Strip steel rolling method and related equipment

Abstract

The invention discloses a strip steel rolling method and related equipment, and relates to the technical field of metallurgy, the method comprises the following steps: before first-pass rolling, default gain parameters are input into a target single-stand rolling mill, and the target single-stand rolling mill is used for carrying out first-pass rolling on target strip steel; before rolling of the Nth pass, the current reduction rate of the target strip steel is obtained, and N is an integer larger than 1; model input parameters are substituted into the correction relation model, a current correction coefficient corresponding to rolling of the Nth pass is obtained, and the model input parameters comprise the current reduction rate; the corrected gain parameter is input into the target single-stand rolling mill, the target strip steel is subjected to Nth-pass rolling through the target single-stand rolling mill, and the corrected gain parameter is a gain parameter obtained through calculation according to the default gain parameter and the current correction coefficient. According to the method, the gain parameters are dynamically adjusted to adapt to the current states of the target strip steel in different rolling passes, and the rolling precision of the strip steel is improved.

Description

Technical Field

[0001] The present application relates to the field of metallurgical technology, and more specifically, to a strip steel rolling method and related equipment. Background Art

[0002] With the rapid development of modern manufacturing industry, strip rolling is a key link in the steel production process. The continuous improvement of its technical level is of great significance to improving production efficiency, ensuring product quality and reducing production costs. As a key measure of the quality of cold-rolled products, thickness accuracy is of self-evident importance. It is usually strictly controlled within ±20μm, and for ultra-thin products, it is required to reach the ultimate accuracy of ±10μm. Therefore, thickness control technology is not only the core competitiveness in the field of strip rolling, but also a key link to ensure product quality and market competitiveness. In the strip rolling process, single-stand rolling mills (especially reciprocating reversible rolling mills) play a vital role. This type of rolling mill is equipped with two left and right coilers, which flexibly switch the uncoiling and coiling functions to support continuous multi-pass rolling operations. Each pass represents a complete rolling cycle, and it usually takes 5 to 9 passes to complete the rolling task, and the product is then offline. During the entire rolling process, automatic thickness control strategies are implemented in each pass to accurately lock the actual thickness at the preset target value to ensure the thickness accuracy of the final product.

[0003] However, although the traditional thickness control algorithm is relatively mature, its core - the setting of gain parameters - has limitations. Existing gain parameters are often calculated based on static parameters such as raw material thickness, target finished product thickness, strip width and material yield strength, and remain unchanged during the production cycle of a coil of steel. This fixed gain parameter setting method is powerless when faced with the actual situation that the work hardening of strip steel intensifies with the increase in the number of passes. The intensification of work hardening makes it increasingly difficult to thin the strip, and the accuracy of thickness control decreases accordingly, which ultimately leads to product thickness exceeding specification requirements and an increase in scrap rate. In other words, there is a technical problem of low rolling accuracy of strip steel in the related technology. Summary of the invention

[0004] A series of simplified concepts are introduced in the summary of the invention, which will be further described in detail in the detailed description. The summary of the invention of this application does not mean to attempt to define the key features and essential technical features of the technical solution claimed for protection, nor does it mean to attempt to determine the scope of protection of the technical solution claimed for protection.

[0005] The strip rolling method and related devices provided in the present application can improve the rolling accuracy of the strip by dynamically adjusting the gain parameters to adapt to the current state of the target strip in different rolling passes.

[0006] In a first aspect, the present application provides a strip rolling method, comprising: before the first rolling pass, inputting default gain parameters into a target single-stand rolling mill, and performing the first rolling pass on the target strip by the target single-stand rolling mill; before the Nth rolling pass, obtaining the current reduction rate of the target strip, wherein N is an integer greater than 1; substituting model input parameters into a correction relationship model to obtain a current correction coefficient corresponding to the Nth rolling pass, wherein the model input parameters include the current reduction rate; inputting correction gain parameters into the target single-stand rolling mill, and performing the Nth rolling pass on the target strip by the target single-stand rolling mill, wherein the correction gain parameters are gain parameters calculated based on the default gain parameters and the current correction coefficients.

