a less severe failure or alert 258, and other information. - As this example has shown, a user who knows very few equipment details, or a user who knows all equipment details, can use the
program 40 to create a predictive maintenance database. Theprogram 40 creates a predictive maintenance database that is more than adequate for data collection and analysis purposes, even when few details are known about the equipment. The more information that can be input into theprogram 40, the more detailed the measurement points, analysis parameter sets, and alarm limit sets will be. - Referring again to FIG. 30, the “boiler
feed pump # 1” configuration may be reused to define other like configurations for the creation of additional configurations in predictive maintenance databases. In addition, each of thecomponents 102′, 104′, 106′ and their corresponding templates may be reused in defining other equipment configurations, as illustrated in Example 2 given below. - In this example, FIGS.42-52 will be used to illustrate the ability of the
program 40 to reuse already configured components when configuring equipment. - As shown in
box 140 of FIG. 42 (see also FIG. 10), the new configuration created in this example will be called “condensate pump # 1”. Completed configurations are listed inbox 142. - At the screen shown in FIG. 43, the
user 48 is prompted to specify whether existing configuration information will be used. Existing information can be recalled from one of three types of stored information, includingcomponent information 144, template information 146, andconfiguration information 148. Component information includes the appropriate template information as well as bearing setup information. Template information contains detailed machine setup information (excluding bearing setup information) and is stored in a component warehouse 64 (either a read-only warehouse or a user-defined warehouse). Elements of a component that are not changeable are considered as template information. Configuration information includes complete equipment train information, which usually consists of at least one driver and one driven component connected by a coupling. Theuser 48 clicks the template 146 selection and is taken to the screen shown in FIG. 44. - In FIG. 44, it can be seen that the template146 may be selected from a
local file 153, a user-definedcomponent warehouse 154, or a read-only component warehouse 155. Thelocal file 153 includes templates that theuser 48 will reuse only in the present database. Typically, such templates are created for equipment that can be found at only one site. Theuser warehouse 154 includes templates which have been configured and stored by theuser 48 and can be edited, and thesupplier warehouse 155 includes templates provided by theprogram 40 supplier and cannot be edited. A list of standard motor types contained in thesupplier warehouse 155 are displayed inbox 152, and amotor 150 has been selected from the list. Although there is template information present in thecomponent warehouse 155 for the selectedmotor 150, themotor 150 is considered to be unconfigured at this point since the physical characteristics have not yet been defined. - General component definition information is provided by the
user 48 in FIG. 45 (see also FIG. 12). The motor component will be created based on the information contained in the template identified inbox 156, which is grayed out and not editable since this template is part of a predefined component warehouse that was provided with theprogram 40. Information corresponding to motor construction and bearing types is grayed out in FIGS. 46 and 47 (see also FIG. 14) as well. Thus, while the information can be displayed, it is not changeable by theuser 48. - Detailed bearing information is required, however, and this information is defined by clicking the “Advanced”
button 158 which brings up the screen shown in FIG. 47. By clicking on next, the bearing screen shown in FIG. 48 is displayed. The bearing information shown in this screen has been input by theuser 48. - After the above information has been provided, measurement points160 and
corresponding identifiers 162 are created and displayed as shown in FIG. 49. The measurement points 160 can be edited by theuser 48. - In FIG. 50, the motor151′ is now configured. The
user 48 has selected agearbox 164 from a list of predefined gearbox components displayed inbox 166. Apopup box 168 prompts theuser 48 as to whether the gearbox should be edited. Clicking “Yes” takes theuser 48 to the screen shown in FIG. 51. Since all information relating to the gearbox has been predefined in the component warehouse, theuser 48 may only examine the information shown in FIG. 51. - In FIG. 52, the “
condensate pump # 1” configuration has been completed. The configuration includes themotor 150′,gearbox 164′, apump 170 which was selected from thelocal file 153 and not edited, acoupling 172 interconnecting thepump 150′ andgearbox 164′, and acoupling 174 interconnecting thepump 170 andgearbox 164′. Theuser 48 is now ready to insert this information into his predictive maintenance database as described above with reference to FIGS. 31-33 (note that FIG. 32 includes the “condensate pump # 1”) and to view or edit the new database information as described in FIGS. 34-41. - As previously mentioned, there is no unique
correct knowledge base 52 orinference engine 46. Both must necessarily be constructed according to a particular application. Theknowledge base 52 is a set of information and rules. The information is physical data and the rules relate different types of physical data one to the other. For example, a rule could relate a particular motor type of a particular physical description to a set of measurement points. Theknowledge base 52 does not directly relate anything to a predictive maintenance database. - The
inference engine 46 relates data in theknowledge base 52 and data generated by the knowledge base and its rules, collectively or individually, to a particular set of data in a predictive maintenance database. Since these concepts are somewhat complicated, they may best be understood by reference to a simplified example of aknowledge base 52 andinference engine 46 as given below in Example 3. - In this example, information for a predictive maintenance database will be created for an AC induction motor. The following information was known about the motor and was input to the
program 40 to configure the motor: - Number of Phases: 3
- Number of Poles: 2
- Number of Rotor Bars: 68
- Number of Stator Slots: 54
- Inboard Bearing: antifriction
- Outboard Bearing: antifriction
- Shaft RPM: 3575
- Probe Type: casing
- Line Frequency: 60 Hz
- Based on this information, the following steps illustrate how the analysis parameter and alarm limit sets were created by the
program 40. It is worth noting that it is common for auser 48 to not know all of the information given above. As previously described, minimal information is needed for theprogram 40 to create the analysis parameter sets and alarm limit sets. For rotating equipment such as AC induction motors, the absolute minimum information needed is the specification of an equipment type and the speed of the equipment. - Analysis Parameter Set Creation
- Step 1: The first rule for an AC induction motor is to create the analysis parameter (AP) set and alarm limit (AL) set based on bearing type and name the sets as follows:
- Create AP Set “AC MTR,ROLLING BRG”
- Create AL Set “AC MTR,ROLLING BRT”
- Step 2: Next, following rules for AC motors, the
inference engine 46 will in the measurement details of the analysis parameter set as follows: - Set the Maximum Analysis Frequency=70.5 Orders
- Set the Minimum Analysis Frequency=0.0 Orders
- Set the Lines of Resolution=1600 lines
- Set Number of Averages=5
- Set Spectral Averaging Mode=Normal Mode
- Set Window Type=Hanning
- Set Spectral Weighting=None
- Set Perform ⅓Octave Analysis=False
- No special signal processing parameters will be used.
- A special time waveform will be collected in acceleration units with the maximum time in the waveform based on a spectral Fmax of 80 orders with 1024 points in the waveform.
- The number of lines of resolution selected was based on the following rules:
- IF 3000<Turning Speed, THEN
- Set # Lines=1600
- IF 800<Turning Speed≦3000, THEN
- Set # Lines=800
- IF Turning Speed≦800, THEN
- Set # Lines=400
- Since the Turning Speed=3575 was greater than 3000, the number of lines set= 1600.
- Step 3: The remaining details of the parameter set forth above are default settings for this type of AC induction motor. For this type motor, the rules provide that the following parameter bands will be measured for trending:
- Peak to Peak Waveform band (Overall Amplitude)
- Crest Factor Waveform band (Overall Amplitude)
- Subharmonic Frequency band (0.0 to 0.8 orders)
- 1×Turning Speed Frequency band (0.8 to 1.4 orders)
- 2×Turning Speed Frequency band (1.4 to 2.4 orders)
- 3×to 8×Turning Speed Frequency band (2.4 to 8.4 orders)
- 9×to 25×Turning Speed Frequency band (8.4 to 25.4 orders)
- 25×to 75×Turning Speed Frequency band (24.4 to 75.4 orders)
- 1 kHz to 20 kHz High Frequency band (1000 to 20,000 Hz)
- Step 4: The following parameters bands will be created based on certain rules:
- 2×Line Frequency band (115 to 125 Hz)
- The creation of this band is dependent on the Line Frequency and the following rule:
- SET LF=Line Frequency, THEN
- SET HZ AP Band to Monitor: High freq=(2*LF)+5, Low Freq=(2*LF)−5
- The default value will be 60 Hz, which is the line frequency standard in North America.
