Method for controlling the shape of a cold-rolled strip

Abstract

The application discloses a cold-rolled strip plate shape regulation method, which comprises the following steps: obtaining a plurality of order plate shape components of a cold-rolled strip, wherein the plurality of order plate shape components comprise a first order plate shape component, a second order plate shape component and a third order plate shape component, the first order plate shape component is used for reflecting the overall plate shape defect of the cold-rolled strip, the second order plate shape component is used for reflecting the first local plate shape defect of the cold-rolled strip, and the third order plate shape component is used for reflecting the second local plate shape defect of the cold-rolled strip; according to the first order plate shape component, the plate shape of the cold-rolled strip is adjusted by a rolling mill; and according to the second order plate shape component and the third order plate shape component, the area of the cold-rolled strip where the first local plate shape defect and the second local plate shape defect exist is independently adjusted by the rolling mill. The application can realize fine regulation and control of the cold-rolled strip and improve the plate shape regulation and control precision of the cold-rolled strip.

Description

Technical Field

[0001] This application belongs to the field of strip steel control technology, and particularly relates to a method for controlling the shape of cold-rolled strip steel. Background Technology

[0002] Shape control of cold-rolled strip plays a crucial role in improving finished product quality. As the thickness of the strip decreases, the difficulty of strip shape control increases dramatically, leading to instability and poor adjustment accuracy in the shape control process. Summary of the Invention

[0003] The embodiments of this application provide a method for controlling the shape of cold-rolled strip steel, which can at least to a certain extent achieve fine control of the shape of cold-rolled strip steel and improve the accuracy of shape control of cold-rolled strip steel.

[0004] Other features and advantages of this application will become apparent from the following detailed description, or may be learned in part from practice of this application.

[0005] The first aspect of this application provides a method for controlling the shape of cold-rolled strip steel, including: A multi-order shape component of cold-rolled strip steel is obtained. The multi-order shape component includes a first-order shape component, a second-order shape component, and a third-order shape component. The first-order shape component is used to reflect the overall shape defect of the cold-rolled strip steel. The second-order shape component is used to reflect the first local shape defect of the cold-rolled strip steel. The third-order shape component is used to reflect the second local shape defect of the cold-rolled strip steel. The complexity of the second local shape defect is greater than that of the first local shape defect. Based on the first-order strip shape component, the rolling mill is controlled to adjust the strip shape of the cold-rolled strip so that the overall strip shape of the cold-rolled strip meets the preset overall strip shape standard. Based on the second-order shape component and the third-order shape component, the rolling mill is controlled to independently adjust the regions in the cold-rolled strip where the first local shape defect and the second local shape defect exist, so that the local shape of the cold-rolled strip meets the preset local shape standard.

[0006] Optionally, the multi-order plate shape components are characterized by the following formula: ; ; in, This represents the coordinates of the cold-rolled strip in the width direction. This represents the multi-order plate shape component, where u represents the total number of orders. This represents the basic board shape pattern of the k-th order. Represents the k-th order plate shape component. This represents the basic plate shape pattern of the (k-1)th order.

[0007] Optionally, before controlling the rolling mill to adjust the shape of the cold-rolled strip based on the first-order shape component, the method further includes: Obtain the shape control matrix of the cold-rolled strip, wherein the shape control matrix includes multiple influence coefficients, each influence coefficient being the influence coefficient of the adjustment amount of one shape control means of the rolling mill on the shape component of one order of the cold-rolled strip.

[0008] Optionally, the step of controlling the rolling mill to adjust the shape of the cold-rolled strip according to the first-order shape component, so that the overall shape of the cold-rolled strip meets the preset overall shape standard, includes: The first component to be adjusted is determined based on the deviation between the first-order plate shape component and the target plate shape component set in the preset overall plate shape standard. Based on the plate shape control matrix, determine the first plate shape control method corresponding to the first component to be adjusted and the first adjustment amount of the first plate shape control method; The rolling mill is controlled to adjust the shape of the cold-rolled strip according to the first control method and the first adjustment amount.

[0009] Optionally, the first control means includes a bending roller and at least one of the bending rollers.

[0010] Optionally, controlling the rolling mill to independently adjust the regions in the cold-rolled strip containing the first local shape defect and the second local shape defect based on the second-order shape component and the third-order shape component, so that the local shape of the cold-rolled strip meets a preset local shape standard, includes: The second component to be adjusted is determined based on the deviations between the second-order plate shape component and the third-order plate shape component and the target plate shape component set in the preset local plate shape standard. Based on the plate shape control matrix, determine the second plate shape control method corresponding to the second component to be adjusted and the second adjustment amount of the second plate shape control method; The rolling mill is controlled to adjust the shape of the cold-rolled strip according to the second control method and the second adjustment amount.

