CN105301985A - Method and system for measuring length of calcium carbide furnace electrode - Google Patents
Method and system for measuring length of calcium carbide furnace electrode Download PDFInfo
- Publication number
- CN105301985A CN105301985A CN201510819613.2A CN201510819613A CN105301985A CN 105301985 A CN105301985 A CN 105301985A CN 201510819613 A CN201510819613 A CN 201510819613A CN 105301985 A CN105301985 A CN 105301985A
- Authority
- CN
- China
- Prior art keywords
- electrode
- consumed
- calcium carbide
- function
- prediction models
- 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.)
- Pending
Links
Abstract
The invention provides a method for detecting the length of a calcium carbide furnace electrode. The method comprises the steps: obtaining a non-linear prediction model of electrode consumption according to a model training sample set, wherein electrode temperature T, electrode power P, a furnace charge ratio R and calcium carbide output G are sample input variables, and the electrode consumption is a sample output variable; determining electrode consumption in a current working condition according to the non-linear prediction model of electrode consumption; and determining the length of an electrode according to the electrode consumption in the current working condition. The method can monitor the position changes of an electrode in real time and then guide pressing and releasing for electrodes, so the pressing and releasing amount for electrodes can be accurately controlled, and electrodes are made to work in a balance manner. The method guarantees stable production and energy-saving operation of a calcium carbide furnace.
Description
Technical field
The present invention relates to industrial control information field, particularly a kind of measuring method of furnace of calcium carbide electrode length and system.
Background technology
Furnace of calcium carbide is the main equipment producing calcium carbide, and it mainly carrys out material in heating furnace by the submerged arc electric heating of electrode and the resistance electrothermal of material, as unslaked lime and carbon element etc., makes material reaction generate calcium carbide.
In furnace of calcium carbide, the normal electrode adopted comprises self-baking electrode, graphite electrode or carbon pole, electrode handle big current is delivered in stove, produce electric arc at the end of electrode, and then convert electrical energy into heat energy, owing to electric arc creating high temperature, electrode tip distils, cause electrode constantly consume and shorten, therefore, need regularly to press electrode to keep certain electrode length, can acting be stablized, ensure the quality of output calcium carbide.
At present, electrode press operation, namely the setting of Electrode Fluctuation interval time, depends on the experience of production, and artificial factor is comparatively large, and this can cause the insertion depth of each phase electrode there are differences, and acting is uneven, then affects calcium carbide quality and power consumption.If can Real-time Obtaining electrode length, the change in location of monitoring electrode, and then instruct electrode press operation, to control the Pressure Slipping Volume of each electrode accurately, each electrode is done work balance, for the steady production of furnace of calcium carbide and energy-saving run provide safeguard.
But mainly obtain electrode length at furnace shutdown period by manual measurement at present, blow-on run duration also cannot detect the change of electrode length in real time, therefore, is necessary the detection method proposing a kind of electrode length, can obtains the length of electrode in real time.
Summary of the invention
In view of this, the object of the present invention is to provide a kind of measuring method of furnace of calcium carbide electrode length, realize Real-time Obtaining electrode length, for the steady production of furnace of calcium carbide and energy-saving run provide safeguard.
For achieving the above object, the present invention has following technical scheme:
A detection method for furnace of calcium carbide electrode length, described method comprises:
Based on model training sample set, obtain the Nonlinear Prediction Models of consumed electrode, wherein, electrode temperature T, electrode power P, charge composition R and calcium carbide production amount G are sample input variable, and consumed electrode is sample output variable;
According to the Nonlinear Prediction Models of consumed electrode, determine the consumed electrode under current working;
By the consumed electrode under current working, determine front electrode length.
Optionally, based on model training sample set, the step obtaining the Nonlinear Prediction Models of consumed electrode comprises:
By Nonlinear Mapping, the input amendment of model training sample set is mapped to feature space, constructs the optimum linearity regression function of this feature space;
Utilize structural risk minimization, set up the objective optimization function of optimum linearity regression function, in objective optimization function, select 2 norms of training error as loss function, and adopt equality constraint;
According to Lagrange multiplier, set up the Lagrangian function of objective optimization function;
By least square method, determine the model based on Lagrange multiplier;
To be kernel function based on the function sets in the model of Lagrange multiplier, thus obtain the Nonlinear Prediction Models of consumed electrode.
