CN102628738B - State monitoring and failure diagnosis system for thick plate mill AGC servo valve - Google Patents
State monitoring and failure diagnosis system for thick plate mill AGC servo valve Download PDFInfo
- Publication number
- CN102628738B CN102628738B CN201210082699.1A CN201210082699A CN102628738B CN 102628738 B CN102628738 B CN 102628738B CN 201210082699 A CN201210082699 A CN 201210082699A CN 102628738 B CN102628738 B CN 102628738B
- Authority
- CN
- China
- Prior art keywords
- valve
- data
- servo
- module
- health degree
- 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.)
- Expired - Fee Related
Links
Landscapes
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention relates to a state monitoring and failure diagnosis system for a thick plate mill AGC servo valve. The system comprises a diagnosis operation module, a diagnosis result display module, an information input module, a historical data analysis module and a neural network training module, wherein the diagnosis operation module reads the text file to be tested, performs diagnosis and transmits the diagnosis result to the diagnosis result display module; the diagnosis result comprises the health degree tendency of the servo valve and the current operation state represented by the health degree; the information input module inputs the information of a new valve when the mill exchanges the new servo valve; the neural network training module is used for training the data of the new servo valve and inputting the result into a knowledge base; and the historical data analysis module can check the related information such as the historical operation state and the like of the selected valve. The system has the functions of automatically diagnosing state failure and storing and checking historical data and provides real-time guarantee for finding system failure and exchanging the servo valve timely so as to reduce loss caused by equipment failure to the maximum degree.
Description
Technical field
The present invention relates to a kind of rolling mill hydraulic AGC system, specifically a kind of heavy plate mill AGC servo-valve condition monitoring and failure diagnosis system.
Background technology
Band mill makes rolled piece pass through to have the roll of certain roll gap thus produce a kind of metal-pressed machine machine of expection thick plates band.In plate strip rolling process, the dimensional accuracy of thickness of slab is the most important quality index that must guarantee, rolling mill hydraulic AGC system is the important means of modern strip-mill strip thickness of slab precision controlling, Strip Shape Control.AGC system is according to actual measurement thickness of slab and thickness ratio comparatively its deviation requiring rolling, and by the control of servo system, adjustment depress oil cylinder, to reach required outlet thickness of slab.
Rolling mill hydraulic AGC system is that control is complicated, load force is large, disturbance relation complexity, control accuracy and the exigent equipment of response speed, and with the raising day by day that milling train automatization level and board quality require, require also more and more higher to rolling mill hydraulic AGC system control performance.Serviceability quality and the reliability height of hydraulic AGC system, directly affect the normal work of whole milling train, affect the quality of product.And electrohydraulic servo valve is the key element of hydraulic AGC system, its property relationship, to the control accuracy of whole system and response speed, also directly has influence on reliability and the life-span of whole system work.
Electrohydraulic servo valve requires accurate, and cost is more expensive, and system requires high to actuating medium cleanliness, and management maintenance expense is comparatively large, and be the position of the most easily breaking down in electrohydraulic servo system, its Performance And Reliability is by the Performance And Reliability of direct influential system.The research carrying out electrohydraulic servo valve intelligent fault diagnosis aspect can improve reliability and the security of whole AGC system, ensure the normally good production order and product quality, in the serviceable life of extension device, reduce maintenance cost, the modernization of puopulsion equipment maintenance system and mode.Otherwise, if hydraulic AGC system is once break down, will causes and shut down or affect product quality, huge economic loss can be brought.
Electrohydraulic servo valve itself is that its fault is usually expressed as the complicated coupling of mechanical fault, electric fault, hydraulic fault in conjunction with mechanical, electrical, liquid three kinds of technology precision element in one, and these bring certain difficulty to relevant fault diagnosis work.Electrohydraulic servo valve is one of parts complicated and the most crucial in hydraulic system, and electrohydraulic servo valve intelligent maintenance technology and level are the important reflections of hydraulic system maintenance technology and level.
