Intelligent control method for surface PC value of cold-rolled strip steel based on optimization algorithm

Abstract

The invention discloses a cold-rolled strip steel surface PC value intelligent control method based on an optimization algorithm, and the method achieves the effective control of the strip steel surface PC value through the mechanism analysis of PC value transfer printing in the cold rolling process, the calculation through a model optimization algorithm, and the intelligent adjustment of rolling process parameters. By the adoption of the method, a rolling two-stage control model can be directly imported for online parameter optimization, the method can be directly applied to cold continuous rolling unit production, intellectualized transformation of enterprises is promoted, and the control precision and stability are improved.

Description

Technical Field

[0001] The invention belongs to the technical field of strip steel surface, and relates to an intelligent control method for PC value of cold-rolled strip steel surface based on an optimization algorithm. Background Art

[0002] In the steel industry, cold-rolled strip is an important material, and its surface quality is crucial to the final performance of the product. As an important parameter to measure the surface morphology of the strip, the surface PC value directly affects the performance of the strip in subsequent processing and use, such as coating adhesion, surface finish, corrosion resistance and aesthetics. Therefore, controlling the surface PC value is of great significance to improving product quality and meeting customer needs. However, there are considerable technical challenges in controlling the surface PC value. First, the cold rolling process involves multiple variables, such as rolling speed, rolling force, lubrication conditions and cooling rate. These variables affect each other, making the control of the surface PC value complicated. In addition, the inevitable process fluctuations and equipment wear in the production process will also affect the surface PC value, making it more difficult to stably and accurately control the PC value.

[0003] Prior to this invention, the patents related to this invention mainly include the following: (1) Patent CN113943899A discloses a method for controlling the surface morphology of cold-rolled deep-drawing steel, including smelting, continuous casting, hot rolling, acid rolling, and annealing processes. The chemical composition and mass percentage of the steel are: C: ≤0.0030%, Si: ≤0.030%, Mn: ≤0.30%, P: ≤0.015%, S: ≤0.015%, Als: 0.020~0.060%, Ti: ≤0.080%, Nb: 0.003~0.008%, N: ≤0.0040%, and the remainder is Fe and unavoidable impurities. This invention obtains a cold-rolled deep-drawing steel with stable surface morphology by controlling key process parameters such as smelting chemical composition, hot rolling lubrication state, cold rolling tempering roll surface morphology and elongation. In addition to meeting the forming performance of deep drawing, it can also achieve high surface quality requirements such as no mid-coating required for automobiles. In the pickling continuous rolling process, the work roll roughness of the cold rolling stands F1 and F2 is Ra = 0.5-1.0 μm, the work roll roughness of the F3 and F4 stands is Ra = 0.3-0.6 μm, and the work roll roughness of the F5 stand is Ra = 3.0-3.5 μm. The roughness of the steel strip after cold continuous rolling is Ra = 0.6-1.2 μm, and the peak value Rpc = 90-100 pieces / cm. This method does not control the PC value of the work rolls and cannot optimize the work roll surface parameters for the target PC setting value.

[0004] (2) Patent CN114032467A discloses a cold-rolled high-strength steel plate and its preparation method. The chemical composition of the cold-rolled high-strength steel plate is as follows: C: 0.1-0.2%, Mn: 1.5-2.5%, S: ≤0.005%, P ≤0.015%, Si: 0.5-2.0%, Als: 0.015-0.060%, N ≤0.005%, with the remainder being Fe and unavoidable impurities. The process flow of the preparation method is, in order, smelting and casting, hot rolling and coiling, pickling and cold rolling, continuous annealing, and leveling. The phosphating film on the surface of the cold-rolled automobile sheet prepared by the method of the invention has a dense structure, uniform crystallization, granular shape, low porosity, and high paintability. It can effectively solve the problem of poor phosphating performance of the existing cold-rolled high-strength steel sheet with high formability. The surface roughness Ra value of the strip after leveling is controlled to be 1.0~1.3 μm, the Rpc value is 80~130, and the surface energy is 1.2~1.8 J / m 2 This method mainly controls the surface parameters through the leveling process, and does not put forward control requirements for the process parameters of the cold rolling process. At the same time, the control of surface parameters by this method is mainly based on the design of the target value of the strip surface parameters, and does not provide detailed information on how to achieve the target value.

