CN116187180A - Medium plate camber state analysis and identification method, device, equipment and medium - Google Patents
Medium plate camber state analysis and identification method, device, equipment and medium Download PDFInfo
- Publication number
- CN116187180A CN116187180A CN202310092951.5A CN202310092951A CN116187180A CN 116187180 A CN116187180 A CN 116187180A CN 202310092951 A CN202310092951 A CN 202310092951A CN 116187180 A CN116187180 A CN 116187180A
- Authority
- CN
- China
- Prior art keywords
- data
- model
- steel plate
- real
- analyzing
- 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
- 238000000034 method Methods 0.000 title claims abstract description 93
- 238000004458 analytical method Methods 0.000 title claims abstract description 83
- 229910000831 Steel Inorganic materials 0.000 claims abstract description 93
- 239000010959 steel Substances 0.000 claims abstract description 93
- 230000008569 process Effects 0.000 claims abstract description 52
- 238000012545 processing Methods 0.000 claims abstract description 40
- 238000004519 manufacturing process Methods 0.000 claims abstract description 35
- 238000004886 process control Methods 0.000 claims abstract description 28
- 238000005452 bending Methods 0.000 claims abstract description 21
- 230000036541 health Effects 0.000 claims abstract description 17
- 238000005096 rolling process Methods 0.000 claims description 67
- 230000009467 reduction Effects 0.000 claims description 17
- 239000011159 matrix material Substances 0.000 claims description 14
- 238000005266 casting Methods 0.000 claims description 11
- 238000004891 communication Methods 0.000 claims description 10
- 238000005516 engineering process Methods 0.000 claims description 9
- 230000004927 fusion Effects 0.000 claims description 9
- 238000003860 storage Methods 0.000 claims description 9
- 230000000694 effects Effects 0.000 claims description 8
- 238000010606 normalization Methods 0.000 claims description 8
- 238000007418 data mining Methods 0.000 claims description 7
- 238000013135 deep learning Methods 0.000 claims description 7
- 230000010354 integration Effects 0.000 claims description 7
- 238000005457 optimization Methods 0.000 claims description 7
- 238000009877 rendering Methods 0.000 claims description 7
- 238000004088 simulation Methods 0.000 claims description 7
- 238000012850 discrimination method Methods 0.000 claims description 5
- 239000002436 steel type Substances 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 2
- 238000007781 pre-processing Methods 0.000 description 7
- 238000011156 evaluation Methods 0.000 description 6
- 238000000605 extraction Methods 0.000 description 5
- 230000008901 benefit Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 2
- 230000006399 behavior Effects 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005538 encapsulation Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000004806 packaging method and process Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 238000012800 visualization Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 238000007621 cluster analysis Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000000875 corresponding effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009440 infrastructure construction Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 238000009966 trimming Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/17—Mechanical parametric or variational design
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T15/00—3D [Three Dimensional] image rendering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- 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]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Geometry (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Computer Hardware Design (AREA)
- Computer Graphics (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Medical Informatics (AREA)
- Investigating Strength Of Materials By Application Of Mechanical Stress (AREA)
- Control Of Metal Rolling (AREA)
- General Factory Administration (AREA)
Abstract
The invention belongs to the technical field of intelligent manufacturing in metallurgical industry, and particularly relates to a medium plate camber state analysis and identification method, device, equipment and medium, wherein the method comprises the following steps: acquiring process data and IBA process control data; the acquired data are integrated into a database after being processed; processing analysis and iterative learning are carried out on the integrated data, and an optimal analysis model is obtained; constructing a three-dimensional model of the steel plate, and merging the three-dimensional model of the steel plate into an optimal analysis model, and dynamically driving the three-dimensional model of the steel plate through real-time production process data and process data to obtain a real-time dynamic model; and matching and pre-judging the sickle bending information displayed by the real-time dynamic model with pre-stored information, and outputting the current sickle bending cause and the health state. Solves the current situation that the same sickle bending problem repeatedly happens and is difficult to analyze, is more efficient in practical application, and can reduce labor intensity.
Description
Technical Field
The invention relates to the technical field of intelligent manufacturing in metallurgical industry, in particular to a method, a device, equipment and a medium for analyzing and identifying the camber state of a medium plate.
Background
The medium plate is an important steel variety, is widely applied to multiple industries such as infrastructure construction, shipbuilding, engineering machinery, containers, energy, buildings and the like, and plays an important role in national economy construction.
With the continuous development and increasing maturity of rolling technology and automatic control technology, the dimensional accuracy and the process control level of products reach a high degree. However, the automatic system is not only introduced but also autonomously integrated, and is affected by uneven thickness of the blank, uneven temperature, wedge-shaped blank, wedge-shaped roll gap, biting deviation, different rolling forces on two sides of a rolling mill frame and the like, so that the rolled steel plate presents an arc shape, namely a camber phenomenon is generated. In the production process, once the camber occurs, if no measures are taken for control, the smooth running of the rolling process is seriously influenced, the yield is influenced by the increase of the trimming quantity of a light person, the qualified product cannot be produced due to the waste rolling of a heavy person, and even the equipment is damaged to cause production stopping.
