Continuous casting method and device based on digital twinning, storage medium and computer equipment

Abstract

The application discloses a continuous casting method and device based on digital twinning, a storage medium and computer equipment, relates to the technical field of continuous casting, and mainly aims at improving the continuous casting efficiency and accuracy. The method comprises the following steps: constructing a preset continuous casting digital twinning model based on actual continuous casting scene data corresponding to a target continuous casting device; in response to a continuous casting signal of the target continuous casting device for a current continuous casting process, acquiring real-time running state data corresponding to the target continuous casting device and real-time continuous casting process parameters under the current continuous casting process; based on the real-time running state data and the real-time continuous casting process parameters, analyzing a billet solidification process under a next continuous casting process by using the preset continuous casting digital twinning model to obtain a billet solidification process behavior rule; based on the billet solidification process behavior rule, determining predicted running state data corresponding to the target continuous casting device under the next continuous casting process; and based on the predicted running state data, controlling the continuous casting operation of the target continuous casting device for the next continuous casting process.

Description

Technical Field

[0001] This invention relates to the field of continuous casting technology, and in particular to a continuous casting method, apparatus, storage medium and computer equipment based on digital twins. Background Technology

[0002] Continuous casting, also known as continuous casting, is a process in which molten steel is poured, cooled, and cut through specific equipment (continuous casting machine) to directly obtain a cast billet. Continuous casting technology is a major technological advancement compared to traditional ingot casting. With the development of technology, the quality control of continuously cast products has become particularly important.

[0003] Currently, continuous casting is typically achieved through manual control of the continuous casting machine. However, this manual control method leads to low continuous casting efficiency. Furthermore, due to varying skill levels among operators, errors in the continuous casting machine control can occur, resulting in low casting accuracy and consequently, poor quality of the cast billets. Summary of the Invention

[0004] This invention provides a continuous casting method, apparatus, storage medium, and computer equipment based on digital twins, which mainly improves continuous casting efficiency and accuracy.

[0005] According to a first aspect of the present invention, a continuous casting method based on digital twins is provided, comprising:

[0006] Based on the actual continuous casting scenario data corresponding to the target continuous casting device, a preset digital twin model of continuous casting is constructed.

[0007] In response to the continuous casting signal from the target continuous casting device for the current continuous casting process, the real-time operating status data of the target continuous casting device and the real-time continuous casting process parameters under the current continuous casting process are acquired.

[0008] Based on the real-time operating status data and the real-time continuous casting process parameters, the solidification process of the billet under the next continuous casting process is analyzed using the preset continuous casting digital twin model to obtain the behavior law of the billet solidification process under the next continuous casting process.

[0009] Based on the behavior pattern of the billet solidification process, the predicted operating status data of the target continuous casting device under the next continuous casting process is determined.

[0010] Based on the predicted operating status data, the target continuous casting device is controlled to perform continuous casting operations for the next continuous casting process.

[0011] Optionally, the preset continuous casting digital twin model includes: a thermophysical property parameter calculation layer, a thermal shrinkage parameter calculation layer, a microstructure prediction layer, a hydrocarbon calculation layer, a billet pressure calculation layer, and a behavior pattern prediction layer; based on the real-time operating status data and the real-time continuous casting process parameters, the preset continuous casting digital twin model is used to analyze the billet solidification process in the next continuous casting process to obtain the billet solidification process behavior pattern in the next continuous casting process, including:

[0012] Based on the real-time operating status data and the real-time continuous casting process parameters, the thermal property parameter calculation layer is used to calculate the parameters and obtain the billet thermal property parameters under the next continuous casting process.

[0013] The real-time operating status data and the real-time continuous casting process parameters are input into the heat shrinkage parameter calculation layer to calculate the parameters and obtain the billet heat shrinkage parameters for the next continuous casting process.

[0014] The real-time operating status data and the real-time continuous casting process parameters are input into the microstructure prediction layer to predict the microstructure parameters and obtain the billet microstructure parameters under the next continuous casting process.

[0015] The real-time operating status data and the real-time continuous casting process parameters are input into the hydrocarbon calculation layer to calculate the precipitation data, thereby obtaining the billet hydrocarbon precipitation data for the next continuous casting process.

[0016] The real-time operating status data and the real-time continuous casting process parameters are input into the billet pressure calculation layer to calculate the billet pressure, and the billet pressure data under the next continuous casting process is obtained.

[0017] The thermophysical parameters, thermal shrinkage parameters, billet microstructure parameters, hydrocarbon precipitation data, and billet pressing force data are input into the behavior prediction layer to predict the behavior of the billet solidification process under the next continuous casting process.

[0018] Optionally, the step of inputting the thermophysical parameters, thermal shrinkage parameters, billet microstructure parameters, hydrocarbon precipitation data, and billet pressing force data into the behavior prediction layer to predict the behavior of the billet solidification process under the next continuous casting process includes:

[0019] Based on the aforementioned thermophysical parameters, thermal shrinkage parameters, billet microstructure parameters, hydrocarbon precipitation data, and billet pressing force data, the three-dimensional temperature field diagram, solid-liquid phase line diagram, and stress-strain data extraction diagram at different locations of the billet are determined for the next continuous casting process.

[0020] The three-dimensional temperature field diagram, solid-liquid phase line diagram, and stress-strain data extraction diagram are input into the behavior law prediction layer to predict the behavior law, thereby obtaining the behavior law of the billet solidification process under the next continuous casting process.

[0021] Optionally, the predicted operating status includes: predicted reduction, predicted water volume, and predicted roll gap; the step of controlling the continuous casting operation of the target continuous casting device for the next continuous casting process based on the predicted operating status data includes:

[0022] Based on the predicted reduction amount, the target continuous casting device is controlled to perform a reduction operation for the next continuous casting process;

[0023] Based on the predicted water volume, the target continuous casting device is controlled to perform water volume adjustment operations for the next continuous casting process.

[0024] Based on the predicted roll gap, the target continuous casting device is controlled to perform roll gap adjustment operations for the next continuous casting process.

[0025] Optionally, before analyzing the solidification process of the billet in the next continuous casting process using the preset continuous casting digital twin model based on the real-time operating status data and the real-time continuous casting process parameters to obtain the behavior law of the billet solidification process in the next continuous casting process, the method further includes:

[0026] Determine the maximum and minimum operating status data in the real-time operating status data, and subtract the minimum operating status data from the maximum operating status data to obtain the operating status interval value;

[0027] Subtract the real-time operating status data from the minimum operating status data to obtain the real-time operating status difference;

[0028] Divide the real-time operating status difference by the operating status interval value to obtain the standardized operating status data corresponding to the real-time operating status data;

[0029] Determine the maximum and minimum continuous casting process parameters in the real-time continuous casting process parameters, and subtract the maximum continuous casting process parameter from the continuous casting process parameter to obtain the continuous casting process spacing value;

[0030] Subtract the real-time continuous casting process parameters from the minimum continuous casting process parameters to obtain the real-time continuous casting process difference.

[0031] Divide the real-time continuous casting process difference by the continuous casting process spacing value to obtain the standardized continuous casting process parameters corresponding to the real-time continuous casting process parameters.

[0032] Based on the real-time operating status data and the real-time continuous casting process parameters, the pre-set continuous casting digital twin model is used to analyze the solidification process of the billet in the next continuous casting process, and the behavioral rules of the billet solidification process in the next continuous casting process are obtained, including:

[0033] Based on the standardized operating status data and the standardized continuous casting process parameters, the solidification process of the billet in the next continuous casting process is analyzed using the preset continuous casting digital twin model to obtain the behavior law of the billet solidification process in the next continuous casting process.