[0005] (3) Patent CN114231822A discloses a method for improving the paintability of cold-rolled automobile sheet. The process flow of the method is, in order, smelting and casting, hot rolling and coiling, pickling and cold rolling, continuous annealing, leveling and oiling, degreasing and pickling, surface adjustment and phosphating. The phosphating film layer on the surface of the cold-rolled automobile sheet prepared by this method has a dense structure, uniform crystallization, and is granular. The average grain size is 2~3 μm, the porosity is small, and it has high paintability. It effectively solves the problem of poor paintability of cold-rolled automobile sheet by existing methods. In the leveling and oiling process, the surface roughness Ra value of the strip after leveling is controlled to be 0.7~1.3 μm and the Rpc value is 80~130. On the one hand, the control of the strip surface parameters is concentrated on the leveling process. On the other hand, it only proposes the target value of the strip surface parameters without proposing specific control measures. Summary of the Invention

[0006] The purpose of the present invention is to provide an intelligent control method for the PC value of the surface of cold-rolled strip based on an optimization algorithm. By performing mechanism analysis and mathematical modeling on the cold rolling roller transfer, which has a greater impact on the surface PC value, the rolling process parameters are intelligently adjusted through the model optimization algorithm to achieve precise control of the PC value of the strip surface.

[0007] To achieve the above object, the technical solution adopted by the present invention is as follows: (a) Setting the target PC value RPc Ti ,i Indicates the number of rolling mill stands; (b) Collect initial parameters: roll PC value RPc wi ; (c) Initialize the learning rate α and tolerance error β ; (d) Define the loss function ; (e) Initialize the iteration counter ( t =0); (f) Calculate the initial PC value of the strip steel at the outlet of each rack RPc i ; (g) Calculate the total loss through step (d) L ; (h) For each RPc wi , calculate the partial derivative ( ) and update the PC value of each stand roller; (i) Update the PC value of each rack outlet strip RPc i ; (j) Repeat steps (g) to (i); (k) Output optimized roll PC value RPc wi .

[0008] Furthermore, in step (c), the learning rate needs to be balanced. If the learning rate is too small, the convergence will be slow; if the learning rate is too large, the loss will fluctuate or even increase. Comprehensively analyze the initialization learning rate and tolerance error multiple times to finally determine the initialization learning rate. α and tolerance error β， Satisfy β / α =100.

[0009] Further, in step (d), RPc i By Calculated, a 0=168.85±4.93, a 1=50.25±6.12, a 2=-18.79±7.48, a 3=25.26±1.28.

[0010] Further, in step (j), until ( L < β ) or the calculation stops when the maximum number of iterations is reached.

[0011] This invention provides an intelligent control method for the PC value of cold-rolled steel strip surface based on an optimization algorithm. By analyzing the mechanism of PC value transfer during cold rolling, the PC values ​​of each stand roll are optimized based on the optimization algorithm. This method effectively controls the surface PC value without the need for additional auxiliary equipment or extensive modifications. The method can be directly integrated into the secondary rolling control model for online parameter optimization. This method can be directly applied to cold tandem mill production, promoting the intelligent transformation of enterprises and improving control accuracy and stability. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 This is a flow chart of the intelligent control method for the PC value of the cold-rolled strip surface. DETAILED DESCRIPTION

[0013] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. The following description of exemplary embodiments of the experimental method is actually only illustrative and is in no way intended to limit the present invention and its application or use. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making creative work are within the scope of protection of the present invention.