Through finding the literature search of prior art, Chinese patent (patent No. CN101183050) proposes a kind of electrohydraulic servo valve dynamic performance high precision measurement method that deformation based is measured, adopt displacement transducer as no-load cylinder movement detecting element, displacement signal and current signal test electrohydraulic servo valve dynamic performance through process and correlation analysis.Toshiba Corporation's patent (patent No. CN1519480) proposes a kind of servo valve control device for controlling servo-valve aperture, to make servo-valve aperture meet a target by the servo-valve aperture of input reality and the signal of servo-valve aperture desired value, this control device has a controller, it is configured to receive the difference signal between servo-valve aperture desired value and actual servo valve opening, and produces the servo command signal for driving this servo-valve.But the semaphore that above-mentioned patent adopts is more single, does not provide the current operating conditions of servo-valve, and lack performance degradation prediction.
Summary of the invention
The present invention is directed to the deficiencies in the prior art, a kind of heavy plate mill AGC servo-valve condition monitoring and failure diagnosis system is proposed, it is made to possess status fault self diagnosis and history data store and look facility, real-time guarantees is provided, in the hope of farthest reducing the loss that equipment failure causes with timely servo-valve of changing to the discovery of the system failure.
The present invention is achieved by the following technical solutions, the present invention includes following five modules: diagnostic operation module, diagnostic result display module, MIM message input module, historical data analysis module and neural metwork training module, first gather the roll-force of milling train, transmission side and the displacement of fore side and the opening degree signal of servo-valve with sensor before described system cloud gray model and on-line storage is text; Wherein:
Described MIM message input module is carried out typing when milling train exchanges new servo-valve for new valve information and preserves data, calls for described diagnostic operation module;
Described neural metwork training module, when there being new servo-valve data, adopting neural network to train these data and result is added knowledge base, and these trained data called for described diagnostic operation module;
Described diagnostic operation module reads text to be tested, or/and the data of described MIM message input module and described neural metwork training module, diagnoses servo-valve, and result is sent to described diagnostic result display module;
Described diagnostic result display module then shows date of servo-valve, valve number, location number, diagnostic result and health degree information; Described health degree is the index characterizing servo-valve service condition, and its scope is 0 ~ 1,0 expression worst state, and 1 represents optimum condition;
Described historical data analysis module provides the history run state information searching of a certain valve.
Described MIM message input module primary responsibility change new servo-valve after for the typing of new servo-valve information, machine time, numbering and upper machine location number can be inputted on servo-valve, and preserve after valve being sorted according to the information of input.The relevant information of used servo-valve can be preserved by this module, be convenient to the accurate judgement of diagnostic procedure, also can be provided with post analysis and use.
Described neural metwork training module comprises Data Update submodule and network training submodule, when there being new servo-valve data, described network training submodule adopts neural network to carry out network training to these data, result after training is updated to knowledge base by described Data Update submodule, calls for described diagnostic operation module.The knowledge base of servo-valve presence is in systems in which integrated, filters out representative data by current existing data by the requirement of characteristic quantity.The representational quality of knowledge base data is closely related with the rate of correct diagnosis height of system and travelling speed speed.Knowledge base has the function of dilatation and upgrading, thus improves the adaptability of system and equipment working condition.
Described diagnostic operation module comprises digital independent submodule and data diagnosis submodule, and described digital independent submodule is used for choosing the text needing test, judge data date and data are wherein passed to diagnostic result show in time variable; Described data diagnosis submodule obtains the proper vector characterizing servo-valve working condition after the data that digital independent submodule reads being processed.
Described diagnostic result display module comprises diagnostic result display sub-module and health degree curve display sub-module, and the diagnostic result of described diagnostic result display sub-module display comprises date display, valve number display, valve position number display, the display of health degree numerical value and the display of last diagnostic result; Described health degree curve display sub-module shows this valve health degree situation of nearest 10 days.Servo-valve health degree trend and current situation can be seen intuitively by described diagnostic result display module.