[0011] Optionally, the second control means includes at least one of segmented cooling, roll profile, and roll lateral movement.

[0012] Optionally, determining the second plate shape control method corresponding to the second component to be adjusted and the second adjustment amount of the second plate shape control method according to the plate shape control matrix includes: Based on the second component to be adjusted, the second plate shape control method and the second adjustment amount of the second plate shape control method are determined in the plate shape control matrix based on the plate shape control evaluation model; The plate shape control evaluation model is as follows: ; in, The expression represents the control effect, where m represents the number of second control quantities and the number of plate shape changes under the second control quantities, wherein each second control quantity corresponds to a second plate shape control method, and i represents the i-th plate shape change. This represents the w-th second adjustment. This represents the effect coefficient of the w-th second adjustment on the i-th plate shape change. This refers to the remaining shape component in the cold-rolled strip after the overall shape of the cold-rolled strip meets the preset overall shape standard.

[0013] Optionally, in the process of controlling the rolling mill to adjust the shape of the cold-rolled strip or controlling the rolling mill to independently adjust the regions in the cold-rolled strip where the first local shape defect and the second local shape defect exist, the method further includes: The rolling mill uses symmetrical and / or asymmetrical control quantities to adjust the shape of the cold-rolled strip.

[0014] Optionally, after controlling the rolling mill to independently adjust the regions in the cold-rolled strip containing the first local shape defect and the second local shape defect based on the second-order shape component and the third-order shape component, the method further includes: Obtain the actual shape components of the cold-rolled strip after adjustment, store the actual shape components as historical samples in a standard sample library, perform cluster analysis based on several historical samples in the standard sample library, and determine the standard target curve corresponding to each shape component of the cold-rolled strip; and / or The actual adjustment amount and actual shape component of the cold-rolled strip are obtained, and the actual adjustment amount and actual shape component are input into the neural network model for training. The influence coefficients in the shape control matrix are updated based on the trained model parameters.

[0015] A second aspect of this application provides a cold-rolled strip shape control device, comprising: An acquisition unit is used to acquire multi-order shape components of cold-rolled strip steel. The multi-order shape components include a first-order shape component, a second-order shape component, and a third-order shape component. The first-order shape component is used to reflect the overall shape defect of the cold-rolled strip steel. The second-order shape component is used to reflect the first local shape defect of the cold-rolled strip steel. The third-order shape component is used to reflect the second local shape defect of the cold-rolled strip steel. The complexity of the second local shape defect is greater than that of the first local shape defect. The first control unit is used to control the rolling mill to adjust the shape of the cold-rolled strip steel according to the first order shape component, so that the overall shape of the cold-rolled strip steel meets the preset overall shape standard. The second control unit is used to control the rolling mill to independently adjust the regions in the cold-rolled strip where the first local shape defect and the second local shape defect exist, based on the second-order shape component and the third-order shape component, so that the local shape of the cold-rolled strip meets the preset local shape standard.

[0016] A third aspect of this application provides a computer-readable storage medium storing at least one computer program instruction, which is loaded and executed by a processor to perform the operations as described in any of the methods in the first aspect.

[0017] A fourth aspect of this application provides an electronic device including one or more processors and one or more memories, wherein at least one piece of program code is stored in the one or more memories, and the at least one piece of program code is loaded and executed by the one or more processors to perform the operation as described in any of the methods in the first aspect.

[0018] The one or more technical solutions provided in the embodiments of the present invention achieve at least the following technical effects or advantages: The cold-rolled strip shape control method of this application includes: acquiring multi-order shape components of the cold-rolled strip, the multi-order shape components including a first-order shape component, a second-order shape component, and a third-order shape component, wherein the first-order shape component is used to reflect the overall shape defect of the cold-rolled strip, the second-order shape component is used to reflect the first local shape defect of the cold-rolled strip, and the third-order shape component is used to reflect the second local shape defect of the cold-rolled strip, wherein the complexity of the second local shape defect is greater than that of the first local shape defect; controlling the rolling mill to adjust the shape of the cold-rolled strip according to the first-order shape component so that the overall shape of the cold-rolled strip meets a preset overall shape standard; and controlling the rolling mill to independently adjust the regions in the cold-rolled strip where the first local shape defect and the second local shape defect exist according to the second-order shape component and the third-order shape component so that the local shape of the cold-rolled strip meets a preset local shape standard. Therefore, the embodiments of this application construct multiple order plate shape components for cold-rolled strip steel, thereby reflecting not only the overall defects of cold-rolled strip steel, but also more local defects. After adjusting the overall plate shape components, the local plate shape components are then adjusted to achieve fine control and improve the plate shape control accuracy of cold-rolled strip steel.