- Based on the above rule, the parameter band for 2×Line Frequency band will trend the frequency range between 115 Hz to 125 Hz.
- Step 5: Next, the
inference engine 46 creates a parameter band to trend the frequency related to the number of rotor bars and a parameter band to trend the frequency related to the number of stator slots. - Rotor Bar Pass Frequency band (63.0 to 73.0 orders)
- Stator Slot Frequency band (49.0 to 59.0 orders)
- These frequency ranges were determined based on the following rule:
- IF Number of Stator Slots and Rotor Bars is known,
- ANDIF Number of Stator Slots>21
- AND Number of Stator Slots is divisible by 3, THEN
- Assume # of Rotor Bars and Stator Slots is correct
- ELSE Assume Stator and Rotor Bars is incorrect and use 0.0 for each.
- Rotor Bars pass freq range=(#rotor bars−5) to (#rotor bars+5) orders
- Sator Slot pass freq range=(#stator slots−5) to (#stator slots+5) orders
- Based on the number of rotor bars=68 and the number of stator slots=54 and the above rule, the Rotor Bar Pass Frequency band will trend the amplitude of the frequencies between 63.0 and 73.0 orders while the Stator Slot Frequency band will trend the amplitude of the frequencies between 49.0 to 59.0 orders.
- Alarm Limit Set Creation
- The alarm limit set created by the
inference engine 46 will include alarm limits appropriate for each of the parameter bands described above. The alarm limit values are based on the type of equipment and the alarm criteria specified by theuser 48. For this example, the alarm criteria was set to moderate. If the alarm criteria had been set to “smooth”, the default alarm levels would be set at alarm limits which are lower than those for the “moderate” setting. Conversely, if the alarm criteria had been specified as “rough”, the default alarm levels would be set at alarm limits higher than those for the “moderate” setting. - Measurement Points
- FIG. 53 is a table of candidate measurement points which the
program 40 uses as rules to determine, based on the operational significance defined by theuser 48, which measurement points will be generated for an AC induction motor. The values of 1-5 are used in FIG. 53 to indicate operational significance where “critical” corresponds to an operational significance value of “1”, “essential” corresponds to “2”, “important” corresponds to “3”, “secondary” corresponds to “4”, and “non-essential” corresponds to “5”. In this example, the operational significance of the motor was set as “essential” which equates to an operational significance of “2” in the table shown in FIG. 53. Accordingly, each candidate measurement point for which a check mark appears incolumn 2 was selected as a measurement point for the motor. - In summary, the above examples and description explain how the analysis parameter sets, alarm limit sets, and measurement points are selected by the
program 40 based on information provided to theprogram 40 by theuser 48. The selections are made based on rules known by the program'sinference engine 46. The inference engine rules are preferably accepted industry practices which are likely to be unknown to a novice user of theprogram 40. The rules are designed to produce a predictive maintenance database which will allow theuser 48 to collect predictive maintenance data more correctly for each type of equipment that is to be monitored, even when minimal information is known about each piece of equipment, thereby enabling theuser 48 to achieve a greater degree of analysis accuracy with significantly less information, experience, and time. - It will be appreciated, however, that the rules are not invariable. For example, in some applications it may be unnecessary or undesirable to determine operational significance, and in such case, there would be no need for rules related to operational significance. Thus, the rules can and should be changed for different circumstances.
- Lookup Technique
- While it is preferred to use an
inference engine 46 andknowledge base 52 as described above, the invention may be implemented with a more simplistic lookup technique or combination of both the lookup technique and the inference engine technique. In the latter case, the user can choose between the two techniques. - As shown in FIG. 53, the lookup technique is selected from the pull-down menu labeled “Options”218. The lookup technique is preferably implemented by providing a Master Component/Database file 200 that contains at least two fields of data, namely, a
component identification field 202 and adatabase information field 210, each corresponding to a particular component, such as a motor or a pump. While it would be possible to use a single component identification field and a single database information field, in most applications these two “fields” will actually be a group of related fields. For example, the component identification field may include a separate field for the manufacturer'sname 204, themodel number 206, and eachphysical attribute 208 such as the horsepower rating of a motor or the number of rotor bars in a motor. Likewise, the database information field will normally include many different fields such as those disclosed in FIGS. 34-41. - To build a database using the lookup technique, the
user 48 first uses thecomponent identification field 202 to find and select a record in the master component/database file 200 corresponding to the component to be monitored. When the component record is selected, either automatically or by theuser 48, the database information (or record) found in the master component/database file 200 is added to the database that is being built. - As mentioned above, the
component identification field 202 may contain a number of fields containing physical attributes or physical descriptions of the component or a manufacturer and model number, and it preferably has both. To select a component, theuser 48 first names the component in the same manner as discussed above with reference to FIG. 6. Theuser 48 may also provide an operational significance and alarm information as discussed above, but this is not required. - After naming the component, a corresponding component record may be found in the master component/
database file 200 by two basic techniques. In one technique, theuser 48 provides physical criteria describing the physical component. For example, the user may provide the following physical criteria of a component such as a motor: 3 phases, 2 poles, 68 rotor bars, 54 stator slots, rated RPM of 3575, rated horsepower of 25, rated voltage of 440 volts and rated current of 200 amps. When theuser 48 is finished entering the physical criteria, he initiates a search, such as by clicking on asearch button program 40 searches the physical attributes in thecomponent identification field 202 for the best fit. Theprogram 40 may automatically select the best fit component record from the master component/database file 200 and automatically add the selected record to the database being built. However, preferably, theprogram 40 may also display a best fit group of component records and allow theuser 48 to select one record. The best fit group would usually include all of the component records that exactly fit the physical criteria provided by theuser 48, plus additional records that had physical attributes that were near the physical criteria provided by theuser 48. - The best fit group of records is prioritized with the most likely candidate record listed earlier or higher in the best fit group. Priority may be based on the closeness of the fit and/or the prevalence or popularity of the component in the market. For example, a component priority could be proportional to the quantity of the component manufactured or the quantity of the components in use in a particular market.
- When the
user 48 selects one record from the best fit group, such as by clicking on it, that selected record is associated with the name of the component previously provided by theuser 48, and the combined information is added to the database being created as another record. In this lookup technique, the database information is contained in the master component/database file 200 and there is no need to perform any operations on the information in the master component/database file 200 in order to generate database information for the database being created. - The other way of selecting a component record from the master component/
database file 200 is by using the manufacturer and model number. In this case, theuser 48 inputs the model number, which preferably includes the manufacturer as shown inblock 216 of FIG. 53 (i.e., “GE” represents General Electric as the manufacturer), and theprogram 40 searches the identification field for a record having the exact model number. If an exact match is found, it is either automatically chosen and the database being created is updated with the chosen record as described above, or the record having the exact match is displayed. Whether the selection is made automatically or manually is preferably determined by a user option. - If more than one exact match is found, all of the exact matches are displayed and the user is requested to select one. If no exact matches are found, a best fit group is displayed in the manner described before. The group is prioritized in an order based upon the closeness of the model number in a record as compared to the model number provided by the user and based upon the popularity or prevalence of each component in the group.
