Bar tolerance control method and control system and electronic equipment

Abstract

The embodiment of the invention provides a bar tolerance control method and system and electronic equipment, and belongs to the field of automatic control. The control method comprises the following steps: training a neural network model by using a plurality of historical production data and a plurality of corresponding historical process data of a plurality of varieties of bars to obtain a process adjustment parameter prediction model; according to the bar tolerance and the bar variety which are measured in real time and by utilizing the process adjustment parameter prediction model, process adjustment parameters corresponding to the bar variety are obtained; and converting the process adjustment parameters into corresponding instructions, and sending the instructions to a rolling mill roll gap position closed-loop control system so as to realize adjustment of the rolling mill. According to the embodiment of the invention, manual control on the rolling mill is reduced, the accuracy of bar tolerance control can be improved, and meanwhile, the yield is improved.

Description

Technical Field

[0001] The present invention relates to the field of automatic control technology, and in particular to a method for controlling bar tolerance, a control system for bar tolerance, electronic equipment, a computer-readable storage medium and a computer program product. Background Art

[0002] In the field of steel rolling, bar tolerance is an important indicator in the manufacturing and processing of bars, and its size directly affects the quality and use effect of bars. In the production process, tolerances need to be strictly controlled, and the accuracy and stability of bars are guaranteed by measures such as improving production process levels, updating production equipment, and optimizing raw material quality. However, the existing bar tolerance control usually adopts manual open-loop control, that is, workers manually adjust the mill roll gap for bars that do not meet the tolerance value so that the bars reach the preset target tolerance to achieve the purpose of tolerance control. However, manual control requires rich operating experience and is overly dependent on manual labor, making it impossible to achieve precise adjustment. At the same time, it makes it difficult to improve the accuracy of tolerance control, reducing the yield. Summary of the invention

[0003] The purpose of the embodiments of the present invention is to provide a method for controlling bar tolerance, a control system for bar tolerance, an electronic device, a computer-readable storage medium and a computer program product, which can partially or completely solve the problems of excessive reliance on manual labor, inability to accurately adjust tolerances and low yields.

[0004] In order to achieve the above object, an embodiment of the present invention provides a method for controlling the tolerance of a bar material, the control method comprising:

[0005] A neural network model is trained using multiple historical production data of multiple varieties of bars and corresponding multiple historical process data to obtain a process adjustment parameter prediction model; process adjustment parameters corresponding to the bar variety are obtained based on real-time measured bar tolerances and bar varieties and using the process adjustment parameter prediction model; and the process adjustment parameters are converted into corresponding instructions and sent to a rolling mill roll gap position closed-loop control system to achieve adjustment of the rolling mill.

[0006] Optionally, before executing the step of training the neural network model using multiple historical production data of multiple varieties of rods and corresponding multiple historical process data, the control method also includes: preprocessing the multiple historical production data of the multiple varieties of rods and corresponding multiple historical process data, and the preprocessing includes removing outliers and noise, data cleaning and data normalization.

[0007] Optionally, the control method further comprises: simultaneously using the real-time measured bar tolerance, bar type and the obtained process adjustment parameters corresponding to the bar type to train the neural network model.

[0008] Optionally, the multiple historical production data include multiple bar varieties, multiple historical measured bar tolerances, and multiple preset bar tolerances, and the multiple historical process data include multiple rolling mill roll gap values, multiple rolling mill roll gap adjustment amounts, multiple rolled product temperatures, and multiple rolling mill loads. The neural network model is trained using the multiple historical production data of the multiple varieties of bars and the corresponding multiple historical process data to obtain the process adjustment parameter prediction model, including: training the neural network model using the multiple bar varieties, multiple historical measured bar tolerances, multiple preset bar tolerances, and multiple rolling mill roll gap values ​​corresponding to the bar varieties, multiple rolling mill roll gap adjustment amounts, multiple rolled product temperatures, and multiple rolling mill loads to obtain the process adjustment parameter prediction model.