[0019] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0020] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application. It is obvious that the drawings described below are merely some embodiments of this application, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort. In the drawings: Figure 1 A flowchart of the cold-rolled strip shape control method according to an embodiment of this application is shown; Figure 2 A structural diagram of the cold-rolled strip shape control device according to an embodiment of this application is shown; Figure 3 A schematic diagram of the structure of a computer system suitable for implementing the electronic device of the present application is shown. Detailed Implementation

[0021] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0022] Furthermore, the described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. Numerous specific details are provided in the following description to give a thorough understanding of embodiments of this application. However, those skilled in the art will recognize that the technical solutions of this application can be practiced without one or more of the specific details, or other methods, components, apparatuses, steps, etc., can be employed. In other instances, well-known methods, apparatuses, implementations, or operations are not shown or described in detail to avoid obscuring various aspects of this application.

[0023] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different models and / or processor devices and / or microcontroller devices.

[0024] The flowcharts shown in the accompanying drawings are merely illustrative and do not necessarily include all content and operations / steps, nor do they necessarily have to be performed in the described order. For example, some operations / steps can be broken down, while others can be combined or partially combined; therefore, the actual execution order may change depending on the specific circumstances.

[0025] It should also be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such uses of these terms can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described.

[0026] With the increasing prevalence of high-end industrial applications, the demand for high-quality and large-format cold-rolled strip is growing. However, the thinner and larger the strip, the more difficult it is to control its shape. During the rolling deformation process, problems such as tearing, breakage, waviness, and wrinkling are prone to occur, seriously affecting the product quality and technical specifications of cold-rolled strip.

[0027] Currently, the main types of rolling mills used for producing cold-rolled strip include four-roll, six-roll, eight-roll, sixteen-roll, and twenty-roll mills. Taking the most common six-roll cold-rolled strip mill as an example, the strip shape control methods mainly include tilting rolls, bending rolls, lateral movement, and segmented cooling, which can be used to adjust typical strip shape characteristics such as single-sided wave, double-sided wave, middle wave, and rib wave (1 / 4 wave or 3 / 4 wave).

[0028] To date, for cold-rolled strips with a thickness of 0.2mm or more, the aforementioned typical shape characteristics can be adjusted to within 4I or even within 2I. For cold-rolled strips with a thickness of 0.1mm-0.2mm, they can also be adjusted to within 6I or even 4I. For cold-rolled strips with a thickness of 0.1mm, the difficulty of shape control increases dramatically. Moreover, with the increase in width, various composite and local wavy shapes occur frequently, leading to instability in the shape control process. The shape indicators often fail to meet the requirements, necessitating further system upgrades and process optimization.

[0029] To address the aforementioned issues, related technologies employ two approaches. First, they utilize new rolling mills for structural upgrades, such as replacing eight-roll, sixteen-roll, or twenty-roll mills to enhance shape control capabilities. This approach involves significant modifications, high costs, and considerable difficulty, often necessitating the construction of new equipment. Second, they leverage the existing functions of four-roll and six-roll mills, employing mechanistic models and big data intelligent models for process optimization. This enhances the mill's inherent control capabilities, improving the shape control range and performance indicators of the original control system. This approach is highly operable and low-cost, as functional improvements can be achieved using model systems. However, existing models struggle to address shape defects such as complex or localized waviness.

[0030] In view of this, the present application provides a method for controlling the shape of cold-rolled strip steel, which can at least to a certain extent achieve fine control of the shape of cold-rolled strip steel and improve the shape control accuracy of cold-rolled strip steel.

[0031] The method for controlling the shape of cold-rolled strip steel according to embodiments of this application will be described below with reference to the accompanying drawings.

[0032] Figure 1 A flowchart of the cold-rolled strip shape control method according to an embodiment of this application is shown.

[0033] The first aspect of this application provides a method for controlling the shape of cold-rolled strip steel, including but not limited to: Step S10. Obtain multi-order shape components of cold-rolled strip steel, the multi-order shape components including a first-order shape component, a second-order shape component and a third-order shape component, wherein the first-order shape component is used to reflect the overall shape defect of the cold-rolled strip steel, the second-order shape component is used to reflect the first local shape defect of the cold-rolled strip steel, and the third-order shape component is used to reflect the second local shape defect of the cold-rolled strip steel, wherein the complexity of the second local shape defect is greater than the complexity of the first local shape defect; In some embodiments, the multi-order plate shape components can be described by multi-order polynomials, for example, using polynomials of degree 8 or higher to describe deformation components of different orders, wherein the first-order plate shape component can be of order 1-2, the second-order plate shape component can be of order 3-4, and the third-order plate shape component can be of order 5 or higher.