Described historical data analysis module comprises 1# valve data, 2# valve data, 3# valve data three submodules, select a certain valve data submodule, then in the window ejected, show servo-valve health degree curve in broken line graph mode, and show the location number of this valve, valve number at title place and use commencement date and deadline.
Compared with prior art, the present invention has following beneficial effect: the present invention combines artificial intelligence technology, Knowledge Base Techniques and computer technology, achieve servo-valve health degree state-detection and fault diagnosis generally, greatly reduce the occurrence frequency of fault, ensure the safety of equipment, product and related personnel, reduce maintenance workload and maintenance cost, thus improve the competitive power of manufacturing enterprise.
Accompanying drawing explanation
Fig. 1 is heavy plate mill AGC system position control schematic diagram;
Fig. 2 is the structured flowchart of one embodiment of the invention.
Embodiment
Below in conjunction with accompanying drawing, embodiments of the invention are elaborated: the present embodiment is implemented under premised on technical solution of the present invention, give detailed embodiment and process, but protection scope of the present invention is not limited to following embodiment.
As shown in Figure 1, be general heavy plate mill AGC system position control schematic diagram, system is according to actual measurement thickness of slab and thickness ratio comparatively its deviation requiring rolling, and by the control of servo system, adjustment depress oil cylinder, to reach required outlet thickness of slab.
Electrohydraulic servo valve 1,2 and 3 is connected in parallel in hydraulic circuit, when normally working, only can use two in three valves, if with 1 and 2, then have the operating valve that main in 1 and 2, another then just enables the underfed making up main valve when the flow of main valve can not be satisfied the demand.Servo-valve operationally can feed back the positional information of spool, i.e. the opening degree of valve, is defined as valve core of servo valve displacement and maximum displacement ratio, and opening degree corresponding when spool positive-displacement is maximum is 1, when negative sense is maximum, and corresponding opening degree is-1.
Before heavy plate mill AGC servo-valve condition monitoring and failure diagnosis system described in the present embodiment runs, first by sensor collection signal data, be respectively the piston side of pressure cylinder as parts in Fig. 14 and 5 and have HAD 3840 pressure transducer of bar side, the pressure changing in pressure cylinder can be detected thus.Piston because of pressure cylinder may occur crooked when rising, for eliminating crooked and metrical error that is that produce, two SONY HA-705-LK 907/MSS-976-R magnetic grids 6,7 are housed in the both sides of pressure cylinder, and the mean value of fetch bit shifting signal controls.The method is adopted to gather servo-valve data, and simultaneously online stored in text.
As shown in Figure 2, the present embodiment provides a kind of heavy plate mill AGC servo-valve condition monitoring and failure diagnosis system to comprise following five modules: diagnostic operation module, diagnostic result display module, MIM message input module, historical data analysis module and neural metwork training module.Wherein:
Described MIM message input module is carried out typing when milling train exchanges new servo-valve for new valve information and preserves data, calls for described diagnostic operation module;
Described neural metwork training module, when there being new servo-valve data, adopting neural network to train these data and result is added knowledge base, and these trained data called for described diagnostic operation module;
Described diagnostic operation module reads the data text to be tested gathered in advance, or/and the data of described MIM message input module and described neural metwork training module, diagnoses servo-valve, and result is sent to described diagnostic result display module;
Described diagnostic result display module then shows date of servo-valve, valve number, location number, diagnostic result and health degree information;
Described historical data analysis module provides the history run state information searching of a certain valve.
Below the modules specific implementation of the present embodiment is described in detail:
1. diagnostic operation module, this is the main user operation region of system, and this module is shown diagnostic result information being delivered in diagnostic result display module after data processing diagnosis.It comprises digital independent submodule and data diagnosis submodule.
