A method for setting bending roll force and roll shifting amount for hot-rolled strip shape control

Abstract

The present invention belongs to the field of rolling technology and relates to a method for setting a bending roll force and a roll shifting amount for controlling the plate shape of a hot-rolled strip, comprising: collecting historical production data of the strip in actual production; performing outlier detection on the historical production data of the strip using the 3σ principle, removing the outliers, and dividing the data into a training set and a test set; establishing a convexity prediction model based on Lasso regression, and training the convexity prediction model using the training set data; testing the trained convexity prediction model based on Lasso regression using the test set; establishing a plate shape target function; establishing constraints for rolling variables based on each frame equipment in a finishing mill and plate shape theory; and using a peregrine falcon optimization algorithm to search for the bending roll force and the roll shifting amount of each frame in the finishing mill within the range of the constraints, so that the plate shape target function is minimized, and the setting values ​​of the bending roll force and the roll shifting amount are obtained.

Description

Technical Field

[0001] The invention belongs to the technical field of rolling, and in particular relates to a method for setting a bending roll force and a roll shifting amount for controlling the shape of a hot-rolled strip. Background Art

[0002] Hot-rolled strip products, with their exceptional strength, excellent ductility, and superior mechanical properties, occupy a crucial position in China's industrial system and are widely used in high-end industries such as machinery, transportation, and aviation. Dimensional accuracy of strip has become a crucial indicator of finished product quality. With the rapid development and mature application of various rolling technologies and equipment, the thickness of hot-rolled strip has largely met market requirements. However, insufficient control accuracy still exists in shape control, resulting in flatness issues such as center waves, edge waves, and middle waves at the head of the rolled strip. However, the hot-rolled strip shape control mechanism is highly complex, characterized by multivariate, strong coupling, and nonlinear characteristics. Factors such as rolling force, bending force, roll shifting, rolling speed, and rolling temperature within each finishing mill affect the strip shape. Therefore, achieving accurate hot-rolled strip shape prediction is a challenging task. Existing strip shape models are overly simplified and incompletely consider factors influencing strip shape, resulting in low strip shape prediction accuracy. Furthermore, the setting of the strip shape rolling force variables is prone to falling into local optima and zero gradients. Therefore, it is necessary to improve the setting accuracy of the strip shape and reduce the shape defects of the hot-rolled strip. Summary of the Invention

[0003] In order to overcome the wave shape problem caused by low accuracy in the existing hot-rolled strip shape setting, the present invention provides a method for setting the bending roll force and the roll shifting amount for controlling the shape of the hot-rolled strip.

[0004] The present invention provides a method for setting a bending roll force and a roll shifting amount for controlling the shape of a hot-rolled strip, comprising the following steps:

[0005] Step 1: Collect historical production data of strip steel in actual production;

[0006] Step 2: Use the 3σ principle to detect outliers in the historical strip production data, remove outliers, and divide the data into training and test sets;

[0007] Step 3: Establish a convexity prediction model based on Lasso regression and train the convexity prediction model using the training set data;

[0008] Step 4: Use the test set to test the trained convexity prediction model based on Lasso regression;

[0009] Step 5: Establish the plate shape objective function;

[0010] Step 6: Establish the constraints of rolling variables based on the equipment of each stand in the finishing mill and the plate shape theory;

[0011] Step 7: Using the eagle optimization algorithm, search for the bending roll force and roll shifting amount of each stand in the finishing mill within the constraints of step 6, so as to minimize the plate shape objective function and obtain the set values ​​of the bending roll force and roll shifting amount.

[0012] The method for setting the bending roll force and roll shifting amount for controlling the shape of hot-rolled strip steel of the present invention has at least the following beneficial effects:

[0013] First, the present invention proposes a data-driven crown prediction model that effectively quantifies the impact of rolling variables on strip crown during the rolling process. Next, a flatness objective function and constraints for the bending force and roll shifting in the finishing mill are presented. Finally, an intelligent algorithm is employed to search for the bending force and roll shifting that minimize the flatness objective function, obtaining and setting the optimal bending force and roll shifting. This method for setting flatness control addresses flatness issues such as center wave, edge wave, and intermediate wave. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 This is a flow chart of a method for setting the bending roll force and roll shifting amount for hot-rolled strip shape control according to the present invention;

[0015] Figure 2 This is a diagram showing the prediction effect of the convexity prediction model based on Lasso regression on the test set for strip convexity. DETAILED DESCRIPTION

[0016] The specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. In this example, a 7-row finishing mill of a hot rolling mill is taken as an example. The rolling rolls of the finishing mill are all flat rolls, and the rolling variables are set.