[0014] Example 1: (a) Setting the target PC value RPc Ti ={140,215,220,122,190}, i ={1,2,3,4,5}; (b) Collect initial parameters: roll PC value RPc wi ={125,153,143,168,107}, i ={1,2,3,4,5}; (c) Initialize the learning rate α = 0.1 and tolerance error β =10; (d) Define the loss function ; (e) Initialize the iteration counter ( t =0); (f) Calculate the initial PC value of the strip steel at the outlet of each rack RPc i ={133,202,213,115,173}, i ={1,2,3,4,5}; (g) Calculation of total loss L =605; (h) For each RPc wi , calculate partial derivatives = {3.5, -5.02, 1.89, -2.09, -6.23}, i ={1,2,3,4,5}; and update each rack RPc wi Value = {124.64, 153.50, 142.81, 168.21, 107.62}, i ={1,2,3,4,5}; (i) Update the PC value of each rack outlet strip RPc i ={126.05,196.13,216.35,121.09,168.54}, i ={1,2,3,4,5}; (j) Repeat steps (g) to (i) until ( L < β ); (k) Output optimized roll PC value RPc wi ={178,192,196,173,136}, i ={1,2,3,4,5}.

[0015] Example 2: (a) Setting the target PC value RPc Ti ={130,135,150,140,160}, i ={1,2,3,4,5}; (b) Collect initial parameters: roll PC value RPc wi ={120,130,150,160,155}, i ={1,2,3,4,5}; (c) Initialize the learning rate α =1 and tolerance error β =100; (d) Define the loss function ; (e) Initialize the iteration counter ( t =0); (f) Calculate the initial PC value of the strip steel at the outlet of each rack RPc i ={118,152,210,155,149}, i={1,2,3,4,5}; (g) Calculation of total loss L =4379; (h) For each RPc wi , calculate partial derivatives = {-0.16, 5.86, -3.32, -6.07, -5.78}, i ={1,2,3,4,5}; and update each rack RPc wi Value = {118.60, 124.48, 153.32, 166.07, 160.78}, i ={1,2,3,4,5}; (i) Update the PC value of each rack outlet strip RPc i ={118.60,124.48,197.05,126.86,152.52}, i ={1,2,3,4,5}; (j) Repeat steps (g) to (i) until ( L < β ); (k) Output optimized roll PC value RPc wi ={125,164,161,163,159}, i ={1,2,3,4,5}.

Claims

1. An intelligent control method for PC value of cold-rolled strip surface based on optimization algorithm, characterized in that: Specifically include: (a) Setting the target PC value RPc Ti , i Indicates the number of rolling mill stands; (b) Collect initial parameters: roll PC value RPc wi ; (c) Initialize the learning rate α and tolerance error β ; (d) Define the loss function ; (e) Initialize the iteration counter, t =0; (f) Calculate the initial PC value of the strip steel at the outlet of each rack RPc i ; (g) Calculate the total loss through step (d) L ; (h) For each RPc wi , calculate the partial derivatives , and update the PC value of each stand roll; (i) Update the PC value of each rack outlet strip RPc i ; (j) Repeat steps (g) to (i); (k) Output optimized roll PC value RPc wi .

2. The intelligent control method of PC value of cold-rolled strip surface based on optimization algorithm according to claim 1 is characterized in that: In step (c), determine the initial learning rate α and tolerance error β satisfy β / α =100.

3. The intelligent control method of PC value of cold-rolled strip surface based on optimization algorithm according to claim 1 is characterized in that: In step (d), RPc i By Calculated, a 0=168.85±4.93, a 1=50.25±6.12, a 2=-18.79±7.48, a 3=25.26±1.

28.

4. The intelligent control method of PC value of cold-rolled strip surface based on optimization algorithm according to claim 1 is characterized in that: Further, in step (h), RPc wi The calculation formula is .

5. The intelligent control method of PC value of cold-rolled strip surface based on optimization algorithm according to claim 1 is characterized in that: In step (j), until L < β， Or the calculation stops when the maximum number of iterations is reached.

Images