The production stability is severely restricted due to the fact that the camber of the steel plate is very complex in various aspects including equipment factors, automatic system factors, production organization, operation and the like, and meanwhile, the steel plate is one of the main factors affecting the yield of products. At present, field operators of medium and thick plate factories at home and abroad generally intervene in the process control of a rolling mill by adopting own experience so as to eliminate the camber, but the overall control effect is not ideal.
Disclosure of Invention
In order to overcome the defects in the prior art, the invention provides a method, a device, equipment and a medium for analyzing and identifying the camber state of a medium plate. And the camber state of the steel plate is displayed in real time by constructing a three-dimensional model of the steel plate and fusing an optimal analysis model of process control big data and process production data, so that the control level of the production process is improved.
In a first aspect, the present invention provides a method for analyzing and identifying a camber state of a medium plate, including the following steps:
acquiring process data and IBA process control data;
the acquired data are integrated into a database after being processed;
processing analysis and iterative learning are carried out on the integrated data, and an optimal analysis model is obtained;
constructing a three-dimensional model of the steel plate, and merging the three-dimensional model of the steel plate into an optimal analysis model, and dynamically driving the three-dimensional model of the steel plate through real-time production process data and process data to obtain a real-time dynamic model;
and matching and pre-judging the sickle bending information displayed by the real-time dynamic model with pre-stored information, and outputting the current sickle bending cause and the health state.
As a further limitation of the technical solution of the present invention, the step of integrating the acquired data into the database after processing includes:
and converting the acquired data OPCUA protocol into a unified communication standard, setting the consistency of the data time stamps, and integrating the data into a database.
As further limitation of the technical scheme of the invention, the process data comprise the length, width and thickness dimensions of a casting blank, the number of the casting blank, the number of plate steel types, the finished rolling pass, the target width and thickness of a steel plate, the target length of the steel plate, the furnace charging temperature, the start rolling temperature information and the BASID information;
the IBA process control data includes upper and lower main drive motor speeds, voltages, currents, torques, rolling reductions on the operating and drive sides of the mill body, actual rolling forces, roll gaps, EGC position, HGC position, maximum offset centerline amount, and BASID information.
As a further limitation of the technical scheme of the present invention, the step of converting the acquired data OPCUA protocol into a unified communication standard, setting the consistency of the data time stamp, and integrating the data time stamp into the database includes:
and setting BASID information as an identity discrimination method of IBA process control data and process data in the same time period to package data, so as to realize integration of multi-source heterogeneous data.
As a further limitation of the technical scheme of the present invention, the steps of performing processing analysis and iterative learning on the integrated data to obtain an optimal analysis model include:
performing reduction and normalization processing on the integrated data;
extracting features of the processed data, and establishing a feature matrix;
generating a sample set from data with different dimensions in a feature matrix, correlating the sample set through a data mining technology, and performing iterative optimization through a machine deep learning method to obtain a differential state analysis model of the same-specification steel plate under different working conditions;
and evaluating each analysis model to obtain an optimal analysis model.
As a further limitation of the technical scheme of the invention, the steps of constructing the three-dimensional model of the steel plate and merging the three-dimensional model into the optimal analysis model and dynamically driving the three-dimensional model of the steel plate through real-time production process data and process data to obtain the real-time dynamic model comprise the following steps:
determining the minimum key equipment quantity for constructing a model;
counting and drawing process flow charts of rolling passes of different steel grades, and carrying out three-dimensional modeling on key equipment by taking the upper roll surface of a working roll of a rolling mill as a reference surface;
and constructing a high simulation environment by using the Unity3D software, performing effect rendering on the constructed three-dimensional model, importing an optimal analysis model into the Unity3D software, and realizing dynamic driving on the three-dimensional model by using real-time production process data and process data according to equipment operation data and operation logic to obtain a real-time dynamic model.
As a further limitation of the technical solution of the present invention, the method further comprises:
analyzing the camber historical data;
and establishing association relations between different hook information and hook causes and association relations between different hook information and hook health states, and pre-storing the established relations.
In a second aspect, the technical scheme of the invention also provides a medium plate camber state analysis and identification device, which comprises a data acquisition module, a data fusion analysis module, an analysis model generation module, a three-dimensional module and a processing output module;
the data acquisition module is used for acquiring process data and IBA process control data;
the data fusion analysis module is used for processing the acquired data and integrating the processed data into a database;
the analysis model generation module is used for processing and analyzing the integrated data and performing iterative learning to obtain an optimal analysis model;
the three-dimensional module is used for constructing a steel plate three-dimensional model and integrating the steel plate three-dimensional model into an optimal analysis model, and dynamically driving the steel plate three-dimensional model through real-time production process data and process data to obtain a real-time dynamic model;
and the processing output module is used for carrying out matching pre-judgment on the sickle bending information displayed by the real-time dynamic model and pre-stored information and outputting the current sickle bending cause and the health state.