[0034] It should be noted that the first-order, second-order, and third-order shape components can be global mathematical decompositions of the stress distribution curve of the cold-rolled strip across the entire width of the strip. Each shape component attempts to describe the characteristics of the entire curve using a different basic waveform.

[0035] It is understandable that the shape of cold-rolled strip steel measured by the shape meter is a complete transverse stress distribution curve, for example, from the operating side to the transmission side. Based on this, a high-order polynomial is applied to the transverse stress distribution curve. After fitting, a polynomial containing multiple shape components is obtained, each of which is a curve defined over the entire strip width. Therefore, the actual shape stress curve is composed of the superposition of multiple shape components, i.e., multi-order shape components.

[0036] It should be noted that the overall shape defects of cold-rolled strip steel include, but are not limited to: edge wave defects and center wave defects; the first local shape defects include, but are not limited to: composite wave shape and asymmetrical wave shape; the second local shape defects include, but are not limited to: broken edge wave, local center wave, irregular wave, rib wave (1 / 4 rib wave or 1 / 3 rib wave), composite edge and center wave, composite edge and rib wave, flat and waveless, etc.

[0037] In some embodiments, the multi-order plate shape components are characterized by the following formula: ; ; in, This represents the coordinates of the cold-rolled strip in the width direction. This represents the multi-order plate shape component, where u represents the total number of orders. This represents the basic board shape pattern of the k-th order. Represents the k-th order plate shape component. This represents the basic plate shape pattern of the (k-1)th order.

[0038] Therefore, the above formula can express the shape components of cold-rolled strip at any order, thus encompassing all shape information of cold-rolled strip.

[0039] Step S20. Based on the first-order strip shape component, control the rolling mill to adjust the strip shape of the cold-rolled strip so that the overall strip shape of the cold-rolled strip meets the preset overall strip shape standard; In some embodiments, before controlling the rolling mill to adjust the shape of the cold-rolled strip according to the first-order shape component, the method further includes: Obtain the shape control matrix of the cold-rolled strip, wherein the shape control matrix includes multiple influence coefficients, each influence coefficient being the influence coefficient of the adjustment amount of one shape control means of the rolling mill on the shape component of one order of the cold-rolled strip.

[0040] Understandably, by utilizing the first, second, and third shape components, symmetrical and asymmetrical control quantities of rolling mill shape control methods (such as tilting rolls, bending rolls, lateral movement, roll profile, and segmented cooling) can be obtained. On the one hand, the mechanism of shape components and control quantities can be predicted through a rolling model; on the other hand, intelligent training of shape components and control quantities can be performed using on-site measured data. This represents the adjustment amount of the j-th plate shape control method. For the i-th plate shape component The influence coefficient.

[0041] For each plate shape control method, when a certain adjustment amount is applied, it will affect... The q plate shape component coefficients, combined with u plate shape control methods, form a... Plate shape control matrix , is represented as: ; In some embodiments, controlling the rolling mill to adjust the shape of the cold-rolled strip according to the first-order shape component, so that the overall shape of the cold-rolled strip meets a preset overall shape standard, includes: Step S201. Determine the first component to be adjusted based on the deviation between the first-order plate shape component and the target plate shape component set in the preset overall plate shape standard; Step S202. Based on the plate shape control matrix, determine the first plate shape control method corresponding to the first component to be adjusted and the first adjustment amount of the first plate shape control method; Step S203. Control the rolling mill to adjust the shape of the cold-rolled strip according to the first control means and the first adjustment amount.

[0042] In some embodiments, the first control means includes a bending roller and at least one of the bending rollers.

[0043] Understandably, based on the extracted first-order strip shape component coefficients, the system compares them with a preset global strip shape target (e.g., setting the target value of each lower-order component to zero) to calculate the current lower-order strip shape deviation. Subsequently, a pre-established strip shape control matrix is ​​invoked, which explicitly defines the influence coefficients of various basic strip shape control methods (such as work roll bending force, intermediate roll bending force, roll tilt, etc.) on the lower-order components. Through the inverse operation or optimization algorithm of this matrix, a set of optimal symmetrical control quantities (e.g., bending force) and asymmetrical control quantities (e.g., roll tilt) are solved, and this solution is used as the setpoint and sent to the actuator. Based on this, the control system first drives the mill to apply bending force and tilt adjustment to correct the overall profile of the strip. During this process, strip shape feedback is continuously monitored, forming a closed-loop control circuit, dynamically fine-tuning the control quantities until the measured value of the first-order strip shape component stably enters the target tolerance range, indicating that the macroscopic strip shape has been effectively controlled. The completion of this step ensures the global flatness of the strip and avoids new overall deformation caused by subsequent adjustments to higher-order defects.

