CN116603869B - Deviation correction control method and system based on feedback optimization - Google Patents
Deviation correction control method and system based on feedback optimization Download PDFInfo
- Publication number
- CN116603869B CN116603869B CN202310889667.0A CN202310889667A CN116603869B CN 116603869 B CN116603869 B CN 116603869B CN 202310889667 A CN202310889667 A CN 202310889667A CN 116603869 B CN116603869 B CN 116603869B
- Authority
- CN
- China
- Prior art keywords
- deviation
- data
- thickness
- control
- strip steel
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 45
- 238000005457 optimization Methods 0.000 title claims abstract description 30
- 238000012937 correction Methods 0.000 title claims description 62
- 229910000831 Steel Inorganic materials 0.000 claims abstract description 137
- 239000010959 steel Substances 0.000 claims abstract description 137
- 238000001514 detection method Methods 0.000 claims abstract description 107
- 230000003993 interaction Effects 0.000 claims abstract description 30
- 238000011156 evaluation Methods 0.000 claims description 13
- 230000003746 surface roughness Effects 0.000 claims description 10
- 238000012544 monitoring process Methods 0.000 claims description 8
- 238000012795 verification Methods 0.000 claims description 8
- 238000012216 screening Methods 0.000 claims description 4
- 238000004220 aggregation Methods 0.000 claims description 3
- 230000002776 aggregation Effects 0.000 claims description 3
- 238000004891 communication Methods 0.000 claims description 3
- 238000012549 training Methods 0.000 description 23
- 230000008569 process Effects 0.000 description 8
- 238000004519 manufacturing process Methods 0.000 description 7
- 230000000694 effects Effects 0.000 description 6
- 229910000975 Carbon steel Inorganic materials 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 238000012360 testing method Methods 0.000 description 4
- 239000010962 carbon steel Substances 0.000 description 3
- 238000005096 rolling process Methods 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000006116 polymerization reaction Methods 0.000 description 2
- 230000000717 retained effect Effects 0.000 description 2
- 238000010977 unit operation Methods 0.000 description 2
- 229910000838 Al alloy Inorganic materials 0.000 description 1
- VYZAMTAEIAYCRO-UHFFFAOYSA-N Chromium Chemical compound [Cr] VYZAMTAEIAYCRO-UHFFFAOYSA-N 0.000 description 1
- 208000017667 Chronic Disease Diseases 0.000 description 1
- 238000000137 annealing Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 229910052804 chromium Inorganic materials 0.000 description 1
- 239000011651 chromium Substances 0.000 description 1
- 239000010960 cold rolled steel Substances 0.000 description 1
- 238000005538 encapsulation Methods 0.000 description 1
- 238000005246 galvanizing Methods 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005554 pickling Methods 0.000 description 1
- 238000007747 plating Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 239000010935 stainless steel Substances 0.000 description 1
- 229910001220 stainless steel Inorganic materials 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B21—MECHANICAL METAL-WORKING WITHOUT ESSENTIALLY REMOVING MATERIAL; PUNCHING METAL
- B21B—ROLLING OF METAL
- B21B37/00—Control devices or methods specially adapted for metal-rolling mills or the work produced thereby
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Abstract
The application provides a deviation rectifying control method and system based on feedback optimization, which relate to the technical field of intelligent control, and the method comprises the following steps: the method comprises the steps of carrying out control parameter interaction of a unit through a data interaction unit to obtain a unit equipment data set, carrying out deviation detection on a first area of strip steel through a photoelectric detection unit, inputting basic data of the strip steel obtained based on interaction after a real-time deviation detection result is obtained, and constructing a deviation rectifying feedback model through the unit equipment data set, outputting deviation rectifying control data, carrying out thickness detection on the first area and the second area of the strip steel through the photoelectric detection unit, outputting a thickness detection result, inputting the thickness detection result into a fuzzy control unit, outputting predictive fuzzy control data, and then carrying out deviation rectifying control through combining with the deviation rectifying control data.
Description
Technical Field
The application relates to the technical field of intelligent control, in particular to a deviation rectifying control method and system based on feedback optimization.
Background
As an important industrial production raw material, the cold-rolled steel strip is rapidly developed in the fields of construction, home appliances, automobiles, light industry and the like, and the requirements on the material, performance, plate shape, surface quality and dimensional accuracy are becoming more and more strict. In the production of various units, an important precondition for continuous operation of the strip is that the strip is stably located on the central line of the unit. In particular to a pickling and rolling mill combination unit, a continuous annealing unit and a continuous hot galvanizing unit, and the maximum length of the whole-line strip steel can reach thousands of meters. Therefore, the effective control of the strip steel deviation is a primary premise for ensuring the efficient production of the unit. However, in actual production, the deflection of the strip steel is always a chronic disease.
In the prior art, the strip steel is easy to deviate, so that the technical problem of low quality of strip steel production products is solved.
Disclosure of Invention
The application provides a deviation rectifying control method and system based on feedback optimization, which are used for solving the technical problem that the quality of a strip steel production product is low because strip steel is easy to deviate in the prior art.
In view of the above problems, the application provides a deviation rectifying control method and system based on feedback optimization.