As a further limitation of the technical scheme of the invention, the data fusion analysis module is specifically configured to convert the acquired data OPCUA protocol into a unified communication standard, and set the BASID information as an identity discrimination method of IBA process control data and process data in the same time period to perform data encapsulation, so as to realize integration of multi-source heterogeneous data.
As further limitation of the technical scheme of the invention, the process data comprise the length, width and thickness dimensions of a casting blank, the number of the casting blank, the number of plate steel types, the finished rolling pass, the target width and thickness of a steel plate, the target length of the steel plate, the furnace charging temperature, the start rolling temperature information and the BASID information;
the IBA process control data includes upper and lower main drive motor speeds, voltages, currents, torques, rolling reductions on the operating and drive sides of the mill body, actual rolling forces, roll gaps, EGC position, HGC position, maximum offset centerline amount, and BASID information.
As a further limitation of the technical scheme of the invention, the analysis model generation module comprises a data preprocessing unit, a feature extraction unit, a model creation unit and an evaluation unit;
the data preprocessing unit is used for performing reduction and normalization processing on the integrated data;
the feature extraction unit is used for extracting features of the processed data and establishing a feature matrix;
the model creation unit is used for generating a sample set from data with different dimensions in the feature matrix, correlating the sample set through a data mining technology, and carrying out iterative optimization through a machine deep learning method to obtain a differential state analysis model of the same-specification steel plate under different working conditions;
and the evaluation unit is used for evaluating each analysis model to obtain an optimal analysis model.
As a further limitation of the technical scheme of the invention, the three-dimensional module comprises a device determining unit, a modeling unit and a model processing unit;
the device determining unit is used for determining the minimum key device quantity for constructing the model;
the modeling unit is used for statistically drawing process flow charts of rolling passes of different steel grades, and carrying out three-dimensional modeling on key equipment by taking the roll surface on the working roll of the rolling mill as a reference surface;
the model processing unit is used for constructing a high simulation environment by using the Unity3D software, guiding the optimal analysis model into the Unity3D software after the constructed three-dimensional model is subjected to effect rendering, and realizing dynamic driving of the three-dimensional model through real-time production process data and process data according to equipment operation data and operation logic to obtain a real-time dynamic model.
As a further limitation of the technical scheme of the invention, the device also comprises a preprocessing module for analyzing the camber history data; and establishing association relations between different hook information and hook causes and association relations between different hook information and hook health states, and pre-storing the established relations.
In a third aspect, the present invention further provides an electronic device, where the electronic device includes:
at least one processor; the method comprises the steps of,
a memory communicatively coupled to the at least one processor; wherein,,
the memory stores computer program instructions executable by the at least one processor to enable the at least one processor to perform the method of analyzing and identifying a medium plate camber condition as described in the first aspect.
In a fourth aspect, the present invention further provides a non-transitory computer readable storage medium, where the non-transitory computer readable storage medium stores computer instructions, and the computer instructions cause the computer to execute the method for analyzing and identifying the camber state of the medium plate according to the first aspect.
From the above technical scheme, the invention has the following advantages:
1. according to the invention, a plurality of production process parameters related to the quality of the camber are added, compared with the traditional one-sided detection adjustment, the method can detect and prevent the abnormal working condition behaviors affecting the quality of the product in an all-around manner, discover the factor causing the camber and give out the optimal suggestion. And the later-stage staff takes a solution in time according to the given optimal proposal, avoids the formation of obvious camber due to bending accumulation, and well improves the rolling quality of the steel plate.
2. The invention adopts multi-source data fusion, changes the search under the specific working condition of the previous sickle bend problem assumption, can deeply analyze the complex working condition of the actual production process, ensures that the sickle bend root cause analysis is more definite, reduces the intervention quantity of operators, solves the current situation that the same sickle bend problem repeatedly occurs and is difficult to analyze, is more efficient in practical application, and can reduce the labor intensity.
3. The invention establishes a technical process camber real-time monitoring dynamic model based on a complex production process of a rolling mill, and can form advantage complementation with the original production process control model, thereby improving the quality of products and increasing the benefit of enterprises.
In addition, the invention has reliable design principle, simple structure and very wide application prospect.
It can be seen that the present invention has outstanding substantial features and significant advances over the prior art, as well as its practical advantages.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required to be used in the description of the embodiments or the prior art will be briefly described below, and it will be obvious to those skilled in the art that other drawings can be obtained from these drawings without inventive effort.
FIG. 1 is a schematic flow chart of a method of one embodiment of the invention.
Fig. 2 is a schematic flow chart of a method of another embodiment of the invention.