[0044] Step S30. Based on the second-order strip shape component and the third-order strip shape component, control the rolling mill to independently adjust the regions in the cold-rolled strip where the first local strip shape defect and the second local strip shape defect exist, so that the local strip shape of the cold-rolled strip meets the preset local strip shape standard.

[0045] In some embodiments, controlling the rolling mill to independently adjust the regions in the cold-rolled strip where the first local shape defect and the second local shape defect exist, based on the second-order shape component and the third-order shape component, so that the local shape of the cold-rolled strip meets a preset local shape standard, includes: Step S301. Determine the second component to be adjusted based on the deviation between the second-order plate shape component and the third-order plate shape component and the target plate shape component set in the preset local plate shape standard; Understandably, after adjusting the first-order plate shape components, the second-order and third-order plate shape components are further adjusted. The second-order (e.g., 3-4 orders, corresponding to wider local waviness) and the third-order (e.g., 5 orders or higher, corresponding to fine defects such as broken edges and waviness) are adjusted. These plate shape components are compared with a preset local plate shape standard. This standard is typically not a single numerical value, but rather a tolerance zone set for different order components. The deviation between the coefficient of each higher-order component and its corresponding target value is calculated. Determining the second component to be adjusted is not a simple selection of all components, but a dynamic decision-making process. For example, the magnitude of each deviation and its weight in the final quality are evaluated, and the component combination that exceeds the tolerance and has the greatest impact on subsequent processing is selected as the subset that needs to be focused on in the current adjustment cycle. This achieves the transition from full-scale adjustment to precise adjustment of key defects.

[0046] Step S302. Based on the plate shape control matrix, determine the second plate shape control means corresponding to the second component to be adjusted and the second adjustment amount of the second plate shape control means; In some embodiments, determining the second plate shape control means corresponding to the second component to be adjusted and the second adjustment amount of the second plate shape control means according to the plate shape control matrix includes: Based on the second component to be adjusted, the second plate shape control method and the second adjustment amount of the second plate shape control method are determined in the plate shape control matrix based on the plate shape control evaluation model; The plate shape control evaluation model is as follows: ; in, The expression represents the control effect, where m represents the number of second control quantities and the number of plate shape changes under the second control quantities, wherein each second control quantity corresponds to a second plate shape control method, and i represents the i-th plate shape change. This represents the w-th second adjustment. This represents the effect coefficient of the w-th second adjustment on the i-th plate shape change. This refers to the remaining shape component in the cold-rolled strip after the overall shape of the cold-rolled strip meets the preset overall shape standard.

[0047] Understandably, more precise adjustments to local shape components, especially ultra-high-order local shape components, are necessary. These components exhibit distinct local characteristics, such as edge waviness and center waviness, within a narrow range, manifesting as obvious shape defects that cannot be concealed even under high tension. Therefore, independent control of these high- and ultra-high-order shape components is required. After adjusting the low-order shape components, the combined effect of symmetrical and asymmetrical control quantities is used to obtain a low-order shape state that meets the requirements. Then, segmented cooling combined with roll lateral movement is used to individually adjust the high- and ultra-high-order shape components to meet the final shape index. Whether the final shape index is met can be determined by a shape evaluation model. This model provides a second shape control method and a second adjustment amount for meeting the final shape index.

[0048] In some embodiments, the second control means includes at least one of segmented cooling, roll profile, and roll lateral movement.

[0049] Step S303. Control the rolling mill to adjust the shape of the cold-rolled strip according to the second control means and the second adjustment amount.

[0050] For example, a segmented cooling system applies differentiated spray cooling to specific width areas of the strip, fine-tuning the roll gap by altering local thermal crown, thereby eliminating target local defects. The roll traversing mechanism operates synchronously, changing the axial position of the work rolls or intermediate rolls to optimize the roll gap shape to coordinate with cooling adjustments. Because thermal regulation has a lag, it can be adjusted multiple times—through detection, feedback, and adjustment—to improve adjustment accuracy.

[0051] Therefore, the hot roll type time delay compensation takes into account the time delay effect of the hot roll type, realizes the coupled control of segmented cooling and roll lateral movement, avoids the induction of changes in low-order shape components when adjusting high-order and ultra-high-order shape components, and reduces the phenomenon of neglecting one aspect for another.

[0052] In some embodiments, during the process of controlling the rolling mill to adjust the shape of the cold-rolled strip or controlling the rolling mill to independently adjust the regions in the cold-rolled strip where the first local shape defect and the second local shape defect exist, the method further includes: The rolling mill uses symmetrical and / or asymmetrical control quantities to adjust the shape of the cold-rolled strip.