A) digital independent submodule, by digital independent button control, its role is to the text reading data to be tested, the data file of general every day reads 5, constantly judge to read in the vector of data, date while reading, whether valve number is identical and whether have invalid data, and require that in each file read, rolling number of times must not be less than 10 times, if there is above-mentioned situation, then stops this digital independent.If it is correct to read data, then all data are passed in data diagnosis submodule to dependent variable.
B) data diagnosis submodule, by data diagnosis button control, its effect is processed the data of reading, judges its health status.Be exactly specifically first judge that the location number of valve is 1#, 2# or 3#, then process for transmission side and fore side respectively, extract final characteristic quantity: displacement difference average, opening degree average, peak value, large several number and traversing times.
Described displacement difference average refers to that transmission side and fore side depress the mean value of difference in height in an operation of rolling, characterizes the average case of steel rolling thickness difference;
The opening degree of described valve refers to valve core of servo valve displacement and maximum displacement ratio, and opening degree corresponding when spool positive-displacement is maximum is 1, when negative sense is maximum, and corresponding opening degree is-1.Its average and peak value characterize mean value and the maximal value of spool relative displacement in a rolling respectively.By a large amount of data analyses, find the threshold line of an opening degree, an operation of rolling split shed degree exceedes counting of this threshold line and is the large several number of opening degree, and broken line graph is traversing times through the number of times of threshold line, characterizes the fluctuation situation of opening degree.Emulate by the neural network trained after extracting characteristic quantity, draw healthy angle value, then use clustering algorithm to draw last diagnostic result according to data cases a few days ago.
2. diagnostic result display module, in servo-valve health degree state-detection process, system reads the data detected, the process for the treatment of and analysis and result, all can show at diagnostic result display module.It comprises diagnostic result display sub-module and health degree curve display sub-module.Both runs simultaneously, and system works process and diagnostic result are fed back to user intuitively.
A) diagnostic result display sub-module, comprises the display of servo-valve date, valve number display, the display of servo-valve location number, the display of health degree numerical value and the display of last diagnostic result.Last diagnostic result has three kinds of situations: normal, fault and undetermined.Normal expression servo-valve each side data display is normal, and a certain index of representation for fault servo-valve occurs abnormal, system malfunctions, and valve is changed in suggestion.Undeterminedly refer to that this diagnosis differs comparatively greatly with previous diagnosis, servo-valve health degree state cannot be judged.
B) health degree curve display sub-module, represents servo-valve health degree state with broken line graph, and horizontal ordinate is the use date (if use the date to be less than ten days, all show, then showed ten days more than ten days) of this valve, and ordinate is health degree numerical value.Also having a threshold line in figure, is the roughly separatrix of health degree numerical value.Transmission side and fore side health degree are presented in same figure with the curve of different colours.User very intuitively can arrive the tendency of servo-valve health degree curve by this figure.
3. MIM message input module, is mainly that diagnostic operation module and diagnostic result display module prepare Primary Stage Data, needs the typing of relevant information, to facilitate calling and judging in monitoring, diagnosing process after changing new servo-valve.This module needs the information of typing to comprise: machine time, numbering and upper machine location number on servo-valve.Input complete click afterwards after valve then sorts according to the information of input by preservation to preserve.
4. historical data analysis module, this module relatively lags behind and independently module, it is the health degree situation of the valve using (comprise and using) in order to check, mainly comprise 1# valve data, 2# valve data, 3# valve data three buttons and corresponding drop-down menu, in the window ejected, show servo-valve health degree curve in broken line graph mode after selecting a certain valve, and show the location number of this valve, valve number at title place and use commencement date and deadline.As: 2# transmission side 461 servo-valve health degree data, use date: 2009.10.1-200912.20.Associative operation can be carried out to this data plot, as preserved, amplifying, reduce at toolbar.
