A method for online prediction and optimization of steel loss in silicon steel, terminal equipment and storage medium

Abstract

This invention relates to a method, terminal equipment, and storage medium for online prediction and optimization of iron loss in silicon steel. The method includes: establishing a historical dataset; calculating the correlation coefficient between each process parameter and iron loss data, and removing variables with correlation coefficients less than a threshold; constructing a regression model using SVR; ranking the variables by score according to the regression model, and removing the variable with the lowest score; repeating the steps until the number of variables equals the minimum number of variables, calculating the root mean square error of the regression model under different numbers of variables using cross-validation, and selecting the optimal variable set; obtaining an iron loss prediction model based on the optimal variable set; predicting iron loss using a quality prediction model based on the actual values ​​of process parameters for completed processes and the median and upper / lower limits of process parameters for uncompleted processes, and optimizing the process parameters for uncompleted processes using a particle swarm optimization algorithm. This invention can be used for both process parameter optimization and online iron loss prediction.

Description

Technical Field

[0001] This invention relates to the field of silicon steel production, and in particular to a method, terminal equipment and storage medium for online prediction and optimization of silicon steel losses. Background Technology

[0002] Iron loss is a crucial quality indicator for silicon steel, directly determining its performance in cold-rolled applications. To optimize the entire silicon steel production process while ensuring safe operation, iron loss should be minimized. Current research primarily suggests that steelmaking composition and temperature, as well as hot-rolling heating and cooling regimes, significantly impact iron loss. However, a mechanistic or data-driven model of the relationship between process parameters and iron loss throughout the entire silicon steel production process, along with relevant optimization control models, has not yet been established. Summary of the Invention

[0003] To address the aforementioned problems, this invention proposes an online prediction and optimization method for silicon steel losses, a terminal device, and a storage medium.

[0004] The specific plan is as follows:

[0005] A method for online prediction and optimization of steel loss in silicon steel includes the following steps:

[0006] S1: Establish a historical dataset to store the process parameters and iron loss data of each completed steel coil in all stages of the production process;

[0007] S2: Using the Pearson correlation coefficient method, calculate the correlation coefficient between each process parameter and iron loss data in the historical dataset, and remove variables whose absolute value of the correlation coefficient is less than the correlation coefficient threshold from the historical dataset;

[0008] S3: Construct a regression model using the support vector machine regression method;

[0009] S4: Based on the regression model, sort the variables in the historical dataset by score and remove the variable with the lowest score to obtain a new set of variables;

[0010] S5: Check if the number of variables is equal to the set minimum number of variables. If yes, proceed to S6; otherwise, return to S3.

[0011] S6: Use cross-validation to calculate the root mean square error of the regression model under different numbers of variables, and select the variable set with the smallest root mean square error as the optimal variable set;

[0012] S7: Based on the optimal variable set and historical data, the support vector machine regression method is used to perform regression and obtain the iron loss prediction model;

[0013] S8: Based on the actual values ​​of the process parameters of the currently completed processes of the steel coil and the median of the process parameters of the subsequent uncompleted processes in the optimal historical dataset, iron loss is predicted using a quality prediction model; the particle swarm optimization algorithm is used to optimize the process parameters corresponding to the subsequent uncompleted processes based on the upper and lower limits of the actual values ​​of the process parameters of the currently completed processes of the steel coil and the corresponding process parameters of the subsequent uncompleted processes.

[0014] Furthermore, the process includes: steelmaking, hot rolling, normalizing and pickling unit, rolling mill, and continuous annealing unit.

[0015] Furthermore, the correlation coefficient threshold is 0.1.

[0016] A terminal device for online prediction and optimization of steel loss in silicon steel includes a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of the method described in the embodiments of the present invention.

[0017] A computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the method described above in the embodiments of the present invention.