[0053] Understandably, in the process of adjusting strip shape deviation, whether targeting overall or local defects, precise control can be achieved through the coordinated combination of symmetrical and asymmetrical control quantities. Symmetrical control quantities mainly refer to control methods that act equally and in the same direction on the transmission and operation sides of the rolling mill, such as the symmetrical bending force of the work roll and the intermediate roll. Their main function is to adjust the overall crown (quadratic curve) of the strip cross-section, effectively correcting macroscopic symmetrical defects such as center waves or edge waves. Asymmetrical control quantities refer to control methods that act unequally or in opposite directions on both sides of the rolling mill, such as roll tilting, single-sided bending force adjustment, or asymmetrical cooling distribution. Their main function is to correct the linear tilt (primary component) of the strip and complex asymmetrical local waves, such as strip deviation, wedge shape, local crown, local wear, and local thermal crown. In actual control, based on the mathematical decomposition results of the strip shape deviation (symmetrical and asymmetrical components), the combination of these two types of control quantities is dynamically calculated and allocated, thereby achieving decoupled strip shape control from macroscopic morphology to microscopic contour.

[0054] As cold-rolled strips become wider and thinner, the shape problem becomes more prominent. Traditional control methods are difficult to implement, lack coupling analysis, and the mechanism model cannot fully predict the logical relationship between various parameters. The intelligent model cannot establish a high-precision mathematical model, which makes the shape control of cold-rolled strips with large width-to-thickness ratio a persistent challenge.

[0055] In some embodiments, after controlling the rolling mill to independently adjust the regions in the cold-rolled strip where the first local shape defect and the second local shape defect exist based on the second-order shape component and the third-order shape component, the method further includes: Step S40. Obtain the actual shape components of the cold-rolled strip after adjustment, store the actual shape components as historical samples in a standard sample library, perform cluster analysis based on several historical samples in the standard sample library, and determine the standard target curve corresponding to each shape component of the cold-rolled strip; and / or Step S30. Obtain the actual adjustment amount and actual shape component of the cold-rolled strip, input the actual adjustment amount and the actual shape component into the neural network model for training, and update the influence coefficient in the shape control matrix based on the trained model parameters.

[0056] Understandably, after independently adjusting the local strip shape, an adaptive self-learning loop can be used to continuously improve the control accuracy. This loop includes: First, dynamic optimization of the standard target curve based on big data. The actual strip shape components after this rolling process (i.e., the coefficient values ​​of each order achieved after adjustment) are stored as a complete historical sample in the standard sample library. As data accumulates, the system uses clustering algorithms (such as K-means) to analyze massive samples and automatically identify recurring, stable, high-quality strip shape pattern clusters. For each cluster, the average strip shape curve of its best sample or the ideal curve set by the process is determined as the dynamic standard target curve for that type of working condition. This means that the standard target is not fixed, but intelligently matched and evolved according to the clustering results of steel grade, specification, and defect pattern, providing a more accurate benchmark for subsequent control. Second, online evolution of the control model based on neural networks. The actual adjustment amounts applied to achieve the desired plate shape (such as the cooling opening of each section, changes in bending roller force, etc.) are recorded synchronously and used to form an "input and output" training pair with the corresponding actual plate shape components. This pair is then input into a pre-defined neural network model (e.g., deep feedforward neural network, convolutional neural network, long short-term memory network, or recurrent neural network) for training. This network continuously adjusts its internal weights by learning the complex nonlinear mapping between control actions and plate shape response under massive operating conditions. After training, the new knowledge contained in the network is used to update the influence coefficients in the plate shape control matrix online, enabling the originally mechanism-based static matrix to dynamically adapt to equipment conditions and process changes, thus achieving increasingly accurate adjustments.

[0057] Based on the above disclosure, the embodiments of this application can achieve more precise closed-loop control of low-order shape, and implement quantitative control of various complex shape components using symmetric control quantities and asymmetric control. Furthermore, it can obtain high-order and ultra-high-order shape component information, avoiding the neglect of high-order and ultra-high-order shape components by traditional pattern recognition. Since most local shape features have ultra-high-order shape component characteristics, classifying shape components into low-order, high-order, and ultra-high-order categories helps to implement quantitative control with different weighting factors for different shape component characteristics, improving control efficiency and stability. Simultaneously, for various local shape features, using rolling mechanism models and on-site big data models, it is possible to better perform big data sample clustering analysis and adaptive self-learning training for different shape components, improving the fine-grained control of shape and better enhancing the shape difference index of cold-rolled strip.

[0058] Figure 2 A structural diagram of the cold-rolled strip shape control device according to an embodiment of this application is shown.