[0034] Optionally, before analyzing the solidification process of the billet in the next continuous casting process using the preset continuous casting digital twin model based on the real-time operating status data and the real-time continuous casting process parameters to obtain the behavior law of the billet solidification process in the next continuous casting process, the method further includes:

[0035] Determine the median corresponding to the real-time running status data, and determine the first intermediate value between the minimum value in the real-time running status data and the median, and determine the first intermediate value as the first quartile corresponding to the real-time running status data;

[0036] Determine a second intermediate value between the maximum value and the median in the real-time running status data, and determine the second intermediate value as the third quartile corresponding to the real-time running status data;

[0037] Calculate the distance between the first quartile and the third quartile, and determine the distance as the interquartile interval corresponding to the real-time running status data;

[0038] Calculate the lower limit value for anomaly detection corresponding to the real-time operating status data based on the first quartile and the interquartile range;

[0039] Calculate the upper limit of anomaly detection corresponding to the real-time running status data based on the third quartile and the interquartile range;

[0040] In the real-time operating status data, data outside the anomaly detection lower limit to the anomaly detection upper limit is identified as abnormal data;

[0041] The abnormal data in the real-time operating status data is removed to obtain the real-time operating status data after the abnormal data is removed.

[0042] Optionally, after acquiring the real-time operating status data corresponding to the target continuous casting device, the method further includes:

[0043] Based on the real-time operating status data, it is determined whether the target continuous casting device is operating abnormally;

[0044] If the target continuous casting device malfunctions, an malfunction alarm message is generated and sent to the maintenance personnel's terminal so that the maintenance personnel can perform maintenance on the target continuous casting device based on the malfunction alarm message.

[0045] According to a second aspect of the present invention, a digital twin-based continuous casting apparatus is provided, comprising:

[0046] The construction unit is used to build a preset digital twin model of continuous casting based on the actual continuous casting scenario data corresponding to the target continuous casting device;

[0047] The acquisition unit is used to acquire, in response to the continuous casting signal of the target continuous casting device for the current continuous casting process, the real-time operating status data of the target continuous casting device and the real-time continuous casting process parameters under the current continuous casting process.

[0048] The analysis unit is used to analyze the solidification process of the billet in the next continuous casting process based on the real-time operating status data and the real-time continuous casting process parameters, using the preset continuous casting digital twin model, and to obtain the behavior law of the solidification process of the billet in the next continuous casting process.

[0049] The determining unit is used to determine the predicted operating status data of the target continuous casting device in the next continuous casting process based on the behavior law of the solidification process of the billet.

[0050] A control unit is used to control the continuous casting operation of the target continuous casting device for the next continuous casting process based on the predicted operating status data.

[0051] According to a third aspect of the present invention, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the above-described digital twin-based continuous casting method.

[0052] According to a fourth aspect of the present invention, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the above-described continuous casting method based on digital twins.

[0053] According to the present invention, a continuous casting method, apparatus, storage medium, and computer equipment based on digital twins, compared with the current method of realizing the continuous casting process by manually controlling the operation of the continuous casting machine, the present invention constructs a preset continuous casting digital twin model based on the actual continuous casting scenario data corresponding to the target continuous casting device; and in response to the continuous casting signal of the target continuous casting device for the current continuous casting process, acquires the real-time operating status data of the target continuous casting device and the real-time continuous casting process parameters under the current continuous casting process; simultaneously, based on the real-time operating status data and the real-time continuous casting process parameters, the preset continuous casting digital twin model is used to analyze the solidification process of the billet under the next continuous casting process to obtain the behavior law of the billet solidification process under the next continuous casting process; then, based on the behavior law of the billet solidification process, the predicted operating status data of the target continuous casting device under the next continuous casting process is determined; finally, based on the predicted operating status data, the continuous casting operation of the target continuous casting device for the next continuous casting process is controlled. Therefore, by constructing a digital twin model corresponding to a real continuous casting scenario, the real-time operating status data of the target continuous casting device in the real continuous casting scenario and the real-time continuous casting process parameters under the current continuous casting process are fed into the digital twin model. Based on the data obtained from the real continuous casting scenario, the solidification process of the billet is analyzed in real time through the digital twin model to obtain the behavior law of the billet solidification process. Then, based on the behavior law of the billet solidification process, the predicted operating status data of the target continuous casting device under the next continuous casting process is determined. Finally, based on the predicted operating status data, the continuous casting operation of the target continuous casting device for the next continuous casting process is controlled. Thus, by using digital modeling to modularly and digitally reconstruct the key process simulation system of the continuous casting process, a prototype mirror of the key process simulation system of the digital continuous casting process is built, namely the digital twin model. This solves the problem of difficult on-site operation control in existing continuous casting research. Through the digital twin model, the behavior law of the billet solidification process can be accurately predicted, thereby enabling precise control of the operating status of the target continuous casting device, which in turn improves continuous casting efficiency and accuracy, and improves the quality of the billet obtained by continuous casting. Attached Figure Description

[0054] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0055] Figure 1 A flowchart of a continuous casting method based on digital twins provided by an embodiment of the present invention is shown;

[0056] Figure 2 A flowchart of another continuous casting method based on digital twins provided by an embodiment of the present invention is shown;

[0057] Figure 3A schematic diagram of a continuous casting device based on digital twins provided in an embodiment of the present invention is shown;

[0058] Figure 4 A schematic diagram of another continuous casting device based on digital twin provided in an embodiment of the present invention is shown;

[0059] Figure 5 A schematic diagram of the physical structure of a computer device provided in an embodiment of the present invention is shown. Detailed Implementation

[0060] The present invention will be described in detail below with reference to the accompanying drawings and embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in the present application can be combined with each other.

[0061] Currently, the method of controlling the operation of the continuous casting machine manually to achieve the continuous casting process results in low continuous casting efficiency. At the same time, due to the uneven skill levels of the staff, errors in the control of the continuous casting machine may occur, leading to low accuracy in continuous casting.

[0062] To address the aforementioned problems, embodiments of the present invention provide a continuous casting method based on digital twins, such as... Figure 1 As shown, the method includes:

[0063] 101. Based on the actual continuous casting scenario data corresponding to the target continuous casting device, construct a preset continuous casting digital twin model.

[0064] The actual continuous casting scenario data refers to all data related to the continuous casting process, including the three-dimensional dimensions and position data of the target continuous casting device, the three-dimensional dimensions of the continuous casting model, and the process data of the continuous casting site. The target continuous casting device is the continuous casting device that needs to be controlled in this embodiment of the invention, such as a continuous casting machine. The target continuous casting device refers to a device that uses continuous casting technology to directly solidify high-temperature molten steel into a billet (such as a slab) or other profile with a predetermined shape and size.

[0065] In this embodiment of the invention, based on digital twin technology and modular design concepts, a modular digital reconstruction of the key process simulation system for continuous casting is performed using digital modeling. A prototype mirror of the digital continuous casting process key process simulation system is built, i.e., a preset continuous casting digital twin model. This meets the multi-level testing requirements, such as continuous casting machine system verification, and solves the problem of difficult on-site operation control in existing continuous casting research. The simulator kernel unit simulates the casting machine status and main pouring conditions in conjunction with the actual continuous casting production process, making it applicable to different types of continuous casting machines, thus achieving the versatility of the offline system in this invention. Furthermore, this embodiment of the invention can handle real-time changes in pouring temperature and casting speed, and loads a dynamic secondary cooling system that changes with casting speed. Adaptive slicing avoids the slowdown in calculation speed caused by slice accumulation at low casting speeds in traditional real-time heat transfer models. Finally, all input condition parameters are set as preset interfaces, and an HMI (Human Machine Interface) is provided for user convenience and further research. This invention can quantitatively describe the behavior of the billet temperature field under various processes (reduction, water volume, etc.), and can also simulate the influence of different casting conditions (section, casting speed, steel grade, superheat, etc.) on characteristic temperature points (solidification endpoint, surface temperature, etc.) of the billet. Accurate and rapid temperature field prediction provides a theoretical basis for the formulation of the operating status, process, and working conditions of the continuous casting machine, ultimately achieving the research goal of improving the production quality of continuously cast billets. This invention provides open interfaces for all input parameters, allowing for convenient and clear input and modification of relevant parameters. Furthermore, the interface allows for secondary development of the model, further refining it and providing a software foundation for deeper scientific research. This invention is mainly applicable to scenarios involving continuous casting of billets. The executing entity of this invention is a device or equipment capable of continuous casting of billets, specifically located on a server side.