[0017] like Figure 1 As shown, a method for setting the bending roll force and roll shifting amount for controlling the shape of a hot-rolled strip according to the present invention comprises the following steps:

[0018] Step 1: Collect historical strip production data from actual production, including: strip width, inlet temperature of each stand, inlet thickness of each stand, rolling force of each stand, bending roll force of each stand, roll shifting amount of each stand, wear crown of each stand, thermal crown of each stand, inlet crown of each stand, original crown of the rolls of each stand, measured strip outlet crown of each stand, and target crown of the finished product.

[0019] Step 2: Use the 3σ principle to detect outliers in the historical strip production data, remove outliers, and divide it into training and test sets.

[0020] Step 3: Establish a convexity prediction model based on Lasso regression and train the convexity prediction model using the training set data. Specifically:

[0021] Step 3.1: Establish a mathematical relationship model between rolling variables and predicted crown:

[0022] ;

[0023] in, For the i Predicted strip exit crown of the stand, W i For the i The strip steel width of the rack, in mm; For the i The efficiency coefficient of the strip width of the rack, in μm / mm; P i For the i The rolling force of the stand, in kN; For the i The efficiency coefficient of the rolling force of the stand, in μm / kN; F i For the i The bending roll force of the frame, in kN; For the i The efficiency coefficient of the frame bending roll force, in μm / kN; S i For the i The roller shifting amount of the frame, in mm; For the i The efficiency coefficient of the roll shifting amount of the frame, in μm / mm; For the i The entrance convexity of the rack, in μm; For the i Efficiency coefficient of the rack inlet convexity; For the i The inlet temperature of the rack, in °C; For the i Efficiency factor for rack inlet temperature; For the i The entrance thickness of the rack, in mm; For the i Efficiency coefficient of the rack inlet thickness, in μm / mm; For the i The wear crown of the stand rollers, in μm; No. i Thermal crown of the stand roll, in μm; For the iThe original crown of the stand roller, in μm; No. i Efficiency coefficient of roll gap crown of the stand;

[0024] Step 3.2: Establish the loss function of Lasso regression:

[0025] ;

[0026] in, For the i vector of efficiency coefficients of stand rolling variables; is calculated based on the mathematical relationship model in step 3.1. i Rack j The predicted convexity of the strip steel outlet, in μm; It is i Rack j The measured convexity of the strip outlet is in μm; N is the number of strips in the training set; λ is the penalty coefficient; is the square of the L1-norm.

[0027] Step 3.3: Initialize i Efficiency coefficient vector of rolling stand variables β i , bring into the mathematical relationship model of step 3.1 and calculate the current strip export predicted convexity.

[0028] Step 3.4: Take one of the efficiency coefficients in the efficiency coefficient vector as a variable and the other efficiency coefficients as constants, bring the efficiency coefficient vector into the mathematical relationship model, calculate the current strip export prediction convexity and the loss function value of the Lasso regression, and continuously update the efficiency coefficient as a variable to minimize the loss function value of the Lasso regression. According to the above process, loop through all efficiency coefficients. When the maximum number of iterations is reached, stop the iteration and obtain a set of optimal efficiency coefficient vectors that minimize the loss function value of the Lasso regression.

[0029] Step 3.5: Assign the obtained optimal efficiency coefficient vector to the mathematical relationship model of step 3.1 to obtain the convexity prediction model based on Lasso regression.

[0030] Step 4: Use the test set to test the trained convexity prediction model based on Lasso regression. Figure 2 As shown in the figure, the convexity values ​​calculated by the convexity model based on Lasso regression have a good fitting effect with the measured convexity values.

[0031] Step 5: In order to minimize the strip wave shape and make the finished product convexity as close to the target convexity as possible, the flatness objective function is established as follows:

[0032] ;

[0033] ;

[0034] in, F i For the i The bending roll force of the frame, in kN; S i For the i The roller shifting amount of the frame, in mm; is the first value calculated based on the convexity prediction model in step 3. i The predicted strip crown of the stand, in mm; h i For the i The outlet thickness of the rack, in mm; C tar is the target convexity, α 1 and α 2 is the weight coefficient.

[0035] Step 6: Establish the constraints of rolling variables based on the equipment of each stand in the finishing mill and the plate shape theory, specifically:

[0036] Step 6.1: Set the maximum and minimum roll shifting allowed for each finishing stand.

[0037] Step 6.2: Set the maximum and minimum bending forces allowed for each finishing stand.