[0059] A second aspect of this application provides a cold-rolled strip shape control device 200, comprising: The acquisition unit 201 is used to acquire multi-order shape components of cold-rolled strip steel. The multi-order shape components include a first-order shape component, a second-order shape component, and a third-order shape component. The first-order shape component is used to reflect the overall shape defect of the cold-rolled strip steel. The second-order shape component is used to reflect the first local shape defect of the cold-rolled strip steel. The third-order shape component is used to reflect the second local shape defect of the cold-rolled strip steel. The complexity of the second local shape defect is greater than that of the first local shape defect. The first control unit 202 is used to control the rolling mill to adjust the shape of the cold-rolled strip steel according to the first order shape component, so that the overall shape of the cold-rolled strip steel meets the preset overall shape standard. The second control unit 203 is used to control the rolling mill to independently adjust the regions in the cold-rolled strip where the first local shape defect and the second local shape defect exist, based on the second-order shape component and the third-order shape component, so that the local shape of the cold-rolled strip meets the preset local shape standard.

[0060] A third aspect of this application provides a computer-readable storage medium storing at least one computer program instruction, which is loaded and executed by a processor to perform the operations as described in any of the methods in the first aspect.

[0061] Computer-readable storage media may be portable compact disc read-only memory (CD-ROM) and include program code, and may run on a terminal device, such as a personal computer. However, the computer-readable storage medium of this application is not limited thereto. In this application, the readable storage medium may be any tangible medium that contains or stores a program that may be used by or in conjunction with an instruction execution system, apparatus, or device.

[0062] Readable storage media can be, for example, but not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: electrical connections having one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, and portable compact disk read-only memory (CD). ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0063] Program code for performing the operations of this application can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can execute entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0064] A fourth aspect of this application provides an electronic device including one or more processors and one or more memories, wherein at least one piece of program code is stored in the one or more memories, and the at least one piece of program code is loaded and executed by the one or more processors to perform the operation as described in any of the methods in the first aspect.

[0065] like Figure 3 As shown, the electronic device 400 is manifested in the form of a general-purpose computing device. The components of the electronic device 400 may include, but are not limited to: at least one processing unit 410, at least one storage unit 420, and a bus 430 connecting different system components (including storage unit 420 and processing unit 410).

[0066] The storage unit stores program code, which can be executed by the processing unit 410, causing the processing unit 410 to perform the steps described in the "Embodiment Method" section above according to various exemplary embodiments of this application.

[0067] Storage unit 420 may include readable media in the form of volatile storage units, such as random access memory (RAM) 421 and / or cache 422, and may further include read-only memory (ROM) 423.

[0068] Storage unit 420 may also include a program / utility 424 having a set (at least one) of program modules 425, such program modules 425 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each or some combination of these examples may include an implementation of a network environment.

[0069] Bus 430 can represent one or more of several types of bus structures, including a memory cell bus or memory cell controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any of the various bus structures.

[0070] Electronic device 400 can also communicate with one or more external devices 500 (e.g., keyboard, pointing device, Bluetooth device, etc.), and with one or more devices that enable a user to interact with electronic device 400, and / or with any device that enables electronic device 400 to communicate with one or more other computing devices (e.g., router, modem, etc.). This communication can be performed through I / O (input / output) interface 450, which can also be connected to display unit 440 to display the communication content. Furthermore, electronic device 400 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public network, such as the Internet) through network adapter 460. As shown, network adapter 460 communicates with other modules of electronic device 400 via bus 430. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with electronic device 400, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0071] The functions described herein can be implemented in hardware, software executed by a processor, firmware, or any combination thereof. If implemented in software executed by a processor, the functions can be stored as one or more instructions or codes on or transmitted via a computer-readable medium. Other examples and embodiments are within the scope and spirit of this invention and the appended claims. For example, due to the nature of software, the functions described above can be implemented using software executed by a processor, hardware, firmware, hardwired, or any combination thereof. Furthermore, the functional units can be integrated into a single processing unit, or each unit can exist physically separately, or two or more units can be integrated into a single unit.

[0072] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual couplings, direct couplings, or communication connections may be through some interfaces; indirect couplings or communication connections between units or modules may be electrical or other forms.

[0073] The units described as separate components may or may not be physically separate. Similarly, the components of the control device may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0074] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0075] The above description is merely an embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for controlling the shape of cold-rolled strip steel, characterized in that, include: A multi-order shape component of cold-rolled strip steel is obtained. The multi-order shape component includes a first-order shape component, a second-order shape component, and a third-order shape component. The first-order shape component is used to reflect the overall shape defect of the cold-rolled strip steel. The second-order shape component is used to reflect the first local shape defect of the cold-rolled strip steel. The third-order shape component is used to reflect the second local shape defect of the cold-rolled strip steel. The complexity of the second local shape defect is greater than that of the first local shape defect. Based on the first-order strip shape component, the rolling mill is controlled to adjust the strip shape of the cold-rolled strip so that the overall strip shape of the cold-rolled strip meets the preset overall strip shape standard. Based on the second-order shape component and the third-order shape component, the rolling mill is controlled to independently adjust the regions in the cold-rolled strip where the first local shape defect and the second local shape defect exist, so that the local shape of the cold-rolled strip meets the preset local shape standard.