[0066] 102. In response to the continuous casting signal from the target continuous casting unit for the current continuous casting process, acquire the real-time operating status data of the target continuous casting unit and the real-time continuous casting process parameters under the current continuous casting process.

[0067] Among them, real-time operating status data refers to the reduction amount, water injection amount, roll gap, cooling temperature, solidification temperature, drawing parameters, and cutting parameters set at any time for the target continuous casting machine; real-time continuous casting process parameters refer to data such as drawing speed, tundish temperature, steel grade, cold billet width, cold billet thickness, and water meter readings during continuous casting in the target real continuous casting scenario.

[0068] In this embodiment of the invention, upon receiving the continuous casting signal from the target continuous casting device, the on-site personnel have already started the target continuous casting device for continuous casting operation. Since the data between the preset continuous casting digital twin model and the real continuous casting scenario is bidirectional, when the continuous casting signal is received, the preset continuous casting digital twin model can obtain any data from the real continuous casting scenario, such as the real-time operating status data of the target continuous casting device and the real-time continuous casting process parameters under the current continuous casting process. Subsequently, based on the real-time operating status data and the real-time continuous casting process parameters, the preset continuous casting digital twin model can analyze the behavior law of the billet solidification process under the next continuous casting process. Finally, based on the behavior law of the billet solidification process, it determines the operating state that the target continuous casting device should be set for the next continuous casting process, and controls the target continuous casting device to perform continuous casting operation according to the operating state, thereby improving continuous casting efficiency and accuracy.

[0069] 103. Based on real-time operating status data and real-time continuous casting process parameters, the solidification process of the billet under the next continuous casting process is analyzed using a preset continuous casting digital twin model to obtain the behavior law of the billet solidification process under the next continuous casting process.

[0070] In this embodiment of the invention, after entering the interface of the digital twin system for key continuous casting processes, before starting the simulation of key processes in continuous casting, a target continuous casting device is selected. Then, based on the analysis and research results, a target process model is selected (wherein, the target process model refers to the process that requires molten steel and other elements to be continuously cast into a billet according to the pattern of the target process model). After that, real-time data from the field is acquired, including real-time operating status data and real-time continuous casting process parameters. Anomaly detection and standardization processing are performed on the real-time operating status data and real-time continuous casting process parameters to obtain processed real-time operating status data and real-time continuous casting process parameters. Then, the server starts reading system settings and runtime data every clock cycle. After that, the processed data measured by the data acquisition system is continuously imported into the basic data model database. The processed real-time data from the field (real-time operating status data and real-time continuous casting process parameters) is imported into the preset continuous casting digital twin model through the data initialization module to start the continuous casting process reproduction. The built-in intelligent analysis algorithm is used for comparative analysis to obtain the billet solidification process behavior law under the next continuous casting process. Based on the billet solidification process behavior law, the operating conditions and equipment status of the next continuous casting process are dynamically evaluated, diagnosed, and predicted. Furthermore, the preset continuous casting digital twin model will combine the uploaded data to conduct digital twin experiments, generating twin data. Operators can directly view information that is difficult to observe in actual processing online, including a three-dimensional temperature field display, a solid-liquid phase line display, historical data of key process variables, stress and strain extraction at locations, and control of key variables. For example, if the physical property parameter calculation module is selected, twin data of the key process simulation system of continuous casting will be generated, providing data support for temperature field, thermal shrinkage, etc., and establishing a dynamic link library of thermophysical parameters that can be called for calculations during solidification heat transfer simulation. The preset continuous casting digital twin model is used to perform operational analysis and production process analysis of the target continuous casting unit based on the twin data from the previous step, and to determine the prediction information for the next continuous casting process based on the analysis results, completing data monitoring and management tasks. Therefore, by constructing a pre-set digital twin model of continuous casting that corresponds to the real continuous casting scenario, the continuous casting process can be reproduced through the digital twin model. This allows for the accurate acquisition of the behavior law of the billet solidification process. Based on the behavior law of the billet solidification process, the operating status of the target continuous casting device in the next continuous casting process can be accurately predicted. Finally, by using the accurate operating status, the continuous casting process of the continuous casting device can be reasonably controlled, thereby improving the efficiency and accuracy of continuous casting.

[0071] 104. Based on the behavior law of the billet solidification process, determine the predicted operating status data of the target continuous casting unit in the next continuous casting process.

[0072] Among them, the preset operating status data refers to the operating status that the target continuous casting device should be set in the next continuous casting process in order to obtain high-quality billets, including data such as reduction amount, water volume, and roll gap.

[0073] In this embodiment of the invention, after predicting the behavior of the billet solidification process in the next continuous casting process through a preset continuous casting digital twin model, in order to ensure that a high-quality billet is obtained after continuous casting, the predicted operating status data of the target continuous casting device in the next continuous casting process can be determined according to the behavior of the billet solidification process. The target continuous casting device can then perform continuous casting operation according to the predicted operating status data to obtain a high-quality billet.

[0074] 105. Based on the predicted operating status data, control the continuous casting operation of the target continuous casting unit for the next continuous casting process.

[0075] In this embodiment of the invention, after predicting the operating status data of the target continuous casting device in the next continuous casting process, the preset continuous casting digital twin model will input the predicted operating status data to the target continuous casting device in the real continuous casting scenario in real time, thereby enabling real-time control of the continuous casting operation of the target continuous casting device. This embodiment of the invention proposes and sets an HMI (Human-Machine Interface) input interface. After acquiring the digital twin data from the real continuous casting scenario, these results are presented to the user through data visualization methods, achieving continuous casting process simulation at the second level, real-time acquisition of the time scale, efficient data extraction, and output of computational information, including the computational information of the digital twin operation. This computational information includes: the behavior law of the billet solidification process, etc. Simultaneously, it can also output a three-dimensional temperature field display, a solid-liquid phase line display, historical data of key process variables, stress-strain interception at location, key variable control, and other information. Based on the above information, the operating status that the target continuous casting device should be set in the next continuous casting process can be accurately predicted, thereby improving continuous casting efficiency and accuracy, and ensuring the formation of high-quality billets.

[0076] According to the present invention, a continuous casting method based on digital twins, compared with the current method of realizing the continuous casting process by manually controlling the operation of the continuous casting machine, the present invention constructs a preset continuous casting digital twin model based on the actual continuous casting scenario data corresponding to the target continuous casting device; and in response to the continuous casting signal of the target continuous casting device for the current continuous casting process, acquires the real-time operating status data of the target continuous casting device and the real-time continuous casting process parameters under the current continuous casting process; simultaneously, based on the real-time operating status data and the real-time continuous casting process parameters, the preset continuous casting digital twin model is used to analyze the solidification process of the billet under the next continuous casting process to obtain the behavior law of the billet solidification process under the next continuous casting process; then, based on the behavior law of the billet solidification process, the predicted operating status data of the target continuous casting device under the next continuous casting process is determined; finally, based on the predicted operating status data, the continuous casting operation of the target continuous casting device for the next continuous casting process is controlled. Therefore, by constructing a digital twin model corresponding to a real continuous casting scenario, the real-time operating status data of the target continuous casting device in the real continuous casting scenario and the real-time continuous casting process parameters under the current continuous casting process are fed into the digital twin model. Based on the data obtained from the real continuous casting scenario, the solidification process of the billet is analyzed in real time through the digital twin model to obtain the behavior law of the billet solidification process. Then, based on the behavior law of the billet solidification process, the predicted operating status data of the target continuous casting device under the next continuous casting process is determined. Finally, based on the predicted operating status data, the continuous casting operation of the target continuous casting device for the next continuous casting process is controlled. Thus, by using digital modeling to modularly and digitally reconstruct the key process simulation system of the continuous casting process, a prototype mirror of the key process simulation system of the digital continuous casting process is built, namely the digital twin model. This solves the problem of difficult on-site operation control in existing continuous casting research. Through the digital twin model, the behavior law of the billet solidification process can be accurately predicted, thereby enabling precise control of the operating status of the target continuous casting device, which in turn improves continuous casting efficiency and accuracy, and improves the quality of the billet obtained by continuous casting.