Optionally, described kernel function is Radial basis kernel function.
Optionally, described model training sample set is multiple, after the Nonlinear Prediction Models obtaining consumed electrode, also comprises:
Based on error training sample set, obtain the error assessment index of the Nonlinear Prediction Models of consumed electrode;
Determine that the minimum Nonlinear Prediction Models of error assessment index is the Nonlinear Prediction Models of the consumed electrode during electrode length detects.
Optionally, described model training sample set is through data prediction, wherein, electrode temperature T, electrode power P are the mean value before current time within the scope of first schedule time, charge composition R is the mean value before current time within the scope of second schedule time, and calcium carbide production amount G is the product often criticizing calcium carbide production strike number and single pot of calcium carbide weight.
Optionally, front electrode length H=H
0+ Δ H
sj+ Δ d*C-Δ H
xh* T, wherein: H is front electrode length, H
0for previous moment electrode length, Δ H
sjfor rise fall of electrodes amount, Δ d is electrode single Pressure Slipping Volume, C for pressing number of times, Δ H
xhfor consumed electrode, T is electrode length H and H
0the mistiming in corresponding moment.
In addition, present invention also offers a kind of detection system of furnace of calcium carbide electrode length, comprising:
Consumed electrode forecast model acquisition module, for based on model training sample set, obtain the Nonlinear Prediction Models of consumed electrode, wherein, electrode temperature T, electrode power P, charge composition R and calcium carbide production amount G are sample input variable, and consumed electrode is sample output variable;
Consumed electrode determination module, for the Nonlinear Prediction Models according to consumed electrode, determines the consumed electrode under current working;
Front electrode length determination modul, for by the consumed electrode under current working, determines front electrode length.
Optionally, consumed electrode forecast model acquisition module comprises:
By Nonlinear Mapping, the input amendment of model training sample set is mapped to feature space, constructs the optimum linearity regression function of this feature space;
Utilize structural risk minimization, set up the objective optimization function of optimum linearity regression function, in objective optimization function, select 2 norms of training error as loss function, and adopt equality constraint;
According to Lagrange multiplier, set up the Lagrangian function of objective optimization function;
By least square method, determined the Nonlinear Prediction Models of the consumed electrode based on Lagrange multiplier and kernel function by Lagrangian function.
Optionally, described kernel function is Radial basis kernel function.
Optionally, described model training sample set is multiple, also comprises:
Error assessment module, based on error training sample set, obtains the error assessment index of the Nonlinear Prediction Models of consumed electrode; And determine that the minimum Nonlinear Prediction Models of error assessment index is the Nonlinear Prediction Models of the consumed electrode during electrode length detects.
Optionally, also comprise data preprocessing module, for model training sample set is carried out data prediction, wherein, electrode temperature T, electrode power P are the mean value before current time within the scope of first schedule time, charge composition R is the mean value before current time within the scope of second schedule time, and calcium carbide production amount G is the product often criticizing calcium carbide production strike number and single pot of calcium carbide weight.
Optionally, in front electrode length determination modul, front electrode length H=H
0+ Δ H
sj+ Δ d*C-Δ H
xh* T, wherein: H is front electrode length, H
0for previous moment electrode length, Δ H
sjfor rise fall of electrodes amount, Δ d is electrode single Pressure Slipping Volume, C for pressing number of times, Δ H
xhfor consumed electrode, T is electrode length H and H
0the mistiming in corresponding moment.
The detection method of the furnace of calcium carbide electrode length that the embodiment of the present invention provides and system, by these sample input variables of electrode temperature T, electrode power P, charge composition R and calcium carbide production amount G, obtain the Nonlinear Prediction Models of consumed electrode, the consumed electrode under current working can be obtained by this Nonlinear Prediction Models, then, determine front electrode length by consumed electrode, realize the hard measurement of electrode length.Like this, can the change in location of monitoring electrode in real time, and then instruct electrode press operation, to control the Pressure Slipping Volume of each electrode accurately, each electrode is done work balance, for the steady production of furnace of calcium carbide and energy-saving run provide safeguard.