[0018] This invention employs the above-described technical solution, which can effectively extract process parameters that significantly impact iron loss in silicon steel, reduce the number of variables in the model, and improve the model's generalization ability. It can be used for optimizing process parameters throughout the entire silicon steel production process, as well as for online iron loss prediction and optimized control. Attached Figure Description

[0019] Figure 1 The diagram shown is a flowchart of Embodiment 1 of the present invention. Detailed Implementation

[0020] To further illustrate the various embodiments, the present invention provides accompanying drawings. These drawings are part of the disclosure of the present invention, primarily used to illustrate the embodiments, and can be used in conjunction with the relevant descriptions in the specification to explain the operating principles of the embodiments. With reference to these drawings, those skilled in the art should be able to understand other possible implementations and the advantages of the present invention.

[0021] The present invention will now be further described in conjunction with the accompanying drawings and specific embodiments.

[0022] Example 1:

[0023] This invention provides a method for online prediction and optimization of steel loss in silicon steel, such as... Figure 1 As shown, the method includes the following steps:

[0024] S1: Establish a historical dataset to store the process parameters and iron loss data of each completed steel coil in all stages of the production process.

[0025] In this embodiment, the process includes at least steelmaking, hot rolling, normalizing and pickling unit, rolling mill, and continuous annealing unit. Input data (process parameters) and output data (iron loss data) for each steel coil can be obtained from these processes.

[0026] S2: Using the Pearson correlation coefficient method, calculate the correlation coefficient between each process parameter and iron loss data in the historical dataset, and remove variables (i.e. process parameters) whose absolute values ​​of the correlation coefficients are less than the correlation coefficient threshold from the historical dataset.

[0027] In this embodiment, the correlation coefficient threshold is preferably 0.1. In other embodiments, those skilled in the art can adjust it according to their needs, and no restrictions are imposed here.

[0028] S3: Construct a regression model using the Support Vector Machine (SVR) method.

[0029] S4: Based on the regression model, sort the variables in the historical dataset by score and remove the variable with the lowest score to obtain a new set of variables.

[0030] S5: Determine if the number of variables is equal to the set minimum number of variables. If yes, proceed to S6; otherwise, return to S3.

[0031] The minimum number of variables can be set by those skilled in the art as needed, and no limit is imposed here.

[0032] S6: Cross-validation is used to calculate the root mean square error of the regression model under different numbers of variables, and the historical dataset with the smallest root mean square error is selected as the optimal historical dataset.

[0033] By comparing the root mean square error of the cross-validation of regression models with different numbers of variables, the optimal number of variables (minimum root mean square error) can be selected, i.e., the optimal variable set.

[0034] S7: Based on the optimal variable set and historical data, the support vector machine regression method is used to perform regression and obtain the iron loss prediction model.

[0035] S8: Based on the actual values ​​of the process parameters of the currently completed processes of the steel coil and the median of the process parameters of the subsequent uncompleted processes in the optimal historical dataset, iron loss is predicted using a quality prediction model; the particle swarm optimization algorithm is used to optimize the process parameters corresponding to the subsequent uncompleted processes based on the upper and lower limits of the actual values ​​of the process parameters of the currently completed processes of the steel coil and the corresponding process parameters of the subsequent uncompleted processes.

[0036] This embodiment has the following beneficial effects:

[0037] 1. Based on the process parameters of the entire process of steelmaking, hot rolling, cold rolling, and continuous annealing, the Pearson correlation coefficient method is used to screen variables, and the support vector regression plus recursive variable elimination method is used to eliminate variables. The optimal variable set is obtained by cross-validation. This method can effectively extract the process parameters that have a significant impact on silicon steel loss, reduce the number of variables in the model, and improve the generalization ability of the model.

[0038] 2. An impact model for iron loss in cold-rolled silicon steel was established to investigate the influence of process parameters throughout the silicon steel production process on iron loss. The model can be used for optimization of process parameters throughout the silicon steel production process, as well as for online iron loss prediction and optimization control.

[0039] 3. Based on the iron loss prediction model, the particle swarm optimization algorithm is used to optimize the process parameters online and provide suggestions for optimizing and controlling the process parameters of subsequent processes so that the iron loss meets the set value.