[0009] Optionally, after obtaining the process adjustment parameters corresponding to the bar variety using the process adjustment parameter prediction model, it also includes: comparing the process adjustment parameters with the historical optimal process adjustment parameters; when the process adjustment parameters match the historical optimal process adjustment parameters, determining the process adjustment parameters as target process adjustment parameters; converting the target process adjustment parameters into corresponding instructions, and sending them to the rolling mill roll gap position closed-loop control system to achieve adjustment of the rolling mill.

[0010] On the other hand, the present invention also provides a control system for bar tolerances, the control system comprising: a training module, used to train a neural network model using multiple historical production data of multiple varieties of bars and corresponding multiple historical process data to obtain a process adjustment parameter prediction model; an acquisition module, used to obtain process adjustment parameters corresponding to the bar variety based on the real-time measured bar tolerances and bar varieties and using the process adjustment parameter prediction model; and a control module, used to convert the process adjustment parameters into corresponding instructions and send them to the rolling mill roll gap position closed-loop control system to achieve adjustment of the rolling mill.

[0011] Optionally, the control system also includes: a preprocessing module, which is used to preprocess the multiple historical production data of the multiple varieties of rods and the corresponding multiple historical process data before the training module executes the training of the neural network model using the multiple historical production data of the multiple varieties of rods and the corresponding multiple historical process data, and the preprocessing includes removing outliers and noise, data cleaning and data normalization.

[0012] Optionally, the control system further comprises: an optimization module for simultaneously using the real-time measured bar tolerance, bar type and the obtained process adjustment parameters corresponding to the bar type to train the neural network model.

[0013] Optionally, the multiple historical production data include multiple bar varieties, multiple historical measured bar tolerances, and multiple preset bar tolerances, and the multiple historical process data include multiple rolling mill roll gap values, multiple rolling mill roll gap adjustment amounts, multiple rolled product temperatures, and multiple rolling mill loads. The training module is used to train the neural network model using the multiple historical production data of multiple varieties of bars and the corresponding multiple historical process data to obtain the process adjustment parameter prediction model, which includes: training the neural network model using the multiple bar varieties, multiple historical measured bar tolerances, multiple preset bar tolerances, and multiple rolling mill roll gap values ​​corresponding to the bar varieties, multiple rolling mill roll gap adjustment amounts, multiple rolled product temperatures, and multiple rolling mill loads to obtain the process adjustment parameter prediction model.

[0014] Optionally, the control system also includes: a comparison module, which is used to compare the process adjustment parameters with the historical optimal process adjustment parameters after the acquisition module obtains the process adjustment parameters corresponding to the bar variety using the process adjustment parameter prediction model; a determination module, which is used to determine that the process adjustment parameters are target process adjustment parameters when the process adjustment parameters match the historical optimal process adjustment parameters; and an adjustment module, which is used to convert the target process adjustment parameters into corresponding instructions and send them to the rolling mill roll gap position closed-loop control system to achieve adjustment of the rolling mill.

[0015] On the other hand, the present invention also provides an electronic device, a processor, and a memory communicatively connected to the processor; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory to implement the bar tolerance control method as described.

[0016] On the other hand, the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, they are used to implement the control method of the bar tolerance as described above.

[0017] In yet another aspect, the present invention further provides a computer program product, comprising a computer program, which implements the method for controlling the tolerance of a bar material when the computer program is executed by a processor.

[0018] Through the above technical scheme, a neural network model is trained using multiple historical production data of multiple varieties of bars and corresponding multiple historical process data to obtain a process adjustment parameter prediction model; based on the real-time measured bar tolerance and bar variety and using the process adjustment parameter prediction model, the process adjustment parameters corresponding to the bar variety are obtained; and the process adjustment parameters are converted into corresponding instructions and sent to the rolling mill roll gap position closed-loop control system to achieve adjustment of the rolling mill.

[0019] The embodiment of the present invention uses historical production data and corresponding multiple historical process data to train the neural network model to obtain a process adjustment parameter prediction model; the trained model is used to predict the process adjustment parameters of the bar tolerance measured in real time, and the parameters are sent to the rolling mill roll gap position closed-loop control system, and the rolling mill is adjusted to process the bar, and finally the bar that meets the tolerance requirements is obtained. The embodiment of the present invention reduces manual control of the rolling mill, can improve the accuracy of bar tolerance control, and at the same time improves the yield rate.