Accompanying drawing explanation
In order to be illustrated more clearly in the embodiment of the present invention or technical scheme of the prior art, be briefly described to the accompanying drawing used required in embodiment or description of the prior art below, apparently, accompanying drawing in the following describes is some embodiments of the present invention, for those of ordinary skill in the art, under the prerequisite not paying creative work, other accompanying drawing can also be obtained according to these accompanying drawings.
Fig. 1 is the process flow diagram of the detection method of the furnace of calcium carbide electrode length of the embodiment of the present invention;
Fig. 2 is the process flow diagram of the Nonlinear Prediction Models obtaining consumed electrode in the detection method of the embodiment of the present invention;
Fig. 3 is the structural representation of the detection system of furnace of calcium carbide electrode length according to the embodiment of the present invention;
Fig. 4 is the structural representation of the detection system of furnace of calcium carbide electrode length according to another embodiment of the present invention.
Embodiment
For making the object of the embodiment of the present invention, technical scheme and advantage clearly, below in conjunction with the accompanying drawing in the embodiment of the present invention, technical scheme in the embodiment of the present invention is clearly and completely described, obviously, described embodiment is the present invention's part embodiment, instead of whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art, not making the every other embodiment obtained under creative work prerequisite, belong to the scope of protection of the invention.
As the description of background technology, mainly obtain electrode length at furnace shutdown period by manual measurement at present, blow-on run duration also cannot detect the change of electrode length in real time, electrode press operation, namely the setting of Electrode Fluctuation interval time, depends on the experience of production, artificial factor is larger, this can cause the insertion depth of each phase electrode there are differences, and acting is uneven, then affects calcium carbide quality and power consumption.For this reason, the present invention proposes a kind of detection method of furnace of calcium carbide electrode length, shown in figure 1, described method comprises:
Based on model training sample set, obtain the Nonlinear Prediction Models of consumed electrode, wherein, electrode temperature T, electrode power P, charge composition R and calcium carbide production amount G are sample input variable, and consumed electrode is sample output variable;
According to the Nonlinear Prediction Models of consumed electrode, determine the consumed electrode under current working;
By the consumed electrode under current working, determine front electrode length.
In the method, by these sample input variables of electrode temperature T, electrode power P, charge composition R and calcium carbide production amount G, obtain the Nonlinear Prediction Models of consumed electrode, the consumed electrode under current working can be obtained by this Nonlinear Prediction Models, then, determine front electrode length by consumed electrode, realize the hard measurement of electrode length.Like this, can the change in location of monitoring electrode in real time, and then instruct electrode press operation, to control the Pressure Slipping Volume of each electrode accurately, each electrode is done work balance, for the steady production of furnace of calcium carbide and energy-saving run provide safeguard.
Technical scheme for a better understanding of the present invention and technique effect, be described in detail specific embodiment below with reference to particular flow sheet.
First, in step S101, based on model training sample set, obtain the Nonlinear Prediction Models of consumed electrode, wherein, electrode temperature T, electrode power P, charge composition R and calcium carbide production amount G are sample input variable, and consumed electrode is sample output variable.
In the present invention, choice electrode temperature T, electrode power P, charge composition R and calcium carbide production amount G are sample input variable, and consumed electrode is the model training sample set of sample output variable, determines the Nonlinear Prediction Models of consumed electrode.
Wherein, electrode temperature T characterizes electrode soft or hard degree; Electrode power P characterizes electrode acting size; Charge composition R is the carbon element amount of every 100kg lime institute adapted, characterizes the size of carbon element amount in furnace charge, calcium carbide production amount G be often criticize calcium carbide go out furnace volume, characterize furnace of calcium carbide actual motion load height.By the sample set that these samples input, obtain the Nonlinear Prediction Models of consumed electrode.
In embodiments of the present invention, sample set can comprise model training sample set and error training sample set, can further include checking sample set, model training sample set can be multiple, in order to improve the precision of prediction of forecast model, to sample notebook data representative, and the service data covered as far as possible in furnace of calcium carbide production run under normal range of operation and different operating load, according to following structure composition sample, and can collect sample data, sample expression formula is { x
i, y
i, the data structure of sample is as shown in table 1 below:
Table 1 sample data structure
Wherein, x
ifor the input of sample, the auxiliary variable namely chosen---electrode temperature T, electrode power P, charge composition R, calcium carbide production amount G.The output y of sample
ifor leading variable to be estimated, i.e. consumed electrode Δ H
xh, the actual value of consumed electrode can calculate according to the electrode length measured value of twice furnace shutdown period and the total Pressure Slipping Volume of electrode.