- The searching capabilities described above provide significant advantages over known predictive database programs. While it was certainly possible to copy portions of databases produced by prior art programs and attach such copies to another database, there was no specialized searching capability for finding what needed to be copied. To the extent that one database was used to make another, it was generally a manual process. In the lookup technique described herein, the searching capability enables the user to build a database systematically using some information about the machine or machines for which the database is being built. The searching feature is flexible in that a variety of information may be used to conduct the search, including physical information, model numbers or manufacturers. In addition the program provides for building a configuration composed of more than one machine and using the lookup technique for building a database for the overall configuration. In such case the lookup technique searches the master component/
database file 200 first for the specific combination of machines, such as a particular pump, coupling and pump. If the specific combination is found, it is used to construct the database. If the combination is not found, the master component/database file 200 is searched for the individual machines seperately and the database information for each machine is combined to produce the database for the overall configuration. - It will be appreciated that the lookup technique requires the use of a master component/
database file 200 that is typically much larger than any file necessary when the inference engine technique is used. To facilitate operations, the master component/database file 200 may actually exist as a number of files. For example, a separate file may be created for different types of components. A separate file may be provided for pumps, gear boxes, motors, etc. Also, separate files may be provided for different sub-categories of components, such as induction motors versus synchronous motors. Also, conventional searching techniques and enhancements would be used for searching and finding data within the files. Preferably, the data in all of the fields would be indexed to enhance searching. - If alarm information and/or operational significance information is to be included in the lookup technique, the database generated by the technique must reflect the operational significance and/or the alarm level provided by the
user 48. One way to incorporate operational significance into the lookup technique is to provide multiple entries (records) for the same component, with a separate record for each operational significance. In other words, if there were three levels of operational significance that auser 48 could choose, each component in the master component/database file 200 would require three separate records, one for each operational significance. Likewise, if alarm levels are used, each component must have a separate record for each alarm level. If both operational significance and alarm level is provided, the master component/database file 200 should have a separate record for each combination of operational significance and alarm level. For example, a first record must be provided for alarm level one, operational significance one, and a second record must be provided for alarm level one, operational significance two. It will be appreciated that the use of alarm levels and operational significance can cause the master component/database file 200 to grow dramatically. - To avoid this type of growth in the size of the files, one may blend the inference engine technique and the lookup table technique. For example, the lookup technique could be used to produce preliminary database information based solely on the component identity ignoring alarm level and operational significance. Then, an
inference engine 46 or a set of rules can be used to modify the preliminary database information based upon both the alarm levels and the operational significance provided by theuser 48. - It is contemplated, and will be apparent to those skilled in the art from the foregoing specification, drawings, and examples that modifications and/or changes may be made in the embodiments of the invention. Accordingly, it is expressly intended that the foregoing are only illustrative of preferred embodiments and modes of operation, not limiting thereto, and that the true spirit and scope of the present invention be determined by reference to the appended claims.
Claims (51)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US09/753,595 US20010001851A1 (en) | 1998-09-15 | 2001-01-02 | Database wizard |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US09/153,690 US6192325B1 (en) | 1998-09-15 | 1998-09-15 | Method and apparatus for establishing a predictive maintenance database |
US09/753,595 US20010001851A1 (en) | 1998-09-15 | 2001-01-02 | Database wizard |
Related Parent Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US09/153,690 Continuation US6192325B1 (en) | 1998-09-15 | 1998-09-15 | Method and apparatus for establishing a predictive maintenance database |
Publications (1)
Publication Number | Publication Date |
---|---|
US20010001851A1 true US20010001851A1 (en) | 2001-05-24 |
Family
ID=22548314
Family Applications (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US09/153,690 Expired - Lifetime US6192325B1 (en) | 1998-09-15 | 1998-09-15 | Method and apparatus for establishing a predictive maintenance database |
US09/753,595 Abandoned US20010001851A1 (en) | 1998-09-15 | 2001-01-02 | Database wizard |
Family Applications Before (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US09/153,690 Expired - Lifetime US6192325B1 (en) | 1998-09-15 | 1998-09-15 | Method and apparatus for establishing a predictive maintenance database |
Country Status (2)
Country | Link |
---|---|
US (2) | US6192325B1 (en) |
GB (1) | GB2345166B (en) |
Cited By (35)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20020046048A1 (en) * | 2000-07-11 | 2002-04-18 | Hidetada Fukushima | System, method, computer program, and recording medium for machine-management |
US20030048300A1 (en) * | 2001-09-10 | 2003-03-13 | International Business Machines Corporation | Wizard user interface providing interim system product generation and reversion during wizard traversal |
US20030065673A1 (en) * | 2001-10-01 | 2003-04-03 | Sun Microsystems, Inc. | Method and device for marking and filtering data elements in a database |
US20030135349A1 (en) * | 2000-07-04 | 2003-07-17 | Osamu Yoshie | System for diagnosing facility apparatus, managing apparatus and diagnostic apparatus |
US6604061B2 (en) * | 2000-07-13 | 2003-08-05 | Hitachi, Ltd. | Instruments management system and method and monitoring apparatus, database apparatus and data base client apparatuses and recording medium |
US20030225710A1 (en) * | 2002-05-29 | 2003-12-04 | Kirk Arneson | Automated package information and configuration communication process |
US20040078733A1 (en) * | 2000-07-13 | 2004-04-22 | Lewis Lundy M. | Method and apparatus for monitoring and maintaining user-perceived quality of service in a communications network |
US20040103106A1 (en) * | 2002-09-27 | 2004-05-27 | Matsushita Electric Industrial Co., Ltd. | Data processing apparatus, data processing method, and data processing program |
US20040150665A1 (en) * | 2000-10-13 | 2004-08-05 | General Electric Company | Selection of statistical tool |