[0077] Furthermore, to better illustrate the above-described continuous casting process based on digital twins, as a refinement and extension of the above embodiments, this invention provides another continuous casting method based on digital twins, such as... Figure 2 As shown, the method includes:

[0078] 201. Based on the actual continuous casting scenario data corresponding to the target continuous casting device, construct a preset continuous casting digital twin model.

[0079] Specifically, firstly, real continuous casting scene data corresponding to the target continuous casting device is collected, and based on the real continuous casting scene data, the real continuous casting scene is modularly and digitally reconstructed using digital modeling to build a prototype mirror of a key process simulation system for digital continuous casting, thus obtaining a preset digital twin model of continuous casting.

[0080] 202. In response to the continuous casting signal from the target continuous casting device for the current continuous casting process, acquire the real-time operating status data of the target continuous casting device and the real-time continuous casting process parameters under the current continuous casting process.

[0081] Specifically, when a continuous casting signal is received from the target continuous casting unit for the current continuous casting process, the real-time operating status data of the target continuous casting unit and the real-time continuous casting process parameters under the current continuous casting process are acquired. The real-time operating status data and real-time continuous casting process parameters are input into a preset continuous casting digital twin model. Through the preset continuous casting digital twin model, the solidification process of the billet can be analyzed, thereby obtaining the behavior law of the billet solidification process under the next continuous casting process. Then, based on the behavior law of the billet solidification process, while ensuring the generation of high-quality billets, the predicted operating status data of the target continuous casting unit under the next continuous casting process is determined. Finally, based on the predicted operating status data, the continuous casting operation of the target continuous casting unit for the next continuous casting process is controlled. Thus, the operating status data of the continuous casting unit under the next continuous casting process is determined through the digital twin method, and the continuous casting unit is finally controlled to perform continuous casting operation according to the operating status data, which can improve the continuous casting efficiency and accuracy, thereby ensuring the generation of high-quality billets.

[0082] 203. Standardize the real-time operating status data and real-time continuous casting process parameters to obtain standardized operating status data and standardized continuous casting process parameters.

[0083] According to an embodiment of the present invention, after obtaining the real-time operating status data of the target continuous casting device, in order to ensure the smooth operation of the target continuous casting device, it is also necessary to detect the operating status of the target continuous casting device. Based on this, the method includes: determining whether the target continuous casting device is operating abnormally based on the real-time operating status data; if the target continuous casting device is operating abnormally, generating an abnormal operation alarm message and sending the abnormal operation alarm message to the maintenance personnel terminal, so that the maintenance personnel at the maintenance personnel terminal can perform maintenance on the target continuous casting device based on the abnormal operation alarm message.

[0084] Specifically, based on real-time operational status data, it is possible to detect whether the target continuous casting unit is operating normally. If the target continuous casting unit is operating normally, the operational status of the target continuous casting unit in the next continuous casting process can be predicted. If the target continuous casting unit is operating abnormally, an abnormal alarm message needs to be generated. This abnormal alarm message contains the identification information of the target continuous casting unit and the abnormality type, and the abnormal alarm message is sent to the operation and maintenance personnel via preset communication methods such as SMS and email, so that the operation and maintenance personnel can carry out maintenance on the target continuous casting unit based on the abnormal alarm message.

[0085] In this embodiment of the invention, to improve the accuracy of continuous casting, after obtaining the real-time operating status data of the target continuous casting device and the real-time continuous casting process parameters under the current continuous casting process, it is first necessary to exclude abnormal data in the real-time operating status data and real-time continuous casting process parameters. Based on this, the method includes: determining the median corresponding to the real-time operating status data, and determining a first intermediate value between the minimum value in the real-time operating status data and the median, and determining the first intermediate value as the first quartile corresponding to the real-time operating status data; determining a second intermediate value between the maximum value in the real-time operating status data and the median, and determining the second intermediate value as the third quartile corresponding to the real-time operating status data; calculating the distance between the first quartile and the third quartile, and determining the distance as the interquartile range corresponding to the real-time operating status data; calculating the lower limit value for anomaly detection corresponding to the real-time operating status data based on the first quartile and the interquartile range; calculating the upper limit value for anomaly detection corresponding to the real-time operating status data based on the third quartile and the interquartile range; and adjusting the values ​​from the lower limit value to the upper limit value in the real-time operating status data. Data outside the specified values ​​are identified as abnormal data. Abnormal data is removed from the real-time operating status data to obtain anomaly-free real-time operating status data. The median corresponding to the real-time continuous casting process parameters is determined, and a first intermediate value between the minimum value and the median is determined, with the first intermediate value being designated as the first quartile corresponding to the real-time continuous casting process parameters. A second intermediate value between the maximum value and the median is determined, with the second intermediate value being designated as the third quartile corresponding to the real-time continuous casting process parameters. The distance between the first quartile and the third quartile is calculated, and this distance is designated as the interquartile range corresponding to the real-time continuous casting process parameters. Anomaly detection lower limit is calculated based on the first quartile and the interquartile range. Anomaly detection upper limit is calculated based on the third quartile and the interquartile range. Data outside the anomaly detection lower limit to the anomaly detection upper limit in the real-time continuous casting process parameters is identified as abnormal data. Abnormal data is removed from the real-time continuous casting process parameters to obtain anomaly-free real-time continuous casting process parameters.

[0086] Specifically, first, the median Q2 of the real-time running status data is determined, which is the middle value of the dataset. Based on the median, the first quartile Q1 of the real-time running status data is determined, which is the median between the minimum and median of the dataset. Then, based on the median, the third quartile Q3 of the real-time running status data is determined, which is the median between the median and maximum value of the dataset. The interquartile range IQR of the real-time running status data is also determined, which is the distance between the first and third quartiles. Finally, the upper limit value (upper = Q3 + 1.5 * IQR) and the lower limit value (lower = Q1) of the real-time running status data are calculated. -1.5*IQR is used to identify data outside the lower-upper range in the real-time operating status data. This data is then classified as anomalous and removed from the real-time operating status data, resulting in the anomaly-free data. Similarly, when identifying anomalous data in the real-time continuous casting process parameters, the median Q2 (the middle value in the dataset) is first used. Based on the median, the first quartile Q1 (the median between the minimum and median) is determined. Then, based on the median, the third quartile Q3 (the median between the median and maximum value) is determined. The interquartile range IQR (the distance between the first and third quartiles) is also determined. Finally, the upper limit (upper = Q3 + 1.5*IQR) and lower limit (lower = Q1) of the real-time continuous casting process parameters are calculated. -1.5*IQR, finally the data outside the lower-upper range in the real-time continuous casting process parameters are determined, and the data outside the lower-upper range are identified as abnormal data. Finally, the abnormal data in the real-time continuous casting process parameters are deleted to obtain the real-time continuous casting process parameters after the abnormal data is eliminated.