[0038] Step 6.3: Set the minimum and maximum values ​​of the relative convexity difference between the roll gaps of two adjacent stands caused by roll shifting. The relative convexity of the roll gap is the ratio of the roll gap convexity to the roll gap value.

[0039] Step 6.4: Set the minimum and maximum values ​​of the relative convexity change of the strip steel at the exit of two adjacent stands, which is allowed under the condition that each stand maintains good straightness. The relative convexity of the strip steel at the exit is the ratio of the convexity of the strip steel at the exit to the thickness of the strip steel at the exit.

[0040] Step 6.5: Set the minimum and maximum values ​​of the relative crown of the exit strip allowed for the last effective stand in the finishing mill. The relative crown of the exit strip is the ratio of the crown of the exit strip to the thickness of the exit strip.

[0041] Step 7: Using the eagle optimization algorithm, search for the bending force and roll shifting of each stand in the finishing mill within the constraints of step 6 to minimize the plate shape objective function and obtain the set values ​​of the bending force and roll shifting. Specifically,

[0042] Step 7.1: Generate an initial secretary bird population of 100 individuals. Each secretary bird individual contains the bending roll force and roll shifting amount of each stand of the finishing mill.

[0043] Step 7.2: Assign the bending roll force, roll shifting amount, and other real-time on-site production data of each secretary bird to the Lasso regression crown prediction model in step 3 and calculate the predicted strip outlet crown of each stand. Substitute the predicted strip outlet crown of each stand into the flatness objective function in step 5 to calculate the fitness value of each secretary bird.

[0044] Step 7.3: Sort the individuals by fitness value from low to high, and retain the top 30 individuals. After the remaining individuals perform aerial flight and underwater foraging operations, a population of 100 secretary bird species is obtained again.

[0045] Step 7.4: Repeat steps 7.2 to 7.3 until the iteration termination condition is met.

[0046] Step 7.5: After the iteration is terminated, the bending roll force and roll shifting amount corresponding to the individual with the lowest fitness value are the set values ​​for plate shape control.

[0047] The present invention was implemented on a hot rolling line, and the resulting finished strip shape quality of the examples is shown in Table 1. As can be seen from Table 1, the convexity of the finished products of the examples is close to the target convexity, and the flatness of the finished products is less than 20 IU, indicating that the finished products of the examples have good shape under the shape settings of the present invention.

[0048] Table 1 Plate quality of finished products of the examples.

[0049]

[0050] The above description is only a preferred embodiment of the present invention and is not intended to limit the concept of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for setting the bending roll force and roll shifting amount for hot-rolled strip shape control, characterized in that: The following steps are involved: Step 1: Collect historical production data of strip steel in actual production; Step 2: Use the 3σ principle to detect outliers in the historical strip production data, remove outliers, and divide the data into training and test sets; Step 3: Establish a convexity prediction model based on Lasso regression and train the convexity prediction model using the training set data; Step 4: Use the test set to test the trained convexity prediction model based on Lasso regression; Step 5: Establish the plate shape objective function; Step 6: Establish the constraints of rolling variables based on the equipment of each stand in the finishing mill and the plate shape theory; Step 7: Using the eagle optimization algorithm, search for the bending force and roll shifting amount of each stand in the finishing mill within the constraints of step 6 to minimize the plate shape objective function and obtain the set values ​​of the bending force and roll shifting amount; The step 3 is specifically as follows: Step 3.1: Establish a mathematical relationship model between rolling variables and predicted crown: in, is the predicted convexity of the strip steel outlet at the i-th stand, W i is the strip width of the i-th rack, in mm; P is the efficiency coefficient of the strip width of the i-th rack, in μm / mm; i is the rolling force of the i-th stand, in kN; is the efficiency coefficient of the rolling force of the i-th stand, in μm / kN; F i is the bending roll force of the i-th stand, in kN; is the efficiency coefficient of the bending roll force of the i-th stand, in μm / kN; S i is the roller shifting amount of the i-th frame, in mm; is the efficiency coefficient of the roller shifting of the i-th stand, in μm / mm; is the entrance convexity of the i-th rack, in μm; is the efficiency coefficient of the convexity of the inlet of the i-th rack; is the inlet temperature of the i-th rack, in °C; is the efficiency coefficient of the inlet temperature of the i-th rack; is the inlet thickness of the i-th rack, in mm; is the efficiency coefficient of the thickness of the i-th rack entrance, in μm / mm; is the wear crown of the roll of the i-th stand, in μm; Thermal crown of the roll in stand i, in μm; is the original crown of the roll of the i-th stand, in μm; The efficiency coefficient of the roll gap crown of the i-th stand; Step 3.2: Establish the loss function of Lasso regression: in, is the efficiency coefficient vector of the rolling variables of the i-th stand; is the predicted strip exit crown of the jth stand calculated based on the mathematical relationship model in step 3.1, in μm; is the measured crown of the j-th strip outlet at the i-th stand, in μm; N is the number of strips in the training set; λ is the penalty coefficient; ||·||1 is the square of the L1-norm; Step 3.3: Initialize the efficiency coefficient vector β of the rolling variables of the i-th stand i , bring in the mathematical relationship model in step 3.1 and calculate the current strip export predicted convexity; Step 3.4: Use one of the efficiency coefficients in the efficiency coefficient vector as a variable and the other efficiency coefficients as constants. Substitute the efficiency coefficient vector into the mathematical relationship model, calculate the current strip export forecast convexity and the loss function value of the Lasso regression, continuously update the efficiency coefficient as a variable to minimize the loss function value of the Lasso regression, repeat the above process to loop through all efficiency coefficients, and stop the iteration when the maximum number of iterations is reached to obtain a set of optimal efficiency coefficient vectors that minimize the loss function value of the Lasso regression; Step 3.5: Assign the obtained optimal efficiency coefficient vector to the mathematical relationship model of step 3.1 to obtain the convexity prediction model based on Lasso regression.