US20050018745A1 (en) * | 2002-10-09 | 2005-01-27 | Peng Lee | Method to detect termite infestation in a structure |
US20050096873A1 (en) * | 2002-12-30 | 2005-05-05 | Renata Klein | Method and system for diagnostics and prognostics of a mechanical system |
US20050259715A1 (en) * | 2003-03-12 | 2005-11-24 | Peng Lee | Nondestructive residential inspection method |
US20050289071A1 (en) * | 2004-06-25 | 2005-12-29 | Goin Todd M | Method and system for clustering computers into peer groups and comparing individual computers to their peers |
US20060020604A1 (en) * | 2004-07-20 | 2006-01-26 | Justin Murez | Apparatus and method for performing process hazard analysis |
US20060028345A1 (en) * | 2002-10-09 | 2006-02-09 | Peng Lee | Termite acoustic detection |
US20060067334A1 (en) * | 2004-08-18 | 2006-03-30 | Ougarov Andrei V | System and methods for dynamic generation of point / tag configurations |
US20060116836A1 (en) * | 2000-07-04 | 2006-06-01 | Osamu Yoshie | System for diagnosing facility apparatus, managing apparatus and diagnostic apparatus |
US20060136386A1 (en) * | 2004-12-20 | 2006-06-22 | Microsoft Corporation | Long running requests |
US20060161597A1 (en) * | 2005-01-14 | 2006-07-20 | Ougarov Andrei V | Child data structure update in data management system |
US20060200741A1 (en) * | 1999-11-01 | 2006-09-07 | Demesa Jesse G | Modeling system for retrieving and displaying data from multiple sources |
US20060218131A1 (en) * | 2005-03-28 | 2006-09-28 | Mario Brenes | Interface chaining to populate a class-based model |
US20080208890A1 (en) * | 2007-02-27 | 2008-08-28 | Christopher Patrick Milam | Storage of multiple, related time-series data streams |
US20080271057A1 (en) * | 2007-04-26 | 2008-10-30 | Mtelligence Corporation | System and methods for the universal integration of plant floor assets and a computerized management system |
US7445377B2 (en) | 2003-03-12 | 2008-11-04 | Peng Lee | Nondestructive residential inspection method and apparatus |
US20090306955A1 (en) * | 2008-06-09 | 2009-12-10 | Honeywell International Inc. | Method and system for analyzing rolling element bearing systems |
US20100036619A1 (en) * | 2008-08-08 | 2010-02-11 | Bolt Donald W | Oil sample analysis calculator and method of using the same |
US20100063267A1 (en) * | 2008-09-09 | 2010-03-11 | Samsung Electronics Co., Ltd | Bi-functional compound positively charged at first ph and negatively charged at second ph, solid support comprising the bi-functional compound, and method of isolating nucleic acid using the same |
US20100251118A1 (en) * | 2009-03-26 | 2010-09-30 | Peterson Michael L | Help utility with expanded content display |
WO2017105181A1 (en) * | 2015-12-14 | 2017-06-22 | Diaz Quintanar José Antonio | System and method for predicting faults in remotely distributed equipment |
EP2345878A3 (en) * | 2010-01-15 | 2017-08-02 | Fluke Corporation | User interface system and method for diagnosing a rotating machine condition not based upon prior measurement history |
US9842302B2 (en) | 2013-08-26 | 2017-12-12 | Mtelligence Corporation | Population-based learning with deep belief networks |
US10192170B2 (en) | 2013-03-15 | 2019-01-29 | Mtelligence Corporation | System and methods for automated plant asset failure detection |
EP2938970B1 (en) * | 2012-11-30 | 2020-04-22 | Spectro Scientific, Inc. | Route-based substance analysis system |
EP3767269A4 (en) * | 2018-03-16 | 2021-05-05 | Sumitomo Heavy Industries, Ltd. | Failure diagnosis system |
WO2022114948A1 (en) * | 2020-11-25 | 2022-06-02 | Petroliam Nasional Berhad (Petronas) | Methods and systems for analyzing equipment |
Families Citing this family (125)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP1088211B1 (en) * | 1998-04-17 | 2003-06-25 | Siemens Aktiengesellschaft | Acoustic diagnostic system and method |
DE19850122A1 (en) * | 1998-04-17 | 1999-10-28 | Siemens Ag | Automatic configuration arrangement for technical object testing arrangement e.g. for electric motors |
US7539549B1 (en) | 1999-09-28 | 2009-05-26 | Rockwell Automation Technologies, Inc. | Motorized system integrated control and diagnostics using vibration, pressure, temperature, speed, and/or current analysis |
US7308322B1 (en) * | 1998-09-29 | 2007-12-11 | Rockwell Automation Technologies, Inc. | Motorized system integrated control and diagnostics using vibration, pressure, temperature, speed, and/or current analysis |
US6651034B1 (en) * | 1999-10-28 | 2003-11-18 | General Electric Company | Apparatus and method for performance and fault data analysis |
US6594621B1 (en) * | 2000-03-06 | 2003-07-15 | James H. Meeker | System and method for determining condition of plant |
US20010032109A1 (en) * | 2000-04-13 | 2001-10-18 | Gonyea Richard Jeremiah | System and method for predicting a maintenance schedule and costs for performing future service events of a product |
US6742000B1 (en) * | 2000-05-03 | 2004-05-25 | Honeywell International Inc. | System and method for defining a maintenance program |
US6549869B1 (en) * | 2000-06-20 | 2003-04-15 | Csi Technology, Inc. | Expert analysis modules for machine testing |
US6650346B1 (en) * | 2000-07-20 | 2003-11-18 | Ge Medical Technology Services, Inc. | Method and apparatus for classifying equipment in asset management database |
WO2002027418A2 (en) * | 2000-09-25 | 2002-04-04 | Motorwiz, Inc. | Model-based machine diagnostics and prognostics using theory of noise and communications |
US7457763B1 (en) | 2001-09-04 | 2008-11-25 | Accenture Global Services Gmbh | Predictive maintenance system |
US6820038B1 (en) | 2001-09-04 | 2004-11-16 | Accenture Global Services Gmbh | Component provisioning or issuance in a maintenance, repair or overhaul environment |
US7461008B2 (en) * | 2001-09-04 | 2008-12-02 | Accenture Global Services Gmbh | Planning and scheduling modification of a configuration |
US8655698B2 (en) * | 2000-10-17 | 2014-02-18 | Accenture Global Services Limited | Performance-based logistics for aerospace and defense programs |
US6738748B2 (en) * | 2001-04-03 | 2004-05-18 | Accenture Llp | Performing predictive maintenance on equipment |
US7440906B1 (en) * | 2001-09-04 | 2008-10-21 | Accenture Global Services Gmbh | Identification, categorization, and integration of unplanned maintenance, repair and overhaul work on mechanical equipment |
US6980959B1 (en) * | 2000-10-17 | 2005-12-27 | Accenture Llp | Configuring mechanical equipment |
US7124059B2 (en) * | 2000-10-17 | 2006-10-17 | Accenture Global Services Gmbh | Managing maintenance for an item of equipment |
US7457762B2 (en) * | 2001-09-04 | 2008-11-25 | Accenture Global Services Gmbh | Optimization of management of maintenance, repair and overhaul of equipment in a specified time window |
JP2002236736A (en) * | 2000-12-08 | 2002-08-23 | Hitachi Ltd | Method, device and system for supporting group management of building or the like and computer program storage medium |
JP2002197212A (en) * | 2000-12-25 | 2002-07-12 | Toshiba Tec Corp | Pos terminal remote maintenance system |
US20020091972A1 (en) * | 2001-01-05 | 2002-07-11 | Harris David P. | Method for predicting machine or process faults and automated system for implementing same |
US7313534B2 (en) * | 2001-01-22 | 2007-12-25 | W.W. Grainger, Inc. | System and method for predictive maintenance and service parts fulfillment in a supply chain |
US20020143669A1 (en) * | 2001-01-22 | 2002-10-03 | Scheer Robert H. | Method for managing inventory within an integrated supply chain |
US7324966B2 (en) * | 2001-01-22 | 2008-01-29 | W.W. Grainger | Method for fulfilling an order in an integrated supply chain management system |