[0087] Furthermore, to improve the computational efficiency and accuracy of the preset continuous casting digital twin model, it is also necessary to standardize the real-time operating status data and the real-time continuous casting process parameters after the rejection of defects. Based on this, step 203 specifically includes: determining the maximum and minimum operating status data in the real-time operating status data, and subtracting the maximum and minimum operating status data to obtain the operating status interval value; subtracting the minimum and maximum operating status data to obtain the real-time operating status difference value; dividing the real-time operating status difference value by the operating status interval value to obtain the standardized operating status data corresponding to the real-time operating status data; determining the maximum and minimum continuous casting process parameters in the real-time continuous casting process parameters, and subtracting the maximum and minimum continuous casting process parameters to obtain the continuous casting process interval value; subtracting the minimum and maximum continuous casting process parameters to obtain the real-time continuous casting process difference value; dividing the real-time continuous casting process difference value by the continuous casting process interval value to obtain the standardized continuous casting process parameters corresponding to the real-time continuous casting process parameters.

[0088] Specifically, the real-time operating status data can be standardized using the following formula:

[0089]

[0090] Where, x b This represents standardized operational status data, where x represents real-time operational status data. max This represents the maximum running status data, x min This represents the minimum operating status data, and thus, the above formula enables the standardized processing of real-time operating status data.

[0091] Furthermore, the real-time continuous casting process parameters can be standardized using the following formula:

[0092]

[0093] Among them, y b y represents the standardized continuous casting process parameters, and y represents the real-time continuous casting process parameters. max This represents the maximum continuous casting process parameter, y. min This represents the minimum continuous casting process parameter, and thus, the standardization of real-time continuous casting process parameters can be achieved according to the above formula.

[0094] 204. Based on standardized operating status data and standardized continuous casting process parameters, the solidification process of the billet under the next continuous casting process is analyzed using a preset continuous casting digital twin model to obtain the behavior law of the billet solidification process under the next continuous casting process.

[0095] The preset continuous casting digital twin model is a pre-trained and constructed model. The preset continuous casting digital twin model includes: a thermophysical parameter calculation layer, a thermal shrinkage parameter calculation layer, a microstructure prediction layer, a hydrocarbon calculation layer, a billet force calculation layer, and a behavior law prediction layer.

[0096] In this embodiment of the invention, after the real-time operating status data and real-time continuous casting process parameters are processed for rejection and standardization, it is necessary to analyze the solidification process of the billet in the next continuous casting process based on the above data. Therefore, step 204 specifically includes: inputting the real-time operating status data and the real-time continuous casting process parameters into the thermophysical property parameter calculation layer for parameter calculation to obtain the thermophysical property parameters of the billet in the next continuous casting process; inputting the real-time operating status data and the real-time continuous casting process parameters into the thermal shrinkage parameter calculation layer for parameter calculation to obtain the thermal shrinkage parameters of the billet in the next continuous casting process; inputting the real-time operating status data and the real-time continuous casting process parameters into the group... The microstructure prediction layer predicts the microstructure parameters to obtain the billet microstructure parameters for the next continuous casting process; the real-time operating status data and the real-time continuous casting process parameters are input to the hydrocarbon calculation layer to calculate the precipitation data to obtain the billet hydrocarbon precipitation data for the next continuous casting process; the real-time operating status data and the real-time continuous casting process parameters are input to the billet pressing force calculation layer to calculate the billet pressing force to obtain the billet pressing force data for the next continuous casting process; the thermophysical parameters, thermal shrinkage parameters, billet microstructure parameters, hydrocarbon precipitation data, and billet pressing force data are input to the behavior law prediction layer to predict the behavior law of the billet solidification process for the next continuous casting process. Specifically, the method for determining the solidification process behavior of the billet under the next continuous casting process includes: based on the thermophysical parameters, thermal shrinkage parameters, billet microstructure parameters, hydrocarbon precipitation data, and billet pressing force data, determining the three-dimensional temperature field diagram, solid-liquid phase line diagram, and stress-strain data at different positions of the billet under the next continuous casting process; inputting the three-dimensional temperature field diagram, solid-liquid phase line diagram, and stress-strain data into the behavior prediction layer to predict the behavior, thereby obtaining the solidification process behavior of the billet under the next continuous casting process.

[0097] Among them, the three-dimensional temperature field diagram refers to the temperature distribution at different locations of the semi-cast billet in three-dimensional space, the solid-liquid phase line diagram refers to the solid phase line and the liquid phase line. The solid phase line is entirely composed of solid phase, and the liquid phase line generally refers to the temperature at the intersection of solid and liquid states of molten steel.

[0098] Specifically, real-time operating status data and the real-time continuous casting process parameters are input into the thermophysical property parameter calculation layer. This layer outputs the billet thermophysical properties, such as temperature and solute, for the next continuous casting process. Simultaneously, the real-time operating status data and real-time continuous casting process parameters are input into the thermal shrinkage parameter calculation layer for parameter calculation. This layer outputs the billet thermal shrinkage parameters, such as the bulging effect of the non-uniform solidification process, for the next continuous casting process. Furthermore, the real-time operating status data and real-time continuous casting process parameters are input into the microstructure prediction layer for microstructure parameter prediction. This layer outputs the billet microstructure parameters for the next continuous casting process, including austenite grain size cloud map, grain boundary migration rate curve, corner ferrite film thickness curve, and austenite side carbon concentration distribution curve. Finally, the real-time operating status data and real-time continuous casting process parameters are input into the hydrocarbon calculation layer for further analysis. The precipitation data calculation layer can output data such as the amount of carbonitride precipitation and the distribution map of carbonitride precipitation at different locations on the billet for the next continuous casting process. Simultaneously, real-time operating status data and real-time continuous casting process parameters are input to the billet pressure calculation layer for billet pressure calculation. This layer can output data such as strain, temperature, and stress on the billet pressure for the next continuous casting process. Then, based on thermophysical parameters, thermal shrinkage parameters, billet microstructure parameters, hydrocarbon precipitation data, and billet pressure data, a three-dimensional temperature field map, a solid-liquid phase line map, and stress-strain data at different locations on the billet can be plotted for the next continuous casting process. Finally, the three-dimensional temperature field map, solid-liquid phase line map, and stress-strain data are input to the behavior prediction layer for behavior prediction. The behavior prediction layer then outputs the behavior law of the billet solidification process for the next continuous casting process.

[0099] 205. Based on the behavior law of the billet solidification process, determine the predicted operating status data of the target continuous casting device in the next continuous casting process.

[0100] 206. Based on the predicted operating status data, control the continuous casting operation of the target continuous casting unit for the next continuous casting process.

[0101] The predicted operating status data includes: predicted reduction, predicted water volume, and predicted roll gap. Reduction is one of the technical parameters of casting, used to measure the amount of plastic deformation between the casting billet material and the mandrel. Water volume refers to the amount of cooling water used by the continuous casting device. Roll gap refers to the gap left between the two ends of the roll when the continuous casting device is working.

[0102] In this embodiment of the invention, after determining the behavior pattern of the billet solidification process in the next continuous casting process, the predicted operating status data of the target continuous casting device in the next continuous casting process can be determined by the billet solidification process behavior pattern, while ensuring the acquisition of high-quality billets. Then, based on the predicted operating status data, the continuous casting operation of the target continuous casting device for the next continuous casting process is controlled. Based on this, step 206 specifically includes: controlling the target continuous casting device to perform a reduction operation for the next continuous casting process based on the predicted reduction amount; controlling the target continuous casting device to perform a water volume adjustment operation for the next continuous casting process based on the predicted water volume; and controlling the target continuous casting device to perform a roll gap adjustment operation for the next continuous casting process based on the predicted roll gap.

[0103] Specifically, after predicting the operating status data that the target continuous casting unit should be set to produce high-quality billets, that is, after predicting the predicted reduction, predicted water volume, and predicted roll gap for the next continuous casting process of the target continuous casting unit, the current reduction of the target continuous casting unit can be adjusted to the predicted reduction based on the predicted reduction, the current cooling water volume of the target continuous casting unit can be adjusted to the predicted water volume based on the predicted water volume, and the current gap between the rolls of the target continuous casting unit can be adjusted to the predicted roll gap based on the predicted roll gap. Thus, the target continuous casting unit can perform the next continuous casting process by adjusting the operating status, and high-quality billets can be obtained after continuous casting is completed.