In order to eliminate the noise of data, data prediction can be carried out to gathered data sample, concrete, electrode temperature T, electrode power P are the mean value before current time within the scope of first schedule time, charge composition R is the mean value before current time within the scope of second schedule time, and calcium carbide production amount G is the product often criticizing calcium carbide production strike number and single pot of calcium carbide weight.After pre-service, apparent error and invalid data can be rejected, stress release treatment, improve the accuracy of the model obtained.
In the present embodiment, shown in figure 2, obtain the Nonlinear Prediction Models based on the consumed electrode of each model training sample set by following concrete step:
In step S201, by Nonlinear Mapping, the input amendment of model training sample set is mapped to feature space, constructs the optimum linearity regression function of this feature space.
For with [electrode temperature T, electrode power P, charge composition R, calcium carbide production amount G] T as mode input x
i, consumed electrode Δ H
xhy is exported as model
i, composing training model sample set
wherein x
i∈ R
4, y
i∈ R.First pass through a Nonlinear Mapping ψ () input amendment from input space R
4be mapped to feature space
optimum linearity regression function is constructed in this high-dimensional feature space:
(w∈R
dn，b∈R)
In formula: w
tfor weight vector; B is amount of bias.
Then, in step S202, utilize structural risk minimization, set up the objective optimization function of optimum linearity regression function, in objective optimization function, select 2 norms of training error as loss function, and adopt equality constraint.
In this step, nonlinear estimation function is converted into the Linear Estimation problem in high-dimensional feature space, utilizes structural risk minimization, find w, b and minimize exactly
wherein || w||
2the complexity of Controlling model, C is regularization parameter, R
empfor control errors function, it is also ε insensitive loss function.In this optimization, loss function is training error ξ
i2 norms.Like this, the objective optimization function setting up optimum linearity regression function is:
Equality constraint st:
i=1 ..., l.
Then, in step S203, according to Lagrange multiplier, the Lagrangian function of objective optimization function is set up.
Solve this optimization problem by Lagrangian method in this step, setting up Lagrangian function is:
Wherein α
i, i, j=1,2 ..., l is Lagrange multiplier.
Then, in step S204, by least square method, determined the Nonlinear Prediction Models of the consumed electrode based on Lagrange multiplier and kernel function by Lagrangian function.
According to optimal conditions:
Can obtain
α
i＝cξ
i，
By above formula, and define kernel function
i, j=1,2 ..., l, is converted into optimization problem and solves linear equation:
Regression coefficient α is obtained by least square method
iwith deviation b, obtain model parameter [the b α based on Lagrange multiplier
1α
2α
l], and then obtain the Nonlinear Prediction Models of consumed electrode:
For kernel function K (x
i, x
j), it is any symmetric kernel function meeting Metcer condition, and preferably, described kernel function is Radial basis kernel function, finally, obtains the Nonlinear Prediction Models of consumed electrode:
For many group models training sample set, the Nonlinear Prediction Models of the consumed electrode based on this group model training sample set can be obtained respectively.
Then, based on error training sample set, error assessment can be carried out to above-mentioned Nonlinear Prediction Models, thus, the Nonlinear Prediction Models of the consumed electrode detecting from wherein selecting more excellent model as electrode length.
Concrete, first, based on error training sample set, obtain the error assessment index of the Nonlinear Prediction Models of consumed electrode.
Based on error training sample set S, comprising sample data is l, definition error function:
Wherein: i=1,2 ..., l.Selection final error evaluation function is:
e(γ,δ)＝min(e
1+ηe
2)
In formula: γ is error punishment parameter; δ is nuclear parameter; η is weight parameter.