US7212976B2 (en) * | 2001-01-22 | 2007-05-01 | W.W. Grainger, Inc. | Method for selecting a fulfillment plan for moving an item within an integrated supply chain |
US6795799B2 (en) * | 2001-03-07 | 2004-09-21 | Qualtech Systems, Inc. | Remote diagnosis server |
US7194415B2 (en) * | 2001-03-09 | 2007-03-20 | Hitachi, Ltd. | Support system for maintenance contract of elevator |
AUPR530801A0 (en) * | 2001-05-28 | 2001-06-21 | Almator Pty Ltd | A method of and system for managing operations in an enterprise or institute |
JP4235373B2 (en) * | 2001-05-29 | 2009-03-11 | キヤノン株式会社 | Information processing apparatus for requesting work performed on equipment used via network, control method therefor, program, and storage medium |
US20030004598A1 (en) * | 2001-05-31 | 2003-01-02 | Morris Martin M. | Apparatus and method for facilities maintenance management |
JP2002372440A (en) * | 2001-06-14 | 2002-12-26 | Ho Jinyama | Signal recording device having state judging method, device, and function |
US7546273B2 (en) * | 2001-08-30 | 2009-06-09 | International Business Machines Corporation | System and method for evaluating residual values of products |
US8266066B1 (en) * | 2001-09-04 | 2012-09-11 | Accenture Global Services Limited | Maintenance, repair and overhaul management |
US6871160B2 (en) * | 2001-09-08 | 2005-03-22 | Scientific Monitoring Inc. | Intelligent condition-based engine/equipment management system |
JP4031928B2 (en) * | 2001-11-09 | 2008-01-09 | 株式会社日立製作所 | Equipment maintenance work support method and maintenance work support server |
US7133804B2 (en) * | 2002-02-22 | 2006-11-07 | First Data Corporatino | Maintenance request systems and methods |
US7120830B2 (en) * | 2002-02-22 | 2006-10-10 | First Data Corporation | Maintenance request systems and methods |
US20030229726A1 (en) * | 2002-03-18 | 2003-12-11 | Daseke Michael J. | Default device configuration system and method for thin devices |
US20030229785A1 (en) * | 2002-03-18 | 2003-12-11 | Daseke Michael J. | Dynamic hierarchies system and method for thin devices |
JP2004005461A (en) * | 2002-04-02 | 2004-01-08 | Hitachi Ltd | Rotation planning method and rotation planning device |
US6839660B2 (en) | 2002-04-22 | 2005-01-04 | Csi Technology, Inc. | On-line rotating equipment monitoring device |
US8504396B2 (en) * | 2002-12-24 | 2013-08-06 | Sap Aktiengeselleschaft | Flexible maintenance planning |
US20050027656A1 (en) * | 2003-02-11 | 2005-02-03 | Tyson Foods, Inc. | A system and method for monitoring facility data |
US8019793B2 (en) * | 2003-02-14 | 2011-09-13 | Accenture Global Services Limited | Methodology infrastructure and delivery vehicle |
US20040205397A1 (en) * | 2003-03-28 | 2004-10-14 | Vrinda Rajiv | Complex system diagnostic analysis model correction method and apparatus |
US20040215468A1 (en) * | 2003-04-23 | 2004-10-28 | Doeberl Terrence M. | System and method for managing business machine assets |
US6901318B1 (en) | 2003-04-25 | 2005-05-31 | Northrup Grumman Corporation | Method of management of maintenance activities for vehicles |
US7263680B2 (en) * | 2003-06-12 | 2007-08-28 | Synopsys, Inc. | Graphical user interface for a cell router usable by both novice and advanced users |
US6990431B2 (en) * | 2003-06-23 | 2006-01-24 | Municipal And Industrial Data Labs, Inc. | System and software to monitor cyclic equipment efficiency and related methods |
US20050090372A1 (en) * | 2003-06-24 | 2005-04-28 | Mark Burrows | Method and system for using a database containing rehabilitation plans indexed across multiple dimensions |
WO2005002431A1 (en) * | 2003-06-24 | 2005-01-13 | Johnson & Johnson Consumer Companies Inc. | Method and system for rehabilitating a medical condition across multiple dimensions |
US8645420B2 (en) * | 2003-08-05 | 2014-02-04 | Accenture Global Services Limited | Methodology framework and delivery vehicle |
US8134445B2 (en) * | 2004-04-20 | 2012-03-13 | Cooper Technologies Company | RFID open fuse indicator, system, and method |
US7369029B2 (en) * | 2004-04-20 | 2008-05-06 | Cooper Technologies Company | Wireless communication fuse state indicator system and method |
EP1767053A4 (en) * | 2004-06-14 | 2009-07-01 | Johnson & Johnson Consumer | System for and method of increasing convenience to users to drive the purchase process for hearing health that results in purchase of a hearing aid |
WO2005125279A1 (en) * | 2004-06-14 | 2005-12-29 | Johnson & Johnson Consumer Companies, Inc. | Hearing device sound simulation system and method of using the system |
WO2005125278A2 (en) * | 2004-06-14 | 2005-12-29 | Johnson & Johnson Consumer Companies, Inc. | At-home hearing aid training system and method |
EP1792518A4 (en) * | 2004-06-14 | 2009-11-11 | Johnson & Johnson Consumer | At-home hearing aid tester and method of operating same |
EP1767059A4 (en) * | 2004-06-14 | 2009-07-01 | Johnson & Johnson Consumer | System for and method of optimizing an individual"s hearing aid |
US20080269636A1 (en) * | 2004-06-14 | 2008-10-30 | Johnson & Johnson Consumer Companies, Inc. | System for and Method of Conveniently and Automatically Testing the Hearing of a Person |
US20080167575A1 (en) * | 2004-06-14 | 2008-07-10 | Johnson & Johnson Consumer Companies, Inc. | Audiologist Equipment Interface User Database For Providing Aural Rehabilitation Of Hearing Loss Across Multiple Dimensions Of Hearing |
WO2005125275A2 (en) * | 2004-06-14 | 2005-12-29 | Johnson & Johnson Consumer Companies, Inc. | System for optimizing hearing within a place of business |
EP1767061A4 (en) * | 2004-06-15 | 2009-11-18 | Johnson & Johnson Consumer | Low-cost, programmable, time-limited hearing aid apparatus, method of use and system for programming same |
US20060010152A1 (en) * | 2004-07-12 | 2006-01-12 | Snecma Services | System and method for managing machine servicing including workscope generation |
US7561200B2 (en) * | 2004-07-26 | 2009-07-14 | Csi Technology, Inc. | Apparatus and method for automation of imaging and dynamic signal analyses |
US20070194942A1 (en) * | 2004-09-10 | 2007-08-23 | Darr Matthew R | Circuit protector monitoring assembly, system and method |
BRPI0515159A (en) * | 2004-09-10 | 2008-07-08 | Cooper Technologies Co | system and method for circuit protector monitoring and management |
US8169331B2 (en) * | 2004-09-10 | 2012-05-01 | Cooper Technologies Company | Circuit protector monitoring assembly |
US20060087397A1 (en) * | 2004-10-26 | 2006-04-27 | Cooper Technologies Company | Fuse state indicating optical circuit and system |
EP1875154A4 (en) * | 2005-04-25 | 2009-10-28 | M E A Testing Systems Ltd | Predictive maintenance method |
US7260498B2 (en) * | 2005-06-17 | 2007-08-21 | Dade Behring Inc. | Context-specific electronic performance support |
US9015059B2 (en) * | 2005-09-19 | 2015-04-21 | Omnitracs, Llc | Wireless system for automatic ordering of maintenance parts for equipment |
US20070088550A1 (en) * | 2005-10-13 | 2007-04-19 | Dimitar Filev | Method for predictive maintenance of a machine |
US20070106784A1 (en) * | 2005-11-08 | 2007-05-10 | Dickman David T | Systems, methods and apparatus to identify network maintenance zones |
US20070294093A1 (en) | 2006-06-16 | 2007-12-20 | Husky Injection Molding Systems Ltd. | Preventative maintenance system |
WO2007143813A1 (en) * | 2006-06-16 | 2007-12-21 | Husky Injection Molding Systems Ltd. | Preventative maintenance update system |
US20070294040A1 (en) * | 2006-06-16 | 2007-12-20 | Husky Injection Molding Systems Ltd. | Preventative maintenance indicator system |