2. The method for setting the bending roll force and roll shifting amount for hot-rolled strip shape control according to claim 1, wherein: The historical strip production data in step 1 includes: strip width, inlet temperature of each stand, inlet thickness of each stand, rolling force of each stand, bending roll force of each stand, roll shifting amount of each stand, wear crown of each stand, thermal crown of each stand, inlet crown of each stand, original crown of the rolls of each stand, measured strip outlet crown of each stand, and target crown of the finished product.

3. The method for setting the bending roll force and roll shifting amount for hot-rolled strip shape control according to claim 1, wherein: The plate shape objective function in step 5 is: Among them, F i is the bending roll force of the i-th stand, in kN; S i is the roller shifting amount of the i-th frame, in mm; h is the predicted strip crown of the i-th stand calculated based on the crown prediction model in step 3, in mm; i is the outlet thickness of the i-th rack, in mm; C tar is the target convexity, α1 and α2 are weight coefficients.

4. The method for setting the bending roll force and roll shifting amount for hot-rolled strip shape control according to claim 1, wherein: The step 6 is specifically as follows: Step 6.1: Set the maximum and minimum roll shifting allowed for each stand in the finishing mill; Step 6.2: Set the maximum and minimum bending forces allowed for each stand of the finishing mill; Step 6.3: Set the minimum and maximum values ​​of the relative crown difference between the roll gaps of two adjacent stands caused by roll shifting. The relative crown of the roll gap is the ratio of the roll gap crown to the roll gap value. Step 6.4: Set the minimum and maximum values ​​of the relative crown variation of the strips exiting two adjacent stands, while maintaining good straightness of the strips at each stand. The relative crown of the strips exiting is the ratio of the crown of the strips exiting to the thickness of the strips exiting. Step 6.5: Set the minimum and maximum values ​​of the relative crown of the exit strip allowed for the last effective stand in the finishing mill. The relative crown of the exit strip is the ratio of the crown of the exit strip to the thickness of the exit strip.

5. The method for setting the bending roll force and roll shifting amount for hot-rolled strip shape control according to claim 1, wherein: The step 7 is specifically as follows: Step 7.1: Generate an initial population of 100 Secretary Birds. Each Secretary Bird individual contains the roll bending force and roll shifting amount of each stand in the finishing mill. Step 7.2: Assign the roll bending force, roll shifting amount, and other real-time production data of each secretary bird individual to the Lasso regression crown prediction model in Step 3 and calculate the predicted strip outlet crown of each stand. Substitute the predicted strip outlet crown of each stand into the flatness objective function in Step 5 to calculate the fitness value of each secretary bird individual. Step 7.3: Sort the individuals by fitness value from low to high, and keep the top 30 individuals. After the remaining individuals perform aerial flight and underwater foraging operations, a population of 100 secretary bird species is obtained again. Step 7.4: Repeat steps 7.2 to 7.3 until the iteration termination condition is met; Step 7.5: After the iteration is terminated, the bending roll force and roll shifting amount corresponding to the individual with the lowest fitness value are the set values ​​for plate shape control.

Images