[0104] In the continuous casting process of this invention embodiment, the CNN-LSTM model (convolutional neural network-long short-term memory) can also be used for abnormal working condition monitoring and identification.

[0105] According to another continuous casting method based on digital twins provided by the present invention, compared with the current method of realizing the continuous casting process by manually controlling the operation of the continuous casting machine, the present invention constructs a preset continuous casting digital twin model based on the actual continuous casting scenario data corresponding to the target continuous casting device; and in response to the continuous casting signal of the target continuous casting device for the current continuous casting process, it acquires the real-time operating status data of the target continuous casting device and the real-time continuous casting process parameters under the current continuous casting process; simultaneously, based on the real-time operating status data and the real-time continuous casting process parameters, it uses the preset continuous casting digital twin model to analyze the solidification process of the billet under the next continuous casting process, and obtains the behavior law of the billet solidification process under the next continuous casting process; then, based on the behavior law of the billet solidification process, it determines the predicted operating status data of the target continuous casting device under the next continuous casting process; finally, based on the predicted operating status data, it controls the continuous casting operation of the target continuous casting device for the next continuous casting process. Therefore, by constructing a digital twin model corresponding to a real continuous casting scenario, the real-time operating status data of the target continuous casting device in the real continuous casting scenario and the real-time continuous casting process parameters under the current continuous casting process are fed into the digital twin model. Based on the data obtained from the real continuous casting scenario, the solidification process of the billet is analyzed in real time through the digital twin model to obtain the behavior law of the billet solidification process. Then, based on the behavior law of the billet solidification process, the predicted operating status data of the target continuous casting device under the next continuous casting process is determined. Finally, based on the predicted operating status data, the continuous casting operation of the target continuous casting device for the next continuous casting process is controlled. Thus, by using digital modeling to modularly and digitally reconstruct the key process simulation system of the continuous casting process, a prototype mirror of the key process simulation system of the digital continuous casting process is built, namely the digital twin model. This solves the problem of difficult on-site operation control in existing continuous casting research. Through the digital twin model, the behavior law of the billet solidification process can be accurately predicted, thereby enabling precise control of the operating status of the target continuous casting device, which in turn improves continuous casting efficiency and accuracy, and improves the quality of the billet obtained by continuous casting.

[0106] Furthermore, as Figure 1 In a specific implementation, this invention provides a continuous casting device based on digital twins, such as... Figure 3 As shown, the device includes: a construction unit 31, an acquisition unit 32, an analysis unit 33, a determination unit 34, and a control unit 35.

[0107] The construction unit 31 can be used to construct a preset digital twin model of continuous casting based on the actual continuous casting scenario data corresponding to the target continuous casting device.

[0108] The acquisition unit 32 can be used to acquire the real-time operating status data of the target continuous casting device and the real-time continuous casting process parameters under the current continuous casting process in response to the continuous casting signal of the target continuous casting device for the current continuous casting process.

[0109] The analysis unit 33 can be used to analyze the solidification process of the billet in the next continuous casting process based on the real-time operating status data and the real-time continuous casting process parameters, using the preset continuous casting digital twin model, to obtain the behavior law of the billet solidification process in the next continuous casting process.

[0110] The determining unit 34 can be used to determine the predicted operating status data of the target continuous casting device in the next continuous casting process based on the behavior law of the billet solidification process.

[0111] The control unit 35 can be used to control the continuous casting operation of the target continuous casting device for the next continuous casting process based on the predicted operating status data.

[0112] In specific application scenarios, in order to determine the behavior of the billet solidification process in the next continuous casting process, such as... Figure 4 As shown, the analysis unit 33 includes a calculation module 331 and a prediction module 332.

[0113] The calculation module 331 can be used to perform parameter calculations based on the real-time operating status data and the real-time continuous casting process parameters input to the thermophysical parameter calculation layer, so as to obtain the thermophysical parameters of the billet under the next continuous casting process.

[0114] The calculation module 331 can also be used to input the real-time operating status data and the real-time continuous casting process parameters into the heat shrinkage parameter calculation layer to calculate the parameters and obtain the billet heat shrinkage parameters under the next continuous casting process.

[0115] The prediction module 332 can be used to input the real-time operating status data and the real-time continuous casting process parameters into the microstructure prediction layer to predict the microstructure parameters and obtain the microstructure parameters of the billet under the next continuous casting process.

[0116] The calculation module 331 can also be used to input the real-time operating status data and the real-time continuous casting process parameters into the hydrocarbon calculation layer to calculate the precipitation data and obtain the billet hydrocarbon precipitation data under the next continuous casting process.

[0117] The calculation module 331 can also be used to input the real-time operating status data and the real-time continuous casting process parameters into the billet pressure calculation layer to calculate the billet pressure and obtain the billet pressure data under the next continuous casting process.

[0118] The prediction module 332 can also be used to input the thermal property parameters, thermal shrinkage parameters, billet microstructure parameters, hydrocarbon precipitation data, and billet pressing force data into the behavior pattern prediction layer to predict the behavior pattern and obtain the billet solidification process behavior pattern under the next continuous casting process.

[0119] In specific application scenarios, in order to obtain the behavior law of the billet solidification process under the next continuous casting process, the prediction module 332 can be used to determine the three-dimensional temperature field diagram, solid-liquid phase line diagram, and stress-strain data map of different positions of the billet under the next continuous casting process based on the thermophysical parameters, thermal shrinkage parameters, billet microstructure parameters, hydrocarbon precipitation data, and billet pressure data; input the three-dimensional temperature field diagram, solid-liquid phase line diagram, and stress-strain data map into the behavior law prediction layer to predict the behavior law, and obtain the behavior law of the billet solidification process under the next continuous casting process.

[0120] In specific application scenarios, in order to control the continuous casting operation of the target continuous casting device for the next continuous casting process, the control unit 35 can be specifically used to control the target continuous casting device to perform a reduction operation for the next continuous casting process based on the predicted reduction amount; to control the target continuous casting device to perform a water volume adjustment operation for the next continuous casting process based on the predicted water volume; and to control the target continuous casting device to perform a roll gap adjustment operation for the next continuous casting process based on the predicted roll gap.

[0121] In specific application scenarios, in order to standardize real-time operating status data and real-time continuous casting process parameters, the device further includes a standardization unit 36.

[0122] The standardization unit 36 ​​can be used to determine the maximum and minimum operating status data in the real-time operating status data, and subtract the maximum and minimum operating status data to obtain the operating status interval value; subtract the minimum operating status data from the real-time operating status data to obtain the real-time operating status difference value; divide the real-time operating status difference value by the operating status interval value to obtain the standardized operating status data corresponding to the real-time operating status data; determine the maximum and minimum continuous casting process parameters in the real-time continuous casting process parameters, and subtract the maximum and minimum continuous casting process parameters to obtain the continuous casting process interval value; subtract the minimum and maximum continuous casting process parameters to obtain the real-time continuous casting process difference value; divide the real-time continuous casting process difference value by the continuous casting process interval value to obtain the standardized continuous casting process parameters corresponding to the real-time continuous casting process parameters.

[0123] The analysis unit 33 can also be used to analyze the solidification process of the billet in the next continuous casting process based on the standardized operating status data and the standardized continuous casting process parameters, using the preset continuous casting digital twin model, to obtain the behavior law of the billet solidification process in the next continuous casting process.

[0124] In specific application scenarios, in order to exclude abnormal data in the real-time operating status data, the device further includes an exclusion unit 37.