In a first aspect, the present application provides a correction control method based on feedback optimization, where the method includes: performing control parameter interaction of a unit through the data interaction unit to obtain a unit equipment data set, wherein the unit equipment data set comprises equipment control tension data, unit running speed data and roller surface roughness data; performing deviation detection on a first area of the strip steel through the photoelectric detection unit to obtain a real-time deviation detection result; the method comprises the steps of interactively obtaining basic data of the strip steel, wherein the basic data comprise strip steel hardness data, strip steel thickness range data and strip steel width data; constructing a deviation rectifying feedback model based on the basic data and the unit equipment data set, inputting the real-time deviation detection result into the deviation rectifying feedback model, and outputting deviation rectifying control data; performing thickness detection on a first region and a second region of the strip steel through the photoelectric detection unit, and outputting a thickness detection result, wherein the thickness detection result has region identifiers of the first region and the second region; inputting the thickness detection result into the fuzzy control unit, and outputting predictive fuzzy control data; performing transverse area division of the strip steel based on the strip steel width data to obtain N transverse area division results, wherein N is an odd number greater than 3; after the thickness detection result is input into the fuzzy control unit, center region deviation analysis is carried out on the N transverse region division results; if the deviation value of the central area relative to other areas can not meet a preset deviation threshold, eliminating thickness data of the central area; if the deviation value of the central area relative to other areas can meet the preset deviation threshold, obtaining a position mark of an area corresponding to a deviation extremum in the deviation value; calling symmetrical thickness data in the thickness detection result through the region position identification and the symmetrical region position identification; generating the foreseeable fuzzy control data through the thickness difference, the symmetrical distance and the deviation extremum of the symmetrical thickness data; and executing deviation rectifying control by combining the deviation rectifying control data and the predictive fuzzy control data.
In a second aspect, the present application provides a feedback optimization-based deviation rectification control system, the system comprising: the parameter interaction module is used for carrying out control parameter interaction of the unit through the data interaction unit to obtain a unit equipment data set, wherein the unit equipment data set comprises equipment control tension data, unit running speed data and roller surface roughness data; the deviation detection module is used for performing deviation detection on the first area of the strip steel through the photoelectric detection unit to obtain a real-time deviation detection result; the basic data acquisition module is used for interactively acquiring basic data of the strip steel, wherein the basic data comprise strip steel hardness data, strip steel thickness range data and strip steel width data; the first output module is used for constructing a deviation rectifying feedback model based on the basic data and the unit equipment data set, inputting the real-time deviation detection result into the deviation rectifying feedback model and outputting deviation rectifying control data; the second output module is used for performing thickness detection on a first area and a second area of the strip steel through the photoelectric detection unit and outputting a thickness detection result, wherein the thickness detection result has area identifications of the first area and the second area; the third output module is used for inputting the thickness detection result into the fuzzy control unit and outputting predictive fuzzy control data; the transverse area dividing module is used for dividing the transverse area of the strip steel based on the strip steel width data to obtain N transverse area dividing results, wherein N is an odd number larger than 3; the deviation analysis module is used for carrying out central area deviation analysis on the N transverse area division results after the thickness detection results are input into the fuzzy control unit; the clearing module is used for clearing thickness data of the central area if the deviation value of the central area relative to other areas cannot meet a preset deviation threshold; the system comprises a threshold value meeting module and a position identification module, wherein the threshold value meeting module is used for acquiring a position identification of a region corresponding to a deviation extremum in a deviation value if the deviation value of the central region relative to other regions can meet the preset deviation threshold value; the identification module is used for calling the symmetrical thickness data in the thickness detection result through the region position identification and the symmetrical region position identification; the data generation module is used for generating the foreseeable fuzzy control data through the thickness difference, the symmetrical distance and the deviation extremum of the symmetrical thickness data; and the execution module is used for combining the deviation rectifying control data and the predictive fuzzy control data to execute deviation rectifying control.
One or more technical schemes provided by the application have at least the following technical effects or advantages:
the application provides a deviation rectifying control method and system based on feedback optimization, relates to the technical field of intelligent control, solves the technical problem that the strip steel is easy to deviate in the prior art, and the quality of strip steel products is low, achieves the purpose of intelligent deviation rectifying control on the strip steel, and further achieves the effect of improving the quality of the strip steel products.
Drawings
FIG. 1 is a schematic flow chart of a deviation rectifying control method based on feedback optimization;
FIG. 2 is a schematic diagram of a flow chart of thickness data for removing a center region in a deviation rectifying control method based on feedback optimization;
FIG. 3 is a schematic diagram of a predictive fuzzy control data flow in a deviation correcting control method based on feedback optimization;
FIG. 4 is a schematic diagram of a deviation rectification control flow executed in a deviation rectification control method based on feedback optimization;
FIG. 5 is a schematic diagram of an optimization compensation flow for correcting deviation in a correction control method based on feedback optimization;
fig. 6 is a schematic structural diagram of a deviation rectifying control system based on feedback optimization.
Reference numerals illustrate: the system comprises a parameter interaction module 1, a deviation detection module 2, a basic data acquisition module 3, a first output module 4, a second output module 5, a third output module 6 and an execution module 7.
Detailed Description
The application provides a deviation correction control method and a deviation correction control system based on feedback optimization, which are used for solving the technical problem that in the prior art, the strip steel is easy to deviate, so that the quality of a strip steel production product is low.
Example 1
As shown in fig. 1, an embodiment of the present application provides a correction control method based on feedback optimization, where the method is applied to a correction control system, and the correction control system is communicatively connected to a photoelectric detection unit, a data interaction unit, and a fuzzy control unit, and the method includes:
step S100: performing control parameter interaction of a unit through the data interaction unit to obtain a unit equipment data set, wherein the unit equipment data set comprises equipment control tension data, unit running speed data and roller surface roughness data;
specifically, the deviation rectifying control method based on feedback optimization is applied to a deviation rectifying control system, the deviation rectifying control system is in communication connection with a photoelectric detection unit, a data interaction unit and a fuzzy control unit, and the photoelectric detection unit, the data interaction unit and the fuzzy control unit are used for collecting and controlling strip steel parameters.