US20080172281A1 (en) * | 2007-01-12 | 2008-07-17 | David Malthe Probst | Scheduling Service Based on Usage Data |
US20090049094A1 (en) * | 2007-08-16 | 2009-02-19 | Facility Audit Solutions, Llc | System and method for performing site audits on facilities |
US20090048949A1 (en) * | 2007-08-16 | 2009-02-19 | Facility Audit Solutions, Llc | System and method for managing photographs from site audits of facilities |
US8655988B2 (en) | 2007-12-19 | 2014-02-18 | Telefonaktiebolaget L M Ericsson (Publ) | Method and system for configuring network access nodes |
US8224492B2 (en) | 2008-09-30 | 2012-07-17 | Lakomiak Jason E | Auto-configuring condition monitoring system and method |
US8996321B2 (en) | 2008-09-30 | 2015-03-31 | Rockwell Automation Technologies, Inc. | Modular condition monitoring integration for control systems |
US8290630B2 (en) | 2008-09-30 | 2012-10-16 | Rockwell Automation Technologies, Inc. | Condition monitoring parameter normalization system and method |
US8463417B2 (en) * | 2009-09-04 | 2013-06-11 | Csi Technology, Inc. | Method and apparatus to configure control system to link to machinery monitoring system |
US8280544B2 (en) * | 2009-11-02 | 2012-10-02 | Mold Masters (2007) Limited | System for use in performance of injection molding operations |
US20110106284A1 (en) * | 2009-11-02 | 2011-05-05 | Mold-Masters (2007) Limited | System for use in performance of injection molding operations |
US20110106285A1 (en) * | 2009-11-02 | 2011-05-05 | Mold-Masters (2007) Limited | System for use in performance of injection molding operations |
US8442688B2 (en) | 2010-01-28 | 2013-05-14 | Holcim (US), Inc. | System for monitoring plant equipment |
US8370046B2 (en) * | 2010-02-11 | 2013-02-05 | General Electric Company | System and method for monitoring a gas turbine |
EP2393066A1 (en) * | 2010-06-04 | 2011-12-07 | BAE Systems Bofors AB | Configuration management for a fleet of equipment units |
CA2707254A1 (en) | 2010-07-12 | 2010-09-15 | Ibm Canada Limited - Ibm Canada Limitee | Asset management system to monitor and control greenhouse gas emissions |
US8803698B1 (en) | 2010-11-23 | 2014-08-12 | Fluke Corporation | Removable stand alone vibration monitor with automatically configured alarm thresholds |
US9311615B2 (en) | 2010-11-24 | 2016-04-12 | International Business Machines Corporation | Infrastructure asset management |
US20120173301A1 (en) * | 2011-01-04 | 2012-07-05 | International Business Machines Corporation | System and method for failure association analysis |
US20130096979A1 (en) * | 2011-10-12 | 2013-04-18 | Acm Automation Inc. | System for monitoring safety protocols |
CN104170244B (en) | 2011-12-13 | 2018-01-09 | 沙特阿拉伯石油公司 | Submersible electric pump monitors and failure predication |
US20130173202A1 (en) * | 2011-12-30 | 2013-07-04 | Aktiebolaget Skf | Systems and Methods for Dynamic Prognostication of Machine Conditions for Rotational Motive Equipment |
WO2013102202A1 (en) | 2011-12-31 | 2013-07-04 | Aktiebolaget Skf | Systems and methods for energy efficient machine condition monitoring of fans, motors, pumps, compressors and other equipment |
US20140095133A1 (en) * | 2012-09-28 | 2014-04-03 | General Electric Company | Systems and methods for managing mechanical systems and components |
US9664492B2 (en) | 2012-12-27 | 2017-05-30 | General Electric Company | Methods and apparatus for defining a probe configuration using a probe configuration tool |
US9507484B2 (en) | 2012-12-27 | 2016-11-29 | General Electric Company | Methods and apparatus for configuring a data analyzer |
US9323766B2 (en) | 2013-03-15 | 2016-04-26 | Metrix Instrument Co., Lp | Data collection device and method |
US10502594B2 (en) | 2013-04-29 | 2019-12-10 | Emerson Electric (Us) Holding Corporation (Chile) Limitada | Dynamic transducer with digital output and method for use |
USD751103S1 (en) | 2014-03-14 | 2016-03-08 | Microsoft Corporation | Display screen with graphical user interface |
USD751085S1 (en) * | 2014-03-14 | 2016-03-08 | Microsoft Corporation | Display screen with graphical user interface |
USD751086S1 (en) | 2014-03-14 | 2016-03-08 | Microsoft Corporation | Display screen with graphical user interface |
USD760772S1 (en) | 2014-03-14 | 2016-07-05 | Microsoft Corporation | Display screen with graphical user interface |
US9921136B2 (en) | 2014-08-05 | 2018-03-20 | 01dB-Metravib, Societe Par Actions Simplifee | Wireless collection and analysis of machine data |
US10533920B2 (en) | 2014-08-05 | 2020-01-14 | Acoem France | Automatic rotating-machine fault diagnosis with confidence level indication |
US9524629B2 (en) | 2014-08-13 | 2016-12-20 | Computational Systems, Inc. | Adaptive and state driven data collection |
US10909607B2 (en) | 2015-06-05 | 2021-02-02 | Boveda Inc. | Systems, methods and devices for controlling humidity in a closed environment with automatic and predictive identification, purchase and replacement of optimal humidity controller |
US10055781B2 (en) | 2015-06-05 | 2018-08-21 | Boveda Inc. | Systems, methods and devices for controlling humidity in a closed environment with automatic and predictive identification, purchase and replacement of optimal humidity controller |
CN109073316B (en) | 2016-03-28 | 2021-07-06 | 开利公司 | Automatic diagnostics for transport refrigeration unit |
DE102017124135B4 (en) | 2016-10-21 | 2023-06-07 | Computational Systems Inc. | Machine failure prediction based on an analysis of periodic information in a signal |
US9913006B1 (en) | 2016-11-28 | 2018-03-06 | 01dB-METRAVIB, Société par Actions Simplifiée | Power-efficient data-load-efficient method of wirelessly monitoring rotating machines |
US10551243B2 (en) | 2016-11-28 | 2020-02-04 | Acoem France | Power efficient machine diagnostic monitoring using multiple vibration sensor wireless configuration |
US10643187B2 (en) * | 2017-06-09 | 2020-05-05 | Kidde Technologies, Inc. | Reporting and prioritizing faults for aircraft downtime reduction |
US10823749B2 (en) | 2018-04-05 | 2020-11-03 | Computational Systems, Inc. | Determination of RPM from vibration spectral plots |
US11086749B2 (en) | 2019-08-01 | 2021-08-10 | International Business Machines Corporation | Dynamically updating device health scores and weighting factors |
US11300482B2 (en) | 2019-08-06 | 2022-04-12 | Computational Systems, Inc. | Graphical differentiation of spectral frequency families |
US11573153B2 (en) | 2019-08-21 | 2023-02-07 | Computational Systems, Inc. | Prediction of machine failure based on vibration trend information |
US11941521B2 (en) | 2020-09-11 | 2024-03-26 | Acoem France | Vibrating machine automated diagnosis with supervised learning |
Family Cites Families (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4612620A (en) * | 1983-06-06 | 1986-09-16 | Ird Mechanalysis, Inc. | Apparatus for collecting scheduled maintenance data |
US5404506A (en) | 1985-03-27 | 1995-04-04 | Hitachi, Ltd. | Knowledge based information retrieval system |
US4885707A (en) * | 1987-02-19 | 1989-12-05 | Dli Corporation | Vibration data collecting and processing apparatus and method |
EP0411873A3 (en) * | 1989-08-02 | 1993-11-18 | Westinghouse Electric Corp | Improved plant operating system employing a deterministic, probabilistic and subjective modeling system |
US5210704A (en) * | 1990-10-02 | 1993-05-11 | Technology International Incorporated | System for prognosis and diagnostics of failure and wearout monitoring and for prediction of life expectancy of helicopter gearboxes and other rotating equipment |
