Material temperature determination method and device and nonvolatile storage medium

Abstract

The invention discloses a material temperature determination method and device and a nonvolatile storage medium. The method comprises the steps that a material parameter combination is determined, the material parameter combination is input into a finite element model, and the finite element model is used for constructing a material model according to the material parameter combination and generating temperature data corresponding to the material model; target points of the material model are determined according to preset material data, and the preset material data comprise preset material parameters of a preset material and preset target point information on the preset material; target data are determined from the temperature data according to the target point, and the target data are temperature values of the target point at all the time points; a temperature determination model is trained according to the material parameter combination and the target data, and the temperature determination model is used for determining the material temperature according to the material parameter combination. The technical problem that the temperature determination efficiency is low due to the fact that the material temperature is determined through experimental temperature measurement in the prior art is solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of metal material heat treatment, in particular, to a material temperature determination method and device and a nonvolatile storage medium. BACKGROUND

[0002] In the heat treatment process of metal materials, accurately predicting the temperature distribution and change trajectory of ingots or plates during the heating process is crucial for optimizing process parameters and improving product quality. This not only relates to the performance and quality of the final product, but also directly affects production efficiency and energy consumption. Experimental temperature measurement can provide relatively accurate temperature data, but it relies on actual operation and requires a lot of time, manpower and material resources for each test. Moreover, it cannot fully cover various combinations of process parameters, resulting in high experimental costs and low data collection efficiency.

[0003] At present, there is no effective solution to the above problems. SUMMARY

[0004] The embodiments of the present application provide a material temperature determination method, device and nonvolatile storage medium to at least solve the technical problem of low temperature determination efficiency caused by determining material temperature through experimental temperature measurement in the related art.

[0005] According to an aspect of an embodiment of the present application, a material temperature determination method is provided, comprising: determining a material parameter combination, inputting the material parameter combination into a finite element model, wherein the finite element model is used to construct a material model according to the material parameter combination, and generate temperature data corresponding to the material model, the temperature data including temperature values of each point in the material model at each time point; determining a target point of the material model according to preset material data, wherein the preset material data includes preset material parameters of a preset material and preset target point information on the preset material; determining target data from the temperature data according to the target point, wherein the target data is the temperature value of the target point at each time point; training a temperature determination model according to the material parameter combination and the target data, wherein the temperature determination model is used to determine the material temperature according to the material parameter combination.

[0006] Optionally, the material parameters include at least one of the following: material thickness, material length, material width, and furnace gas temperature; determining the material parameter combination includes: obtaining a preset value range of the material parameters and a parameter step of the material parameters; determining a value set of the material parameters according to the value range of the material parameters and the parameter step of the material parameters; traversing the values in the value set of each material parameter to obtain all value combinations of the material parameters; and taking all value combinations as the material parameter combination.

[0007] Optionally, determining the target data from the temperature data according to the target point comprises: extracting a temperature value corresponding to the target point in the temperature data as the target data; and converting the target data into a preset format, wherein the preset format is a format of input data of the temperature determination model.

[0008] Optionally, determining the target point of the material model according to the preset material data comprises: determining a preset size of the preset material according to a preset material parameter; determining a size of the material model according to the material parameter; determining a size mapping relationship between the material model and the preset material according to the size of the material model and the preset size; and determining the target point according to the size mapping relationship and preset target point information.

[0009] Optionally, after training the temperature determination model, the method further comprises: obtaining a target material parameter of a target material; inputting the target material parameter into the temperature determination model; and obtaining material temperature data output by the temperature determination model.

[0010] Optionally, after inputting the parameter into the finite element model, the method further comprises: determining a change rate of the temperature value of the target point; reducing a time step of the finite element model in simulation when the change rate is greater than a first preset threshold; and increasing the time step of the finite element model in simulation when the change rate is less than a second preset threshold.

[0011] Optionally, the material parameter combination further comprises a material type, and training the temperature determination model according to the material parameter combination and the target data further comprises: dividing the target data according to the material type to obtain a training data set, wherein target data belonging to the same training data set correspond to the same material type; and training a temperature determination model corresponding to the material type according to the training data set.

[0012] Optionally, after training the temperature determination model according to the material parameter combination and the target data, the method further comprises: obtaining a target material type selected by a user; determining a target temperature determination model corresponding to the target material type; and determining material temperature data of a target material according to the target temperature determination model.

[0013] According to a further aspect of the embodiments of the present application, a device for determining material temperature is also provided, comprising: a first processing module configured to determine a material parameter combination, and input the material parameter combination into a finite element model, wherein the finite element model is configured to construct a material model according to the material parameter combination, and generate temperature data corresponding to the material model, the temperature data comprising temperature values of each point in the material model at each time point; a second processing module configured to determine a target point of the material model according to preset material data, wherein the preset material data comprises preset material parameters of a preset material, and preset target point information on the preset material; a third processing module configured to determine target data from the temperature data according to the target point, wherein the target data is a temperature value of the target point at each time point; and a fourth processing module configured to train a temperature determination model according to the material parameter combination and the target data, wherein the temperature determination model is configured to determine material temperature according to the material parameter combination.