5. neural metwork training module is relevant to the upgrade function of system.The effect of neural metwork training is directly connected to the performance of system, and therefore this module is a vital link in system.
A) network training submodule, first typical data are selected, the rolling situation of steel plate is observed in data acquisition, pick out the data that rolling situation is comparatively stable and break down, the failure cause of Dual Injector Baffle formula electrohydraulic servo valve has the demagnetization of little ball wear, permanent magnet, valve pocket seal wear, the wearing and tearing of main valve plug seamed edge, main valve plug gauge wear, the stuck clamping stagnation of main valve plug, spray nozzle clogging, blocked primary orifice, internal core block and electronic circuit fault etc. in valve.Wherein topmost failure mode can be summarized as three major types, is respectively blocking type fault in servo-valve, clamping stagnation type fault and leak type fault.Then the data analysis these broken down, extract fault characteristic value, comprise displacement difference average, opening degree average, peak value, large several number and traversing times, same characteristic quantity is also extracted to the servo-valve of normal work simultaneously, then adopt BP neural network function to train.
B) Data Update submodule, is updated to knowledge base by during the fructufy of network training submodule, knowledge base can be made so constantly to carry out dilatation and upgrading, thus improve the adaptability of system and equipment working condition.Dilatation and upgrade function need complete under complete MATLAB environment.
In the present embodiment, before module is run, first adopt sensor (mainly to comprise roll-force to signal, displacement difference, transmission side and fore side opening degree etc.) carry out collection and simultaneously online stored in text, then in diagnostic operation module, ' reading data ' button is clicked, read text data to be tested, continuous reading 5 files on the same day, then ' data diagnosis ' is clicked, diagnostic operation module is run complete, then show its diagnostic result (date of test data at diagnostic result display module, valve number, location number, the net result of diagnosis and this valve health degree situation of nearest 10 days).So constantly circulate execution, just can test the health degree situation of every day.Need to click ' on new valve machine ' in MIM message input module when milling train exchanges new servo-valve for and Data Enter is carried out to new valve, comprise the location number of machine time, valve number and valve.When needing the history run state of checking a certain valve, then can click related valves in historical data analysis module and check its relevant information.When the change of servo-valve operating mode or when having new data to need to add knowledge base, will Data Update be carried out in neural metwork training module and carry out repeatedly neural metwork training, select wherein effectiveness comparison good as final training result, to keep the accuracy of fault diagnosis.
Present system possess status fault diagnosis and early warning, warning function, the health degree state of servo-valve can be judged more accurately, real-time guarantees is provided to system stable operation, and to the discovery of fault with change servo-valve and provide quick response, greatly reduce the occurrence frequency of fault, ensure the safety of equipment, steel rolling product and related personnel.
Although content of the present invention has done detailed introduction by above preferred embodiment, will be appreciated that above-mentioned description should not be considered to limitation of the present invention.After those skilled in the art have read foregoing, for multiple amendment of the present invention and substitute will be all apparent.Therefore, protection scope of the present invention should be limited to the appended claims.