Fig. 3 is a schematic view of an embodiment of classification of steel grades in the present invention.
FIG. 4 is a schematic diagram of a three-dimensional modeling embodiment of the present invention.
Fig. 5 is a schematic view of a steel plate camber embodiment.
Fig. 6 is a schematic block diagram of an apparatus of one embodiment of the present invention.
Detailed Description
In order to make the technical solution of the present invention better understood by those skilled in the art, the technical solution of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
As shown in fig. 1, an embodiment of the present invention provides a method for analyzing and identifying a camber state of a medium plate, including the following steps:
step 1: acquiring process data and IBA process control data;
step 2: the acquired data are integrated into a database after being processed;
step 3: processing analysis and iterative learning are carried out on the integrated data, and an optimal analysis model is obtained;
step 4: constructing a three-dimensional model of the steel plate, and merging the three-dimensional model of the steel plate into an optimal analysis model, and dynamically driving the three-dimensional model of the steel plate through real-time production process data and process data to obtain a real-time dynamic model;
step 5: and matching and pre-judging the sickle bending information displayed by the real-time dynamic model with pre-stored information, and outputting the current sickle bending cause and the health state.
In the embodiment of the invention, the process data comprises the length, width and thickness dimensions of a casting blank, the number of the casting blank, the number of steel types of plates, the finished rolling pass, the target width and thickness of a steel plate, the target length of the steel plate, the furnace feeding temperature, the information of the initial rolling temperature and the BASID information;
the IBA process control data includes upper and lower main drive motor speeds, voltages, currents, torques, rolling reductions on the operating and drive sides of the mill body, actual rolling forces, roll gaps, EGC position, HGC position, maximum offset centerline amount, and BASID information.
The data processing and integration are implemented by converting the OPCUA protocol of the acquired data into a unified communication standard, and setting the consistency of the data time stamps and integrating the data into a database. Because IBA process control data and process production data belong to different servers, the data time stamps have larger difference, and the consistency of the data time stamps is set by setting BASID information as an identity discrimination method of the IBA process control data and the process data in the same time period to package the data, so that the integration of multi-source heterogeneous data is realized.
Here, the acquisition frequency was set to 50ms each time the information was acquired. The BASID information is unique and associated with the current rolling sheet steel grade.
And a plurality of production process parameters related to the quality of the camber are added, compared with the traditional one-sided detection adjustment, the method can detect and prevent the abnormal working condition behaviors affecting the quality of the product in an all-around manner, discover the factor causing the camber and give out the optimal suggestion. And the later-stage staff takes a solution in time according to the given optimal proposal, avoids the formation of obvious camber due to bending accumulation, and well improves the rolling quality of the steel plate.
In some embodiments, the steps of processing and analyzing the integrated data and iteratively learning to obtain an optimal analysis model include:
step 31: performing reduction and normalization processing on the integrated data;
step 32: extracting features of the processed data, and establishing a feature matrix;
step 33: generating a sample set from data with different dimensions in a feature matrix, correlating the sample set through a data mining technology, and performing iterative optimization through a machine deep learning method to obtain a differential state analysis model of the same-specification steel plate under different working conditions;
step 34: and evaluating each analysis model to obtain an optimal analysis model.
In some embodiments, the step of constructing the three-dimensional model of the steel sheet and integrating the three-dimensional model of the steel sheet into the optimal analytical model, and dynamically driving the three-dimensional model of the steel sheet by the real-time production process data and the process data to obtain the real-time dynamic model comprises:
step 41: determining the minimum key equipment quantity for constructing a model;
step 42: counting and drawing process flow charts of rolling passes of different steel grades, and carrying out three-dimensional modeling on key equipment by taking the upper roll surface of a working roll of a rolling mill as a reference surface;
step 43: and constructing a high simulation environment by using the Unity3D software, performing effect rendering on the constructed three-dimensional model, importing an optimal analysis model into the Unity3D software, and realizing dynamic driving on the three-dimensional model by using real-time production process data and process data according to equipment operation data and operation logic to obtain a real-time dynamic model.
In addition, the embodiment of the invention further includes: analyzing the camber historical data; and establishing association relations between different hook information and hook causes and association relations between different hook information and hook health states, and pre-storing the established relations.
The current sickle-shaped type and the current sickle-shaped size are pre-judged in real time through the steel plate information, the steel plate sickle-shaped information is displayed in multiple directions and dimensions from rolling force, steel grade, rolling temperature, roll gap, rolling reduction and the like, one-key inquiry of the steel plate sickle-shaped cause and evaluation of health state are realized, and references are provided for rolling of the next pass or the next variety.
As shown in fig. 2, the present invention implements, for example, a camber visualization with 4300mm plate mill entity, in the following manner:
in S201, the type and kind of the rolling mill IBA process control data are determined, including the rotation speed, voltage, current and torque of the upper and lower main driving motors, the rolling reduction of the operating side and the driving side of the rolling mill body, the actual rolling force, the roll gap, the EGC position, the HGC position and other parameters, and the BASID information, and the collection frequency is 50ms each time.