In order to ensure the efficiency of correcting the strip steel in the later stage, the data interaction unit connected with the current correction control system is required to interact control parameters of the current unit, namely, the current unit is used for enabling the unit equipment to normally operate through the interaction of various control parameters in the process of controlling the strip steel, then the data of the current unit are acquired, the acquired data can comprise equipment control tension data of the unit equipment, unit operation speed data of the unit equipment and roller surface roughness data of the unit equipment, the equipment control tension data refer to the data of the pulling force of the equipment on the strip steel, the unit operation speed data refer to the adjustable rolling speed of a roller steering fixing, the roller surface roughness data refer to the surface roughness of a roller, the data belong to microscopic geometric shape errors, and further, the data are recorded as a unit equipment data set after the three are integrated, and the correction control is executed for the later stage as an important reference basis.
Step S200: performing deviation detection on a first area of the strip steel through the photoelectric detection unit to obtain a real-time deviation detection result;
specifically, the photoelectric detection unit connected with the current deviation correction control system is used for performing deviation detection on a first area of the current strip steel, the photoelectric detection unit is used for converting an optical signal into a weak electric signal through a photoelectric sensor in the deviation correction control system, the actions such as shading, deviation tracking and pinhole position identification are controlled through a signal processing by using an upper computer and a lower computer, the deviation detection is performed on the first area of the current strip steel, the first area of the strip steel is used for a longitudinal area of a roller running on the strip steel, so that the deviation detection is performed on the longitudinal area of the strip steel, and a real-time deviation detection result of the longitudinal area of the strip steel is correspondingly obtained, so that the deviation correction control is realized.
Step S300: the method comprises the steps of interactively obtaining basic data of the strip steel, wherein the basic data comprise strip steel hardness data, strip steel thickness range data and strip steel width data;
specifically, basic data of strip steel in the current unit equipment is acquired through interaction of various control parameters in the current unit equipment, the basic data of the strip steel in the current unit equipment can comprise strip steel hardness data, strip steel thickness range data and strip steel width data, the strip steel hardness data can be that the Rockwell hardness of the annealed plain carbon steel surface is generally 55+ -3, the hardness of the non-annealed rolled cold-rolled strip steel is more than 80, the strip steel thickness range data can be 0.1-3 mm, the strip steel width data can be 100-2000 mm, the strip steel hardness data, the strip steel thickness range data and the strip steel width data are integrated to serve as basic data of the strip steel, and a correction control tamping basis is executed for subsequent realization.
Step S400: constructing a deviation rectifying feedback model based on the basic data and the unit equipment data set, inputting the real-time deviation detection result into the deviation rectifying feedback model, and outputting deviation rectifying control data;
specifically, with the strip steel basic data obtained through interaction and a unit equipment data set obtained through the control parameter interaction of the unit through a data interaction unit as references, a correction feedback model is constructed, and the construction process of the correction feedback model is as follows: inputting each group of training data in the training data set into the deviation correcting feedback model, outputting and supervising and adjusting the deviation correcting feedback model through the supervising data corresponding to the group of training data, wherein each group of training data in the training data set comprises basic data and unit equipment data, the supervising data set is the supervising data corresponding to the training data set one by one, when the output result of the deviation correcting feedback model is consistent with the supervising data, the current group training is finished, all the training data in the training data set are finished, and the deviation correcting feedback model training is finished.
In order to ensure the accuracy of the correction feedback model, the correction feedback model may be tested by the test data set, for example, the test accuracy may be set to 90%, and when the test accuracy of the test data set meets 90%, the correction feedback model is constructed.
And inputting the obtained real-time deviation detection result into a deviation rectification feedback model, and outputting deviation rectification control data.
Step S500: performing thickness detection on a first region and a second region of the strip steel through the photoelectric detection unit, and outputting a thickness detection result, wherein the thickness detection result has region identifiers of the first region and the second region;
specifically, the thickness detection is performed on a first area and a second area divided in the current strip steel through a photoelectric detection unit connected with a deviation correction control system, the first area of the strip steel is a longitudinal area where a roller runs on the strip steel, the second area of the strip steel is an area where the roller is about to run on the strip steel, and the roller with the diameter of 25-90 mm can be selected as an example, and the roller material can be a roller with the standard of carbon steel galvanization, carbon steel chromium plating, carbon steel encapsulation, aluminum alloy, stainless steel and the like.
Step S600: inputting the thickness detection result into the fuzzy control unit, and outputting predictive fuzzy control data;
specifically, the thickness detection results output by the thickness detection of the first area and the second area of the strip steel by the photoelectric detection unit connected with the system are input into the fuzzy control unit connected with the system, the fuzzy control unit is used for carrying out preliminary deviation correction control on the strip steel, firstly, judging whether the deviation value of the central area relative to other areas can meet a preset deviation threshold value, wherein the obtained preset deviation threshold value is preset by related technicians according to the upper limit of the deviation of the central area to the other areas and the data quantity of the lower limit of the deviation of the central area to the other areas, if the deviation value of the central area relative to the other areas can meet the preset deviation threshold value, the upper limit value and the lower limit value contained in the deviation value are identified, on the basis, the symmetrical positions of the central area and the area are taken as the standard, the symmetrical thickness data contained in the thickness detection result of the strip steel in the fuzzy control unit are extracted, and further, the difference value of the thicknesses of the strip steel at two sides and the symmetrical distances of the two sides and the upper limit value and the lower limit value in the deviation value are summarized by the related technicians, and the integrated values are used as the difference values, and the fuzzy control data are carried out, and the fuzzy control is carried out, and the deep deviation correction is carried out.
Step S700: and executing deviation rectifying control by combining the deviation rectifying control data and the predictive fuzzy control data.