Claims (8)
1. a heavy plate mill AGC servo-valve condition monitoring and failure diagnosis system, is characterized in that, comprises following five modules: diagnostic operation module, diagnostic result display module, MIM message input module, historical data analysis module and neural metwork training module; First the roll-force of milling train, transmission side and the displacement of fore side and the opening degree signal of servo-valve is gathered with sensor and on-line storage is text before described system cloud gray model; Wherein:
Described MIM message input module is carried out typing when milling train exchanges new servo-valve for new valve information and preserves data, calls for described diagnostic operation module;
Described neural metwork training module, when there being new servo-valve data, adopting neural network to train these data and result is added knowledge base, and these trained data called for described diagnostic operation module;
Described diagnostic operation module reads text to be tested, or/and the data of described MIM message input module and described neural metwork training module, diagnoses servo-valve, and result is sent to described diagnostic result display module;
Described diagnostic result display module then shows date of servo-valve, valve number, location number, diagnostic result and health degree information;
Described historical data analysis module provides the history run state information searching of a certain valve;
Described diagnostic operation module comprises digital independent submodule and data diagnosis submodule, described digital independent submodule is used for choosing the text needing test, judges the date of data and data are wherein passed to the time variable in diagnostic result display module; Described data diagnosis submodule obtains the proper vector characterizing servo-valve working condition after the data that digital independent submodule reads being processed;
Described digital independent submodule reads the text of data to be tested, the data file of every day reads 5, constantly judge to read in the vector of data, date while reading, whether valve number is identical and whether have invalid data, and require that in each file read, rolling number of times must not be less than 10 times, be less than 10 times if there is rolling number of times, then stop this digital independent; If it is correct to read data, then all data are passed to variable corresponding in data diagnosis submodule;
The data of reading process by described data diagnosis submodule, judge its health status namely: first judge that the location number of valve is 1#, 2# or 3#, then process for transmission side and fore side respectively, extract final characteristic quantity: displacement difference average, opening degree average, peak value, large several number and traversing times.
2. heavy plate mill AGC servo-valve condition monitoring and failure diagnosis system according to claim 1, it is characterized in that, described diagnostic result display module comprises diagnostic result display sub-module and health degree curve display sub-module, and the diagnostic result of described diagnostic result display sub-module display comprises date display, valve number display, valve position number display, the display of health degree numerical value and the display of last diagnostic result; Described health degree curve display sub-module shows this valve health degree situation of nearest 10 days; Servo-valve health degree trend and current situation can be seen intuitively by described diagnostic result display module.
3. heavy plate mill AGC servo-valve condition monitoring and failure diagnosis system according to claim 2, it is characterized in that, described diagnostic result display sub-module, wherein last diagnostic result has three kinds of situations: normal, fault and undetermined; Normal expression servo-valve each side data display is normal, and a certain index of representation for fault servo-valve occurs abnormal, system malfunctions, and valve is changed in suggestion; Undeterminedly refer to that this diagnosis differs comparatively greatly with previous diagnosis, servo-valve health degree state cannot be judged.
4. heavy plate mill AGC servo-valve condition monitoring and failure diagnosis system according to claim 2, it is characterized in that, described health degree curve display sub-module, servo-valve health degree state is represented with broken line graph, horizontal ordinate is the use date of this valve, if use the date to be less than ten days, all show, then showed ten days more than ten days; Ordinate is health degree numerical value, and its scope is 0-1,0 is the poorest, and 1 is best; Also having a threshold line in broken line graph, is the separatrix of health degree numerical value; Transmission side and fore side health degree are presented in same figure with the curve of different colours.
5. heavy plate mill AGC servo-valve condition monitoring and failure diagnosis system according to claim 1, it is characterized in that, described MIM message input module primary responsibility change new servo-valve after for the typing of new servo-valve information, this module needs the information of typing to comprise machine time, numbering and upper machine location number on input servo-valve, and preserves after being sorted by valve according to the information of input; The relevant information of used servo-valve can be preserved by this module, be convenient to the accurate judgement of diagnostic procedure, also can be provided with post analysis and use.
6. heavy plate mill AGC servo-valve condition monitoring and failure diagnosis system according to claim 1, it is characterized in that, described neural metwork training module comprises Data Update submodule and network training submodule, described Data Update submodule, when there being new servo-valve data to add knowledge base, carries out Data Update; Described network training submodule adopts neural network to carry out network training to these data, and these trained data is called for described diagnostic operation module; The knowledge base of servo-valve presence is in systems in which integrated, filters out representative data by current existing data by the requirement of characteristic quantity; Knowledge base has the function of dilatation and upgrading.