The production process data type and kind are determined to comprise information such as length, width and thickness of a casting blank, blank number, steel grade number, finished rolling pass, target width, target thickness, target length, furnace charging temperature, starting rolling temperature and the like and BASID information, and the acquisition frequency is 50ms each time.
The BASID information is automatically generated along with a production system, has uniqueness and can be correlated with the current steel grade of the rolled plate in a simple mode.
IBA process control data exists in a dat format independent package form, and normally, self-dedicated software is required for reading. The IBA process control data is analyzed through an OPCUA protocol to realize real-time reading and storage of the data; and meanwhile, IBA data and process production data belong to different servers, the data time stamps have larger difference, the BASID information is set to be used as an identity screening method of the two types of data in the same time period for data packaging, a large amount of useless process data is screened and washed before data packaging, and then the data is transmitted to an application server for storage and processing, so that the integration of multi-source heterogeneous data is realized.
In S202, the integrated data are classified according to steel grades, wherein the classification method is as follows: and setting different width and thickness specification types for each steel variety, and then performing dimension reduction and normalization processing on the data through a linear or nonlinear algorithm. As shown in FIG. 3, each variety is firstly set with a large category a1, n steel with thickness being a1n category, n steel with width being a2n category, each large category of steel data is subjected to dimension reduction treatment and normalization treatment through a linear and nonlinear algorithm, and feature extraction is carried out, so that a data feature matrix library of different steel types and thicknesses of a1n, a2n and … … ann is obtained, meanwhile, multiple sample sets are generated by data with different dimensions in the feature matrix, relevance analysis is carried out on the sample sets through data mining technologies such as statistical analysis, cluster analysis and the like, iterative optimization is carried out through a machine deep learning method, and a differential state analysis model library of the same-specification steel plate under different working conditions is obtained, and an optimal analysis model is estimated.
In S203, determining the minimum equipment quantity of the constructed model, and constructing a schematic three-dimensional model by taking upper and lower working rolls of a rolling mill as references in FIG. 4, wherein other rolling mill components perform schematic three-dimensional modeling; and obtaining the accurate size of the working roll of the rolling mill, counting and drawing process flow charts of rolling passes of different steel grades, and carrying out part-level three-dimensional modeling on key equipment such as the working roll, the supporting roll and the rolling mill body by taking the roll surface on the working roll of the rolling mill as a reference surface.
And constructing a high simulation environment by using Unity3D software, after performing effect rendering on the constructed three-dimensional model of the rolling mill, establishing operation logic by using process data and process control data, and simultaneously importing an optimal analysis model into the Unity3D software to realize dynamic driving of the three-dimensional visualization model. The steel plate sickle bend information drawn after the current pass of the steel plate is completed is shown in fig. 5, thick lines in the drawing are actual contour lines of the steel plate, thin lines in the drawing are theoretical lines of the steel plate, a and b are respectively the maximum value and the minimum value of the steel plate sickle bend, and meanwhile, the corresponding length position information of the steel plate sickle bend is given through calculation.
In step S204, the current type and size of the sickle bend are pre-determined in real time by processing the current process data information and the process control data of the steel plate, and the sickle bend information of the steel plate is displayed in multiple directions and dimensions from the rolling force, the steel grade, the rolling temperature, the roll gap, the rolling reduction and the like, so that one-key inquiry of the sickle bend cause of the steel plate and evaluation of the health state are realized, and references are provided for rolling of the next pass or the next variety.
As shown in fig. 6, the embodiment of the invention further provides a device for analyzing and identifying the camber state of the medium plate, which comprises a data acquisition module, a data fusion analysis module, an analysis model generation module, a three-dimensional module and a processing output module;
the data acquisition module is used for acquiring process data and IBA process control data;
the data fusion analysis module is used for processing the acquired data and integrating the processed data into a database;
the analysis model generation module is used for processing and analyzing the integrated data and performing iterative learning to obtain an optimal analysis model;
the three-dimensional module is used for constructing a steel plate three-dimensional model and integrating the steel plate three-dimensional model into an optimal analysis model, and dynamically driving the steel plate three-dimensional model through real-time production process data and process data to obtain a real-time dynamic model;
and the processing output module is used for carrying out matching pre-judgment on the sickle bending information displayed by the real-time dynamic model and pre-stored information and outputting the current sickle bending cause and the health state.
The processing output module web terminal displays a steel plate camber real-time dynamic picture to a user based on a B/S mode, and specifically comprises the functions of process alarm information pushing, camber information displaying, report generation and the like. The module can comprehensively display the sickle bend information under the influence of multidimensional data such as rolling force, steel grade, rolling temperature, roll gap, rolling reduction and the like, and the report function can give out information such as guidance opinion, analysis result, sickle bend health degree and the like; the output module also comprises a client based on a C/S mode, and functions of rolling mode, historical inquiry, historical analysis, historical comparison, real-time comparison of each pass and the like are added on the basis of the B/S mode.