[0020] Other features and advantages of the embodiments of the present invention will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the following specific implementations, they are used to explain the embodiments of the present invention, but do not constitute a limitation on the embodiments of the present invention. In the accompanying drawings:

[0022] Figure 1 is a flow chart of a method for controlling bar tolerance provided by an embodiment of the present invention;

[0023] Figure 2 It is a schematic diagram of the control principle of the bar tolerance of the existing technical solution;

[0024] Figure 3 It is a schematic diagram of the overall control principle of the bar tolerance provided by an embodiment of the present invention;

[0025] Figure 4 It is a structural diagram of a control system for bar tolerance provided by a second embodiment of the present invention. DETAILED DESCRIPTION

[0026] The specific implementation of the embodiment of the present invention is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described here is only used to illustrate and explain the embodiment of the present invention, and is not used to limit the embodiment of the present invention.

[0027] like Figure 1The flowchart of the method for controlling the tolerance of a bar provided by an embodiment of the present invention is as follows: A method for controlling the tolerance of a bar, the method comprising the following steps S10-S12.

[0028] S10. Train the neural network model using multiple historical production data of multiple varieties of bars and corresponding multiple historical process data to obtain a process adjustment parameter prediction model.

[0029] Furthermore, before executing the step of training the neural network model using multiple historical production data of multiple varieties of bars and corresponding multiple historical process data, the control method also includes: preprocessing the multiple historical production data of the multiple varieties of bars and corresponding multiple historical process data, and the preprocessing includes removing outliers and noise, data cleaning and data normalization.

[0030] In some embodiments, the rod tolerance involves multiple types, such as dimensional tolerance, straightness tolerance, roundness tolerance, angle tolerance, and cross-sectional area tolerance. It should be noted that the present invention is particularly suitable for controlling the cross-sectional area tolerance of the rod.

[0031] like Figure 2 This is a schematic diagram of the control principle of bar tolerances in the existing technical solutions. One current solution is to obtain the current bar tolerance value by sampling weighing, finished product weighing, online tolerance measurement system, etc. The operator compares the actual measured bar tolerance with the preset bar tolerance (i.e., target bar tolerance). The operator manually adjusts the relevant parameters of the rolling mill according to the difference between the two to obtain bars that meet the preset tolerances. This process requires the operator to have rich operating experience, and manual control results in the acquisition of bars that cannot guarantee the accuracy of the bar tolerances. The current tolerance control technical solution adopts an open-loop control solution with a low degree of automation and is overly dependent on the work experience and adjustment technology of the adjuster. At the same time, the control accuracy is difficult to further improve, and the adjustment results are not stable enough.

[0032] The embodiment of the present invention utilizes multiple historical production data and corresponding multiple historical process data to train a neural network model to obtain a process adjustment parameter prediction model. In order to ensure the accuracy of the neural network model training, the multiple historical production data of the multiple varieties of bars and the corresponding multiple historical process data are preprocessed, and the preprocessing includes removing outliers and noise, data cleaning and data normalization. For production data and process data, outliers may affect the accuracy of data analysis and the performance of the model. Outliers may affect the accuracy of data analysis and the performance of the model. Data cleaning is an important step in data preprocessing, which aims to solve problems such as incompleteness, inconsistency and errors in the data. The preprocessing here is an important step to improve data quality and ensure data analysis accuracy and model performance.

[0033] The embodiment of the present invention trains a neural network model with multiple historical production data of multiple varieties of bars and corresponding multiple historical process data. The training process is specifically implemented through existing technical means, and the embodiment of the present invention does not make specific restrictions. After training the neural network model, a process adjustment parameter prediction model is obtained.

[0034] Furthermore, the multiple historical production data include multiple bar varieties, multiple historical measured bar tolerances, and multiple preset bar tolerances; the multiple historical process data include multiple rolling mill roll gap values, multiple rolling mill roll gap adjustment amounts, multiple rolled piece temperatures, and multiple rolling mill loads; the use of the multiple historical production data of the multiple varieties of bars and the corresponding multiple historical process data to train the neural network model to obtain the process adjustment parameter prediction model includes: using the multiple bar varieties, multiple historical measured bar tolerances, multiple preset bar tolerances, and multiple rolling mill roll gap values ​​corresponding to the bar varieties, multiple rolling mill roll gap adjustment amounts, multiple rolled piece temperatures, and multiple rolling mill loads to train the neural network model to obtain the process adjustment parameter prediction model.