Specifically, the deviation correction control data output by the deviation correction feedback model is input to the real-time deviation detection result and the predictive fuzzy control data output by the fuzzy control unit is input to the thickness detection result are combined, namely, the deviation adjustment direction of the strip steel is extracted from the deviation correction control data, meanwhile, the deviation adjustment is carried out on the extracted deviation adjustment direction based on the thickness data required to be reserved for the strip steel, further, the deviation adjustment and the symmetrical distance between the two obtained edge areas are correspondingly input to the deviation correction adjustment control model as incremental data, a deviation correction adjustment control result is output, deviation correction control is carried out on the strip steel corresponding to the predictive fuzzy control data generated through the deviation correction adjustment control result, the purpose of intelligent deviation correction control on the strip steel is achieved, and the effect of improving the quality of strip steel production products is achieved.
Further, as shown in fig. 2, step S500 of the present application further includes:
step S510: performing transverse area division of the strip steel based on the strip steel width data to obtain N transverse area division results, wherein N is an odd number greater than 3;
step S520: after the thickness detection result is input into the fuzzy control unit, center region deviation analysis is carried out on the N transverse region division results;
step S530: and if the deviation value of the central area relative to other areas can not meet the preset deviation threshold value, clearing the thickness data of the central area.
Specifically, to output the thickness detection result of the strip steel more accurately, firstly, after the current strip steel is subjected to transverse area division on the basis of the width data of the current strip steel, N transverse area division results are correspondingly obtained, N is an odd number larger than 3, and the strip steel is divided into 5 equal parts of transverse areas, the width of each equal part is set to be a, the central axis of the transverse area divided into the width a is in a superposition state with the central axis of the strip steel according to the central axis, further, the current thickness detection result is input into a fuzzy control unit connected with the system, the central area deviation analysis is carried out on the N transverse area division results according to the difference value of the strip steel thicknesses at two sides in the symmetrical thickness data contained in the thickness detection result, the upper limit value and the lower limit value in the deviation value, namely, the transverse areas which are overlapped with the central axis in the N transverse areas divided above are taken as the central areas, in the process of strip steel movement, the central area is compared with the thickness data of other N-1 transverse division areas or not, thereby the preset thickness threshold value is set to be larger than the central area, the important thickness data is not required to be smaller than the central area, and the error correction effect is eliminated when the central area is smaller than the central area is required, and the central area is required to be more important, and the error is eliminated.
Further, as shown in fig. 3, step S600 of the present application further includes:
step S610: if the deviation value of the central area relative to other areas can meet the preset deviation threshold value;
step S620: obtaining a position identifier of a region corresponding to the deviation extremum in the deviation value;
step S630: calling symmetrical thickness data in the thickness detection result through the region position identification and the symmetrical region position identification;
step S640: and generating the foreseeable fuzzy control data through the thickness difference, the symmetrical distance and the deviation extremum of the symmetrical thickness data.
Specifically, after the thickness detection result is input to the fuzzy control unit connected with the system, central region deviation analysis is performed on the N transverse region division results, if the deviation value of the central region contained in the N transverse region division results relative to other regions can meet the preset deviation threshold, a larger deviation condition exists in the thickness of the current strip steel, fuzzy prediction needs to be performed on the deviation condition, further extraction is performed on the deviation value of the current central region relative to other regions, the upper limit, namely the maximum value, of the deviation values, and the lower limit, namely the minimum value, of the deviation values are performed, corresponding identification of the region positions is performed in the N transverse regions divided by the strip steel, and if the strip steel is divided into 5 equal parts of the transverse regions, the thickness data of the central region coincident with the central axis of the strip steel is used as a reference, the thickness in other equal parts is performed, the position of the transverse region corresponding to the maximum thickness value and the transverse region corresponding to the thickness value are extracted, the upper limit, namely the maximum value, the minimum value is used as the position of the central region corresponding to the maximum value, the position of the central region corresponding to the thickness value is extracted, the position of the central region corresponding to the maximum value is further symmetric region, the position of the central region corresponding position of the maximum value is obtained in the symmetric region is identified, and the symmetric position of the symmetric region is obtained in the symmetric position of the symmetric region is obtained, and the symmetric position of the symmetric region is obtained, the symmetric position between the symmetric position of the central region is obtained, and the symmetric position is obtained, and finally, inputting the thickness difference, the symmetrical distance, the deviation extremum and the deviation adjustment direction determined based on the deviation extremum into the constructed deviation correction adjustment control model, outputting a deviation correction adjustment control result, carrying out the predictive fuzzy control positioning of the strip steel operation on the deviation correction adjustment control result through the area identification, and then generating predictive fuzzy control data according to the positioning result, so as to ensure the accuracy of the deviation correction control in the later stage.
Further, step S640 of the present application includes:
step S641: determining a bias adjustment direction based on the bias extremum;
step S642: inputting the thickness difference, the symmetrical distance, the deviation extreme value and the deviation adjustment direction into a deviation correction adjustment control model, and outputting a deviation correction adjustment control result;
step S643: and carrying out predictive fuzzy control positioning on the deviation rectifying and adjusting control result through the area identifier, and generating the predictive fuzzy control data based on the positioning result.
Specifically, setting the mean value thickness information based on the extracted deviation extremum, the mean value thickness information is obtained by adding N thickness data corresponding to N transverse dividing regions and dividing the added value by N, further, screening thickness detection results with different thicknesses by taking the mean value thickness information as a reference, if thickness data of the current region position and thickness data of the symmetrical position thereof do not meet the mean value thickness information, regarding that the thickness value of the current region is overall low, so that the symmetrical part has low influence on deviation, removing the thickness data corresponding to the symmetrical position, performing thickness analysis of the symmetrical position on the thickness data retained after removal, then determining the deviation adjustment direction after performing direction verification on the deviation adjustment direction, further, inputting thickness difference, symmetrical distance, deviation extremum and determined deviation adjustment direction contained in the symmetrical thickness data into a constructed deviation adjustment control model, adjusting the deviation control model into a neural network for machine learning, performing self-iterative optimization continuously, performing deviation adjustment control, and training data set-monitoring the deviation control, and the deviation control model, and the set of the deviation control model being a set of the training data, and the set of the training data being further, the training data is obtained by the training data set, the training data set being the training data set, and the training data set being further set and the training data set being set, when the output result of the deviation rectifying and adjusting control model is consistent with the supervision data, the current group training is finished, all the training data in the training data set are trained, and the deviation rectifying and adjusting control model training is finished.