Rule of thumb select the weight of mean square deviation and maximum variance, generally can select η=1.Above-mentioned error assessment function is utilized to obtain error assessment index.If the error assessment index obtained is not in the threshold range of setting, then need the process that the Nonlinear Prediction Models repeating above-mentioned consumed electrode is set up, if the error assessment index obtained is in the threshold range of setting, then, think that the minimum Nonlinear Prediction Models of error assessment index is optimization model, determine that the minimum Nonlinear Prediction Models of error assessment index is the Nonlinear Prediction Models of the consumed electrode during electrode length detects.
In order to further obtain the Nonlinear Prediction Models of more accurate consumed electrode, can select further to verify sample set, the Nonlinear Prediction Models of the consumed electrode in detecting the above-mentioned electrode length determined is verified further, the input of more above-mentioned Nonlinear Prediction Models and the error of actual measured value, if error is in allowed band, then determine that this model may be used for the on-line prediction of consumed electrode; If error is comparatively large, analyzing electrode consumption models training sample data, continues training pattern, can suitably increase training pattern sample data, repeat above-mentioned modeling process, until obtain optimum model.
In step S102, according to the Nonlinear Prediction Models of consumed electrode, determine the consumed electrode under current working.
When needs detecting electrode length, first obtain the parameter of the electrode temperature T under current working, electrode power P, charge composition R and calcium carbide production amount G, these parameters usually can Real-time Obtaining, then, utilize the Nonlinear Prediction Models of consumed electrode, obtain the consumed electrode under current working.Normally, after these parameters of acquisition, the standardization of data be carried out, be namely normalized, make can carry out computing between the data of different dimension.
In step S103, by the consumed electrode under current working, determine front electrode length.
Can be calculated by following, by the consumed electrode under current working, determine front electrode length H=H
0+ Δ H
sj+ Δ d*C-Δ H
xh* T, wherein: H is front electrode length, H
0for previous moment electrode length, Δ H
sjfor rise fall of electrodes amount, Δ d is electrode single Pressure Slipping Volume, C for pressing number of times, Δ H
xhfor consumed electrode, T is electrode length H and H
0the mistiming in corresponding moment.
Like this, just go out consumed electrode by current working parameter prediction, and then determined front electrode length by consumed electrode, realize the hard measurement of electrode length.Thus, can the change in location of monitoring electrode in real time, so instruct electrode press operation, to control the Pressure Slipping Volume of each electrode accurately, each electrode is done work balance, for the steady production of furnace of calcium carbide and energy-saving run provide safeguard.
In addition, the present invention also provides the detection system of the furnace of calcium carbide electrode length corresponding with said method, shown in figure 3, comprising:
Consumed electrode forecast model acquisition module 300, for based on model training sample set, obtain the Nonlinear Prediction Models of consumed electrode, wherein, electrode temperature T, electrode power P, charge composition R and calcium carbide production amount G are sample input variable, and consumed electrode is sample output variable;
Consumed electrode determination module 310, for the Nonlinear Prediction Models according to consumed electrode, determines the consumed electrode under current working;
Front electrode length determination modul 320, for by the consumed electrode under current working, determines front electrode length.
Wherein, consumed electrode forecast model acquisition module 300 comprises:
By Nonlinear Mapping, the input amendment of model training sample set is mapped to feature space, constructs the optimum linearity regression function of this feature space;
Utilize structural risk minimization, set up the objective optimization function of optimum linearity regression function, in objective optimization function, select 2 norms of training error as loss function, and adopt equality constraint;
According to Lagrange multiplier, set up the Lagrangian function of objective optimization function;
By least square method, determined the Nonlinear Prediction Models of the consumed electrode based on Lagrange multiplier and kernel function by Lagrangian function.
Described kernel function is preferably Radial basis kernel function.
Further, shown in figure 4, described model training sample set is multiple, also comprises:
Error assessment module 340, based on error training sample set, obtains the error assessment index of the Nonlinear Prediction Models of consumed electrode; And determine that the minimum Nonlinear Prediction Models of error assessment index is the Nonlinear Prediction Models of the consumed electrode during electrode length detects.
Further, also comprise data preprocessing module 330, for model training sample set is carried out data prediction, wherein, electrode temperature T, electrode power P are the mean value before current time within the scope of first schedule time, charge composition R is the mean value before current time within the scope of second schedule time, and calcium carbide production amount G is the product often criticizing calcium carbide production strike number and single pot of calcium carbide weight.