[0007] In a feasible implementation manner, the strip rolling method also includes: acquiring historical rolling process data, wherein the historical rolling process data includes historical thickness control errors, historical reduction rates, and historical correction coefficients; screening out model training data based on the historical thickness control errors, wherein the model training data includes model training feature data and model training label data, the model training feature data includes a training reduction rate screened from the historical reduction rates, and the model training label data includes a training correction coefficient screened from the historical correction coefficients; performing model training based on the model training data to obtain the correction relationship model.

[0008] In a feasible implementation manner, the filtering out model training data according to the historical thickness control error includes: determining historical rolling process data corresponding to the rolling process in which the thickness control error is less than a preset error threshold as the model training data.

[0009] In a feasible implementation manner, the historical rolling process data also includes the historical pass number; the model training feature data also includes the training pass number selected from the historical pass number; and the model input parameter also includes N.

[0010] In a feasible implementation manner, the model training is performed according to the model training data to obtain the corrected relationship model, including: linearly fitting the training depression rate and the training correction coefficient according to the number of training channels to obtain a fitting function corresponding to the number of training channels, and determining the fitting function as the corrected relationship model.

[0011] In a feasible implementation, the historical rolling process data also includes historical strip temperature; the model training feature data also includes training strip temperature selected from the historical strip temperature; and the model input parameters also include the current strip temperature of the target strip.

[0012] In a feasible implementation manner, obtaining the current reduction rate of the target strip includes: obtaining the raw material thickness and current thickness of the target strip; calculating the thickness difference between the raw material thickness and the current thickness, and determining the ratio of the thickness difference to the raw material thickness as the current reduction rate.

[0013] In the second aspect, the present application also provides a strip rolling device, comprising: a first rolling unit, used to input default gain parameters into a target single-stand rolling mill before the first rolling pass, and perform the first rolling on the target strip through the target single-stand rolling mill; a reduction rate calculation unit, used to obtain the current reduction rate of the target strip before the Nth rolling pass, wherein N is an integer greater than 1; a correction coefficient determination unit, used to substitute model input parameters into a correction relationship model to obtain a current correction coefficient corresponding to the Nth rolling pass, wherein the model input parameters include the current reduction rate; a second rolling unit, used to input correction gain parameters into the target single-stand rolling mill, and perform the Nth rolling on the target strip through the target single-stand rolling mill, wherein the correction gain parameters are gain parameters calculated based on the default gain parameters and the current correction coefficients.

[0014] In a third aspect, the present application further provides an electronic device, comprising: a memory and a processor, wherein the processor is configured to implement the steps of the strip rolling method described in the first aspect when executing a computer program stored in the memory.

[0015] In a fourth aspect, the present application further provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the strip rolling method described in the first aspect.

[0016] In a fifth aspect, the present application also provides a computer program product, including a computer program or computer executable instructions, which, when executed by a processor, implements the strip rolling method provided in an embodiment of the present application.

[0017] In summary, the present application can more accurately control the key parameters such as rolling force and rolling speed during the rolling process by calculating and applying the corrected gain parameters in real time according to the current reduction rate of the target strip before the Nth rolling pass, thereby improving the accuracy of key quality indicators such as thickness, width, and straightness of the strip after rolling; dynamically adjusting the gain parameters can ensure that the rolling mill is always in the optimal working state in different rolling passes, avoiding energy waste or excessive equipment wear due to fixed parameters, and accurate rolling control can also reduce the scrap rate caused by rolling defects, thereby improving overall production efficiency and economic benefits. In summary, the strip rolling method provided by the present application improves the rolling accuracy of the strip by dynamically adjusting the gain parameters to adapt to the current state of the target strip in different rolling passes. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present specification. Also, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0019] Figure 1 A schematic diagram of a process flow of a strip steel rolling method provided in an embodiment of the present application;

[0020] Figure 2 A schematic diagram of the composition structure of a strip steel rolling device provided in an embodiment of the present application;

[0021] Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0022] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, rather than to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "is" and "has" and any variations thereof involved in the present application are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0023] The term "module" or "unit" in this application refers to a computer program or a part of a computer program that has a predetermined function and works together with other related parts to achieve a predetermined goal, and can be implemented in whole or in part by using software, hardware (such as processing circuits or memories) or a combination thereof. Similarly, a processor (or multiple processors or memories) can be used to implement one or more modules or units. In addition, each module or unit can be part of an overall module or unit that includes the function of the module or unit.