[0035] In some embodiments, multiple historical production data include but are not limited to multiple bar varieties, multiple historical measured bar tolerances, and multiple preset bar tolerances. Among them, multiple bar varieties refer to the types of bars, and the types of bars specifically include steel bars, aluminum bars, copper bars, etc. Among them, the corresponding tolerance standards for different varieties of bars are different. Multiple historical measured bar tolerances refer to the bar tolerances actually measured for different varieties of bars, and multiple preset bar tolerances refer to the target tolerances corresponding to different varieties of bars. The multiple historical process data include multiple rolling mill roll gap values, multiple rolling mill roll gap adjustment amounts, multiple rolled piece temperatures, and multiple rolling mill loads. The historical process data is obtained based on the corresponding historical bar varieties, historical measured bar tolerances, and preset bar tolerances. Historical production data and historical process data can be historical data obtained through past manual processing.

[0036] The neural network model is trained using the multiple bar varieties, multiple historically measured bar tolerances, multiple preset bar tolerances, and multiple mill roll gap values ​​corresponding to the bar varieties, multiple mill roll gap adjustment amounts, multiple rolled product temperatures, and multiple mill loads to obtain a process adjustment parameter prediction model. The model training process can actually be regarded as a process of fitting the relationship between the bar variety, the measured bar tolerance, the preset bar and the process data, and the process adjustment parameter prediction model is obtained by training.

[0037] S11. According to the real-time measured bar tolerance and bar type and the process adjustment parameter prediction model, the process adjustment parameters corresponding to the bar type are obtained.

[0038] In some embodiments, there are multiple ways to measure the tolerance of the bar in real time, such as the existing cooling bed sampling and weighing calculation: the actual meter weight of the current sample is calculated through cooling bed sampling, and the actual tolerance is calculated together with the theoretical meter weight. Finished product weighing calculation: the actual meter weight of the current bar is obtained by weighing the finished product, and the actual tolerance is calculated together with the theoretical meter weight. Diameter gauge measurement: the actual diameter of the bar is directly obtained through the diameter gauge, and the bar tolerance is automatically calculated. However, this method is only applicable to round bars. Bar tolerance online measurement system: the bar tolerance is automatically calculated in real time based on the length measurement results of the multiple-length flying shear.

[0039] The last of the above four measurement methods can ensure the real-time and accuracy of tolerance measurement and can be applied to all bars. Therefore, the present invention adopts an online bar tolerance measurement system to perform online real-time measurement of bar tolerance. The embodiment of the present invention does not impose any specific restrictions on the specific measurement method.

[0040] When the bar type and the bar tolerance measured in real time are obtained, they are input into the process adjustment parameter prediction model, and the preset bar tolerance (i.e., target tolerance) corresponding to the bar type can be obtained. Further, when the bar type, the bar tolerance measured in real time, and the preset tolerance are known, the corresponding process adjustment parameters can be obtained, i.e., the mill roll gap, mill load, and workpiece temperature that need to be adjusted. The bar tolerance is adjusted to the standard bar tolerance according to these process parameters.

[0041] Furthermore, the control method also includes: simultaneously using the real-time measured bar tolerance, bar type and the obtained process adjustment parameters corresponding to the bar type to train the neural network model.

[0042] In some embodiments, in order to make the trained neural network model more accurate, the embodiments of the present invention will also use the online real-time measurement of the bar tolerance, bar type and the obtained process adjustment parameters corresponding to the bar type to train the neural network model in real time.

[0043] S12, converting the process adjustment parameters into corresponding instructions and sending them to the rolling mill roll gap position closed-loop control system to achieve adjustment of the rolling mill.