Further, in front electrode length determination modul 320, front electrode length H=H
0+ Δ H
sj+ Δ d*C-Δ H
xh* T, wherein: H is front electrode length, H
0for previous moment electrode length, Δ H
sjfor rise fall of electrodes amount, Δ d is electrode single Pressure Slipping Volume, C for pressing number of times, Δ H
xhfor consumed electrode, T is electrode length H and H
0the mistiming in corresponding moment.
Each embodiment in this instructions all adopts the mode of going forward one by one to describe, between each embodiment identical similar part mutually see, what each embodiment stressed is the difference with other embodiments.Especially, for system embodiment, because it is substantially similar to embodiment of the method, so describe fairly simple, relevant part illustrates see the part of embodiment of the method.System embodiment described above is only schematic, the wherein said module that illustrates as separating component or unit or can may not be and physically separate, parts as module or unit display can be or may not be physical location, namely can be positioned at a place, or also can be distributed in multiple network element.Some or all of module wherein can be selected according to the actual needs to realize the object of the present embodiment scheme.Those of ordinary skill in the art, when not paying creative work, are namely appreciated that and implement.
The above is only the preferred embodiment of the present invention, although the present invention discloses as above with preferred embodiment, but and is not used to limit the present invention.Any those of ordinary skill in the art, do not departing under technical solution of the present invention ambit, the Method and Technology content of above-mentioned announcement all can be utilized to make many possible variations and modification to technical solution of the present invention, or be revised as the Equivalent embodiments of equivalent variations.Therefore, every content not departing from technical solution of the present invention, according to technical spirit of the present invention to any simple modification made for any of the above embodiments, equivalent variations and modification, all still belongs in the scope of technical solution of the present invention protection.
Claims (12)
1. a detection method for furnace of calcium carbide electrode length, is characterized in that, described method comprises:
Based on model training sample set, obtain the Nonlinear Prediction Models of consumed electrode, wherein, electrode temperature T, electrode power P, charge composition R and calcium carbide production amount G are sample input variable, and consumed electrode is sample output variable;
According to the Nonlinear Prediction Models of consumed electrode, determine the consumed electrode under current working;
By the consumed electrode under current working, determine front electrode length.
2. detection method according to claim 1, is characterized in that, based on model training sample set, the step obtaining the Nonlinear Prediction Models of consumed electrode comprises:
By Nonlinear Mapping, the input amendment of model training sample set is mapped to feature space, constructs the optimum linearity regression function of this feature space;
Utilize structural risk minimization, set up the objective optimization function of optimum linearity regression function, in objective optimization function, select 2 norms of training error as loss function, and adopt equality constraint;
According to Lagrange multiplier, set up the Lagrangian function of objective optimization function;
By least square method, determined the Nonlinear Prediction Models of the consumed electrode based on Lagrange multiplier and kernel function by Lagrangian function.
3. detection method according to claim 2, is characterized in that, described kernel function is Radial basis kernel function.
4. detection method according to claim 2, is characterized in that, described model training sample set is multiple, after the Nonlinear Prediction Models obtaining consumed electrode, also comprises:
Based on error training sample set, obtain the error assessment index of the Nonlinear Prediction Models of consumed electrode;
Determine that the minimum Nonlinear Prediction Models of error assessment index is the Nonlinear Prediction Models of the consumed electrode during electrode length detects.
5. the detection method according to any one of claim 1-4, it is characterized in that, described model training sample set is through data prediction, wherein, electrode temperature T, electrode power P are the mean value before current time within the scope of first schedule time, charge composition R is the mean value before current time within the scope of second schedule time, and calcium carbide production amount G is the product often criticizing calcium carbide production strike number and single pot of calcium carbide weight.
6. detection method according to claim 1, is characterized in that, front electrode length H=H
0+ Δ H
sj+ Δ d*C-Δ H
xh* T, wherein: H is front electrode length, H
0for previous moment electrode length, Δ H
sjfor rise fall of electrodes amount, Δ d is electrode single Pressure Slipping Volume, C for pressing number of times, Δ H
xhfor consumed electrode, T is electrode length H and H
0the mistiming in corresponding moment.