[0125] The exclusion unit 37 can be used to determine the median corresponding to the real-time operating status data, and to determine a first intermediate value between the minimum value in the real-time operating status data and the median, and to determine the first intermediate value as the first quartile corresponding to the real-time operating status data; to determine a second intermediate value between the maximum value in the real-time operating status data and the median, and to determine the second intermediate value as the third quartile corresponding to the real-time operating status data; to calculate the distance between the first quartile and the third quartile, and to determine the distance as the interquartile range corresponding to the real-time operating status data; to calculate the lower limit value for anomaly detection corresponding to the real-time operating status data based on the first quartile and the interquartile range; to calculate the upper limit value for anomaly detection corresponding to the real-time operating status data based on the third quartile and the interquartile range; to determine the data outside the lower limit value to the upper limit value for anomaly detection in the real-time operating status data as anomaly data; and to remove the anomaly data from the real-time operating status data to obtain the excluded real-time operating status data.

[0126] In specific application scenarios, in order to detect the operation of the continuous casting device, the device also includes a maintenance unit 38.

[0127] The maintenance unit 38 can be used to determine whether the target continuous casting device is operating abnormally based on the real-time operating status data; if the target continuous casting device is operating abnormally, an abnormal operation alarm message is generated and sent to the maintenance personnel terminal so that the maintenance personnel on the maintenance personnel terminal can perform maintenance on the target continuous casting device based on the abnormal operation alarm message.

[0128] It should be noted that other corresponding descriptions of the functional modules involved in the digital twin-based continuous casting device provided in this embodiment of the invention can be found in [reference needed]. Figure 1 The corresponding descriptions of the methods shown will not be repeated here.

[0129] Based on the above, Figure 1Accordingly, this embodiment of the invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, performs the following steps: constructing a preset continuous casting digital twin model based on actual continuous casting scenario data corresponding to the target continuous casting device; acquiring real-time operating status data and real-time continuous casting process parameters corresponding to the target continuous casting device in response to a continuous casting signal from the target continuous casting device for the current continuous casting process; analyzing the solidification process of the billet in the next continuous casting process using the preset continuous casting digital twin model based on the real-time operating status data and the real-time continuous casting process parameters, and obtaining the behavior pattern of the billet solidification process in the next continuous casting process; determining the predicted operating status data of the target continuous casting device for the next continuous casting process based on the behavior pattern of the billet solidification process; and controlling the continuous casting operation of the target continuous casting device for the next continuous casting process based on the predicted operating status data.

[0130] Based on the above, Figure 1 The method shown and as Figure 3 The embodiment of the device shown in the invention also provides a physical structure diagram of a computer device, such as... Figure 5 As shown, the computer device includes: a processor 41, a memory 42, and a computer program stored in the memory 42 and executable on the processor. Both the memory 42 and the processor 41 are mounted on a bus 43. When the processor 41 executes the program, it performs the following steps: constructing a preset continuous casting digital twin model based on actual continuous casting scenario data corresponding to the target continuous casting device; in response to the continuous casting signal from the target continuous casting device for the current continuous casting process, acquiring real-time operating status data corresponding to the target continuous casting device and real-time continuous casting process parameters under the current continuous casting process; based on the real-time operating status data and the real-time continuous casting process parameters, analyzing the billet solidification process under the next continuous casting process using the preset continuous casting digital twin model to obtain the billet solidification process behavior pattern under the next continuous casting process; based on the billet solidification process behavior pattern, determining the predicted operating status data corresponding to the target continuous casting device under the next continuous casting process; and based on the predicted operating status data, controlling the continuous casting operation of the target continuous casting device for the next continuous casting process.

[0131] Through the technical solution of this invention, the invention constructs a preset continuous casting digital twin model based on actual continuous casting scenario data corresponding to the target continuous casting device; and in response to the continuous casting signal of the target continuous casting device for the current continuous casting process, acquires the real-time operating status data of the target continuous casting device and the real-time continuous casting process parameters under the current continuous casting process; simultaneously, based on the real-time operating status data and the real-time continuous casting process parameters, the preset continuous casting digital twin model is used to analyze the solidification process of the billet under the next continuous casting process to obtain the behavior law of the billet solidification process under the next continuous casting process; then, based on the behavior law of the billet solidification process, the predicted operating status data of the target continuous casting device under the next continuous casting process is determined; finally, based on the predicted operating status data, the continuous casting operation of the target continuous casting device for the next continuous casting process is controlled. Therefore, by constructing a digital twin model corresponding to a real continuous casting scenario, the real-time operating status data of the target continuous casting device and the real-time continuous casting process parameters under the current continuous casting process in the real continuous casting scenario are fed into the digital twin model. Based on the data obtained from the real continuous casting scenario, the solidification process of the billet is analyzed in real time through the digital twin model to obtain the behavior law of the billet solidification process. Then, based on the behavior law of the billet solidification process, the predicted operating status data of the target continuous casting device under the next continuous casting process is determined. Finally, based on the predicted operating status data, the continuous casting operation of the target continuous casting device for the next continuous casting process is controlled. Thus, by using digital modeling to modularly and digitally reconstruct the key process simulation system of the continuous casting process, a prototype mirror of the key process simulation system of the digital continuous casting process is built, namely the digital twin model. This solves the problem of difficult on-site operation control in existing continuous casting research. By obtaining the operating status data and process parameters of the continuous casting machine in the real continuous casting scenario, the digital twin model can accurately predict the behavior law of the billet solidification process, thereby enabling precise control of the operating status of the target continuous casting device, which in turn improves continuous casting efficiency and accuracy, and improves the quality of the billet obtained by continuous casting.

[0132] It is obvious to those skilled in the art that the modules or steps of the present invention described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. Optionally, they can be implemented using computer-executable program code, thereby storing them in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those presented herein, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0133] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A continuous casting method based on digital twins, characterized in that, include: Based on the actual continuous casting scenario data corresponding to the target continuous casting device, a preset digital twin model of continuous casting is constructed. In response to the continuous casting signal from the target continuous casting device for the current continuous casting process, the real-time operating status data of the target continuous casting device and the real-time continuous casting process parameters under the current continuous casting process are acquired. Based on the real-time operating status data and the real-time continuous casting process parameters, the solidification process of the billet under the next continuous casting process is analyzed using the preset continuous casting digital twin model to obtain the behavior law of the billet solidification process under the next continuous casting process. Based on the behavior pattern of the billet solidification process, the predicted operating status data of the target continuous casting device under the next continuous casting process is determined. Based on the predicted operating status data, the target continuous casting device is controlled to perform continuous casting operations for the next continuous casting process; The preset continuous casting digital twin model includes: a thermophysical property parameter calculation layer, a thermal shrinkage parameter calculation layer, a microstructure prediction layer, a hydrocarbon calculation layer, a billet pressure calculation layer, and a behavior prediction layer. Based on the real-time operating status data and the real-time continuous casting process parameters, the preset continuous casting digital twin model is used to analyze the billet solidification process in the next continuous casting process to obtain the billet solidification process behavior law in the next continuous casting process, including: Based on the real-time operating status data and the real-time continuous casting process parameters, the thermophysical property parameter calculation layer is used to calculate the parameters, obtaining the billet thermophysical property parameters for the next continuous casting process; the real-time operating status data and the real-time continuous casting process parameters are also input into the thermal shrinkage parameter calculation layer to calculate the parameters, obtaining the billet thermal shrinkage parameters for the next continuous casting process; the real-time operating status data and the real-time continuous casting process parameters are then input into the microstructure prediction layer to predict the microstructure parameters, obtaining the billet microstructure parameters for the next continuous casting process; the real-time operating status data... The real-time continuous casting process parameters are input to the hydrocarbon calculation layer to calculate precipitation data, obtaining the slab hydrocarbon precipitation data for the next continuous casting process; the real-time operating status data and the real-time continuous casting process parameters are input to the billet pressure calculation layer to calculate billet pressure, obtaining the slab billet pressure data for the next continuous casting process; the thermophysical parameters, thermal shrinkage parameters, slab microstructure parameters, hydrocarbon precipitation data, and billet pressure data are input to the behavior pattern prediction layer to predict behavior patterns, obtaining the slab solidification process behavior pattern for the next continuous casting process. The process of inputting the thermophysical parameters, thermal shrinkage parameters, billet microstructure parameters, hydrocarbon precipitation data, and billet pressing force data into the behavior prediction layer to predict the behavior of the billet solidification process under the next continuous casting process includes: Based on the aforementioned thermophysical parameters, thermal shrinkage parameters, billet microstructure parameters, hydrocarbon precipitation data, and billet pressing force data, a three-dimensional temperature field diagram, a solid-liquid phase line diagram, and a stress-strain data map at different locations of the billet are determined for the next continuous casting process. The three-dimensional temperature field diagram, solid-liquid phase line diagram, and stress-strain data map are then input into the behavior prediction layer to predict the behavior of the billet solidification process for the next continuous casting process.