Outputting a deviation correcting adjustment control result, and carrying out predictive fuzzy control positioning on the outputted deviation correcting adjustment control result based on the identified area in the strip steel, namely carrying out preliminary positioning control on the area needing to correct the deviation in the current strip steel in advance, so as to generate predictive fuzzy control data on the basis of the positioning result, namely carrying out predictive control on the positioned area, thereby ensuring the high efficiency when the deviation correcting control is executed.
Further, step S641 of the present application includes:
step S6411: setting average thickness information, performing thickness screening of the thickness detection result through the average thickness information, and eliminating thickness data corresponding to the symmetrical positions when the thickness data of the symmetrical positions do not meet the average thickness information;
step S6412: performing thickness analysis of the symmetrical positions on the reserved thickness data, and performing direction verification on the deviation adjustment direction according to a thickness analysis result;
step S6413: and when the direction verification is passed, determining the deviation adjustment direction.
Specifically, the corresponding N thickness data in the N transverse dividing regions are summed, the sum is divided by N, and then the mean thickness information is obtained, so that the mean thickness information is taken as a reference, the thickness detection results are screened for different thicknesses, namely, all the thickness data in the thickness detection results are compared with the obtained mean thickness information, if the thickness data in the current region position and the thickness data in the symmetrical position do not meet the mean thickness information, the thickness value of the current region is regarded as being overall lower, so that the influence of the symmetrical part on deviation is lower, the thickness data corresponding to the symmetrical position is removed, the thickness analysis of the symmetrical position is performed on the thickness data which is reserved after the removal is completed, namely, the degree of the influence of the thickness of the current symmetrical position on deviation is verified, then the direction of deviation adjustment is performed, if the current deviation adjustment direction is the strip steel operation can be more accurately performed, the direction is regarded as being verified, further the deviation adjustment direction is determined, and the technical effect of providing reference for performing deviation correction control is achieved.
Further, as shown in fig. 4, step S700 of the present application further includes:
step S710: the thickness deviation of the reserved thickness data is evaluated according to the deviation adjustment direction, and a thickness deviation evaluation value is selected;
step S720: taking the thickness deviation evaluation value and the corresponding symmetrical distance data as incremental data, and inputting the optimized deviation rectifying adjustment control model;
step S730: and outputting an optimized deviation rectifying adjustment control result, generating the optimized predictive type fuzzy control data according to the optimized deviation rectifying adjustment control result, and executing deviation rectifying control according to the optimized predictive type fuzzy control data.
Specifically, thickness deviation evaluation is performed on the thickness data which is retained after the removal of the thickness data based on the determined deviation adjustment direction, namely whether the strip steel operation can be performed more accurately after the deviation adjustment is performed on the current thickness data, if the strip steel operation can be performed more accurately according to the adjusted thickness data, the current thickness deviation evaluation is qualified, if the strip steel operation cannot be performed more accurately according to the adjusted thickness data, the current thickness deviation evaluation is unqualified, so that the qualified thickness deviation evaluation is selected, further, the selected thickness deviation evaluation value and the symmetrical distance between the areas corresponding to the current area are taken as incremental data together, the incremental data is newly added in the current input data, so that the input data is input into an optimized deviation correction adjustment control model, the optimized deviation correction adjustment control model is added, so that the output deviation correction adjustment control result is more accurate, namely the deviation correction adjustment control result is optimized, and further, the predictive fuzzy control data is optimized through the optimized deviation correction control result, namely the symmetrical deviation correction control is performed between the thickness deviation evaluation value and the area corresponding to the current area, and the final deviation correction control is performed through the optimized deviation control.
Further, as shown in fig. 5, step S800 of the present application further includes:
step S810: executing feedback monitoring of the deviation correction control based on the feedback control unit, and extracting key features according to feedback monitoring results;
step S820: and carrying out correction optimization compensation through the feature aggregation result of the key features.
In particular, in order to more accurately control the deviation of the strip steel in the later running process, the deviation correction control of the strip steel needs to be fed back and monitored in a feedback unit connected with the system, the feedback control unit refers to a control unit for continuously feeding back the real-time deviation correction operation of the strip steel state in the running process of the strip steel, and key characteristics in the running process of the strip steel are extracted in the fed back monitoring result, wherein the key characteristics can be thickness characteristics of the strip steel, width characteristics of the strip steel, hardness characteristics of the strip steel, tension characteristics of unit equipment, running speed characteristics of the unit equipment, roughness characteristics of rollers and the like, the equipment control tension characteristics can be characteristics of the pulling force of the equipment on the strip steel, the machine set running speed characteristic can be the characteristic of adjustable rolling speed with fixed roller turning, the roller surface roughness characteristic can be the characteristic of the surface unevenness of a roller, the strip steel hardness characteristic can be that the Rockwell hardness of the annealed plain carbon steel surface is generally 55 < + > -3, the hardness of the non-annealed hard cold-rolled strip steel is more than 80 as the strip steel hardness characteristic, the strip steel thickness characteristic can be in the range of 0.1-3 mm, the strip steel width characteristic can be in the range of 100-2000 mm, and further, the characteristic point polymerization is carried out on the key characteristics, namely the strip steel characteristics with the same data in the characteristics are summarized, and the characteristic polymerization result is used as the standard, so that the correction optimization compensation is carried out on the running process of the current strip steel, and the technical effect of carrying out accurate correction control on the running process of the strip steel is achieved.