7. a detection system for furnace of calcium carbide electrode length, is characterized in that, comprising:
Consumed electrode forecast model acquisition module, for based on model training sample set, obtain the Nonlinear Prediction Models of consumed electrode, wherein, electrode temperature T, electrode power P, charge composition R and calcium carbide production amount G are sample input variable, and consumed electrode is sample output variable;
Consumed electrode determination module, for the Nonlinear Prediction Models according to consumed electrode, determines the consumed electrode under current working;
Front electrode length determination modul, for by the consumed electrode under current working, determines front electrode length.
8. detection system according to claim 7, is characterized in that, consumed electrode forecast model acquisition module comprises:
By Nonlinear Mapping, the input amendment of model training sample set is mapped to feature space, constructs the optimum linearity regression function of this feature space;
Utilize structural risk minimization, set up the objective optimization function of optimum linearity regression function, in objective optimization function, select 2 norms of training error as loss function, and adopt equality constraint;
According to Lagrange multiplier, set up the Lagrangian function of objective optimization function;
By least square method, determined the Nonlinear Prediction Models of the consumed electrode based on Lagrange multiplier and kernel function by Lagrangian function.
9. detection system according to claim 8, is characterized in that, described kernel function is Radial basis kernel function.
10. detection system according to claim 8, is characterized in that, described model training sample set is multiple, also comprises:
Error assessment module, based on error training sample set, obtains the error assessment index of the Nonlinear Prediction Models of consumed electrode; And determine that the minimum Nonlinear Prediction Models of error assessment index is the Nonlinear Prediction Models of the consumed electrode during electrode length detects.
11. detection systems according to any one of claim 7-10, it is characterized in that, also comprise data preprocessing module, for model training sample set is carried out data prediction, wherein, electrode temperature T, electrode power P are the mean value before current time within the scope of first schedule time, and charge composition R is the mean value before current time within the scope of second schedule time, and calcium carbide production amount G is the product often criticizing calcium carbide production strike number and single pot of calcium carbide weight.
12. detection systems according to claim 1, is characterized in that, in front electrode length determination modul, and front electrode length H=H
0+ Δ H
sj+ Δ d*C-Δ H
xh* T, wherein: H is front electrode length, H
0for previous moment electrode length, Δ H
sjfor rise fall of electrodes amount, Δ d is electrode single Pressure Slipping Volume, C for pressing number of times, Δ H
xhfor consumed electrode, T is electrode length H and H
0the mistiming in corresponding moment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510819613.2A CN105301985A (en) | 2015-11-23 | 2015-11-23 | Method and system for measuring length of calcium carbide furnace electrode |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510819613.2A CN105301985A (en) | 2015-11-23 | 2015-11-23 | Method and system for measuring length of calcium carbide furnace electrode |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105301985A true CN105301985A (en) | 2016-02-03 |
Family
ID=55199383
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510819613.2A Pending CN105301985A (en) | 2015-11-23 | 2015-11-23 | Method and system for measuring length of calcium carbide furnace electrode |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105301985A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106019093A (en) * | 2016-05-15 | 2016-10-12 | 北华大学 | Online soft measurement method for three-phase arc furnace arc length |
| CN108388703A (en) * | 2018-01-30 | 2018-08-10 | 浙江中控软件技术有限公司 | For non-linear and random process flexible measurement method |
| CN108919739A (en) * | 2018-07-25 | 2018-11-30 | 嘉兴市合工业电炉有限公司 | industrial furnace control system |
| CN117268252A (en) * | 2023-11-23 | 2023-12-22 | 中控技术股份有限公司 | Electrode embedding depth prediction method and device, storage medium and electronic equipment |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6493596B1 (en) * | 1996-05-06 | 2002-12-10 | Pavilion Technologies, Inc. | Method and apparatus for controlling a non-linear mill |