[0040] 4. Based on the iron loss prediction model, the particle swarm optimization algorithm is used to optimize the important process parameters throughout the entire process for product quality design.

[0041] Example 2:

[0042] The present invention also provides a terminal device for online prediction and optimization of silicon steel losses, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps in the method embodiment described above in Embodiment 1 of the present invention.

[0043] Furthermore, as an executable solution, the silicon steel loss online prediction and optimization terminal device can be a computing device such as a desktop computer, laptop, handheld computer, or cloud server. The silicon steel loss online prediction and optimization terminal device may include, but is not limited to, a processor and memory. Those skilled in the art will understand that the above-described composition of the silicon steel loss online prediction and optimization terminal device is merely an example and does not constitute a limitation on the silicon steel loss online prediction and optimization terminal device. It may include more or fewer components than described above, or combine certain components, or different components. For example, the silicon steel loss online prediction and optimization terminal device may also include input / output devices, network access devices, buses, etc., and this embodiment of the invention does not limit this.

[0044] Furthermore, as an executable solution, the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor. This processor is the control center of the online prediction and optimization terminal equipment for silicon steel losses, connecting all parts of the equipment via various interfaces and lines.

[0045] The memory can be used to store the computer programs and / or modules. The processor, by running or executing the computer programs and / or modules stored in the memory and calling the data stored in the memory, realizes various functions of the silicon steel loss online prediction and optimization terminal device. The memory may mainly include a program storage area and a data storage area. The program storage area may store the operating system and at least one application program required for a function; the data storage area may store data created based on the use of the mobile phone, etc. In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0046] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the method described in the embodiments of the present invention.

[0047] If the modules / units integrated in the silicon steel loss online prediction and optimization terminal equipment are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), and a software distribution medium, etc.

[0048] Although the invention has been specifically shown and described in conjunction with preferred embodiments, those skilled in the art should understand that various changes in form and detail may be made to the invention without departing from the spirit and scope of the invention as defined in the appended claims, all of which shall be within the scope of protection of the invention.

Claims

1. A method for online prediction and optimization of steel loss in silicon steel, characterized in that, Includes the following steps: S1: Establish a historical dataset to store the process parameters and iron loss data of each completed steel coil in all stages of the production process; S2: Using the Pearson correlation coefficient method, calculate the correlation coefficient between each process parameter and iron loss data in the historical dataset, and remove variables whose absolute value of the correlation coefficient is less than the correlation coefficient threshold from the historical dataset; S3: Construct a regression model using the support vector machine regression method; S4: Based on the regression model, sort the variables in the historical dataset by score and remove the variable with the lowest score to obtain a new set of variables; S5: Check if the number of variables is equal to the set minimum number of variables. If yes, proceed to S6; otherwise, return to S3. S6: Use cross-validation to calculate the root mean square error of the regression model under different numbers of variables, and select the variable set with the smallest root mean square error as the optimal variable set; S7: Based on the optimal variable set and historical data, the support vector machine regression method is used to perform regression and obtain the iron loss prediction model; S8: Based on the actual values ​​of the process parameters of the currently completed processes of the steel coil and the median of the process parameters of the subsequent uncompleted processes in the optimal historical dataset, iron loss is predicted using a quality prediction model. The particle swarm optimization algorithm is used to optimize the process parameters for subsequent unfinished processes based on the actual values ​​of the process parameters for the currently completed processes of the steel coil and the upper and lower limits of the process parameters for the subsequent unfinished processes.

2. The method for online prediction and optimization of silicon steel loss according to claim 1, characterized in that: The process includes: Steelmaking, hot rolling, normalizing and pickling units, rolling mills, and continuous annealing units.

3. The online prediction and optimization method for silicon steel loss according to claim 1, characterized in that: The correlation coefficient threshold is 0.

1.

4. A terminal device for online prediction and optimization of steel loss in silicon steel, characterized in that: It includes a processor, a memory, and a computer program stored in the memory and running on the processor, wherein the processor executes the computer program to implement the steps of the method as described in any one of claims 1 to 3.

5. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 3.

Images