[0024] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. In the following description, it is related to "some embodiments", which describes a subset of all possible embodiments, but it can be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments, and can be combined with each other without conflict.

[0025] See also Figure 1 , Figure 1 1 is a schematic flow chart of a strip steel rolling method provided in an embodiment of the present application. The method may specifically include the following steps 101 to 104:

[0026] Step 101, before the first rolling pass, inputting the default gain parameter into the target single-stand rolling mill, and performing the first rolling pass on the target strip steel by the target single-stand rolling mill;

[0027] Specifically, a pass refers to a complete rolling process of a strip through a rolling mill during the rolling process. In each pass, the strip passes through the rollers of the rolling mill and its thickness decreases. The first pass refers to the process in which the strip passes through the rolling mill for the first time. Each subsequent round of rolling is called the Nth pass, where N is an integer greater than 1. The gain parameter is a parameter used to adjust the intensity of the control action in the automatic control system. During the rolling process, the gain parameter can affect the roll gap setting, tension control, speed adjustment, etc. of the rolling mill, thereby affecting the rolling effect of the strip, such as thickness accuracy, straightness, etc. The default gain parameter refers to the standard gain parameter pre-set by the system without specific adjustment or optimization. It is usually set based on the design parameters and empirical data of the rolling mill and is used for the initial rolling process when there is no more personalized data. The target single-stand rolling mill refers to a rolling mill that performs a specific rolling task. The target strip refers to the specific strip that is undergoing a rolling operation. It is the object of the rolling process and the raw material of the final product. During the rolling process, the target strip undergoes multiple passes of rolling to achieve the required thickness and performance.

[0028] Exemplarily, at the beginning stage of the strip rolling process, that is, before the strip passes through the rolling mill for the first time (before the first rolling pass), the control system inputs the pre-set standard gain parameters (default gain parameters) into the rolling mill (target single-stand rolling mill) that will perform the rolling task; then, the strip to be rolled (target strip) is rolled for the first pass through this rolling mill.

[0029] Through the implementation of step 101, an initial reference setting is provided for the rolling process, ensuring that the rolling process can start smoothly.

[0030] Step 102, before the Nth rolling pass, obtaining the current reduction rate of the target strip steel, wherein N is an integer greater than 1;

[0031] Specifically, in order to accurately obtain the current reduction rate of the target strip before the Nth rolling pass, the thickness data of the target strip after the previous rolling pass can be retrieved and recorded, which is usually achieved by high-precision thickness measuring equipment installed on the rolling mill; at the same time, the database or records storing the original thickness of the target strip (i.e., raw material thickness) can also be accessed; then, the current reduction rate can be calculated based on these two sets of data, that is, the ratio of the difference between the current thickness and the raw material thickness to the raw material thickness.

[0032] By implementing step 102, the current reduction rate is obtained, and the deformation of the strip after the previous rolling can be understood in real time, providing important feedback information for subsequent rolling, and helping to adjust the rolling parameters according to the actual state of the strip, thereby improving the adaptability and flexibility of the rolling process.

[0033] Step 103, substituting the model input parameters into the correction relationship model to obtain the current correction coefficient corresponding to the Nth rolling pass, wherein the model input parameters may include the current reduction rate;

[0034] Specifically, first, the model input parameters can be collected and organized, including but not limited to the current reduction rate of the target strip; then, these parameters can be input into a pre-trained correction relationship model, which is a mathematical model trained based on historical data, and it can predict the gain parameter correction value required under the current rolling conditions based on the input parameters; finally, by calculating the model output, the current correction coefficient corresponding to the Nth rolling pass is obtained.

[0035] By implementing step 103, the correction coefficient can be dynamically calculated according to the actual rolling conditions of the steel strip using the correction relationship model, which helps to control the rolling process more accurately.

[0036] Step 104, inputting the correction gain parameter to the target single-stand rolling mill, and performing N-th pass rolling on the target strip by the target single-stand rolling mill, wherein the correction gain parameter is a gain parameter calculated according to the default gain parameter and the current correction coefficient;

[0037] Specifically, the default gain parameter can be first corrected according to the current correction coefficient obtained in step 103; the default gain parameter is multiplied by the current correction coefficient to obtain the corrected gain parameter; then, the calculated corrected gain parameter is input into the control system of the target single-stand rolling mill. After the corrected gain parameter is set, the target single-stand rolling mill will use these parameters to roll the target strip for the Nth time; in this process, the roll gap setting, tension control and speed regulation of the rolling mill will be adjusted according to the corrected gain parameter to optimize the rolling effect of the strip.