[0044] In some embodiments, the process adjustment parameters obtained in the above steps are converted into corresponding instructions. The conversion method can be implemented by existing technical means, and the embodiments of the present invention do not impose specific restrictions. The converted instructions are sent to the rolling mill roll gap position closed-loop control system to achieve adjustment of the rolling mill. Among them, the rolling mill roll gap position closed-loop control system is an existing control system, and this control system is a vital part of steel rolling production. The roll gap position closed-loop system includes an encoder (for detecting the actual position of the roll gap), a proportional valve or servo valve (for adjusting the roll gap position), and a PI regulator. The control system generates a given proportional valve through the PI regulator according to the error between the actual roll gap position and the set position, and controls the roll to be pressed down or lifted through the proportional valve, thereby achieving closed-loop control of the roll gap position. The specific control method is implemented by the existing PI control method, which will not be repeated here. The adjusted rolling mill adjusts the bar measured in real time again to make its tolerance reach the standard value after processing. As Figure 3 It is a schematic diagram of the overall control principle of the bar tolerance provided by an embodiment of the present invention.

[0045] Furthermore, after obtaining the process adjustment parameters corresponding to the bar variety using the process adjustment parameter prediction model, the control method also includes: comparing the process adjustment parameters with the historical optimal process adjustment parameters; when the process adjustment parameters match the historical optimal process adjustment parameters, determining the process adjustment parameters as target process adjustment parameters; converting the target process adjustment parameters into corresponding instructions, and sending them to the rolling mill roll gap position closed-loop control system to achieve adjustment of the rolling mill.

[0046] In some embodiments, in order to make the process adjustment parameters more accurate and obtain bars that are more in line with standard tolerances, an embodiment of the present invention also provides a method, which, after obtaining the corresponding process adjustment parameters, also includes comparing the obtained process adjustment parameters with the stored historical optimal process parameters. When the obtained process parameters match (i.e., are consistent with) the historical optimal process parameters, the obtained process parameters are determined as the final target process adjustment parameters, and the target process adjustment parameters are converted into corresponding instructions and sent to the mill roll gap position closed-loop control system to achieve adjustment of the mill. The adjustment method is the same as the above embodiment and will not be repeated here.

[0047] When the obtained process parameters do not match the historical optimal process parameters, the historical optimal process parameters can be used as target process adjustment parameters. Similarly, the target parameters are converted into corresponding instructions and sent to the rolling mill roll gap position closed-loop control system to achieve adjustment of the rolling mill.

[0048] Through the above technical scheme, a neural network model is trained using multiple historical production data of multiple varieties of bars and corresponding multiple historical process data to obtain a process adjustment parameter prediction model; based on the real-time measured bar tolerance and bar variety and using the process adjustment parameter prediction model, the process adjustment parameters corresponding to the bar variety are obtained; and the process adjustment parameters are converted into corresponding instructions and sent to the rolling mill roll gap position closed-loop control system to achieve adjustment of the rolling mill.

[0049] The embodiment of the present invention uses historical production data and corresponding multiple historical process data to train the neural network model to obtain a process adjustment parameter prediction model; the trained model is used to predict the process adjustment parameters of the bar tolerance measured in real time, and the parameters are sent to the rolling mill roll gap position closed-loop control system, and the rolling mill is adjusted to process the bar, and finally the bar that meets the tolerance requirements is obtained. The embodiment of the present invention reduces manual control of the rolling mill, can improve the accuracy of bar tolerance control, and at the same time improves the yield rate.

[0050] like Figure 4 4 is a structural diagram of a control system for bar tolerance provided by the second embodiment of the present invention. The second embodiment of the present invention also includes a control system for bar tolerance, and the control system 40 includes: a training module 401, which is used to train a neural network model using multiple historical production data of multiple varieties of bars and corresponding multiple historical process data to obtain a process adjustment parameter prediction model; an acquisition module 402, which is used to obtain process adjustment parameters corresponding to the bar variety based on the real-time measured bar tolerance and bar variety and the process adjustment parameter prediction model; and a control module 403, which is used to convert the process adjustment parameters into corresponding instructions and send them to the rolling mill roll gap position closed-loop control system to achieve adjustment of the rolling mill.

[0051] The implementation principle and technical effects of the bar tolerance control system provided in the second embodiment of the present invention are the same as those of the first embodiment, and will not be described in detail herein.