The data fusion analysis module is specifically configured to convert the acquired data OPCUA protocol into a unified communication standard, and set the BASID information as an identity discrimination method of IBA process control data and process data in the same time period to perform data encapsulation, so as to implement integration of multi-source heterogeneous data.
The process data comprises casting blank length, width and thickness dimensions, casting blank number, plate steel grade number, finished rolling pass, target steel plate width and thickness, target steel plate length, furnace charging temperature, start rolling temperature information and BASID information;
the IBA process control data includes upper and lower main drive motor speeds, voltages, currents, torques, rolling reductions on the operating and drive sides of the mill body, actual rolling forces, roll gaps, EGC position, HGC position, maximum offset centerline amount, and BASID information.
In some embodiments, the analysis model generation module includes a data preprocessing unit, a feature extraction unit, a model creation unit, and an evaluation unit;
the data preprocessing unit is used for performing reduction and normalization processing on the integrated data;
the feature extraction unit is used for extracting features of the processed data and establishing a feature matrix;
the model creation unit is used for generating a sample set from data with different dimensions in the feature matrix, correlating the sample set through a data mining technology, and carrying out iterative optimization through a machine deep learning method to obtain a differential state analysis model of the same-specification steel plate under different working conditions;
and the evaluation unit is used for evaluating each analysis model to obtain an optimal analysis model.
In some embodiments, the three-dimensional module includes a device determination unit, a modeling unit, and a model processing unit;
the device determining unit is used for determining the minimum key device quantity for constructing the model;
the modeling unit is used for statistically drawing process flow charts of rolling passes of different steel grades, and carrying out three-dimensional modeling on key equipment by taking the roll surface on the working roll of the rolling mill as a reference surface;
the model processing unit is used for constructing a high simulation environment by using the Unity3D software, guiding the optimal analysis model into the Unity3D software after the constructed three-dimensional model is subjected to effect rendering, and realizing dynamic driving of the three-dimensional model through real-time production process data and process data according to equipment operation data and operation logic to obtain a real-time dynamic model.
The device also comprises a preprocessing module, a processing module and a processing module, wherein the preprocessing module is used for analyzing the camber historical data; and establishing association relations between different hook information and hook causes and association relations between different hook information and hook health states, and pre-storing the established relations.
The embodiment of the invention also provides electronic equipment, which comprises: the device comprises a processor, a communication interface, a memory and a bus, wherein the processor, the communication interface and the memory are in communication with each other through the bus. The bus may be used for information transfer between the electronic device and the sensor. The processor may call logic instructions in memory to perform the following method: step 1: acquiring process data and IBA process control data; step 2: the acquired data are integrated into a database after being processed; step 3: processing analysis and iterative learning are carried out on the integrated data, and an optimal analysis model is obtained; step 4: constructing a three-dimensional model of the steel plate, and merging the three-dimensional model of the steel plate into an optimal analysis model, and dynamically driving the three-dimensional model of the steel plate through real-time production process data and process data to obtain a real-time dynamic model; step 5: and matching and pre-judging the sickle bending information displayed by the real-time dynamic model with pre-stored information, and outputting the current sickle bending cause and the health state.
Specifically, the processor may call logic instructions in memory to perform the following method: step 31: performing reduction and normalization processing on the integrated data; step 32: extracting features of the processed data, and establishing a feature matrix; step 33: generating a sample set from data with different dimensions in a feature matrix, correlating the sample set through a data mining technology, and performing iterative optimization through a machine deep learning method to obtain a differential state analysis model of the same-specification steel plate under different working conditions; step 34: and evaluating each analysis model to obtain an optimal analysis model.
The processor may call logic instructions in memory to perform the following method: step 41: determining the minimum key equipment quantity for constructing a model; step 42: counting and drawing process flow charts of rolling passes of different steel grades, and carrying out three-dimensional modeling on key equipment by taking the upper roll surface of a working roll of a rolling mill as a reference surface; step 43: and constructing a high simulation environment by using the Unity3D software, performing effect rendering on the constructed three-dimensional model, importing an optimal analysis model into the Unity3D software, and realizing dynamic driving on the three-dimensional model by using real-time production process data and process data according to equipment operation data and operation logic to obtain a real-time dynamic model.