CA2096374C (en) * | 1992-05-18 | 2006-08-08 | Michael A. Sandifer | Computer aided maintenance and repair information system for equipment subject to regulatory compliance |
US5808903A (en) * | 1995-09-12 | 1998-09-15 | Entek Scientific Corporation | Portable, self-contained data collection systems and methods |
US5566092A (en) * | 1993-12-30 | 1996-10-15 | Caterpillar Inc. | Machine fault diagnostics system and method |
US5602761A (en) * | 1993-12-30 | 1997-02-11 | Caterpillar Inc. | Machine performance monitoring and fault classification using an exponentially weighted moving average scheme |
US5644686A (en) | 1994-04-29 | 1997-07-01 | International Business Machines Corporation | Expert system and method employing hierarchical knowledge base, and interactive multimedia/hypermedia applications |
US5596507A (en) * | 1994-08-15 | 1997-01-21 | Jones; Jeffrey K. | Method and apparatus for predictive maintenance of HVACR systems |
US5680025A (en) | 1994-10-07 | 1997-10-21 | Csi Technology, Inc. | Proactive motor monitoring for avoiding premature failures and for fault recognition |
US5633811A (en) | 1994-12-09 | 1997-05-27 | Computational Systems, Inc. | Hand held data collector and analyzer system |
US5710723A (en) | 1995-04-05 | 1998-01-20 | Dayton T. Brown | Method and apparatus for performing pre-emptive maintenance on operating equipment |
US5663894A (en) | 1995-09-06 | 1997-09-02 | Ford Global Technologies, Inc. | System and method for machining process characterization using mechanical signature analysis |
US5734893A (en) | 1995-09-28 | 1998-03-31 | Ibm Corporation | Progressive content-based retrieval of image and video with adaptive and iterative refinement |
US5963884A (en) * | 1996-09-23 | 1999-10-05 | Machine Xpert, Llc | Predictive maintenance system |
CA2272918A1 (en) * | 1996-11-27 | 1998-06-04 | Sundstrand Corporation | Method of maintaining components subject to fatigue failure |
US5852793A (en) * | 1997-02-18 | 1998-12-22 | Dme Corporation | Method and apparatus for predictive diagnosis of moving machine parts |
-
1998
- 1998-09-15 US US09/153,690 patent/US6192325B1/en not_active Expired - Lifetime
-
1999
- 1999-09-02 GB GB9920743A patent/GB2345166B/en not_active Expired - Fee Related
-
2001
- 2001-01-02 US US09/753,595 patent/US20010001851A1/en not_active Abandoned
Cited By (62)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20060200741A1 (en) * | 1999-11-01 | 2006-09-07 | Demesa Jesse G | Modeling system for retrieving and displaying data from multiple sources |
US7143011B2 (en) | 2000-07-04 | 2006-11-28 | Asahi Kasei Engineering Corporation | System for diagnosing facility apparatus, managing apparatus and diagnostic apparatus |
US7139681B2 (en) | 2000-07-04 | 2006-11-21 | Asahi Kasei Engineering Corporation | System for diagnosing facility apparatus, managing apparatus and diagnostic apparatus |
US20030135349A1 (en) * | 2000-07-04 | 2003-07-17 | Osamu Yoshie | System for diagnosing facility apparatus, managing apparatus and diagnostic apparatus |
US20060116836A1 (en) * | 2000-07-04 | 2006-06-01 | Osamu Yoshie | System for diagnosing facility apparatus, managing apparatus and diagnostic apparatus |
US20060129358A1 (en) * | 2000-07-04 | 2006-06-15 | Asahi Kasei Engineering Corporation | System for diagnosing facility apparatus, managing apparatus and diagnostic apparatus |
US7085684B2 (en) * | 2000-07-04 | 2006-08-01 | Asahi Kasei Engineering Corporation | System for diagnosing a facility apparatus |
US7065570B2 (en) * | 2000-07-11 | 2006-06-20 | Komatsu Ltd. | System, method, computer program, and recording medium for machine-management |
US20020046048A1 (en) * | 2000-07-11 | 2002-04-18 | Hidetada Fukushima | System, method, computer program, and recording medium for machine-management |
US6675167B2 (en) | 2000-07-13 | 2004-01-06 | Hitachi, Ltd. | System and method for managing monitoring equipment |
US20040078733A1 (en) * | 2000-07-13 | 2004-04-22 | Lewis Lundy M. | Method and apparatus for monitoring and maintaining user-perceived quality of service in a communications network |
US6604061B2 (en) * | 2000-07-13 | 2003-08-05 | Hitachi, Ltd. | Instruments management system and method and monitoring apparatus, database apparatus and data base client apparatuses and recording medium |
US7689857B2 (en) * | 2000-07-13 | 2010-03-30 | Computer Associates Think, Inc. | Method and apparatus for monitoring and maintaining user-perceived quality of service in a communications network |
US20040150665A1 (en) * | 2000-10-13 | 2004-08-05 | General Electric Company | Selection of statistical tool |
US7089500B2 (en) | 2001-09-10 | 2006-08-08 | International Business Machines Corporation | Wizard user interface providing interim system product generation and reversion during wizard traversal |
US20030048300A1 (en) * | 2001-09-10 | 2003-03-13 | International Business Machines Corporation | Wizard user interface providing interim system product generation and reversion during wizard traversal |
US7162484B2 (en) * | 2001-10-01 | 2007-01-09 | Sun Microsystems, Inc. | Method and system for hierarchical visibility marks for hierarchical elements in hierarchical database structure, filtering hierarchical elements, hide any hierarchical element not having either a user hierarchical visibility mark or a propagated hierarchical visibility mark |
US20030065673A1 (en) * | 2001-10-01 | 2003-04-03 | Sun Microsystems, Inc. | Method and device for marking and filtering data elements in a database |
US7634414B2 (en) * | 2002-05-29 | 2009-12-15 | General Electric Company | Automated package information and configuration communication process |
US20030225710A1 (en) * | 2002-05-29 | 2003-12-04 | Kirk Arneson | Automated package information and configuration communication process |
US20040103106A1 (en) * | 2002-09-27 | 2004-05-27 | Matsushita Electric Industrial Co., Ltd. | Data processing apparatus, data processing method, and data processing program |
US7149758B2 (en) * | 2002-09-27 | 2006-12-12 | Matsushita Electric Industrial Co., Ltd. | Data processing apparatus, data processing method, and data processing program |
US20050018745A1 (en) * | 2002-10-09 | 2005-01-27 | Peng Lee | Method to detect termite infestation in a structure |
US20060028345A1 (en) * | 2002-10-09 | 2006-02-09 | Peng Lee | Termite acoustic detection |
US7271706B2 (en) | 2002-10-09 | 2007-09-18 | The University Of Mississippi | Termite acoustic detection |
US7434990B2 (en) | 2002-10-09 | 2008-10-14 | University Of Mississippi | Method to detect termite infestation in a structure |
US20050096873A1 (en) * | 2002-12-30 | 2005-05-05 | Renata Klein | Method and system for diagnostics and prognostics of a mechanical system |
US7027953B2 (en) | 2002-12-30 | 2006-04-11 | Rsl Electronics Ltd. | Method and system for diagnostics and prognostics of a mechanical system |
US7445377B2 (en) | 2003-03-12 | 2008-11-04 | Peng Lee | Nondestructive residential inspection method and apparatus |
US20050259715A1 (en) * | 2003-03-12 | 2005-11-24 | Peng Lee | Nondestructive residential inspection method |
US20050289071A1 (en) * | 2004-06-25 | 2005-12-29 | Goin Todd M | Method and system for clustering computers into peer groups and comparing individual computers to their peers |
US7203864B2 (en) * | 2004-06-25 | 2007-04-10 | Hewlett-Packard Development Company, L.P. | Method and system for clustering computers into peer groups and comparing individual computers to their peers |
US20060020604A1 (en) * | 2004-07-20 | 2006-01-26 | Justin Murez | Apparatus and method for performing process hazard analysis |