[0052] Furthermore, the control system also includes: a preprocessing module, which is used to preprocess the multiple historical production data of the multiple varieties of bars and the corresponding multiple historical process data before the training module executes the training of the neural network model using the multiple historical production data of the multiple varieties of bars and the corresponding multiple historical process data, and the preprocessing includes removing outliers and noise, data cleaning and data normalization.

[0053] Furthermore, the control system also includes: an optimization module for simultaneously training the neural network model using the bar tolerance and bar variety measured in real time.

[0054] Furthermore, the multiple historical production data include multiple bar varieties, multiple historical measured bar tolerances, and multiple preset bar tolerances; the multiple historical process data include multiple rolling mill roll gap values, multiple rolling mill roll gap adjustment amounts, multiple rolled piece temperatures, and multiple rolling mill loads; the training module is used to train the neural network model using the multiple historical production data of multiple varieties of bars and the corresponding multiple historical process data to obtain the process adjustment parameter prediction model, which includes: training the neural network model using the multiple bar varieties, multiple historical measured bar tolerances, multiple preset bar tolerances, and multiple rolling mill roll gap values ​​corresponding to the bar varieties, multiple rolling mill roll gap adjustment amounts, multiple rolled piece temperatures, and multiple rolling mill loads to obtain the process adjustment parameter prediction model.

[0055] Furthermore, the control system also includes: a comparison module, which is used to compare the process adjustment parameters with the historical optimal process adjustment parameters after the acquisition module obtains the process adjustment parameters corresponding to the bar variety using the process adjustment parameter prediction model; a determination module, which is used to determine that the process adjustment parameters are target process adjustment parameters when the process adjustment parameters match the historical optimal process adjustment parameters; and an adjustment module, which is used to convert the target process adjustment parameters into corresponding instructions and send them to the rolling mill roll gap position closed-loop control system to achieve adjustment of the rolling mill.

[0056] The third embodiment of the present invention also includes an electronic device, including: a processor, and a memory communicatively connected to the processor; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory to implement the bar tolerance control method as described.

[0057] The implementation principle and technical effects of the electronic device provided in the third embodiment of the present invention are the same as those of the first embodiment, and will not be described in detail herein.

[0058] The fourth embodiment of the present invention further includes a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, they are used to implement the control method of the bar tolerance as described above.

[0059] The implementation principle and technical effects of the computer-readable storage medium provided in the fourth embodiment of the present invention are the same as those of the first embodiment described above, and will not be described in detail herein.

[0060] A fifth embodiment of the present invention also includes a computer program product, including a computer program, which implements the control method of the bar tolerance as described above when the computer program is executed by a processor.

[0061] The implementation principle and technical effects of the computer program product provided in the fifth embodiment of the present invention are the same as those of the first embodiment described above, and will not be described in detail herein.

[0062] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0063] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0064] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0065] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0066] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0067] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0068] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0069] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0070] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A method for controlling bar tolerance, characterized in that: The control method comprises: The neural network model is trained using multiple historical production data of multiple varieties of bars and corresponding multiple historical process data to obtain a process adjustment parameter prediction model; According to the real-time measured bar tolerance and bar type and using the process adjustment parameter prediction model, obtaining the process adjustment parameters corresponding to the bar type; and The process adjustment parameters are converted into corresponding instructions and sent to the rolling mill roll gap position closed-loop control system to achieve adjustment of the rolling mill.

2. The method according to claim 1, characterized in that Before executing the step of training the neural network model using a plurality of historical production data of a plurality of varieties of bars and a plurality of corresponding historical process data, the control method further comprises: Preprocessing is performed on the multiple historical production data of the multiple varieties of bars and the corresponding multiple historical process data, wherein the preprocessing includes removing abnormal values ​​and noise, data cleaning and data normalization.

3. The method according to claim 1, characterized in that The control method further comprises: simultaneously using the real-time measured bar tolerance, bar type and the obtained process adjustment parameters corresponding to the bar type to train the neural network model.