Example two
Based on the same inventive concept as the correction control method based on feedback optimization in the foregoing embodiment, as shown in fig. 6, the present application provides a correction control system based on feedback optimization, where the system includes:
the parameter interaction module 1 is used for carrying out control parameter interaction of the unit through the data interaction unit to obtain a unit equipment data set, wherein the unit equipment data set comprises equipment control tension data, unit running speed data and roller surface roughness data;
the deviation detection module 2 is used for performing deviation detection on a first area of the strip steel through the photoelectric detection unit to obtain a real-time deviation detection result;
the basic data acquisition module 3 is used for interactively acquiring basic data of the strip steel, wherein the basic data comprise strip steel hardness data, strip steel thickness range data and strip steel width data;
the first output module 4 is used for constructing a deviation rectifying feedback model based on the basic data and the unit equipment data set, inputting the real-time deviation detection result into the deviation rectifying feedback model, and outputting deviation rectifying control data;
a second output module 5, where the second output module 5 is configured to perform thickness detection on a first area and a second area of the strip steel by using the photoelectric detection unit, and output a thickness detection result, where the thickness detection result has area identifiers of the first area and the second area;
a third output module 6, where the third output module 6 is configured to input the thickness detection result into the fuzzy control unit and output predictive fuzzy control data;
and the execution module 7 is used for executing deviation rectifying control by combining the deviation rectifying control data and the predictive fuzzy control data.
Further, the system further comprises:
the transverse area dividing module is used for dividing the transverse area of the strip steel based on the strip steel width data to obtain N transverse area dividing results, wherein N is an odd number larger than 3;
the deviation analysis module is used for carrying out central area deviation analysis on the N transverse area division results after the thickness detection results are input into the fuzzy control unit;
and the clearing module is used for clearing the thickness data of the central area if the deviation value of the central area relative to other areas cannot meet the preset deviation threshold value.
Further, the system further comprises:
the system comprises a threshold value meeting module and a position identification module, wherein the threshold value meeting module is used for acquiring a position identification of a region corresponding to a deviation extremum in a deviation value if the deviation value of the central region relative to other regions can meet the preset deviation threshold value;
the identification module is used for calling the symmetrical thickness data in the thickness detection result through the region position identification and the symmetrical region position identification;
and the data generation module is used for generating the predictive fuzzy control data through the thickness difference, the symmetrical distance and the deviation extremum of the symmetrical thickness data.
Further, the system further comprises:
the direction determining module is used for determining a deviation adjusting direction based on the deviation extreme value;
the fourth output module is used for inputting the thickness difference, the symmetrical distance, the deviation extremum and the deviation adjustment direction into a deviation correction adjustment control model and outputting a deviation correction adjustment control result;
and the fuzzy control positioning module is used for carrying out predictive fuzzy control positioning on the deviation rectifying and adjusting control result through the area identifier and generating the predictive fuzzy control data based on the positioning result.
Further, the system further comprises:
the data eliminating module is used for setting average thickness information, executing thickness screening of the thickness detection result through the average thickness information, and eliminating the thickness data corresponding to the symmetrical position when the thickness data of the symmetrical position do not meet the average thickness information;
the direction verification module is used for performing thickness analysis of the symmetrical positions on the reserved thickness data and performing direction verification on the deviation adjustment direction according to the thickness analysis result;
and the adjustment direction determining module is used for determining the deviation adjustment direction after the direction verification is passed.
Further, the system further comprises:
the evaluation value selection module is used for evaluating the thickness deviation of the reserved thickness data according to the deviation adjustment direction and selecting a thickness deviation evaluation value;
the first input module is used for taking the thickness deviation evaluation value and the corresponding symmetrical distance data as incremental data and inputting the optimized deviation rectifying adjustment control model;
and the execution deviation rectifying control module is used for outputting an optimized deviation rectifying adjustment control result, generating the optimized predictive type fuzzy control data according to the optimized deviation rectifying adjustment control result, and executing deviation rectifying control according to the optimized predictive type fuzzy control data.
Further, the system further comprises:
the feature extraction module is used for executing feedback monitoring of the deviation correction control based on the feedback control unit and extracting key features according to feedback monitoring results;
and the optimization compensation module is used for carrying out correction optimization compensation through the feature aggregation result of the key features.