[0038] By implementing step 104 and inputting the corrected gain parameters, the control strategy of the rolling mill can be optimized, so that the rolling process is more in line with actual needs. This dynamic adjustment can reduce rolling quality problems caused by parameter mismatch, improve the dimensional accuracy and surface quality of the product, and at the same time reduce adjustment time and improve production efficiency.

[0039] In summary, the embodiment of the present application can more accurately control the key parameters such as rolling force and rolling speed during the rolling process by calculating and applying the corrected gain parameters in real time according to the current reduction rate of the target strip before the Nth rolling pass, thereby improving the accuracy of key quality indicators such as thickness, width, and flatness of the strip after rolling; dynamically adjusting the gain parameters can ensure that the rolling mill is always in the optimal working state in different rolling passes, avoiding energy waste or excessive equipment wear due to fixed parameters, and accurate rolling control can also reduce the scrap rate caused by rolling defects, thereby improving overall production efficiency and economic benefits. In summary, the strip rolling method provided in the embodiment of the present application improves the rolling accuracy of the strip by dynamically adjusting the gain parameters to adapt to the current state of the target strip in different rolling passes.

[0040] In some embodiments, the aforementioned strip rolling method may further include: acquiring historical rolling process data, wherein the aforementioned historical rolling process data may include historical thickness control errors, historical reduction rates, and historical correction coefficients; screening out model training data based on the aforementioned historical thickness control errors, wherein the model training data may include model training feature data and model training label data, the aforementioned model training feature data may include a training reduction rate screened from the aforementioned historical reduction rates, and the model training label data may include a training correction coefficient screened from the historical correction coefficients; performing model training based on the model training data to obtain a correction relationship model.

[0041] Specifically, first, the correction gain parameter can be calculated based on the preset default gain parameter and the current correction coefficient calculated in step 103; the correction gain parameter is usually calculated by multiplying the default gain parameter with the current correction coefficient (or calculating according to other predetermined mathematical relationships); then, this correction gain parameter can be input into the control system of the target single-stand rolling mill, and the rolling mill control system adjusts parameters such as the roller's pressing amount or rolling force according to the received correction gain parameter, thereby performing the Nth pass of rolling on the target strip.

[0042] Through the implementation of the above-mentioned embodiment, historical rolling process data is collected and analyzed, and high-quality model training data is screened out for training the correction relationship model, which can ensure that the model training is based on reliable data, thereby improving the prediction accuracy and generalization ability of the model, making the dynamic adjustment of gain parameters more accurate and effective.

[0043] In some embodiments, the aforementioned screening out of model training data based on historical thickness control errors may include: determining historical rolling process data corresponding to rolling processes in which thickness control errors are less than a preset error threshold as model training data.

[0044] Specifically, first, a preset error threshold can be defined, which is used to measure the accuracy of thickness control in the rolling process; then, all historical rolling process data are traversed, and for each data, its thickness control error is calculated, that is, the difference or relative error between the actual rolling thickness and the target rolling thickness; next, the historical rolling process data corresponding to the rolling processes whose thickness control errors are less than the preset error threshold are selected as model training data. These screened data are considered to be high-quality data because they reflect the characteristics of the rolling process under better thickness control conditions.

[0045] Through the implementation of the above embodiment, a preset threshold of thickness control error is set, and rolling process data with smaller thickness control error is screened out as model training data, which helps to eliminate noise data caused by abnormal or unstable factors and further improve the quality and reliability of model training.

[0046] In some embodiments, the aforementioned historical rolling process data may further include the historical pass number; the aforementioned model training feature data may further include the training pass number selected from the aforementioned historical pass number; and the model input parameters may further include N.

[0047] Specifically, first, the rolling process data including the historical pass numbers can be collected and organized. These data reflect the characteristics and changing laws of the rolling process under different pass numbers. When screening the model training data, the historical thickness control error and the historical pass numbers will be considered at the same time, and those rolling process data that meet the thickness control error requirements and contain different pass numbers will be selected. Then, the training pass numbers are extracted from these screened data as part of the model training feature data. During model training and prediction, the current rolling pass number N will also be used as one of the model input parameters to reflect the stage and characteristics of the current rolling process.

[0048] Through the implementation of the above-mentioned embodiment, taking the historical pass number as part of the model training feature data and considering its role in model training will help the model to more comprehensively capture the pass dependency in the rolling process, making the calculation of the correction coefficient more consistent with the dynamic changes of the actual rolling process.

[0049] In some embodiments, the aforementioned model training based on the model training data to obtain the corrected relationship model may include: linearly fitting the training depression rate and the training correction coefficient according to the number of training passes to obtain a fitting function corresponding to the number of training passes, and determining the fitting function as the corrected relationship model.

[0050] Specifically, first, the screened model training data can be preprocessed to ensure the accuracy and consistency of the data; then, according to the number of training passes, the training data can be grouped or sorted for subsequent pass-related analysis; then, statistical or machine learning methods, such as linear regression, are used to perform linear fitting on the training reduction rate and training correction coefficient for each group or each pass. In this process, a series of fitting parameters, such as slope, intercept, etc., will be calculated, and these parameters together constitute the fitting function corresponding to the number of training passes; finally, this fitting function is determined as a correction relationship model for the subsequent gain parameter correction calculation in the rolling process.

[0051] Through the implementation of the above embodiment, the training pressing rate and the training correction coefficient are linearly fitted to obtain a fitting function corresponding to the number of training passes, and it is used as a correction relationship model, which simplifies the complexity of the model while retaining sufficient prediction ability, making the model easy to implement and effective in practical applications.

[0052] In some embodiments, the aforementioned historical rolling process data may also include historical strip temperatures; the aforementioned model training feature data may also include training strip temperatures selected from the aforementioned historical strip temperatures; and the model input parameters may also include the current strip temperature of the target strip.

[0053] Specifically, first, the temperature record of the strip steel can be collected in real time through the temperature sensor installed on the rolling line and stored in the database. When screening the model training data, in addition to considering factors such as historical thickness control error, historical number of passes, and historical reduction rate, it is also necessary to evaluate the impact of historical strip steel temperature on the rolling effect, and select those rolling processes with complete temperature records and significant impact on the rolling effect as training data; then, the training strip steel temperature is extracted from these data as part of the model training feature data. During model training and prediction, the current strip steel temperature of the target strip steel will also be used as one of the model input parameters, and will work together with other parameters such as the number of training passes and reduction rate in the correction relationship model to calculate a more accurate correction coefficient.

[0054] Through the implementation of the above embodiment, the historical strip temperature is used as part of the model training feature data, and its role in the correction relationship model is considered, which helps the model to more accurately reflect the impact of temperature on the rolling effect during the rolling process and further improve the control of rolling accuracy.

[0055] In some embodiments, the aforementioned acquisition of the current reduction rate of the target strip may include: acquiring the raw material thickness and current thickness of the target strip; calculating the thickness difference between the raw material thickness and the current thickness, and determining the ratio of the thickness difference to the raw material thickness as the current reduction rate.

[0056] Specifically, first, the raw material thickness and the current thickness after rolling of the target strip can be measured respectively by using a thickness measuring device installed on the rolling line (such as a laser thickness gauge, a contact thickness measuring roller, etc.); then, the thickness difference between the raw material thickness and the current thickness, that is, the thickness reduction of the strip during the rolling process, is calculated based on the two measured values; finally, the calculated thickness difference is divided by the raw material thickness, and the ratio obtained is the current reduction rate. This calculation process can be automatically completed by the software algorithm in the rolling control system to achieve real-time and efficient reduction rate monitoring.

[0057] Through the implementation of the above embodiment, the current reduction rate of the target strip (based on the difference between the raw material thickness and the current thickness) is directly calculated, providing an accurate data basis for the input of the correction relationship model. This calculation method is simple and direct, and can reflect the thickness changes during the rolling process in real time, providing strong support for the dynamic adjustment of the gain parameters.

[0058] Furthermore, as an implementation of the aforementioned method embodiment, the present application also provides a strip steel rolling device for implementing the aforementioned method embodiment. The device embodiment corresponds to the aforementioned method embodiment. For ease of reading, the present strip steel rolling device embodiment will no longer repeat the details of the aforementioned method embodiment one by one, but it should be clear that the device in the embodiment of the present application can correspond to and implement all the contents of the aforementioned method embodiment. Figure 2As shown, the strip rolling device 20 includes: a first rolling unit 201, a reduction rate calculation unit 202, a correction coefficient determination unit 203 and a second rolling unit 204, wherein the first rolling unit 201 is used to input the default gain parameter into the target single-stand rolling mill before the first rolling pass, and perform the first rolling pass on the target strip through the aforementioned target single-stand rolling mill; the reduction rate calculation unit 202 is used to obtain the current reduction rate of the target strip before the Nth rolling pass, wherein N is an integer greater than 1; the correction coefficient determination unit 203 is used to substitute the model input parameter into the correction relationship model to obtain the current correction coefficient corresponding to the Nth rolling pass, wherein the model input parameter may include the current reduction rate; the second rolling unit 204 is used to input the correction gain parameter into the target single-stand rolling mill, and perform the Nth rolling pass on the target strip through the target single-stand rolling mill, wherein the correction gain parameter is a gain parameter calculated based on the default gain parameter and the current correction coefficient.

[0059] In some embodiments, the strip rolling device 20 also includes a model training unit for acquiring historical rolling process data, wherein the historical rolling process data includes historical thickness control errors, historical reduction rates, and historical correction coefficients; model training data is screened out based on the historical thickness control errors, wherein the model training data includes model training feature data and model training label data, the model training feature data includes a training reduction rate screened from historical reduction rates, and the model training label data includes a training correction coefficient screened from historical correction coefficients; model training is performed based on the model training data to obtain a correction relationship model.

[0060] In some embodiments, the model training unit is further used to determine historical rolling process data corresponding to a rolling process in which a thickness control error is less than a preset error threshold as model training data.

[0061] In some embodiments, the historical rolling process data also includes the historical pass numbers; the model training feature data also includes the training pass numbers selected from the historical pass numbers; and the model input parameters also include N.

[0062] In some embodiments, the model training unit is further used to perform linear fitting on the training depression rate and the training correction coefficient according to the number of training passes, obtain a fitting function corresponding to the number of training passes, and determine the fitting function as the correction relationship model.

[0063] In some embodiments, the historical rolling process data also includes historical strip temperatures; the model training feature data also includes training strip temperatures selected from the historical strip temperatures; and the model input parameters also include the current strip temperature of the target strip.

[0064] In some embodiments, the reduction rate calculation unit 202 is also used to obtain the raw material thickness and current thickness of the target strip; calculate the thickness difference between the raw material thickness and the current thickness, and determine the ratio of the thickness difference to the raw material thickness as the current reduction rate.

[0065] The present application also provides a computer-readable storage medium, which stores computer-executable instructions or computer programs. When the computer-executable instructions or computer programs are executed by a processor, the processor will be caused to execute any step of the strip rolling method provided in the present application.

[0066] In some embodiments, the computer-readable storage medium may be a memory such as RAM, read-only memory (ROM), flash memory, magnetic surface memory, optical disk, or compact disc read-only memory (CD-ROM); or it may be various devices including one or any combination of the above memories.

[0067] In some embodiments, computer executable instructions may be in the form of a program, software, software module, script or code, written in any form of programming language (including compiled or interpreted languages, or declarative or procedural languages), and may be deployed in any form, including as a stand-alone program or as a module, component, subroutine or other unit suitable for use in a computing environment.

[0068] In some embodiments, computer-executable instructions may, but need not, correspond to a file in a file system, may be stored as part of a file storing other programs or data, for example, in one or more scripts in a HyperText Markup Language (HTML) document, in a single file dedicated to the program in question, or in multiple coordinated files (e.g., files storing one or more modules, subroutines, or code portions).

[0069] In some embodiments, computer executable instructions may be deployed to be executed on one electronic device, or on multiple electronic devices located at one site, or on multiple electronic devices distributed at multiple sites and interconnected by a communication network.

[0070] like Figure 3 As shown, the present application also provides an electronic device 30, including a memory 310, a processor 320, and a computer program 311 stored in the memory 310 and executable on the processor, and when the processor 320 executes the computer program 311, any step of the above-mentioned strip rolling method is implemented.

[0071] The present application also provides a computer program product, which includes a computer program or a computer executable instruction, and the computer program or the computer executable instruction is stored in a computer readable storage medium. The processor of the electronic device reads the computer program or the computer executable instruction from the computer readable storage medium, and the processor executes the computer program or the computer executable instruction, so that the electronic device performs any step of the strip steel rolling method described above in the present application.

[0072] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A strip steel rolling method, characterized in that: include: Before the first rolling pass, inputting the default gain parameter into the target single-stand rolling mill, and performing the first rolling pass on the target steel strip by the target single-stand rolling mill; Before the Nth rolling pass, obtaining the current reduction rate of the target strip steel, wherein N is an integer greater than 1; Substituting the model input parameters into the correction relationship model to obtain a current correction coefficient corresponding to the Nth rolling pass, wherein the model input parameters include the current reduction rate; The correction gain parameter is input into the target single-stand rolling mill, and the target strip is rolled for the Nth time by the target single-stand rolling mill, wherein the correction gain parameter is a gain parameter calculated based on the default gain parameter and the current correction coefficient.

2. The strip rolling method according to claim 1, characterized in that: The strip steel rolling method further comprises: Acquiring historical rolling process data, wherein the historical rolling process data includes historical thickness control errors, historical reduction rates, and historical correction coefficients; Filtering model training data according to the historical thickness control error, wherein the model training data includes model training feature data and model training label data, the model training feature data includes a training reduction rate filtered from the historical reduction rates, and the model training label data includes a training correction coefficient filtered from the historical correction coefficients; Model training is performed according to the model training data to obtain the modified relationship model.

3. The strip rolling method according to claim 2, characterized in that: The step of selecting model training data according to the historical thickness control error includes: The historical rolling process data corresponding to the rolling process in which the thickness control error is less than a preset error threshold is determined as the model training data.

4. The strip rolling method according to claim 2 or 3, characterized in that: The historical rolling process data also includes the historical pass number; the model training feature data also includes the training pass number selected from the historical pass number; and the model input parameter also includes N.

5. The strip rolling method according to claim 4, characterized in that: The performing model training according to the model training data to obtain the modified relationship model includes: The training depression rate and the training correction coefficient are linearly fitted according to the number of training tracks to obtain a fitting function corresponding to the number of training tracks, and the fitting function is determined as the correction relationship model.

6. The strip rolling method according to claim 2 or 3, characterized in that: The historical rolling process data also includes historical strip steel temperatures; the model training feature data also includes training strip steel temperatures screened from the historical strip steel temperatures; and the model input parameters also include the current strip steel temperature of the target strip steel.

7. The strip rolling method according to claim 1, characterized in that: The obtaining of the current reduction rate of the target steel strip comprises: Obtaining the raw material thickness and current thickness of the target steel strip; The thickness difference between the raw material thickness and the current thickness is calculated, and the ratio of the thickness difference to the raw material thickness is determined as the current reduction rate.

8. A strip steel rolling device, characterized in that: include: A first rolling unit is used for inputting a default gain parameter into a target single-stand rolling mill before a first rolling pass, and performing the first rolling pass on a target steel strip through the target single-stand rolling mill; A reduction rate calculation unit, used for obtaining the current reduction rate of the target strip before the Nth rolling pass, wherein N is an integer greater than 1; A correction coefficient determination unit, used for substituting the model input parameters into the correction relationship model to obtain a current correction coefficient corresponding to the Nth rolling pass, wherein the model input parameters include the current reduction rate; The second rolling unit is used to input the correction gain parameter into the target single-stand rolling mill, and perform the Nth rolling on the target strip through the target single-stand rolling mill, wherein the correction gain parameter is a gain parameter calculated based on the default gain parameter and the current correction coefficient.

9. An electronic device, comprising: A memory and a processor, wherein the processor is used to implement the steps of the strip rolling method as described in any one of claims 1 to 7 when executing the computer program stored in the memory.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the strip rolling method according to any one of claims 1 to 7 are implemented.

Images