[0014] According to a further aspect of the embodiments of the present application, a non-volatile storage medium is also provided, the non-volatile storage medium storing a program, wherein the program, when executed, controls a device in which the non-volatile storage medium is located to perform the method for determining material temperature.

[0015] According to a further aspect of the embodiments of the present application, an electronic device is also provided, comprising a memory and a processor, the processor being configured to execute a program stored in the memory, wherein the program, when executed, performs the method for determining material temperature.

[0016] According to a further aspect of the embodiments of the present application, a computer program product is also provided, comprising a computer program, the computer program being executed by a processor to implement the method for determining material temperature.

[0017] In the embodiment of the present application, the material parameter combination is determined, and the material parameter combination is input into a finite element model, wherein the finite element model is used to construct a material model according to the material parameter combination, and temperature data corresponding to the material model is generated, the temperature data including temperature values of each point in the material model at each time point; a target point of the material model is determined according to preset material data, wherein the preset material data includes preset material parameters of a preset material, and preset target point information on the preset material; target data is determined from the temperature data according to the target point, wherein the target data is the temperature value of the target point at each time point; and a temperature determination model is trained according to the material parameter combination and the target data, wherein the temperature determination model is used to determine the material temperature according to the material parameter combination, training data is generated according to the finite element model, the temperature determination model is trained according to the training data, and finally the target material temperature is determined according to the temperature determination model, so as to achieve the purpose of quickly and accurately determining the target material temperature, thereby realizing the technical effect of improving the material temperature determination efficiency, and further solving the technical problem of low temperature determination efficiency caused by the determination of material temperature by experiment in the related art. BRIEF DESCRIPTION OF DRAWINGS

[0018] The accompanying drawings, which are included to provide a further understanding of the present application, constitute a part of the present application, the illustrative embodiments of the present application and their descriptions serve to explain the present application, and do not constitute improper limitations on the present application. In the drawings:

[0019] Figure 1 is a structural schematic diagram of a computer terminal provided according to an embodiment of the present application;

[0020] Figure 2 is a flowchart of a material temperature determination method provided according to an embodiment of the present application;

[0021] Figure 3 is a whole flowchart of material temperature determination provided according to an embodiment of the present application;

[0022] Figure 4 is a structural schematic diagram of a material temperature determination device provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0023] In order for those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should be within the scope of protection of the present application.

[0024] It should be noted that the terms "first", "second" and the like in the description and claims of the application and the above-mentioned accompanying drawings are used to distinguish similar objects, and do not necessarily indicate a specific order or a chronological sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the application described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0025] In order to better understand the embodiments of the present application, the technical terms involved in the embodiments of the present application are explained as follows:

[0026] Finite element model: a mathematical model widely used in engineering analysis, especially in the fields of structural mechanics, fluid mechanics, heat conduction, etc. It divides a complex physical system into many small and simple parts, then analyzes each part independently, and finally synthesizes the results of all parts to approximate the performance of the whole system. This model can consider factors such as nonlinear behavior of materials, complexity of geometric shape and variation of boundary conditions, and provide very detailed analysis results of stress, strain, displacement, temperature distribution, etc. It is one of the indispensable tools for modern engineering design and analysis.

[0027] In the related art, the material temperature is mainly determined according to experimental temperature measurement and artificial experience. However, the experimental temperature measurement has high time cost and large error, and the finite element simulation calculation of ingot temperature field also has the problem of low calculation efficiency: the simulation calculation needs a large amount of computing resources and a long calculation time; it is difficult to balance the calculation accuracy and the calculation efficiency, and the parameter selection is difficult; manual intervention is required in the data extraction process, the automation degree is low, and the data processing is tedious; and the process from data acquisition to the establishment of the prediction model is complex, and the modeling cycle is long.

[0028] In order to solve the above problems, the related solutions are provided in the embodiments of the present application, which are described in detail below.

[0029] According to the embodiments of the present application, a method embodiment of a method for determining the temperature of a material is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described herein can be executed in an order different from that shown herein.

[0030] The method embodiment provided by the embodiments of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device.Figure 1 A hardware structure block diagram of a computer terminal for implementing the material temperature determination method is shown. As shown in the figure, Figure 1 the computer terminal 10 can include one or more processors 102 (the processor 102 can include but not limited to a microprocessor MCU or a programmable logic device FPGA processing device, etc.), a memory 104 for storing data, and a transmission device 106 for communication functions. In addition, it can also include a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which can be included as one of the ports in the BUS bus), a network interface, a power supply and / or a camera. Those skilled in the art can understand that, Figure 1 The structure shown is only schematic, which does not limit the structure of the above-mentioned electronic device. For example, the computer terminal 10 can include more or less components than those shown in Figure 1 or have a different configuration than Figure 1 shown.