US7716239B2 (en) * | 2004-07-20 | 2010-05-11 | Siemens Energy, Inc. | Apparatus and method for performing process hazard analysis |
US20060067334A1 (en) * | 2004-08-18 | 2006-03-30 | Ougarov Andrei V | System and methods for dynamic generation of point / tag configurations |
US8700671B2 (en) | 2004-08-18 | 2014-04-15 | Siemens Aktiengesellschaft | System and methods for dynamic generation of point / tag configurations |
US20060136386A1 (en) * | 2004-12-20 | 2006-06-22 | Microsoft Corporation | Long running requests |
US7587393B2 (en) * | 2004-12-20 | 2009-09-08 | Microsoft Corporation | Long running requests |
US8442938B2 (en) | 2005-01-14 | 2013-05-14 | Siemens Aktiengesellschaft | Child data structure update in data management system |
US20060161597A1 (en) * | 2005-01-14 | 2006-07-20 | Ougarov Andrei V | Child data structure update in data management system |
US8700559B2 (en) | 2005-03-28 | 2014-04-15 | Siemens Aktiengesellschaft | Interface chaining to populate a class-based model |
US20060218131A1 (en) * | 2005-03-28 | 2006-09-28 | Mario Brenes | Interface chaining to populate a class-based model |
US20080208890A1 (en) * | 2007-02-27 | 2008-08-28 | Christopher Patrick Milam | Storage of multiple, related time-series data streams |
US8260783B2 (en) | 2007-02-27 | 2012-09-04 | Siemens Aktiengesellschaft | Storage of multiple, related time-series data streams |
US10114367B2 (en) | 2007-04-26 | 2018-10-30 | Mtelligence Corporation | System and methods for the universal integration of plant floor assets and a computerized management system |
US20080271057A1 (en) * | 2007-04-26 | 2008-10-30 | Mtelligence Corporation | System and methods for the universal integration of plant floor assets and a computerized management system |
US8380842B2 (en) | 2007-04-26 | 2013-02-19 | Mtelligence Corporation | System and methods for the universal integration of plant floor assets and a computerized management system |
US20090306955A1 (en) * | 2008-06-09 | 2009-12-10 | Honeywell International Inc. | Method and system for analyzing rolling element bearing systems |
US20100036619A1 (en) * | 2008-08-08 | 2010-02-11 | Bolt Donald W | Oil sample analysis calculator and method of using the same |
US7917307B2 (en) | 2008-08-08 | 2011-03-29 | Alstom Transportation Inc. | Oil sample analysis calculator and method of using the same |
US8415277B2 (en) | 2008-09-09 | 2013-04-09 | Samsung Electronics Co., Ltd. | Bi-functional compound positively charged at first pH and negatively charged at second pH, solid support comprising the bi-functional compound, and method of isolating nucleic acid using the same |
US20100063267A1 (en) * | 2008-09-09 | 2010-03-11 | Samsung Electronics Co., Ltd | Bi-functional compound positively charged at first ph and negatively charged at second ph, solid support comprising the bi-functional compound, and method of isolating nucleic acid using the same |
US20100251118A1 (en) * | 2009-03-26 | 2010-09-30 | Peterson Michael L | Help utility with expanded content display |
EP2345878A3 (en) * | 2010-01-15 | 2017-08-02 | Fluke Corporation | User interface system and method for diagnosing a rotating machine condition not based upon prior measurement history |
EP2938970B1 (en) * | 2012-11-30 | 2020-04-22 | Spectro Scientific, Inc. | Route-based substance analysis system |
US10192170B2 (en) | 2013-03-15 | 2019-01-29 | Mtelligence Corporation | System and methods for automated plant asset failure detection |
US10733536B2 (en) | 2013-08-26 | 2020-08-04 | Mtelligence Corporation | Population-based learning with deep belief networks |
US9842302B2 (en) | 2013-08-26 | 2017-12-12 | Mtelligence Corporation | Population-based learning with deep belief networks |
WO2017105181A1 (en) * | 2015-12-14 | 2017-06-22 | Diaz Quintanar José Antonio | System and method for predicting faults in remotely distributed equipment |
EP3767269A4 (en) * | 2018-03-16 | 2021-05-05 | Sumitomo Heavy Industries, Ltd. | Failure diagnosis system |
US11703376B2 (en) | 2018-03-16 | 2023-07-18 | Sumitomo Heavy Industries, Ltd. | Failure diagnosis system |
WO2022114948A1 (en) * | 2020-11-25 | 2022-06-02 | Petroliam Nasional Berhad (Petronas) | Methods and systems for analyzing equipment |
Also Published As
Publication number | Publication date |
---|---|
GB2345166A (en) | 2000-06-28 |
GB2345166B (en) | 2002-06-12 |
GB9920743D0 (en) | 1999-11-03 |
US6192325B1 (en) | 2001-02-20 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US6192325B1 (en) | Method and apparatus for establishing a predictive maintenance database | |
US4985857A (en) | Method and apparatus for diagnosing machines | |
CA2288042C (en) | Configuration knowledge as an aid to case retrieval | |
US6560552B2 (en) | Dynamically configurable process for diagnosing faults in rotating machines | |
US5333240A (en) | Neural network state diagnostic system for equipment | |
WO2004040465A1 (en) | System and method for remote diagnosis of distributed objects | |
US11112783B2 (en) | Method and apparatus for machine monitoring with continuous improvement of a predictive maintenance database | |
CN112446144A (en) | Fault diagnosis method and device for large-scale rotating machine set | |
US11300482B2 (en) | Graphical differentiation of spectral frequency families | |
CN114648136A (en) | Method, device and equipment for evaluating health degree of mobile equipment and storage medium | |
US11238192B2 (en) | Support apparatus | |
US7725274B2 (en) | Method and apparatus for identifying a region of interest of transient vibration data requiring analysis | |
KR102502740B1 (en) | Vibration diagnosis method of rotating machine considering the complex conditions | |
JP2020085575A (en) | Analysis assisting device, analysis assisting method, and analysis assisting program | |
US11905892B2 (en) | Flow machine performance modelling | |
JP2995518B2 (en) | Method and apparatus for automatically constructing learning type abnormality diagnosis algorithm | |
CN108871827A (en) | A method of based on the quick diagnosis rotating machinery resonance for intersecting statistical analysis | |
JP2000353094A (en) | Device and method for faulty diagnosis for equipment | |
JP2000162035A (en) | Method and device for determining abnormality in rotating equipment | |
CN108628251A (en) | The method and apparatus processed automatically for gear assembly | |
JPH09147264A (en) | Automatic setting method for alarm value and reference value of rotary equipment vibration monitor and diagnostic system | |
US20230022369A1 (en) | Retrieving Industrial Asset Data from Disparate Data Sources | |
BAKIR | Different Induction Motor Faults by New Proposed Random Forest Method | |
Littler | A user friendly simulation support environment for turbo generator defect diagnosis | |
US10355920B2 (en) | Defining acquisition and measurement definitions in a machine monitoring system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AS | Assignment |
Owner name: CSI TECHNOLOGY, INC, DELAWARE Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:PIETY, KENNETH R.;HEILMON, CHRISTOPHER G.;REEVES, TODD WARREN;AND OTHERS;REEL/FRAME:011423/0872;SIGNING DATES FROM 19980905 TO 19980909 |
|
AS | Assignment |
Owner name: CSI TECHNOLOGY, INC., DELAWARE Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:PIETY, KENNETH R.;HILEMON, CHRISTOPHER G.;REEVES, TODD WARREN;AND OTHERS;REEL/FRAME:011787/0752;SIGNING DATES FROM 19980905 TO 19980909 |
|
STCB | Information on status: application discontinuation |
Free format text: ABANDONED -- FAILURE TO RESPOND TO AN OFFICE ACTION |