4. The method according to claim 1, characterized in that: The multiple historical production data include multiple bar varieties, multiple historical measured bar tolerances, and multiple preset bar tolerances. The plurality of historical process data include a plurality of rolling mill roll gap values, a plurality of rolling mill roll gap adjustment amounts, a plurality of workpiece temperatures and a plurality of rolling mill loads, The neural network model is trained by using a plurality of historical production data of a plurality of varieties of bars and a plurality of corresponding historical process data to obtain a process adjustment parameter prediction model, including: The neural network model is trained using the multiple bar varieties, multiple historically measured bar tolerances, multiple preset bar tolerances, multiple mill roll gap values ​​corresponding to the bar varieties, multiple mill roll gap adjustment amounts, multiple workpiece temperatures, and multiple mill loads to obtain a process adjustment parameter prediction model.

5. The method according to claim 1, characterized in that After obtaining the process adjustment parameters corresponding to the bar variety using the process adjustment parameter prediction model, the control method further includes: comparing the process adjustment parameters with historical optimal process adjustment parameters; When the process adjustment parameter matches the historical optimal process adjustment parameter, determining the process adjustment parameter as the target process adjustment parameter; The target process adjustment parameters are converted into corresponding instructions and sent to the rolling mill roll gap position closed-loop control system to achieve adjustment of the rolling mill.

6. A control system for bar tolerance, characterized in that: The control system comprises: A training module is used to train a neural network model using multiple historical production data of multiple varieties of bars and corresponding multiple historical process data to obtain a process adjustment parameter prediction model; An acquisition module, used to obtain the process adjustment parameters corresponding to the bar material type according to the bar material tolerance and bar material type measured in real time and using the process adjustment parameter prediction model; and The control module is used to convert the process adjustment parameters into corresponding instructions and send them to the rolling mill roll gap position closed-loop control system to achieve adjustment of the rolling mill.

7. The system according to claim 6, characterized in that The control system further comprises: A preprocessing module is used to preprocess the multiple historical production data of the multiple varieties of rods and the corresponding multiple historical process data before the training module executes the training of the neural network model using the multiple historical production data of the multiple varieties of rods and the corresponding multiple historical process data, and the preprocessing includes removing outliers and noise, data cleaning and data normalization.

8. The system according to claim 6, characterized in that The control system further comprises: The optimization module is used to train the neural network model by simultaneously using the real-time measured bar tolerance, bar type and the obtained process adjustment parameters corresponding to the bar type.

9. The system according to claim 6, characterized in that The multiple historical production data include multiple bar varieties, multiple historical measured bar tolerances, and multiple preset bar tolerances. The plurality of historical process data include a plurality of rolling mill roll gap values, a plurality of rolling mill roll gap adjustment amounts, a plurality of workpiece temperatures and a plurality of rolling mill loads, The training module is used to train the neural network model using multiple historical production data of multiple varieties of bars and corresponding multiple historical process data to obtain a process adjustment parameter prediction model, including: The neural network model is trained using the multiple bar varieties, multiple historically measured bar tolerances, multiple preset bar tolerances, multiple mill roll gap values ​​corresponding to the bar varieties, multiple mill roll gap adjustment amounts, multiple workpiece temperatures, and multiple mill loads to obtain a process adjustment parameter prediction model.

10. The system according to claim 6, characterized in that The control system further comprises: A comparison module, configured to compare the process adjustment parameters with the historical optimal process adjustment parameters after the acquisition module obtains the process adjustment parameters corresponding to the bar variety using the process adjustment parameter prediction model; a determination module, configured to determine the process adjustment parameter as a target process adjustment parameter when the process adjustment parameter matches a historical optimal process adjustment parameter; and The adjustment module is used to convert the target process adjustment parameters into corresponding instructions and send them to the rolling mill roll gap position closed-loop control system to achieve adjustment of the rolling mill.

11. An electronic device, characterized in that: include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method for controlling the bar tolerance according to any one of claims 1 to 5.

12. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the bar tolerance control method according to any one of claims 1 to 5 when executed by a processor.

13. A computer program product, characterized in that The invention comprises a computer program, which, when executed by a processor, implements the method for controlling the tolerance of a bar material according to any one of claims 1 to 5.

Images