Through the foregoing detailed description of a deviation rectifying control method based on feedback optimization, those skilled in the art can clearly know that a deviation rectifying control system based on feedback optimization in this embodiment, and for the device disclosed in the embodiment, since the device corresponds to the method disclosed in the embodiment, the description is relatively simple, and relevant places refer to the method part for description.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (6)
1. The method is applied to a deviation rectifying control system, and the deviation rectifying control system is in communication connection with a photoelectric detection unit, a data interaction unit and a fuzzy control unit, and comprises the following steps:
performing control parameter interaction of a unit through the data interaction unit to obtain a unit equipment data set, wherein the unit equipment data set comprises equipment control tension data, unit running speed data and roller surface roughness data;
performing deviation detection on a first area of the strip steel through the photoelectric detection unit to obtain a real-time deviation detection result;
the method comprises the steps of interactively obtaining basic data of the strip steel, wherein the basic data comprise strip steel hardness data, strip steel thickness range data and strip steel width data;
constructing a deviation rectifying feedback model based on the basic data and the unit equipment data set, inputting the real-time deviation detection result into the deviation rectifying feedback model, and outputting deviation rectifying control data;
performing thickness detection on a first region and a second region of the strip steel through the photoelectric detection unit, and outputting a thickness detection result, wherein the thickness detection result has region identifiers of the first region and the second region;
inputting the thickness detection result into the fuzzy control unit, and outputting predictive fuzzy control data;
performing transverse area division of the strip steel based on the strip steel width data to obtain N transverse area division results, wherein N is an odd number greater than 3;
after the thickness detection result is input into the fuzzy control unit, center region deviation analysis is carried out on the N transverse region division results;
if the deviation value of the central area relative to other areas can not meet a preset deviation threshold, eliminating thickness data of the central area;
if the deviation value of the central area relative to other areas can meet the preset deviation threshold, obtaining a position mark of an area corresponding to a deviation extremum in the deviation value;
calling symmetrical thickness data in the thickness detection result through the region position identification and the symmetrical region position identification;
generating the foreseeable fuzzy control data through the thickness difference, the symmetrical distance and the deviation extremum of the symmetrical thickness data;
and executing deviation rectifying control by combining the deviation rectifying control data and the predictive fuzzy control data.
2. The method of claim 1, wherein the method further comprises:
determining a bias adjustment direction based on the bias extremum;
inputting the thickness difference, the symmetrical distance, the deviation extreme value and the deviation adjustment direction into a deviation correction adjustment control model, and outputting a deviation correction adjustment control result;
and carrying out predictive fuzzy control positioning on the deviation rectifying and adjusting control result through the area identifier, and generating the predictive fuzzy control data based on the positioning result.
3. The method of claim 2, wherein the method further comprises:
setting average thickness information, performing thickness screening of the thickness detection result through the average thickness information, and eliminating thickness data corresponding to the symmetrical positions when the thickness data of the symmetrical positions do not meet the average thickness information;
performing thickness analysis of the symmetrical positions on the reserved thickness data, and performing direction verification on the deviation adjustment direction according to a thickness analysis result;
and when the direction verification is passed, determining the deviation adjustment direction.
4. A method as claimed in claim 3, wherein the method further comprises:
the thickness deviation of the reserved thickness data is evaluated according to the deviation adjustment direction, and a thickness deviation evaluation value is selected;
and taking the thickness deviation evaluation value and the corresponding symmetrical distance data as incremental data, inputting the optimized deviation rectifying adjustment control model, outputting an optimized deviation rectifying adjustment control result, generating optimized predictive fuzzy control data through the optimized deviation rectifying adjustment control result, and executing deviation rectifying control through the optimized predictive fuzzy control data.
5. The method of claim 1, wherein the deskew control system is communicatively coupled to a feedback control unit, the method further comprising:
executing feedback monitoring of the deviation correction control based on the feedback control unit, and extracting key features according to feedback monitoring results;
and carrying out correction optimization compensation through the feature aggregation result of the key features.
6. The utility model provides a rectifying control system based on feedback optimization, its characterized in that, rectifying control system and photoelectric detection unit, data interaction unit, fuzzy control unit communication connection, the system includes:
the parameter interaction module is used for carrying out control parameter interaction of the unit through the data interaction unit to obtain a unit equipment data set, wherein the unit equipment data set comprises equipment control tension data, unit running speed data and roller surface roughness data;
the deviation detection module is used for performing deviation detection on the first area of the strip steel through the photoelectric detection unit to obtain a real-time deviation detection result;
the basic data acquisition module is used for interactively acquiring basic data of the strip steel, wherein the basic data comprise strip steel hardness data, strip steel thickness range data and strip steel width data;
the first output module is used for constructing a deviation rectifying feedback model based on the basic data and the unit equipment data set, inputting the real-time deviation detection result into the deviation rectifying feedback model and outputting deviation rectifying control data;
the second output module is used for performing thickness detection on a first area and a second area of the strip steel through the photoelectric detection unit and outputting a thickness detection result, wherein the thickness detection result has area identifications of the first area and the second area;
the third output module is used for inputting the thickness detection result into the fuzzy control unit and outputting predictive fuzzy control data;
the transverse area dividing module is used for dividing the transverse area of the strip steel based on the strip steel width data to obtain N transverse area dividing results, wherein N is an odd number larger than 3;