| CN102297669A (en) * | 2011-01-25 | 2011-12-28 | 东北大学 | Soft measuring method for residue length of melted electrode of electroslag furnace |
| CN102636624A (en) * | 2012-04-28 | 2012-08-15 | 重庆大学 | Method for soft measurement of alumina concentration in electrolyzer during aluminum electrolysis process |
-
2015
- 2015-11-23 CN CN201510819613.2A patent/CN105301985A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6493596B1 (en) * | 1996-05-06 | 2002-12-10 | Pavilion Technologies, Inc. | Method and apparatus for controlling a non-linear mill |
| CN102297669A (en) * | 2011-01-25 | 2011-12-28 | 东北大学 | Soft measuring method for residue length of melted electrode of electroslag furnace |
| CN102636624A (en) * | 2012-04-28 | 2012-08-15 | 重庆大学 | Method for soft measurement of alumina concentration in electrolyzer during aluminum electrolysis process |
Non-Patent Citations (4)
| Title |
|---|
| 何忠 等: "软测量技术在密闭电石炉生产中的应用", 《商业故事》 * |
| 王玮: "集成多SVM的不常用备件需求预测支持系统研究", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
| 陈刚: "软测量技术的研究及其在电石生产中的应用", 《中国优秀硕士学位论文全文数据库工程科技I辑》 * |
| 陈寿辉: "铁合金冶炼矿热炉电极位置检测建模及优化设定研究", 《中国优秀硕士学位论文全文数据库工程科技I辑》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106019093A (en) * | 2016-05-15 | 2016-10-12 | 北华大学 | Online soft measurement method for three-phase arc furnace arc length |
| CN106019093B (en) * | 2016-05-15 | 2018-09-18 | 北华大学 | A kind of online soft sensor method of three-phawse arc furnace arc length |
| CN108388703A (en) * | 2018-01-30 | 2018-08-10 | 浙江中控软件技术有限公司 | For non-linear and random process flexible measurement method |
| CN108919739A (en) * | 2018-07-25 | 2018-11-30 | 嘉兴市合工业电炉有限公司 | industrial furnace control system |
| CN117268252A (en) * | 2023-11-23 | 2023-12-22 | 中控技术股份有限公司 | Electrode embedding depth prediction method and device, storage medium and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105301985A (en) | Method and system for measuring length of calcium carbide furnace electrode | |
| KR102087843B1 (en) | Methods and systems for improved time cost and accuracy of energy usage baselining | |
| CN102682218A (en) | Method for evaluating electricity energy efficiency of industrial user | |
| CN108416691B (en) | Energy substitution environment-friendly potential calculation method | |
| CN108709287B (en) | Air conditioning system cold load prediction method and water chilling unit group control strategy | |
| CN109284576B (en) | Distributed electric heating load scheduling method based on measured data and modeling system thereof | |
| CN103454140B (en) | Simple method for measuring fatigue crack propagation threshold value of metal material | |
| CN101863088A (en) | Method for forecasting Mooney viscosity in rubber mixing process | |
| CN108388703A (en) | For non-linear and random process flexible measurement method | |
| CN106405280B (en) | A kind of intelligent substation on-line monitoring parameter trend method for early warning | |
| CN104181878A (en) | Carbon discharge process monitoring and controlling method | |
| CN106845663A (en) | A kind of method that heat load prediction is carried out based on numerical weather forecast | |
| CN108108530A (en) | A kind of fatigue life calibration method suitable for structural connection | |
| CN102636624A (en) | Method for soft measurement of alumina concentration in electrolyzer during aluminum electrolysis process | |
| CN102277468B (en) | Real-time forecasting method of LF refining furnace molten steel temperature | |
| CN109033509A (en) | A kind of Fusion Model construction method based on dam deformation analysis | |
| CN102637020A (en) | Integrated-type control system of roll steel heating furnace | |
| CN108009311A (en) | A kind of creep Parameters of constitutive model recognition methods for creep test | |
| CN103605323B (en) | The Discrete Control Method of Chemical Manufacture and device | |
| CN111199339A (en) | User energy saving determination method and device | |
| CN105385843B (en) | A kind of hot rolling slab method for heating and controlling based on the last temperature of section | |
| CN116722605A (en) | Power distribution network scheduling optimization method based on Internet of things | |
| CN109471381B (en) | Equipment energy efficiency comprehensive control method based on big data fusion | |
| CN203012544U (en) | Intelligent linear heating temperature control apparatus | |
| CN202057594U (en) | Coke oven heating coal charge moisture online measuring system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160203 |