Further, the logic instructions in the memory described above may be implemented in the form of software functional units and stored in a computer-readable storage medium when sold or used as a stand-alone product. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
Embodiments of the present invention provide a non-transitory computer readable storage medium storing computer instructions that cause a computer to perform the methods provided by the method embodiments described above, for example, including: step 1: acquiring process data and IBA process control data; step 2: the acquired data are integrated into a database after being processed; step 3: processing analysis and iterative learning are carried out on the integrated data, and an optimal analysis model is obtained; step 4: constructing a three-dimensional model of the steel plate, and merging the three-dimensional model of the steel plate into an optimal analysis model, and dynamically driving the three-dimensional model of the steel plate through real-time production process data and process data to obtain a real-time dynamic model; step 5: and matching and pre-judging the sickle bending information displayed by the real-time dynamic model with pre-stored information, and outputting the current sickle bending cause and the health state.
Although the present invention has been described in detail by way of preferred embodiments with reference to the accompanying drawings, the present invention is not limited thereto. Various equivalent modifications and substitutions may be made in the embodiments of the present invention by those skilled in the art without departing from the spirit and scope of the present invention, and it is intended that all such modifications and substitutions be within the scope of the present invention/be within the scope of the present invention as defined by the appended claims. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. The method for analyzing and identifying the camber state of the medium plate is characterized by comprising the following steps of:
acquiring process data and IBA process control data;
the acquired data are integrated into a database after being processed;
processing analysis and iterative learning are carried out on the integrated data, and an optimal analysis model is obtained;
constructing a three-dimensional model of the steel plate, and merging the three-dimensional model of the steel plate into an optimal analysis model, and dynamically driving the three-dimensional model of the steel plate through real-time production process data and process data to obtain a real-time dynamic model;
and matching and pre-judging the sickle bending information displayed by the real-time dynamic model with pre-stored information, and outputting the current sickle bending cause and the health state.
2. The method for analyzing and identifying the camber state of the medium plate according to claim 1, wherein the step of integrating the acquired data into the database after processing the acquired data comprises the steps of:
and converting the acquired data OPCUA protocol into a unified communication standard, setting the consistency of the data time stamps, and integrating the data into a database.
3. The method for analyzing and identifying the camber state of the medium plate according to claim 2, wherein the process data comprises the length, width and thickness dimensions of a casting blank, the number of the casting blank, the number of steel types of plates, the completed rolling pass, the target width and thickness of the steel plate, the target length of the steel plate, the furnace charging temperature, the start rolling temperature information and the BASID information;
the IBA process control data includes upper and lower main drive motor speeds, voltages, currents, torques, rolling reductions on the operating and drive sides of the mill body, actual rolling forces, roll gaps, EGC position, HGC position, maximum offset centerline amount, and BASID information.
4. The method for analyzing and identifying the camber state of the medium plate according to claim 3, wherein the step of converting the acquired data OPCUA protocol into a unified communication standard, setting the consistency of the data time stamps, and integrating the data time stamps into a database comprises the steps of:
and setting BASID information as an identity discrimination method of IBA process control data and process data in the same time period to package data, so as to realize integration of multi-source heterogeneous data.
5. The method for analyzing and identifying the camber state of a medium plate according to claim 4, wherein the step of performing processing analysis and iterative learning on the integrated data to obtain an optimal analysis model comprises:
performing reduction and normalization processing on the integrated data;
extracting features of the processed data, and establishing a feature matrix;
generating a sample set from data with different dimensions in a feature matrix, correlating the sample set through a data mining technology, and performing iterative optimization through a machine deep learning method to obtain a differential state analysis model of the same-specification steel plate under different working conditions;
and evaluating each analysis model to obtain an optimal analysis model.
6. The method for analyzing and identifying the camber state of a medium plate according to claim 5, wherein the step of constructing a three-dimensional model of the steel plate to be integrated into an optimal analysis model and dynamically driving the three-dimensional model of the steel plate by real-time production process data and process data to obtain a real-time dynamic model comprises the steps of:
determining the minimum key equipment quantity for constructing a model;
counting and drawing process flow charts of rolling passes of different steel grades, and carrying out three-dimensional modeling on key equipment by taking the upper roll surface of a working roll of a rolling mill as a reference surface;
and constructing a high simulation environment by using the Unity3D software, performing effect rendering on the constructed three-dimensional model, importing an optimal analysis model into the Unity3D software, and realizing dynamic driving on the three-dimensional model by using real-time production process data and process data according to equipment operation data and operation logic to obtain a real-time dynamic model.
7. The method for analyzing and identifying the camber state of a medium plate according to claim 6, further comprising:
analyzing the camber historical data;
and establishing association relations between different hook information and hook causes and association relations between different hook information and hook health states, and pre-storing the established relations.
8. The device is characterized by comprising a data acquisition module, a data fusion analysis module, an analysis model generation module, a three-dimensional module and a processing output module;
the data acquisition module is used for acquiring process data and IBA process control data;
the data fusion analysis module is used for processing the acquired data and integrating the processed data into a database;
the analysis model generation module is used for processing and analyzing the integrated data and performing iterative learning to obtain an optimal analysis model;
the three-dimensional module is used for constructing a steel plate three-dimensional model and integrating the steel plate three-dimensional model into an optimal analysis model, and dynamically driving the steel plate three-dimensional model through real-time production process data and process data to obtain a real-time dynamic model;
and the processing output module is used for carrying out matching pre-judgment on the sickle bending information displayed by the real-time dynamic model and pre-stored information and outputting the current sickle bending cause and the health state.