2. The method according to claim 1, characterized in that, The predicted operating status data includes: predicted reduction, predicted water volume, and predicted roll gap; the control of the continuous casting operation of the target continuous casting device for the next continuous casting process based on the predicted operating status data includes: Based on the predicted reduction amount, the target continuous casting device is controlled to perform a reduction operation for the next continuous casting process; Based on the predicted water volume, the target continuous casting device is controlled to perform water volume adjustment operations for the next continuous casting process. Based on the predicted roll gap, the target continuous casting device is controlled to perform roll gap adjustment operations for the next continuous casting process.

3. The method according to claim 1, characterized in that, Before analyzing the solidification process of the billet in the next continuous casting process using the preset continuous casting digital twin model based on the real-time operating status data and the real-time continuous casting process parameters to obtain the behavior law of the billet solidification process in the next continuous casting process, the method further includes: Determine the maximum and minimum operating status data in the real-time operating status data, and subtract the minimum operating status data from the maximum operating status data to obtain the operating status interval value; Subtract the real-time operating status data from the minimum operating status data to obtain the real-time operating status difference; Divide the real-time operating status difference by the operating status interval value to obtain the standardized operating status data corresponding to the real-time operating status data; Determine the maximum and minimum continuous casting process parameters in the real-time continuous casting process parameters, and subtract the minimum continuous casting process parameter from the maximum continuous casting process parameter to obtain the continuous casting process spacing value; Subtract the real-time continuous casting process parameters from the minimum continuous casting process parameters to obtain the real-time continuous casting process difference. Divide the real-time continuous casting process difference by the continuous casting process spacing value to obtain the standardized continuous casting process parameters corresponding to the real-time continuous casting process parameters. Based on the real-time operating status data and the real-time continuous casting process parameters, the pre-set continuous casting digital twin model is used to analyze the solidification process of the billet in the next continuous casting process, and the behavioral rules of the billet solidification process in the next continuous casting process are obtained, including: Based on the standardized operating status data and the standardized continuous casting process parameters, the solidification process of the billet under the next continuous casting process is analyzed using the preset continuous casting digital twin model to obtain the behavior law of the billet solidification process under the next continuous casting process.

4. The method according to claim 1, characterized in that, Before analyzing the solidification process of the billet in the next continuous casting process using the preset continuous casting digital twin model based on the real-time operating status data and the real-time continuous casting process parameters to obtain the behavior law of the billet solidification process in the next continuous casting process, the method further includes: Determine the median corresponding to the real-time running status data, and determine the first intermediate value between the minimum value in the real-time running status data and the median, and determine the first intermediate value as the first quartile corresponding to the real-time running status data; Determine a second intermediate value between the maximum value and the median in the real-time running status data, and determine the second intermediate value as the third quartile corresponding to the real-time running status data; Calculate the distance between the first quartile and the third quartile, and determine the distance as the interquartile interval corresponding to the real-time running status data; Calculate the lower limit value for anomaly detection corresponding to the real-time operating status data based on the first quartile and the interquartile range; Calculate the upper limit of anomaly detection corresponding to the real-time running status data based on the third quartile and the interquartile range; In the real-time operating status data, data outside the anomaly detection lower limit to the anomaly detection upper limit is identified as abnormal data; The abnormal data in the real-time operating status data is removed to obtain the real-time operating status data after the abnormal data is removed.

5. The method according to claim 1, characterized in that, After acquiring the real-time operating status data corresponding to the target continuous casting device, the method further includes: Based on the real-time operating status data, it is determined whether the target continuous casting device is operating abnormally; If the target continuous casting device malfunctions, an malfunction alarm message is generated and sent to the maintenance personnel's terminal so that the maintenance personnel can perform maintenance on the target continuous casting device based on the malfunction alarm message.

6. A continuous casting device based on digital twins, characterized in that, include: The construction unit is used to build a preset digital twin model of continuous casting based on the actual continuous casting scenario data corresponding to the target continuous casting device; The acquisition unit is used to acquire, in response to the continuous casting signal of the target continuous casting device for the current continuous casting process, the real-time operating status data of the target continuous casting device and the real-time continuous casting process parameters under the current continuous casting process. The analysis unit is used to analyze the solidification process of the billet in the next continuous casting process based on the real-time operating status data and the real-time continuous casting process parameters, using the preset continuous casting digital twin model, to obtain the behavior law of the billet solidification process in the next continuous casting process. The preset continuous casting digital twin model includes: a thermophysical property parameter calculation layer, a thermal shrinkage parameter calculation layer, a microstructure prediction layer, a hydrocarbon calculation layer, a billet pressure calculation layer, and a behavior law prediction layer. The analysis unit is used to analyze the solidification process of the billet in the next continuous casting process based on the real-time operating status data and the real-time continuous casting process parameters, using the preset continuous casting digital twin model to obtain the behavior law of the billet solidification process in the next continuous casting process. The solidification process behavior of the billet under the next continuous casting process is described, including: inputting the real-time operating status data and the real-time continuous casting process parameters into the thermophysical property parameter calculation layer to calculate the thermophysical property parameters of the billet under the next continuous casting process; inputting the real-time operating status data and the real-time continuous casting process parameters into the thermal shrinkage parameter calculation layer to calculate the thermal shrinkage parameters of the billet under the next continuous casting process; inputting the real-time operating status data and the real-time continuous casting process parameters into the microstructure prediction layer to predict the microstructure parameters of the billet under the next continuous casting process; and inputting the real-time operating status data and the real-time continuous casting process parameters into the microstructure prediction layer to predict the microstructure parameters of the billet under the next continuous casting process. The real-time operating status data and the real-time continuous casting process parameters are input to the hydrocarbon calculation layer to calculate precipitation data, obtaining the billet hydrocarbon precipitation data for the next continuous casting process; the real-time operating status data and the real-time continuous casting process parameters are input to the billet pressure calculation layer to calculate billet pressure, obtaining the billet pressure data for the next continuous casting process; the thermophysical parameters, thermal shrinkage parameters, billet microstructure parameters, hydrocarbon precipitation data, and billet pressure data are input to the behavior prediction layer to predict behavior, obtaining the billet solidification process behavior law for the next continuous casting process; the thermophysical parameters, thermal shrinkage parameters, The billet microstructure parameters, hydrocarbon precipitation data, and billet pressing force data are input into the behavior prediction layer to predict the behavior of the billet solidification process in the next continuous casting process. This includes: determining the three-dimensional temperature field diagram, solid-liquid phase line diagram, and stress-strain data at different positions of the billet in the next continuous casting process based on the thermophysical parameters, thermal shrinkage parameters, billet microstructure parameters, hydrocarbon precipitation data, and billet pressing force data; and inputting the three-dimensional temperature field diagram, solid-liquid phase line diagram, and stress-strain data into the behavior prediction layer to predict the behavior of the billet solidification process in the next continuous casting process. The determining unit is used to determine the predicted operating status data of the target continuous casting device in the next continuous casting process based on the behavior law of the solidification process of the billet. A control unit is used to control the continuous casting operation of the target continuous casting device for the next continuous casting process based on the predicted operating status data.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 5.

8. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 5.

Images