7. heavy plate mill AGC servo-valve condition monitoring and failure diagnosis system according to claim 6, it is characterized in that, first described neural metwork training module selects typical data, the rolling situation of steel plate is observed in data acquisition, pick out the data that rolling situation is comparatively stable and break down, the failure cause of Dual Injector Baffle formula electrohydraulic servo valve has little ball wear, the demagnetization of permanent magnet, valve pocket seal wear, main valve plug seamed edge weares and teares, main valve plug gauge wear, the stuck clamping stagnation of main valve plug, spray nozzle clogging, blocked primary orifice, internal core blocks and electronic circuit fault in valve, wherein topmost failure mode is summarized as four large classes, is respectively electronic circuit fault in servo-valve, blocking type fault, clamping stagnation type fault and leak type fault, then the data analysis these broken down, extract fault characteristic value, comprise displacement difference average, opening degree average, peak value, large several number and traversing times, same characteristic quantity is also extracted to the servo-valve of normal work simultaneously, then adopt BP neural network function to train.
8. heavy plate mill AGC servo-valve condition monitoring and failure diagnosis system according to claim 1, it is characterized in that, described historical data analysis module comprises 1# valve data, 2# valve data, 3# valve data three submodules, select a certain valve data submodule, then in the window ejected, show servo-valve health degree curve in broken line graph mode, and show the location number of this valve, valve number at title place and use commencement date and deadline.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210082699.1A CN102628738B (en) | 2012-03-26 | 2012-03-26 | State monitoring and failure diagnosis system for thick plate mill AGC servo valve |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210082699.1A CN102628738B (en) | 2012-03-26 | 2012-03-26 | State monitoring and failure diagnosis system for thick plate mill AGC servo valve |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102628738A CN102628738A (en) | 2012-08-08 |
| CN102628738B true CN102628738B (en) | 2014-12-24 |
Family
ID=46587037
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210082699.1A Expired - Fee Related CN102628738B (en) | 2012-03-26 | 2012-03-26 | State monitoring and failure diagnosis system for thick plate mill AGC servo valve |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102628738B (en) |
Families Citing this family (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102929236A (en) * | 2012-10-26 | 2013-02-13 | 北京机械设备研究所 | Display device applicable to distributed electro hydraulic servo system |
| CN109101007A (en) * | 2017-06-20 | 2018-12-28 | 宝山钢铁股份有限公司 | A kind of milling train HGC system servo valve inline diagnosis method |
| CN108994088B (en) * | 2018-06-12 | 2019-12-24 | 武汉科技大学 | HAGC cylinder fault diagnosis method and device based on PCA dimension reduction and DBN network |
| CN108980147A (en) * | 2018-09-12 | 2018-12-11 | 山西东润精益电力液压控制有限公司 | A kind of discharge characteristic degeneration monitoring method and its device |
| JP6701294B2 (en) * | 2018-09-19 | 2020-05-27 | 株式会社アマダ | Press brake and management system |
| DE102019209110A1 (en) * | 2019-06-24 | 2020-12-24 | Sms Group Gmbh | Industrial plant, in particular plant in the metal-producing industry or the aluminum or steel industry, and method for operating an industrial plant, in particular a plant in the metal-producing industry or the aluminum or steel industry |
| CN110814054B (en) * | 2019-11-13 | 2020-10-27 | 清华四川能源互联网研究院 | Early warning method based on opening static and dynamic characteristics of hydraulic cylinder servo valve |
| CN111715700B (en) * | 2020-05-08 | 2022-05-27 | 唐山钢铁集团有限责任公司 | AGC state detection control method for strip mill |
| CN112650897B (en) * | 2020-12-23 | 2023-06-30 | 广西交控智维科技发展有限公司 | Information monitoring system and display method based on track asset system |