[0031] It should be noted that the one or more processors 102 and / or other data processing circuits described above can be referred to herein as "data processing circuits" in general. The data processing circuit can be embodied in whole or in part as software, hardware, firmware or any other combination. In addition, the data processing circuit can be a single independent processing module, or all or part of any one of the other elements combined into the computer terminal 10. As referred to in the embodiments of the present application, the data processing circuit serves as a processor control (for example, selection of a variable resistance terminal path connected to an interface).

[0032] The memory 104 can be used to store software programs and modules of application software, such as program instructions / data storage devices corresponding to the material temperature determination method in the embodiments of the present application. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, implements the material temperature determination method described above. The memory 104 can include a high-speed random access memory, and can also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 can further include a memory remotely disposed with respect to the processor 102, which can be connected to the computer terminal 10 through a network. Examples of the above-mentioned network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network and a combination thereof.

[0033] The transmission device 106 is configured to receive or send data via a network. The network can include a wireless network provided by a communication provider of the computer terminal 10. In one example, the transmission device 106 includes a network interface controller (NIC) that can be connected to other network devices through a base station to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module that is configured to communicate with the Internet wirelessly.

[0034] The display can be a liquid crystal display (LCD) that is touch screen type, for example, which can enable a user to interact with a user interface of the computer terminal 10.

[0035] In the above operating environment, the embodiments of the present application provide a method for determining a material temperature, as shown in the following. Figure 2 The method includes the following steps:

[0036] In step S202, a material parameter combination is determined, and the material parameter combination is input into a finite element model. The finite element model is configured to construct a material model according to the material parameter combination, and generate temperature data corresponding to the material model. The temperature data includes temperature values of each point in the material model at each time point.

[0037] Optionally, the material parameters include at least one of a material thickness, a material length, a material width, and a furnace gas temperature. The determination of the material parameter combination includes: obtaining a preset value range of the material parameters and a parameter step of the material parameters; determining a value set of the material parameters according to the value range of the material parameters and the parameter step of the material parameters; traversing the values in the value set of each material parameter to obtain all value combinations of the material parameters; and taking the all value combinations as the material parameter combination.

[0038] Optionally, the parameter step of the material parameters is determined according to the importance difference of each material parameter. Specifically, the material thickness and the furnace gas temperature are the most important parameters, and a small step is used. The value range of the thickness step is 0.01-0.05 m, and the value range of the furnace gas temperature step is 10-50℃. The material width is a relatively important parameter, and a medium step is used. The value range of the step is 0.1-0.5 m. The length is a relatively unimportant parameter, and a large step is used. The value range of the step is 1-5 m.

[0039] Optionally, after determining the preset value range of the material parameter and the parameter step of the material parameter, the automatic batch execution of the finite element calculation is realized through a script, specifically, a Python script is constructed to automatically control the system, to automatically generate parameter combinations according to the parameter range and step setting, to automatically configure the material parameters and boundary conditions, and to automatically input the configuration into the finite element model, to automatically generate the geometric model of the material.

[0040] As an optional implementation, a three-dimensional model of material (e.g., ingot) heat treatment is established using finite element software, and the calculation parameters (including the preset value range of the material parameter and the parameter step of the material parameter) are configured as follows: thickness: preset value range 0.4-0.6m, parameter step 0.05m; furnace gas temperature: preset value range 400-600℃, parameter step 50℃; width: preset value range 1-2m, parameter step 0.2m; length: preset value range 5-11m, parameter step 3m. After configuring the calculation parameters, a Python automatic script is run to automatically generate 375 different parameter combinations (i.e., value sets), and automatically input the parameters into the finite element model and automatically submit the calculation task to the finite element model calculation.

[0041] As an optional implementation, after inputting the parameters into the finite element model, the method further comprises: determining the change rate of the temperature value of the target point; in the case that the change rate is greater than a first preset threshold, reducing the time step of the finite element model during simulation; in the case that the change rate is less than a second preset threshold, increasing the time step of the finite element model during simulation.

[0042] Optionally, through an adaptive step adjustment strategy, the time step is automatically reduced in the stage of rapid temperature change and the step is increased in the stage of stable temperature, so that the dynamic balance of calculation accuracy and efficiency can be achieved.

[0043] Optionally, the progress of the finite element calculation is monitored through a script, and the progress is displayed in real time, specifically, the script periodically queries the calculation state at a preset frequency, determines the proportion of completed tasks to the total tasks and calculates the time consumed by the tasks, and uses a graphics library to generate and update a dynamic chart in real time, to intuitively display the calculation progress and the estimated remaining time, so that the user can intuitively grasp the state of the calculation.

[0044] Meanwhile, by comparing the computation progress growth over a past period with a preset progress threshold (which can be manually set), the system prompts the user whether the current computation efficiency meets their needs. For example, if the computation progress growth is less than 1% (the preset progress threshold) in the last hour, the monitoring interface displays progress information, details the current efficiency status, and provides specific suggestions, such as increasing the step size of non-critical parameters to optimize the computation process. By monitoring task progress and displaying prompts to the user when efficiency falls below expectations, the system can assist the user in choosing a more reasonable step size and balancing accuracy and efficiency.