2. The method according to claim 1, characterized in that, The multi-order plate shape components are characterized by the following formula: ； ； in, This represents the coordinates of the cold-rolled strip in the width direction. This represents the multi-order plate shape component, where u represents the total number of orders. This represents the basic board shape pattern of the k-th order. Represents the k-th order plate shape component. This represents the basic plate shape pattern of the (k-1)th order.

3. The method according to claim 1, characterized in that, Before controlling the rolling mill to adjust the shape of the cold-rolled strip according to the first-order shape component, the method further includes: Obtain the shape control matrix of the cold-rolled strip, wherein the shape control matrix includes multiple influence coefficients, each influence coefficient being the influence coefficient of the adjustment amount of one shape control means of the rolling mill on the shape component of one order of the cold-rolled strip.

4. The method according to claim 3, characterized in that, The step of controlling the rolling mill to adjust the shape of the cold-rolled strip according to the first-order shape component, so that the overall shape of the cold-rolled strip meets the preset overall shape standard, includes: The first component to be adjusted is determined based on the deviation between the first-order plate shape component and the target plate shape component set in the preset overall plate shape standard. Based on the plate shape control matrix, determine the first plate shape control method corresponding to the first component to be adjusted and the first adjustment amount of the first plate shape control method; The rolling mill is controlled to adjust the shape of the cold-rolled strip according to the first control method and the first adjustment amount.

5. The method according to claim 4, characterized in that, The first control means includes a bending roller and at least one of the bending rollers.

6. The method according to claim 3, characterized in that, The step of controlling the rolling mill to independently adjust the regions in the cold-rolled strip containing the first local shape defect and the second local shape defect, based on the second-order shape component and the third-order shape component, so that the local shape of the cold-rolled strip meets a preset local shape standard, includes: The second component to be adjusted is determined based on the deviations between the second-order plate shape component and the third-order plate shape component and the target plate shape component set in the preset local plate shape standard. Based on the plate shape control matrix, determine the second plate shape control method corresponding to the second component to be adjusted and the second adjustment amount of the second plate shape control method; The rolling mill is controlled to adjust the shape of the cold-rolled strip according to the second control method and the second adjustment amount.

7. The method according to claim 6, characterized in that, The second control method includes at least one of segmented cooling, roll profile, and roll lateral movement.

8. The method according to claim 6, characterized in that, The step of determining the second plate shape control method corresponding to the second component to be adjusted and the second adjustment amount of the second plate shape control method according to the plate shape control matrix includes: Based on the second component to be adjusted, the second plate shape control method and the second adjustment amount of the second plate shape control method are determined in the plate shape control matrix based on the plate shape control evaluation model; The plate shape control evaluation model is as follows: ； in, The expression represents the control effect, where m represents the number of second control quantities and the number of plate shape changes under the second control quantities, wherein each second control quantity corresponds to a second plate shape control method, and i represents the i-th plate shape change. This represents the w-th second adjustment. This represents the effect coefficient of the w-th second adjustment on the i-th plate shape change. This refers to the remaining shape component in the cold-rolled strip after the overall shape of the cold-rolled strip meets the preset overall shape standard.

9. The method according to claim 1, characterized in that, In the process of controlling the rolling mill to adjust the shape of the cold-rolled strip or controlling the rolling mill to independently adjust the regions in the cold-rolled strip where the first local shape defect and the second local shape defect exist, the method further includes: The rolling mill uses symmetrical and / or asymmetrical control quantities to adjust the shape of the cold-rolled strip.

10. The method according to claim 3, characterized in that, After controlling the rolling mill to independently adjust the regions in the cold-rolled strip containing the first local shape defect and the second local shape defect based on the second-order shape component and the third-order shape component, the method further includes: Obtain the actual shape components of the cold-rolled strip after adjustment, store the actual shape components as historical samples in a standard sample library, perform cluster analysis based on several historical samples in the standard sample library, and determine the standard target curve corresponding to each shape component of the cold-rolled strip; and / or The actual adjustment amount and actual shape component of the cold-rolled strip are obtained, and the actual adjustment amount and actual shape component are input into the neural network model for training. The influence coefficients in the shape control matrix are updated based on the trained model parameters.

Images