| CN114472517A (en) * | 2022-01-05 | 2022-05-13 | 首钢京唐钢铁联合有限责任公司 | Rolling method, device, equipment and storage medium |
| CN114964841A (en) * | 2022-05-07 | 2022-08-30 | 中国地质大学（武汉） | Mobile robot fault detection system and method based on multi-sensor fusion |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5142612A (en) * | 1990-08-03 | 1992-08-25 | E. I. Du Pont De Nemours & Co. (Inc.) | Computer neural network supervisory process control system and method |
| CN101393543A (en) * | 2007-09-18 | 2009-03-25 | 西门子公司 | Failure analysis and diagnosis method and system |
-
2012
- 2012-03-26 CN CN201210082699.1A patent/CN102628738B/en not_active Expired - Fee Related
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5142612A (en) * | 1990-08-03 | 1992-08-25 | E. I. Du Pont De Nemours & Co. (Inc.) | Computer neural network supervisory process control system and method |
| CN101393543A (en) * | 2007-09-18 | 2009-03-25 | 西门子公司 | Failure analysis and diagnosis method and system |
Non-Patent Citations (3)
| Title |
|---|
| AGC伺服阀故障分析;薛海军;《甘肃冶金》;20111231;第33卷(第6期);全文 * |
| 基于神经网络的电液伺服阀故障诊断;谭树彬 等;《仪器仪表学报》;20060630;第27卷(第6期);正文第401-403页，第418页 * |
| 液压AGC伺服阀在线故障智能诊断的研究;郝圣桥;《中国优秀硕士学位论文全文数据库工程科技Ⅱ辑》;20100115(第01期);正文第9页第1段，第49页倒数第1段，第50页第1段，第54页倒数第2段 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102628738A (en) | 2012-08-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102628738B (en) | State monitoring and failure diagnosis system for thick plate mill AGC servo valve | |
| CN109766334B (en) | Processing method and system for online monitoring abnormal data of power equipment | |
| CN109949436A (en) | Industrial intelligent Optimization of Energy Saving system based on the analysis of emphasis energy consumption equipment Model Diagnosis | |
| WO2014207789A1 (en) | Status monitoring device | |
| CN209485669U (en) | A kind of hobboing cutter information monitoring device | |
| CN106022651A (en) | Risk early warning method based on business attribute and index system | |
| CN102175282A (en) | Method for diagnosing fault of centrifugal air compressor based on information fusion | |
| CN107291830A (en) | A kind of creation method of equipment knowledge base | |
| CN110245053A (en) | Failure predication diagnostic method and system | |
| CN105928710A (en) | Diesel engine fault monitoring method | |
| CN107065834A (en) | The method for diagnosing faults of concentrator in hydrometallurgy process | |
| CN102507244A (en) | Fault self-diagnosis expert system for hydraulic hoist | |
| CN109902871B (en) | Intelligent optimization energy-saving system combining differentiation characteristics of enterprise production line | |
| CN115017214B (en) | Hydropower station auxiliary equipment operation state analysis early warning method, device and storage medium | |
| CN105930957A (en) | Risk early warning method for electric energy meter automatic verification line | |
| CN117348503B (en) | Propylene oxide production data monitoring system and method | |
| CN111159487A (en) | Predictive maintenance intelligent system for automobile engine spindle | |
| CN110307212A (en) | A kind of Hydrauservo System oil leak monitoring method | |
| CN100364743C (en) | Fault monitoring and expert system for rubber banburying producing process and its using method | |
| CN106933097B (en) | Chemical process fault diagnosis method based on multi-layer optimization PCC-SDG | |
| CN108560633A (en) | A kind of hydraulic excavator engine and variable pump complex controll online monitoring system | |
| CN103760845B (en) | Monitoring method and system and rotary drilling rig | |
| CN114670062B (en) | Method and system for detecting wear state of drilling tool in real time | |
| CN104484277A (en) | Process data dynamic analysis device based on monitoring point and use method of process data dynamic analysis device | |
| CN105512801A (en) | Power transmission equipment state estimation method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20141224 Termination date: 20180326 |