[0045] Step S204: Determine the target point of the material model based on the preset material data, wherein the preset material data includes the preset material parameters of the preset material and the preset target point information on the preset material.

[0046] In the technical solution provided in step S204, determining the target point of the material model based on the preset material data includes: determining the preset size of the preset material based on the preset material parameters; determining the size of the material model based on the material parameters; determining the size mapping relationship between the material model and the preset material based on the size of the material model and the preset size; and determining the target point based on the size mapping relationship and the preset target point information.

[0047] Optionally, in the process flow, data at certain points need special attention, such as the center point of the material or the point where the temperature rises the slowest.

[0048] Optionally, the script automatically configures target points in the finite element model based on preset material parameters. Specifically, to accurately locate specific points of interest (target points) in the model, such as the center point of the material or other critical parts with slow heating rates during heat treatment, the script needs to establish a mapping relationship between the dimensions of the material model and the preset material dimensions. This relationship can be established using a coordinate transformation algorithm, converting the coordinate information of the target points on the preset material into their corresponding coordinate positions in the material model. That is, the script first identifies the dimensions and center point position of the preset material, then calculates the relative position of the target point in the model according to the size ratio of the material model, and finally marks it as an observation point for which key data needs to be collected.

[0049] As an optional implementation, assume the preset material is a uniform rectangular sheet with known preset dimensions, and the material's center point has been designated as the preset target point. After reading this preset material data, the script calculates the size ratio between the model and the actual material. For example, if the model's dimensions are 1m × 1m × 1m, and the actual dimensions of the preset material are 2m × 2m × 2m, then the size mapping ratio is 0.5. The script then applies this ratio to locate the corresponding position of the material's center point (target point) within the model.

[0050] In actual operation, by automatically identifying the geometric center of the model, there is no need for the user to manually input coordinates. This automated positioning and data collection greatly improves the efficiency of data collection and reduces human error and time costs.

[0051] Optionally, the slowest heating point can be determined by a script. Specifically, the script automatically constructs a finite element model that matches the geometric characteristics of the actual material based on the size parameters of the pre-set material. This step is based on the thickness, width, and length information of the material to ensure the accuracy and representativeness of the model. After constructing the model, the script drives the finite element model to perform simulation calculations to simulate the temperature distribution changes during the heat treatment process. At this stage, each point in the model will generate corresponding temperature data, and the temperature curves of each point are constructed by the temperature data of each point. These curves record the temperature change trend of each position during the heating process in detail. By collecting and organizing these temperature curves, a comprehensive data set can be formed, providing a rich source of information for subsequent analysis.

[0052] Subsequently, the script analyzes the collected temperature data curves in depth and calculates the heating rate of each observation point. The heating rate refers to the amount of temperature change per unit time, which can intuitively reflect the differences in heating conditions at different locations in the material. After determining the heating rate of each point, the script continues to run and identifies the point with the lowest heating rate. This point, the slowest heating point, is often located inside the material or in an area less affected by the heat source, which directly affects the efficiency of the entire heat treatment process and the final quality of the material. The script quickly locates the position with the smallest heating rate by sorting and filtering the heating rate data and marks it as the slowest heating point.

[0053] Finally, the script feeds back the information of the determined slowest heating point to the user or directly marks it on the model, facilitating the formulation of subsequent process optimization and improvement measures. Through this series of steps, the script not only automatically determines the slowest heating point, but also greatly simplifies the originally complex manual calculation and data analysis process, improving the efficiency and accuracy of the work.

[0054] Through this series of target point determination operations, the script can quickly and accurately determine the target points of the material model, and provide strong support for subsequent data analysis and heat treatment process optimization. This automated process significantly improves the efficiency of heat treatment simulation and reduces the difficulty of operation, helping researchers and engineers focus more on solving core problems.

[0055] Step S206, determining target data from temperature data according to the target point, wherein the target data is the temperature value of the target point at each time point.

[0056] In the technical solution provided in step S206, determining the target data from the temperature data according to the target point includes: extracting a temperature value corresponding to the target point in the temperature data as the target data; and converting the target data into a preset format, where the preset format is a format of input data of the temperature determination model.

[0057] Optionally, after the finite element calculation is completed, the script focuses on automatic extraction of temperature data of a position (i.e., a target point, such as a center of an ingot) and automatic storage of result data (target data). Specifically, data corresponding to the target point is searched for and extracted from data output by the finite element model, and is saved in a CSV format (a preset format). Data in the CSV format can be directly imported into a neural network (such as TensorFlow) or a machine learning model such as polynomial regression, XGBoost, etc. for training.

[0058] In step S208, the temperature determination model is trained according to the material parameter combination and the target data, where the temperature determination model is used to determine a material temperature according to the material parameter combination.

[0059] In the technical solution provided in step S208, after the temperature determination model is trained, the method further includes: obtaining a target material parameter of a target material; inputting the target material parameter into the temperature determination model; and obtaining material temperature data output by the temperature determination model.

[0060] Optionally, the input parameters of the model include an ingot size (a material size) and a furnace gas temperature, and the output data includes a temperature history curve of a key feature point (i.e., material temperature data).

[0061] As an optional implementation, the material parameter combination further includes a material type, and training the temperature determination model according to the material parameter combination and the target data further includes: dividing the target data according to the material type to obtain a training data set, where target data belonging to the same training data set correspond to the same material type; and training a temperature determination model corresponding to the material type according to the training data set.

[0062] As an optional implementation, after the temperature determination model is trained according to the material parameter combination and the target data, the method further includes: obtaining a target material type selected by a user; determining a target temperature determination model corresponding to the target material type; and determining material temperature data of the target material according to the target temperature determination model.

[0063] Optionally, when processing parameter combinations containing material categories, the process first starts with the fine classification of data. The script automatically reads target data containing material categories, size parameters, boundary conditions (including furnace gas temperature, convective heat transfer coefficient), etc., and according to the key information of material categories, the data set is finely divided into multiple subsets, each corresponding to a specific material, such as aluminum, iron, etc. The importance of this classification process lies in the fact that different materials have completely different physical properties, including but not limited to thermal conductivity, specific heat capacity and density, which directly affect the temperature variation of the material during heat treatment. Therefore, dividing the data according to the material category can ensure that the calculation results of the same material are more consistent, providing high-quality input for subsequent model training.

[0064] Subsequently, for each material category subset, the script will start the training process of the machine learning algorithm. Based on the segmented training data set, the script constructs a temperature determination model matched with the material category. For example, for the aluminum material subset, the script will train a model specifically for predicting the temperature variation of aluminum material under different heat treatment conditions; similarly, for the iron material subset, another unique model will also be trained. The training process in this stage makes full use of the characteristic data of each material, ensuring that the model can accurately reflect the temperature variation behavior of the material during heating, improving the accuracy and reliability of the prediction.

[0065] In the model application stage, when the user inputs or selects the target material category, the script can quickly identify this requirement and retrieve the model matched with the user's selected material category from the trained temperature determination model library. This process ensures that the selected model matches the physical properties of the target material, so that after inputting the size parameters of the material, the furnace gas temperature, the convective heat transfer coefficient and other boundary conditions, the most accurate material temperature data prediction can be output. In this way, the script not only simplifies user operations, but also improves the accuracy of heat treatment process temperature prediction, providing strong support for process optimization and product quality control.

[0066] Throughout the process, the characteristics of different materials are fully considered, and through data classification, customized model training and accurate model application, precise control of the material heat treatment process is achieved.

[0067] As an optional implementation, the data set can also be divided into multiple subsets according to the convective heat transfer coefficient, which describes the efficiency of heat exchange between the material surface and the surrounding medium. Different convective heat transfer conditions can significantly change the heating or cooling rate of the material, thereby affecting the final temperature distribution. Therefore, subdividing the target data set into multiple subsets according to the convective heat transfer coefficient can effectively improve the performance of the prediction model. By training temperature determination models corresponding to different convective heat transfer coefficients, the temperature determination model can provide more accurate temperature prediction results when facing different convective heat transfer conditions. This is of great significance for optimizing heat treatment processes, reducing energy consumption and improving product quality, because the optimal process under each convective heat transfer condition may be slightly different. Through the automatic processing of scripts and the personalized training of models, engineers can understand and control the heat treatment process at a more detailed level, making more accurate decisions in actual operation and ensuring the consistency and efficiency of the heat treatment process.

[0068] Optionally, since the type of heating furnace directly determines the value of the corresponding convective heat transfer coefficient, in the model application stage, the corresponding convective heat transfer coefficient value can also be directly associated with the user-selected heating furnace type, improving the convenience of user input data, eliminating the burden of users remembering a large number of device corresponding convective heat transfer coefficient values. By realizing the automatic association of user-selected equipment and convective heat transfer coefficient, the ease of use of the temperature determination method of the present application can be improved, the professional knowledge requirements of the user can be reduced, and the user experience of the user can be enhanced.

[0069] As an optional implementation, for different material geometric shapes (such as cuboid, cylinder, ring, sphere, square box, etc.), material parameters will be different (for example, the material parameters of a ring include at least one of the following: ring inner diameter, ring outer diameter, ring height). After generating corresponding temperature data for different material geometric shapes and extracting target data from the temperature data, different data sets can be divided according to the corresponding set shape of the material, and the corresponding model can be trained. In the application stage, after the user selects the corresponding geometric shape, the system will automatically associate the corresponding material parameter requirements of the user input and select the corresponding temperature determination model, and use the corresponding temperature determination model to determine the material temperature according to the user input material parameter combination. The present application can flexibly expand the model according to different data sets, enrich the application range of the temperature determination model, and provide strong support for the heat treatment process design and optimization of materials of different shapes.

[0070] Optionally, the step length of the specified material parameter can also be changed by fixing other material parameters to determine the calculation time and result accuracy corresponding to different step lengths, thereby assisting the user in selecting a more scientific step length. For example, by fixing other parameters and changing the thickness step length (0.01 m, 0.05 m, 0.1 m), the calculation time and result accuracy can be compared. The results show that when the step length is 0.05 m, the calculation time is reduced by 60% compared to 0.01 m, and the accuracy loss is only 2%. This verifies the scientificity of the step length selection strategy when the step length is 0.05.

[0071] Optionally, Figure 3 The overall flow of material temperature determination is shown as follows: Figure 3 The flow includes the following steps:

[0072] Step S302, determine the parameter range: including setting the size range of the ingot or sheet, such as the maximum and minimum values of thickness, width and length, and environmental condition parameters, such as the high and low limits of furnace gas temperature. The determination of the parameter range needs to be based on engineering experience and the requirements of heat treatment process, to ensure that all possible process conditions are covered, thereby laying a solid foundation for subsequent parameter optimization and model construction.

[0073] Step S304, determine the parameter step length: after the parameter range is determined, the next step is to refine the value interval of the parameter, that is, the step length. The selection of step length is extremely critical, as it will directly affect the accuracy and efficiency of the calculation. Through the preliminary importance analysis of the parameters, the step length of each parameter can be scientifically set. A smaller step length is used for parameters that have a greater impact on temperature to ensure calculation accuracy, while a larger step length is used for parameters that have a smaller impact to improve calculation efficiency. This differentiated step length strategy ensures efficient allocation of computing resources while reducing unnecessary computational burden.

[0074] Step S306, write python script: in order to realize the automation of batch processing of parameters and seamless integration of finite element calculation, a Python script needs to be written to control the entire calculation process. The core of the script design is to flexibly generate the required parameter combinations, automatically configure the boundary conditions and material properties of the finite element model, and submit the calculation task. In addition, the script should also have the function of monitoring the calculation state and automatically extracting the result data, to ensure the automation and efficient operation of the entire calculation process.

[0075] Step S308, batch finite element calculation and output: through the script, batch finite element calculation tasks can be performed, and each combination within the defined parameter range and step length can be simulated. The calculation results will be automatically collected and organized to meet the needs of the subsequent machine learning model. The goal of this stage is to generate a dataset containing temperature history curves, with each set of data being the heat treatment simulation result of the target point under a specific parameter combination, providing rich and comprehensive learning materials for the machine learning model.

[0076] Step S310, machine learning model modeling, after obtaining a large amount of data from finite element calculation, the next step is to use machine learning technology to build a prediction model. This usually involves data preprocessing, including cleaning, feature engineering and standardization, etc., to ensure the quality and consistency of the data. Then, using appropriate machine learning algorithms, the model is trained to predict the temperature change of the material based on the input material parameters and boundary conditions.

[0077] Step S312, establish temperature prediction model, after training and verification, the final output is a model that can quickly predict the temperature change of the material during heat treatment according to the input parameters. This model is used to predict the temperature distribution of the material under new parameter conditions, providing a scientific basis for the heat treatment process control of metal materials, accelerating process design and optimization, and further improving product quality and production efficiency.

[0078] Optionally, by applying the method embodiment of the present application to the ingot heat treatment process optimization of an aluminum company, the traditional 72-hour calculation task can be completed within 36 hours, and the prediction accuracy of the temperature prediction model trained by the obtained data reaches 98%. Based on the data output by the model, the process parameters are optimized, and the product qualification rate is improved by 15%. Through the above steps, the influence of different parameters on the temperature field is analyzed, and different step sizes are set for thickness, furnace gas temperature, width and length; An automatic calculation system is constructed to realize batch generation of finite element models, submission of calculation tasks and extraction of results; The output data directly meet the modeling requirements of machine learning, significantly improving the calculation efficiency and realizing the automation of the whole data processing process, providing efficient data support for heat treatment process optimization. The problems of low calculation efficiency, lack of basis for parameter selection and complicated data processing in related technologies are solved. Specifically, the present application has the following advantages:

[0079] 1. The calculation efficiency is improved by more than 90%, and automatic calculation is supported for 24 hours without interruption;

[0080] 2. Scientifically determine the parameter step size to maximize the calculation efficiency while ensuring accuracy;

[0081] 3. Fully automated data processing flow, eliminating manual intervention;

[0082] 4. The output data can be directly used for machine learning modeling, reducing intermediate processing steps.

[0083] The present application provides a material temperature determination device, Figure 4 is a structural schematic diagram of the device, like Figure 4As shown, the apparatus comprises: a first processing module 40 configured to determine a material parameter combination, and input the material parameter combination into a finite element model, wherein the finite element model is configured to construct a material model according to the material parameter combination, and generate temperature data corresponding to the material model, the temperature data comprising temperature values of each point in the material model at each time point; a second processing module 42 configured to determine a target point of the material model according to preset material data, wherein the preset material data comprises preset material parameters of a preset material, and preset target point information on the preset material; a third processing module 44 configured to determine target data from the temperature data according to the target point, wherein the target data is a temperature value of the target point at each time point; and a fourth processing module 46 configured to train a temperature determination model according to the material parameter combination and the target data, wherein the temperature determination model is configured to determine a material temperature according to the material parameter combination.

[0084] In some embodiments of the present application, the material parameters comprise at least one of: a material thickness, a material length, a material width, and a furnace gas temperature; and the first processing module 40 determining the material parameter combination comprises: obtaining a preset value range of the material parameters and a parameter step length of the material parameters; determining a value set of the material parameters according to the value range of the material parameters and the parameter step length of the material parameters; traversing values in the value set of each material parameter to obtain all value combinations of the material parameters; and taking the all value combinations as the material parameter combination.

[0085] In some embodiments of the present application, the third processing module 44 determining the target data from the temperature data according to the target point comprises: extracting a temperature value corresponding to the target point in the temperature data as the target data; and converting the target data into a preset format, wherein the preset format is a format of input data of the temperature determination model.

[0086] In some embodiments of the present application, the second processing module 42 determining the target point of the material model according to the preset material data comprises: determining a preset size of the preset material according to the preset material parameters; determining a size of the material model according to the material parameters; determining a size mapping relationship between the material model and the preset material according to the size of the material model and the preset size; and determining the target point according to the size mapping relationship and the preset target point information.

[0087] In some embodiments of the present application, after training the temperature determination model, the fourth processing module 46 is further configured to: obtain target material parameters of a target material; input the target material parameters into the temperature determination model; and obtain material temperature data output by the temperature determination model.

[0088] In some embodiments of the present application, after the parameter is input into the finite element model, the first processing module 40 is further configured to: determine a change rate of the temperature value of the target point; in a case where the change rate is greater than a first preset threshold, reduce a time step of the finite element model during simulation; and in a case where the change rate is less than a second preset threshold, increase the time step of the finite element model during simulation.

[0089] In some embodiments of the present application, the material parameter combination further includes a material type, and the fourth processing module 46 is configured to train the temperature determination model according to the material parameter combination and the target data, and the training includes: dividing the target data according to the material type to obtain a training data set, wherein the target data belonging to the same training data set correspond to the same material type; and training the temperature determination model corresponding to the material type according to the training data set.

[0090] In some embodiments of the present application, after the temperature determination model is trained according to the material parameter combination and the target data, the fourth processing module 46 is further configured to: obtain a target material type selected by a user; determine a target temperature determination model corresponding to the target material type; and determine the material temperature data of the target material according to the target temperature determination model.

[0091] It should be noted that each module in the above material temperature determination apparatus can be a program module (for example, a program instruction set for implementing a certain specific function) or a hardware module. For the latter, it can be in the following forms, but is not limited thereto: each module is in the form of a processor, or the functions of each module are implemented by a processor.

[0092] The embodiments of the present application provide a non-volatile storage medium, and the non-volatile storage medium stores a program. When the program is executed, the device in which the non-volatile storage medium is located performs the following method for determining material temperature: determining a material parameter combination, inputting the material parameter combination into a finite element model, wherein the finite element model is used to construct a material model according to the material parameter combination, and generate temperature data corresponding to the material model, the temperature data including temperature values of each point in the material model at each time point; determining a target point of the material model according to preset material data, wherein the preset material data includes preset material parameters of a preset material and preset target point information on the preset material; determining target data from the temperature data according to the target point, wherein the target data is the temperature value of the target point at each time point; and training a temperature determination model according to the material parameter combination and the target data, wherein the temperature determination model is used to determine material temperature according to the material parameter combination.

[0093] The embodiment of the present application provides an electronic device, comprising a memory and a processor, the processor is used for running a program stored in the memory, wherein the program performs the following material temperature determination method when running: determining a material parameter combination, inputting the material parameter combination into a finite element model, wherein the finite element model is used for constructing a material model according to the material parameter combination, and generating temperature data corresponding to the material model, the temperature data comprising temperature values of each point in the material model at each time point; determining a target point of the material model according to preset material data, wherein the preset material data comprises preset material parameters of a preset material, and preset target point information on the preset material; determining target data from the temperature data according to the target point, wherein the target data is the temperature value of the target point at each time point; training a temperature determination model according to the material parameter combination and the target data, wherein the temperature determination model is used for determining the material temperature according to the material parameter combination.

[0094] The embodiment of the present application provides a computer program product, comprising a computer program, the computer program implements the following material temperature determination method when being executed by a processor: determining a material parameter combination, inputting the material parameter combination into a finite element model, wherein the finite element model is used for constructing a material model according to the material parameter combination, and generating temperature data corresponding to the material model, the temperature data comprising temperature values of each point in the material model at each time point; determining a target point of the material model according to preset material data, wherein the preset material data comprises preset material parameters of a preset material, and preset target point information on the preset material; determining target data from the temperature data according to the target point, wherein the target data is the temperature value of the target point at each time point; training a temperature determination model according to the material parameter combination and the target data, wherein the temperature determination model is used for determining the material temperature according to the material parameter combination.

[0095] In the above-mentioned embodiments of the present application, the description of each embodiment has its own focus, and the parts not described in detail in a certain embodiment can be referred to the related description of other embodiments.

[0096] In several embodiments provided in the present application, it should be understood that the disclosed technical contents can be implemented by other ways. Among them, the device embodiments described above are only schematic, for example, the division of the units can be a logical function division, and actual implementation can have another division way, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed each other can be indirect coupling or communication connection through some interfaces, units or modules, which can be electrical or other forms.

[0097] The units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0098] In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can be physically present alone, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0099] The integrated unit, if realized in the form of a software functional unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application or the part that contributes to the related art or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The foregoing storage medium includes: a U disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a mobile hard disk, a magnetic disk or an optical disk, and various program code storage media.

[0100] The above is only the preferred embodiment of the present application, and it should be pointed out that for those skilled in the art, without departing from the principles of the present application, a number of improvements and refinements can be made, and these improvements and refinements should be considered as the protection scope of the present application.

Claims

1. A method of determining the temperature of a material, characterized by, The method comprises the following steps: determining a material parameter combination, inputting the material parameter combination into a finite element model, wherein the finite element model is used to construct a material model according to the material parameter combination, and generate temperature data corresponding to the material model, the temperature data comprising temperature values of each point in the material model at each time point; determining a target point of the material model according to preset material data, wherein the preset material data comprises preset material parameters of a preset material, and preset target point information on the preset material; determining target data from the temperature data according to the target point, wherein the target data is a temperature value of the target point at each time point; training a temperature determination model according to the material parameter combination and the target data, wherein the temperature determination model is used to determine a material temperature according to the material parameter combination.

2. The method of determining the temperature of a material according to claim 1, wherein, The material parameters comprise at least one of the following: material thickness, material length, material width, and furnace gas temperature; determining the material parameter combination comprises: obtaining a preset value range of the material parameters and a parameter step length of the material parameters; determining a value set of the material parameters according to the value range of the material parameters and the parameter step length of the material parameters; traversing values in the value set of each material parameter to obtain all value combinations of the material parameters; taking the all value combinations as the material parameter combination.

3. The method of determining the temperature of a material according to claim 1, wherein, Determining target data from the temperature data according to the target point comprises: extracting temperature values corresponding to the target point in the temperature data as target data; converting the target data into a preset format, wherein the preset format is a format of input data of the temperature determination model.

4. The method of determining the temperature of a material according to claim 1, wherein Determining a target point of the material model according to preset material data comprises: determining a preset size of the preset material according to the preset material parameters; determining a size of the material model according to the material parameters; determining a size mapping relationship between the material model and the preset material according to the size of the material model and the preset size; determining the target point according to the size mapping relationship and the preset target point information.

5. The method of determining the temperature of a material according to claim 1, wherein, After training the temperature determination model, the method further comprises: obtaining target material parameters of a target material; inputting the target material parameters into the temperature determination model; obtaining material temperature data output by the temperature determination model.

6. The method of determining the temperature of a material of claim 1, wherein, After inputting the parameters into the finite element model, the method further comprises: determining a change rate of the temperature value of the target point; in a case where the change rate is greater than a first preset threshold, reducing a time step length of the finite element model during simulation; in a case where the change rate is less than a second preset threshold, increasing the time step length of the finite element model during simulation.

7. The method of determining the temperature of a material according to claim 1, wherein, The material parameter combination further comprises a material type, and training the temperature determination model according to the material parameter combination and the target data further comprises: dividing the target data according to the material type to obtain training data sets, wherein the target data belonging to the same training data set corresponds to the same material type; According to the training data set, a temperature determination model corresponding to the material category is trained.

8. The method of determining the temperature of a material according to claim 1, wherein, After training the temperature determination model according to the material parameter combination and the target data, the method further comprises: obtaining a target material category selected by a user; determining a target temperature determination model corresponding to the target material category; determining material temperature data of a target material according to the target temperature determination model.

9. A material temperature determining apparatus, characterized by comprising: comprise: a first processing module configured to determine a material parameter combination, and input the material parameter combination into a finite element model, wherein the finite element model is configured to construct a material model according to the material parameter combination, and generate temperature data corresponding to the material model, the temperature data comprising temperature values of each point in the material model at each time point; a second processing module configured to determine a target point of the material model according to preset material data, wherein the preset material data comprises preset material parameters of a preset material, and preset target point information on the preset material; a third processing module configured to determine target data from the temperature data according to the target point, wherein the target data is a temperature value of the target point at each time point; a fourth processing module configured to train a temperature determination model according to the material parameter combination and the target data, wherein the temperature determination model is configured to determine a material temperature according to the material parameter combination.

10. A non-volatile storage medium, comprising: The non-volatile storage medium stores a program, wherein when the program is running, the device in which the non-volatile storage medium is located executes the material temperature determination method in any one of claims 1 to 8.

11. An electronic device, comprising: comprise: a memory and a processor, the processor being configured to run a program stored in the memory, wherein the program runs to execute the material temperature determination method in any one of claims 1 to 8.

12. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to realize the material temperature determination method according to any one of claims 1 to 8.

Images