the deviation analysis module is used for carrying out central area deviation analysis on the N transverse area division results after the thickness detection results are input into the fuzzy control unit;
the clearing module is used for clearing thickness data of the central area if the deviation value of the central area relative to other areas cannot meet a preset deviation threshold;
the system comprises a threshold value meeting module and a position identification module, wherein the threshold value meeting module is used for acquiring a position identification of a region corresponding to a deviation extremum in a deviation value if the deviation value of the central region relative to other regions can meet the preset deviation threshold value;
the identification module is used for calling the symmetrical thickness data in the thickness detection result through the region position identification and the symmetrical region position identification;
the data generation module is used for generating the foreseeable fuzzy control data through the thickness difference, the symmetrical distance and the deviation extremum of the symmetrical thickness data;
and the execution module is used for combining the deviation rectifying control data and the predictive fuzzy control data to execute deviation rectifying control.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310889667.0A CN116603869B (en) | 2023-07-20 | 2023-07-20 | Deviation correction control method and system based on feedback optimization |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310889667.0A CN116603869B (en) | 2023-07-20 | 2023-07-20 | Deviation correction control method and system based on feedback optimization |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116603869A CN116603869A (en) | 2023-08-18 |
| CN116603869B true CN116603869B (en) | 2023-11-17 |
Family
ID=87676881
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310889667.0A Active CN116603869B (en) | 2023-07-20 | 2023-07-20 | Deviation correction control method and system based on feedback optimization |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116603869B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1775394A (en) * | 2005-11-29 | 2006-05-24 | 苏州有色金属加工研究院 | Thickness adaptive fuzzy control method for aluminium plate band rolling mill |
| KR20100077317A (en) * | 2008-12-29 | 2010-07-08 | 주식회사 포스코 | System and mehtod using fuzzy control for the plate thickness, and fuzzy thickness control apparatus |
| CN207628906U (en) * | 2017-11-09 | 2018-07-20 | 天津炬坤金属科技有限公司 | A kind of strip uncoiling automatic deviation correction control device |
| CN109647901A (en) * | 2018-12-28 | 2019-04-19 | 中冶南方工程技术有限公司 | A kind of cold-rolling mill feedforward method for controlling thickness and device based on fuzzy control |
| CN110834033A (en) * | 2018-08-17 | 2020-02-25 | 上海梅山钢铁股份有限公司 | Automatic deviation rectifying control method for hot continuous rolling finishing mill group strip steel |
| CN112029990A (en) * | 2020-07-16 | 2020-12-04 | 宝钢湛江钢铁有限公司 | Automatic deviation rectifying control method for cold-rolled strip steel continuous annealing heating furnace |
| CN112446130A (en) * | 2020-10-15 | 2021-03-05 | 宝钢日铁汽车板有限公司 | Strip steel deviation simulation system of continuous hot galvanizing unit annealing furnace and control method |
| CN114854978A (en) * | 2022-04-06 | 2022-08-05 | 武汉钢铁有限公司 | Method and device for predicting strip steel deviation value |
-
2023
- 2023-07-20 CN CN202310889667.0A patent/CN116603869B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1775394A (en) * | 2005-11-29 | 2006-05-24 | 苏州有色金属加工研究院 | Thickness adaptive fuzzy control method for aluminium plate band rolling mill |
| KR20100077317A (en) * | 2008-12-29 | 2010-07-08 | 주식회사 포스코 | System and mehtod using fuzzy control for the plate thickness, and fuzzy thickness control apparatus |
| CN207628906U (en) * | 2017-11-09 | 2018-07-20 | 天津炬坤金属科技有限公司 | A kind of strip uncoiling automatic deviation correction control device |
| CN110834033A (en) * | 2018-08-17 | 2020-02-25 | 上海梅山钢铁股份有限公司 | Automatic deviation rectifying control method for hot continuous rolling finishing mill group strip steel |
| CN109647901A (en) * | 2018-12-28 | 2019-04-19 | 中冶南方工程技术有限公司 | A kind of cold-rolling mill feedforward method for controlling thickness and device based on fuzzy control |
| CN112029990A (en) * | 2020-07-16 | 2020-12-04 | 宝钢湛江钢铁有限公司 | Automatic deviation rectifying control method for cold-rolled strip steel continuous annealing heating furnace |
| CN112446130A (en) * | 2020-10-15 | 2021-03-05 | 宝钢日铁汽车板有限公司 | Strip steel deviation simulation system of continuous hot galvanizing unit annealing furnace and control method |
| CN114854978A (en) * | 2022-04-06 | 2022-08-05 | 武汉钢铁有限公司 | Method and device for predicting strip steel deviation value |
Non-Patent Citations (1)
| Title |
|---|
| 热轧铝板带跑偏模糊控制研究;凌于蓝;锻压技术;第39卷(第3期);第137-140页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116603869A (en) | 2023-08-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN100357953C (en) | Automatic flattening process parameter optimization of metal plate band | |
| CN103406367B (en) | A kind of method improving direct tension control precision of cold calender | |
| CN112036081B (en) | Method for determining addition amount of silicon-manganese alloy in converter tapping based on yield prediction | |
| CN114091800A (en) | Intelligent design evaluation method for silicon steel product production scheme | |
| CN115035106B (en) | Strip steel defect intelligent detection method | |
| CN110197296B (en) | Unit load prediction method based on time series similarity | |
| CN113434994B (en) | Method for predicting cold rolling deformation resistance based on hot rolling process parameters of hot rolled original plate | |
| CN111676365A (en) | LSTM-based method for predicting annealing temperature set value of transition steel coil | |
| CN106825069A (en) | A kind of cold-strip steel high accuracy plate shape surface roughness on-line intelligence control method | |
| CN107900114B (en) | The method and device that a kind of pair of cold-rolled strip steel shape quality is evaluated | |
| CN116603869B (en) | Deviation correction control method and system based on feedback optimization | |
| CN115169453A (en) | Hot continuous rolling width prediction method based on density clustering and depth residual error network | |
| CN117610195A (en) | Strip steel expansion prediction method, device, medium and electronic equipment | |
| CN115106384B (en) | Thick plate rolling roll gap correction method based on random forest | |
| Peng et al. | A novel curve pattern recognition framework for hot-rolling slab camber | |
| CN116703254A (en) | Production information management system for mechanical parts of die | |
| CN105631231A (en) | Method for correcting temperature measured value for hot rolling process | |
| CN111250546A (en) | Edge thinning multipoint optimization control method based on interior point penalty function method | |
| He et al. | Whole process prediction model of silicon steel strip on transverse thickness difference based on Takagi-Sugeno fuzzy network | |
| CN114896735A (en) | Partial least square improved hot-rolled strip steel head wave defect reason identification method | |
| CN107971347A (en) | The thick online hot long method of survey of hot rolled plate in one kind | |
| CN112246878A (en) | Thickness judgment system and judgment method for pickling coil hot rolling process | |
| CN117399435B (en) | Self-adaptive compensation adjustment method and system for copper pipe rolling process | |
| TWI824834B (en) | Roll forming process inspection method | |
| CN114611376B (en) | Continuous annealing deviation prediction method and device based on neural network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |