A method and device for predicting rolling force of hot-rolled seamless steel pipe based on digital twin

Abstract

The present invention provides a method and device for predicting the rolling force of a hot-rolled seamless steel pipe based on digital twins, and relates to the field of metallurgical technology. The present invention predicts the rolling force prediction value through the input vector composed of the rolling force calculation value, the seamless steel pipe parameters, and the continuous rolling unit parameters, combined with the digital twin model of the hot-rolled seamless steel pipe, and integrates the actual data of the rolling mill steel pipe and the rolling force calculation value to improve the accuracy of the rolling force prediction value. After the prediction, the rolling force prediction value is iteratively optimized to make the rolling force prediction more accurate, realize the accurate prediction of the rolling force of the hot-rolled seamless steel pipe, and improve the execution efficiency and accuracy of the seamless steel pipe rolling process.

Description

Technical Field

[0001] The present invention relates to the field of metallurgical technology, and in particular to a method and device for predicting rolling force of a hot-rolled seamless steel pipe based on digital twins. Background Art

[0002] In the production process of hot-rolled seamless steel pipes, the continuous rolling process is the core link. Its complexity, variability and high precision requirements have always been the key factors restricting the improvement of product quality. The continuous rolling process involves a strong coupling relationship between multiple variables and a nonlinear deformation mechanism, which makes it extremely difficult to accurately predict the rolling force. As an important indicator affecting the dimensional accuracy, surface quality and performance of steel pipes, the prediction accuracy of rolling force is directly related to the quality and market competitiveness of the final product.

[0003] For a long time, traditional rolling force prediction methods have relied on empirical formulas and theoretical models, which often have large prediction errors when faced with complex and changeable rolling conditions in actual production. Especially in the continuous rolling process, it is difficult to accurately measure parameters such as the temperature, deformation rate, and dimensional change of the rolled piece at different stages in real time, making the dynamic changes of rolling force even more difficult to capture and predict. In addition, factors such as equipment wear and process parameter fluctuations in the rolling process further increase the difficulty of rolling force prediction. Summary of the invention

[0004] The present invention provides a method and device for predicting the rolling force of a hot-rolled seamless steel pipe based on digital twin, which can realize accurate prediction of the rolling force of the hot-rolled seamless steel pipe and improve the execution efficiency and accuracy of the seamless steel pipe rolling process.

[0005] In the first aspect, the present invention provides a method for predicting the rolling force of a hot-rolled seamless steel pipe based on digital twins, the method comprising: obtaining parameters of a seamless steel pipe to be rolled and parameters of a continuous rolling mill; determining a calculated rolling force value of the seamless steel pipe to be rolled based on the parameters of the seamless steel pipe to be rolled and the parameters of the continuous rolling mill; generating an input vector based on the calculated rolling force value, the parameters of the seamless steel pipe to be rolled and the parameters of the continuous rolling mill; predicting the rolling force based on the input vector and a digital twin model of the hot-rolled seamless steel pipe to obtain a predicted rolling force value; determining an optimized rolling force value of the hot-rolled seamless steel pipe based on the predicted rolling force value and an iterative optimization coefficient to achieve rolling force prediction.

[0006] In a possible implementation, based on the parameters of the seamless steel pipe to be rolled and the parameters of the continuous rolling mill, the rolling force calculation value of the seamless steel pipe to be rolled is determined, including: determining the rolling force calculation value based on the following formula;

[0007] ;

[0008] Where P is the calculated value of rolling force, is the deformation resistance, a is the artificial empirical coefficient, S is the contact area of ​​the deformation zone, is the stress state influence coefficient.

[0009] In a possible implementation, the optimal rolling force value of the hot-rolled seamless steel pipe is determined based on the rolling force prediction value and the iterative optimization coefficient. Before realizing the rolling force prediction, it also includes: obtaining the rolling force prediction value and the actual rolling force value of the previous rolled steel pipe; based on the rolling force prediction value and the actual rolling force value of the previous rolled steel pipe, calculating the iterative optimization coefficient.

[0010] In a possible implementation, the iterative optimization coefficient is calculated based on the predicted rolling force value and the actual rolling force value of the previous rolled steel pipe, including: determining the iterative optimization coefficient based on the following formula;

[0011] ;

[0012] in, is the iterative optimization coefficient, is the predicted value of rolling force of the previous rolled steel pipe, It is the actual value of the rolling force of the previous rolled steel pipe.

[0013] In a possible implementation, rolling force prediction is performed based on an input vector and a digital twin model of a hot-rolled seamless steel pipe. Before obtaining the predicted rolling force value, the method also includes: obtaining rolling data and actual rolling force values ​​of multiple steel pipes during the rolling process of the hot-rolled seamless steel pipe; the rolling data includes seamless steel pipe parameters and continuous rolling mill parameters of each steel pipe; based on the rolling data of multiple steel pipes, a calculated rolling force value of each steel pipe is calculated; based on the calculated rolling force value of each steel pipe, the seamless steel pipe parameters and the continuous rolling mill parameters, an input vector corresponding to each steel pipe is generated; based on the actual rolling force value of each steel pipe, an output vector is generated; based on the input vector and the output vector, a training sample is generated; based on the training sample, a neural network is trained to obtain a digital twin model.

[0014] In one possible implementation, the test accuracy parameters of the digital twin model include: root mean square error, mean absolute error, and determination coefficient; the calculation formula of the test accuracy parameters is as follows:

[0015] ;

[0016] ;

[0017] ;

[0018] Among them, RMSE is the root mean square error, MAE is the mean absolute error, R 2 is the coefficient of determination, N is the sample size; Ot is the expected value; avg is the average value of the expected value; P t The rolling force prediction value output by the digital twin model.

[0019] In one possible implementation, an input vector is generated based on the rolling force calculation value, the parameters of the seamless steel pipe to be rolled, and the parameters of the continuous rolling mill, including: planning the rolling force calculation value, the parameters of the seamless steel pipe to be rolled, and the parameters of the continuous rolling mill to obtain normalized parameters; and generating an input vector based on the normalized parameters.

[0020] In a possible implementation, the rolling force calculation value, the parameters of the seamless steel pipe to be rolled and the parameters of the continuous rolling mill are planned and processed to obtain the normalized parameters, including: calculating the normalized parameters based on the following formula;

[0021]

[0022] in, is the maximum data in the data set X, is the minimum data in the data set X, is the data before normalization, is the normalization parameter.

[0023] In the second aspect, an embodiment of the present invention provides a rolling force prediction device for a hot-rolled seamless steel pipe based on digital twin, and the prediction device includes: a communication module, used to obtain parameters of the seamless steel pipe to be rolled, and parameters of a continuous rolling mill; a processing module, used to determine a calculated rolling force value of the seamless steel pipe to be rolled based on the parameters of the seamless steel pipe to be rolled, and parameters of the continuous rolling mill; based on the calculated rolling force value, parameters of the seamless steel pipe to be rolled and parameters of the continuous rolling mill, an input vector is generated; based on the input vector and a digital twin model of the hot-rolled seamless steel pipe, a rolling force prediction is performed to obtain a rolling force prediction value; based on the rolling force prediction value and an iterative optimization coefficient, an optimized rolling force value of the hot-rolled seamless steel pipe is determined to achieve rolling force prediction.

[0024] In a third aspect, an embodiment of the present invention provides an electronic device, comprising a memory and a processor, the memory storing a computer program, the processor being used to call and run the computer program stored in the memory to perform the steps of the method described in the first aspect and any possible implementation method of the first aspect.

[0025] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and wherein when the computer program is executed by a processor, the steps of the method described in the first aspect and any possible implementation method of the first aspect are implemented.

[0026] The present invention provides a method and device for predicting the rolling force of a hot-rolled seamless steel pipe based on digital twins. The present invention predicts the rolling force prediction value by combining the input vector composed of the rolling force calculation value, the seamless steel pipe parameters, and the continuous rolling mill group parameters, and the digital twin model of the hot-rolled seamless steel pipe. The actual data of the rolling mill steel pipe and the rolling force calculation value are integrated to improve the accuracy of the rolling force prediction value. After the prediction, the rolling force prediction value is iteratively optimized to make the rolling force prediction more accurate, realize the accurate prediction of the rolling force of the hot-rolled seamless steel pipe, and improve the execution efficiency and accuracy of the seamless steel pipe rolling process. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0028] Figure 1 This is a schematic diagram of equipment layout of a production line for hot-rolled seamless steel pipes provided in an embodiment of the present invention;

[0029] Figure 2 This is a data collection network schematic diagram of a hot-rolled seamless steel pipe provided by an embodiment of the present invention;

[0030] Figure 3 It is a flow chart of a method for predicting rolling force of a hot-rolled seamless steel pipe based on digital twin provided in an embodiment of the present invention;

[0031] Figure 4 It is a structural schematic diagram of a rolling force prediction device for hot-rolled seamless steel pipe based on digital twin provided by an embodiment of the present invention;

[0032] Figure 5 It is a structural schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0033] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present invention. However, it should be clear to those skilled in the art that the present invention may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present invention.

[0034] In the description of the present invention, unless otherwise specified, " / " means "or", for example, A / B can mean A or B. "And / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, "at least one" and "plurality" refer to two or more. The words "first", "second", etc. do not limit the quantity and execution order, and the words "first", "second", etc. do not limit them to be different.

[0035] In the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a concrete way for easy understanding.

[0036] In addition, the terms "including" and "having" and any variations thereof mentioned in the description of this application are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or modules is not limited to the listed steps or modules, but may optionally include other steps or modules that are not listed, or may optionally include other steps or modules that are inherent to these processes, methods, products or devices.

[0037] In order to make the purpose, technical solutions and advantages of the present invention more clear, the following will be described through specific embodiments in conjunction with the accompanying drawings of the present invention.

[0038] The production process of hot-rolled seamless steel pipe mainly includes the following steps: Preparation and inspection of tube billets: Select qualified steel billets or solid tube billets, carry out necessary pretreatment and inspection to ensure the quality of raw materials. Heating of tube billets: Send the tube billets into the heating furnace and heat them to an appropriate temperature to improve their plasticity and reduce deformation resistance. Perforation: In the perforator, the heated tube billets are inserted into the hollow thick-walled capillary to form a preliminary hollow tube. Rolling: The perforated tube billets are rolled by the tube rolling mill to further reduce the wall thickness and adjust the tube diameter to form a semi-finished tube. Reheating of steel pipes: According to the process requirements, the semi-finished tubes are heated again to meet the temperature requirements of subsequent processes. Sizing (reducing): The rolled steel pipes are precisely adjusted by sizing machines or reducing machines to meet the specified size and shape requirements. Heat treatment: The steel pipes are subjected to heat treatments such as annealing and normalizing to improve their organizational structure and mechanical properties. Straightening of finished pipes: The heat-treated steel pipes are straightened to eliminate defects such as bending and twisting. Finishing: The steel pipes are subjected to finishing treatments such as cutting heads, cutting tails, and surface treatment to improve the appearance quality and surface finish of the products. Inspection and warehousing: The finished steel pipes are subjected to strict quality inspections, including non-destructive testing, physical and chemical analysis, and dimensional measurement, and are put into storage after passing the inspections.

[0039] High-precision rolling force prediction is of great significance for improving the product quality of hot-rolled seamless steel pipes. For a long time, due to the complex deformation mechanism of the continuous rolling process, it has been difficult to achieve high-precision prediction of rolling force, which has limited the further improvement of product quality accuracy. As a key technology for the integration of information and physics, digital twins play an important role in the new round of industrial intelligent reforms. Because it has the characteristics of maintaining dynamic consistency with the physical space, it can realize two-way interactive mapping of virtual and real, and can further realize the simulation prediction of the physical space. Therefore, the online prediction of rolling force based on digital twins has certain effectiveness and engineering value, especially for continuous rolling processes with many parameters and complex deformations. It has high adaptability. The method of the present invention realizes the modeling and iterative optimization of the rolling force model of hot-rolled seamless steel pipes based on digital twin technology, makes full use of the big data of the industrial site, improves the information perception efficiency through the digitization and visualization of real-time production status, improves the decision-making and execution efficiency, and promotes the continuous improvement of the production line operation system.

[0040] like Figure 1 As shown, an embodiment of the present invention provides a schematic diagram of equipment layout of a hot-rolled seamless steel pipe production line. The hot-rolled seamless steel pipe production line of the present invention includes a ring heating furnace, a rolling mill main line, and digitized three-dimensional spatial information of process equipment such as cooling and finishing.

[0041] like Figure 2As shown, an embodiment of the present invention provides a data collection network schematic diagram of a hot-rolled seamless steel pipe. The embodiment of the present invention collects real-time data, production process management data, and key events in the production process, and completes the association of material and production process curve data, data time-space transformation and data storage, and multi-protocol conversion to complete data interaction and communication. Data curve classification and feature extraction are shown in Table 1.

[0042] Table 1

[0043] Serial number Curve Category Feature extraction content 1 Temperature Original value, average value, maximum value, minimum value, standard deviation, head deviation, tail deviation, local drop, etc. 2 Size Class Original value, average value, maximum value, minimum value, standard deviation, head deviation, tail deviation, local drop, etc. 3 Speed Original value, average value, maximum value, minimum value, standard deviation, etc. 4 Force parameter class Original value, average value, maximum value, minimum value, etc. 5 Location Class Original value, average value, maximum value, minimum value, standard deviation, etc. 6 Traffic Class Original value, average value, maximum value, minimum value, etc. 7 Pressure Average, maximum, minimum, etc.

[0044] like Figure 3 As shown, an embodiment of the present invention provides a method for predicting rolling force of a hot-rolled seamless steel pipe based on digital twin. The method includes steps S101-S105.

[0045] S101. Obtain parameters of the seamless steel pipe to be rolled and parameters of the continuous rolling mill.

[0046] In some embodiments, the seamless steel pipe parameters include roll diameter, mandrel diameter, roll gap, roll speed, and rolling temperature.

[0047] In some embodiments, the parameters of the continuous rolling mill group include the outer diameter of the rough tube at the mill inlet, the wall thickness of the rough tube at the mill inlet, the outer diameter of the rough tube at the mill outlet, the wall thickness of the rough tube at the mill outlet and the rough tube length.

[0048] S102. Determine a calculated rolling force value of the seamless steel pipe to be rolled based on the parameters of the seamless steel pipe to be rolled and the parameters of the continuous rolling mill.

[0049] As a possible implementation manner, the embodiment of the present invention can determine the calculated rolling force value based on the following formula.

[0050] ;

[0051] Where P is the calculated value of rolling force, is the deformation resistance, a is the artificial empirical coefficient, S is the contact area of ​​the deformation zone, is the stress state influence coefficient.

[0052] Among them, deformation resistance reflects the ability of metal to resist deformation during plastic deformation. The magnitude of deformation resistance is related to factors such as the properties of metal materials, deformation temperature, deformation speed and deformation degree. The artificial experience coefficient is a coefficient derived from practical experience, which is used to correct the difference between theoretical calculation and actual situation. Since the rolling process involves many complex factors, it is difficult to obtain accurate rolling force completely through theoretical calculation, so it is necessary to introduce this experience coefficient for correction. The contact area of ​​the deformation zone indicates the contact area between the roller and the workpiece in the deformation zone. The size of this area directly affects the size of the rolling force, because the rolling force is transmitted through the contact surface between the roller and the workpiece. The stress state influence coefficient reflects the influence of the stress state on the rolling force. During the rolling process, the workpiece is subjected to various stresses, and the state of these stresses will affect the size of the rolling force. The stress state influence coefficient is used to describe this influence.

[0053] S103, generating an input vector based on the rolling force calculation value, as well as the parameters of the seamless steel pipe to be rolled and the parameters of the continuous rolling mill.

[0054] In order to eliminate the influence of the differences in dimensions and value ranges between the above parameter variables, so that they can be compared or weighted with each other, data normalization is required.

[0055] As a possible implementation method, the embodiment of the present invention can perform planning processing on the rolling force calculation value, the parameters of the seamless steel pipe to be rolled and the parameters of the continuous rolling mill group to obtain normalized parameters; based on the normalized parameters, an input vector is generated.

[0056] Exemplarily, the embodiment of the present invention may calculate the normalization parameter based on the following formula.

[0057] ;

[0058] in, is the maximum data in the data set X, is the minimum data in the data set X, is the data before normalization, is the normalization parameter.

[0059] S104. Based on the input vector and the digital twin model of the hot-rolled seamless steel pipe, the rolling force is predicted to obtain a predicted rolling force value.

[0060] The embodiment of the present invention selects 11-dimensional parameters, including the calculated value P of the rolling mechanism model, the roll diameter, the mandrel diameter, the roll gap, the roll speed, the rolling temperature, the outer diameter of the rough pipe at the mill entrance, the wall thickness of the rough pipe at the mill entrance, the outer diameter of the rough pipe at the mill exit, the wall thickness of the rough pipe at the mill exit, and the length of the rough pipe, as the input of GRNN; the actual rolling force of each stand, including 6-dimensional parameters, is used as the output of GRNN. The relevant parameters such as rolling temperature, mandrel diameter, outer diameter of rough pipe at the mill exit, and wall thickness of rough pipe at the mill exit are shown in Table 2.

[0061] Table 2

[0062]

[0063] The present invention develops a rolling force prediction model for a continuous rolling mill based on machine learning and rolling mechanism in a digital twin system, and realizes iterative optimization by data drive. The digital twin network is a machine learning model, namely a generalized regression neural network (GRNN), which consists of an input layer, a pattern layer, a summation layer, and an output layer, and can be expressed by the following formula.

[0064] ;

[0065] Among them, the regression analysis of the dependent variable Y relative to the independent variable x is actually to calculate the y with the maximum probability value. Suppose the joint probability density function of the random variables x and y is , given that the observed value of x is X, then the regression of y with respect to X.

[0066] The embodiment of the present invention inputs the input vector into the digital twin model to predict the rolling force and obtain the predicted rolling force value. The prediction results are shown in Table 3.

[0067] Table 3

[0068]

[0069] S105. Based on the rolling force prediction value and the iterative optimization coefficient, the rolling force optimization value of the hot-rolled seamless steel pipe is determined to achieve rolling force prediction.

[0070] It should be noted that, according to the deviation between the rolling force prediction model and the measured rolling force, it is iteratively optimized as shown below: ; Among them, P pre is the rolling force prediction value after iterative optimization; It is the predicted value of rolling force before iterative optimization.

[0071] As a possible implementation method, before step S105, the embodiment of the present invention can obtain the rolling force prediction value and the actual rolling force value of the previous rolled steel pipe; based on the rolling force prediction value and the actual rolling force value of the previous rolled steel pipe, calculate the iterative optimization coefficient.

[0072] Exemplarily, the embodiment of the present invention may determine the iterative optimization coefficient based on the following formula.

[0073] ;

[0074] in, is the iterative optimization coefficient, is the predicted value of rolling force of the previous rolled steel pipe, It is the actual value of the rolling force of the previous rolled steel pipe.

[0075] The optimization results are shown in Table 4. After adding iterative optimization, the deviation of the rolling force prediction is significantly reduced, which fully proves the effectiveness of the iterative optimization of the present invention.

[0076] Table 4

[0077]

[0078] The present invention provides a method for predicting the rolling force of a hot-rolled seamless steel pipe based on digital twins. The rolling force prediction value is predicted by combining the input vectors composed of the rolling force calculation value, the seamless steel pipe parameters, and the continuous rolling mill group parameters with the digital twin model of the hot-rolled seamless steel pipe. The actual data of the rolling mill steel pipe and the rolling force calculation value are integrated to improve the accuracy of the rolling force prediction value. After the prediction, the rolling force prediction value is iteratively optimized to make the rolling force prediction more accurate, realize the accurate prediction of the rolling force of the hot-rolled seamless steel pipe, and improve the execution efficiency and accuracy of the seamless steel pipe rolling process.

[0079] The present invention can also develop a visual monitoring platform to achieve synchronous linkage between digital scenes and actual scenes. The present invention can achieve more accurate rolling force prediction for complex cold rolling conditions, improve the rolling force setting accuracy, and is of great significance for improving the quality of finished strip shape and increasing the accuracy of strip thickness.

[0080] Optionally, the method for predicting rolling force of hot-rolled seamless steel pipe based on digital twin provided in an embodiment of the present invention further includes steps S201-S206 before step S104.

[0081] S201. Obtain rolling data and actual rolling force values ​​of multiple steel pipes during the rolling process of hot-rolled seamless steel pipes.

[0082] In some embodiments, the rolling data includes seamless steel pipe parameters and continuous rolling mill parameters for each steel pipe.

[0083] S202. Calculate a rolling force calculation value of each steel pipe based on rolling data of the plurality of steel pipes.

[0084] S203. Based on the rolling force calculation value of each steel pipe, the seamless steel pipe parameters and the continuous rolling mill parameters, an input vector corresponding to each steel pipe is generated.

[0085] S204. Generate an output vector based on the actual value of the rolling force of each steel pipe.

[0086] S205: Generate training samples based on the input vector and the output vector.

[0087] S206. Based on the training samples, perform neural network training to obtain a digital twin model.

[0088] In some embodiments, the test accuracy parameters of the digital twin model include: root mean square error, mean absolute error, and coefficient of determination;

[0089] The calculation formula of the test accuracy parameter is as follows:

[0090] ;

[0091] ;

[0092] ;

[0093] Among them, RMSE is the root mean square error, MAE is the mean absolute error, R 2 is the coefficient of determination, N is the sample size; O t is the expected value; avg is the average value of the expected value; P t The rolling force prediction value output by the digital twin model.

[0094] In this way, the embodiment of the present invention can perform neural network training based on the rolling data of multiple steel pipes in the historical period to obtain a digital twin model, which is convenient for realizing rolling force prediction.

[0095] The present invention first digitizes the three-dimensional spatial information of the hot-rolled seamless steel pipe production line equipment, develops a digital twin platform, obtains quality and process information from various levels of the hot-rolled production control system and the production management system, realizes the collection of industrial data, and completes data interaction and communication through multi-protocol conversion; develops a rolling force prediction model for the continuous rolling unit based on machine learning and fusion rolling mechanism in the digital twin system, and inputs the real-time data of the production line into the constructed model to achieve iterative optimization; develops a visual monitoring platform, and maps the equipment status, material status, etc. of the production line to the digital twin system of the hot-rolled seamless steel pipe production line in real time, so as to achieve virtual and real synchronous linkage. The method of the present invention realizes the fusion and convergence of industrial production data by developing a digital twin system, and provides a complete data set for establishing a rolling force prediction model. Secondly, by digitizing and visualizing the real-time production status, it improves the efficiency of information perception, decision-making and execution, promotes the continuous improvement of the production line operation system, and is committed to achieving the current and long-term goals of the production line.

[0096] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0097] The following is an embodiment of the device of the present invention. For details not described in detail therein, reference may be made to the corresponding method embodiment described above.

[0098] Figure 4 The schematic diagram of the structure of a rolling force prediction device for hot-rolled seamless steel pipe based on digital twin provided by an embodiment of the present invention is shown. The prediction device 300 includes a communication module 301 and a processing module 302 .

[0099] The communication module 301 is used to obtain the parameters of the seamless steel pipe to be rolled and the parameters of the continuous rolling mill.

[0100] The processing module 302 is used to determine the calculated rolling force value of the seamless steel pipe to be rolled based on the parameters of the seamless steel pipe to be rolled and the parameters of the continuous rolling mill; generate an input vector based on the calculated rolling force value, the parameters of the seamless steel pipe to be rolled and the parameters of the continuous rolling mill; predict the rolling force based on the input vector and the digital twin model of the hot-rolled seamless steel pipe to obtain the predicted rolling force value; determine the optimized rolling force value of the hot-rolled seamless steel pipe based on the predicted rolling force value and the iterative optimization coefficient to achieve rolling force prediction.

[0101] Figure 5 Schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. Figure 5As shown, the electronic device 400 includes: a processor 401, a memory 402, and a computer program 403 stored in the memory 402 and executable on the processor 401. When the processor 401 executes the computer program 403, the steps in the above-mentioned method embodiments are implemented, for example Figure 3 Alternatively, when the processor 401 executes the computer program 403, the functions of each module / unit in the above-mentioned device embodiments are realized, for example, Figure 4 The functions of the communication module 301 and the processing module 302 are shown.

[0102] Exemplarily, the computer program 403 may be divided into one or more modules / units, which are stored in the memory 402 and executed by the processor 401 to implement the present invention. The one or more modules / units may be a series of computer program instruction segments that can implement specific functions, and the instruction segments are used to describe the execution process of the computer program 403 in the electronic device 400. For example, the computer program 403 may be divided into Figure 4 The communication module 301 and the processing module 302 are shown.

[0103] The processor 401 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0104] The memory 402 may be an internal storage unit of the electronic device 400, such as a hard disk or memory of the electronic device 400. The memory 402 may also be an external storage device of the electronic device 400, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 400. Further, the memory 402 may also include both an internal storage unit of the electronic device 400 and an external storage device. The memory 402 is used to store the computer program and other programs and data required by the terminal. The memory 402 may also be used to temporarily store data that has been output or is to be output.

[0105] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such 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 invention, and should all be included in the protection scope of the present invention.

Claims

1. A method for predicting rolling force of hot-rolled seamless steel pipe based on digital twin, characterized in that: The prediction method comprises: Obtaining parameters of the seamless steel pipe to be rolled and parameters of the continuous rolling mill; Determining a calculated rolling force value of the seamless steel pipe to be rolled based on parameters of the seamless steel pipe to be rolled and parameters of the continuous rolling mill; Based on the rolling force calculation value, as well as the parameters of the seamless steel pipe to be rolled and the parameters of the continuous rolling mill, an input vector is generated; Based on the input vector and the digital twin model of the hot-rolled seamless steel pipe, a rolling force prediction is performed to obtain a rolling force prediction value; Based on the rolling force prediction value and the iterative optimization coefficient, the rolling force optimization value of the hot-rolled seamless steel pipe is determined to achieve rolling force prediction; The step of determining the rolling force calculation value of the seamless steel pipe to be rolled based on the parameters of the seamless steel pipe to be rolled and the parameters of the continuous rolling mill unit comprises: determining the rolling force calculation value based on the following formula; ; Where P is the calculated value of rolling force, is the deformation resistance, a is the artificial empirical coefficient, S is the contact area of ​​the deformation zone, is the stress state influence coefficient; The step of generating the input vector based on the rolling force calculation value, the parameters of the seamless steel pipe to be rolled and the parameters of the continuous rolling mill group comprises: performing planning processing on the rolling force calculation value, the parameters of the seamless steel pipe to be rolled and the parameters of the continuous rolling mill group to obtain normalized parameters; generating the input vector based on the normalized parameters; The method of determining the optimal rolling force value of the hot-rolled seamless steel pipe based on the predicted rolling force value and the iterative optimization coefficient, before realizing the rolling force prediction, further includes: obtaining the predicted rolling force value and the actual rolling force value of the previous rolled steel pipe; determining the iterative optimization coefficient based on the following formula; ;in, is the iterative optimization coefficient, is the predicted value of rolling force of the previous rolled steel pipe, is the actual value of the rolling force of the previous rolled steel pipe; The method of performing rolling force prediction based on the input vector and the digital twin model of the hot-rolled seamless steel pipe to obtain the predicted rolling force value also includes: obtaining rolling data and actual rolling force values ​​of multiple steel pipes during the rolling process of the hot-rolled seamless steel pipe; the rolling data includes seamless steel pipe parameters and continuous rolling mill parameters of each steel pipe; calculating the calculated rolling force value of each steel pipe based on the rolling data of the multiple steel pipes; generating an input vector corresponding to each steel pipe based on the calculated rolling force value of each steel pipe, the seamless steel pipe parameters and the continuous rolling mill parameters; generating an output vector based on the actual rolling force value of each steel pipe; generating training samples based on the input vector and the output vector; and performing neural network training based on the training samples to obtain the digital twin model.

2. The method for predicting rolling force of hot-rolled seamless steel pipe based on digital twin according to claim 1, characterized in that: The test accuracy parameters of the digital twin model include: root mean square error, mean absolute error and determination coefficient; The calculation formula of the test accuracy parameter is as follows: ； ； ； Among them, RMSE is the root mean square error, MAE is the mean absolute error, R 2 is the coefficient of determination, N is the number of samples; O t is the expected value; avg is the average value of the expected value; P t It is the rolling force prediction value output by the digital twin model.

3. The method for predicting rolling force of hot-rolled seamless steel pipe based on digital twin according to claim 1, characterized in that: The rolling force calculation value, the parameters of the seamless steel pipe to be rolled and the parameters of the continuous rolling mill are processed in a planned manner to obtain standardized parameters, including: The normalization parameter is calculated based on the following formula: in, is the maximum data in the data set X, is the minimum data in the data set X, is the data before normalization, is the normalization parameter.

4. A rolling force prediction device for hot-rolled seamless steel pipe based on digital twin, characterized in that: The prediction device comprises: A communication module is used to obtain the parameters of the seamless steel pipe to be rolled and the parameters of the continuous rolling mill; A processing module is used to determine a calculated rolling force value of the seamless steel pipe to be rolled based on the parameters of the seamless steel pipe to be rolled and the parameters of the continuous rolling mill; generate an input vector based on the calculated rolling force value, the parameters of the seamless steel pipe to be rolled and the parameters of the continuous rolling mill; perform rolling force prediction based on the input vector and the digital twin model of the hot-rolled seamless steel pipe to obtain a predicted rolling force value; determine an optimized rolling force value of the hot-rolled seamless steel pipe based on the predicted rolling force value and an iterative optimization coefficient to achieve rolling force prediction; The processing module is specifically used to determine the rolling force calculation value based on the following formula; ; Where P is the calculated value of rolling force, is the deformation resistance, a is the artificial empirical coefficient, S is the contact area of ​​the deformation zone, is the stress state influence coefficient; The processing module is specifically used to perform planning processing on the rolling force calculation value, the parameters of the seamless steel pipe to be rolled and the parameters of the continuous rolling mill group to obtain normalized parameters; based on the normalized parameters, generate the input vector; The processing module is also used to obtain the predicted value and actual value of the rolling force of the previous rolled steel pipe; based on the following formula, determine the iterative optimization coefficient; ;in, is the iterative optimization coefficient, is the predicted value of rolling force of the previous rolled steel pipe, is the actual value of the rolling force of the previous rolled steel pipe; The processing module is also used to obtain the rolling data and actual rolling force values ​​of multiple steel pipes during the rolling process of hot-rolled seamless steel pipes; the rolling data include seamless steel pipe parameters and continuous rolling mill parameters of each steel pipe; based on the rolling data of the multiple steel pipes, the calculated rolling force value of each steel pipe is calculated; based on the calculated rolling force value of each steel pipe, the seamless steel pipe parameters and the continuous rolling mill parameters, an input vector corresponding to each steel pipe is generated; based on the actual rolling force value of each steel pipe, an output vector is generated; based on the input vector and the output vector, a training sample is generated; based on the training sample, a neural network training is performed to obtain the digital twin model.

5. An electronic device, characterized in that: The electronic device comprises a memory and a processor, the memory stores a computer program, and the processor is used to call and run the computer program stored in the memory to execute the steps of the method as claimed in any one of claims 1 to 3.

Images