9. An electronic device, the electronic device comprising:
at least one processor; the method comprises the steps of,
a memory communicatively coupled to the at least one processor; wherein,,
the memory stores computer program instructions executable by at least one processor to enable the at least one processor to perform the method of analyzing and identifying a medium plate camber condition according to any one of claims 1 to 7.
10. A non-transitory computer-readable storage medium storing computer instructions that cause the computer to perform the method of analyzing and identifying a medium plate camber state according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310092951.5A CN116187180A (en) | 2023-02-03 | 2023-02-03 | Medium plate camber state analysis and identification method, device, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310092951.5A CN116187180A (en) | 2023-02-03 | 2023-02-03 | Medium plate camber state analysis and identification method, device, equipment and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116187180A true CN116187180A (en) | 2023-05-30 |
Family
ID=86439766
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310092951.5A Pending CN116187180A (en) | 2023-02-03 | 2023-02-03 | Medium plate camber state analysis and identification method, device, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116187180A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117807424A (en) * | 2024-02-29 | 2024-04-02 | 山东钢铁股份有限公司 | Industrial big data driven wide and thick steel plate quality dynamic on-line identification method and device |
| CN117831659A (en) * | 2024-03-04 | 2024-04-05 | 山东钢铁股份有限公司 | Method and device for online detection of quality of wide and thick plates, electronic equipment and storage medium |
-
2023
- 2023-02-03 CN CN202310092951.5A patent/CN116187180A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117807424A (en) * | 2024-02-29 | 2024-04-02 | 山东钢铁股份有限公司 | Industrial big data driven wide and thick steel plate quality dynamic on-line identification method and device |
| CN117807424B (en) * | 2024-02-29 | 2024-04-30 | 山东钢铁股份有限公司 | Industrial big data driven wide and thick steel plate quality dynamic on-line identification method and device |
| CN117831659A (en) * | 2024-03-04 | 2024-04-05 | 山东钢铁股份有限公司 | Method and device for online detection of quality of wide and thick plates, electronic equipment and storage medium |
| CN117831659B (en) * | 2024-03-04 | 2024-05-03 | 山东钢铁股份有限公司 | Method and device for online detection of quality of wide and thick plates, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116187180A (en) | Medium plate camber state analysis and identification method, device, equipment and medium | |
| CN108038553B (en) | Rolling mill equipment state on-line monitoring and diagnosing system and monitoring and diagnosing method | |
| CN109465676B (en) | Tool life prediction method | |
| CN103105820B (en) | Machining cutter abrasion state identification method of numerical control machine tool | |
| Liang et al. | Data-driven anomaly diagnosis for machining processes | |
| CN109263271B (en) | Printing equipment detection and analysis method based on big data | |
| CN112947290B (en) | Edge cloud cooperation-based equipment state monitoring method and system and storage medium | |
| CN111774931A (en) | On-line monitoring method for abrasion of numerical control turning batch machining tools | |
| CN102999451B (en) | Steel number system and method | |
| CN110032146B (en) | Complex machining process stability evaluation method based on multi-machine synergistic factors | |
| US20210394247A1 (en) | Method and system for forming a stamped component using a stamping simulation model | |
| CN115826516A (en) | Intelligent stainless steel chain production management method and system | |
| CN117076899A (en) | Method and system for monitoring and identifying operation faults of roughening machine | |
| CN106054832B (en) | Multivariable-based dynamic online monitoring method and device for intermittent chemical production process | |
| CN117483445A (en) | Automatic control system for rolling forming of ultrathin aluminum foil for capacitor | |
| CN109632081B (en) | Method for extracting vibration characteristics and distinguishing difference of wind generating set | |
| US20230213911A1 (en) | Method and device for testing product, computer device and readable storage medium | |
| CN115758233A (en) | Fault diagnosis method for main transmission gear box of high-speed precision strip steel cold rolling mill | |
| CN115935285A (en) | Multi-element time series anomaly detection method and system based on mask map neural network model | |
| CN105499282A (en) | Online strip shape analysis method and device for cold-rolled strip steel | |
| CN114662856A (en) | Large-scale rolling mill state tracking method and system | |
| CN112685473B (en) | Network abnormal flow detection method and system based on time sequence analysis technology | |
| Banerjee et al. | An IIoT machine model for achieving consistency in product quality in manufacturing plants | |
| CN115187026A (en) | Industrial risk monitoring method and system and readable storage medium | |
| CN112819320B (en) | AGC cylinder performance parameter monitoring method introducing self-adaptive optimization algorithm |
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 |