A thermal boundary condition calculation method, device, equipment and storage medium

Abstract

The application provides a kind of thermal boundary condition calculation method, device, equipment and storage medium, the method comprises: obtaining ambient temperature and temperature variation parameter, and it is divided into test sample data and training sample data, obtain multiple candidate heat transfer coefficients based on preset heat transfer coefficient condition, construct temperature prediction model based on training sample data and candidate heat transfer coefficient, obtain multiple candidate temperature prediction model, and each candidate temperature prediction model is verified based on test sample data, obtain target temperature prediction model, the candidate heat transfer coefficient corresponding to target temperature prediction model is determined as the thermal boundary condition of steel in this ambient temperature;By equivalent into heat transfer coefficient with thermal boundary condition, and based on heat transfer coefficient, a temperature prediction model that meets the conditions is obtained, so as to determine the temperature variation law of steel in this ambient temperature based on simple temperature variation environment, which is conducive to predicting the temperature variation of steel in other complex environments.

Description

Technical Field

[0001] This application relates to the field of metallurgical engineering technology, specifically to a method, apparatus, equipment, and storage medium for calculating thermal boundary conditions. Background Technology

[0002] In the steel rolling process, in order to obtain the optimal process parameters, it is often necessary to record in detail the various parameters during the rolling process, including stress, strain distribution, and the rolling force and torque that the rolling equipment needs to provide. In addition, since the rolled workpiece undergoes heat exchange with the external environment through convection and thermal radiation during the steel rolling process, and when performing numerical simulation of the rolling process, it is necessary to accurately set relevant parameters such as the convection heat transfer coefficient and thermal emissivity, it is also very important to accurately obtain the heat transfer boundary condition parameters in the heat transfer analysis or thermo-mechanical coupling analysis of the rolled workpiece to determine the optimal process parameters.

[0003] However, due to the variety of thermal boundary types and the complexity of the rolling environment, conventional methods for determining thermal boundary conditions are difficult to acquire and have low accuracy. Summary of the Invention

[0004] In view of the shortcomings of the prior art described above, the present invention provides a method, apparatus, device and storage medium for calculating thermal boundary conditions, so as to solve the technical problems of high difficulty in acquiring thermal boundary parameters and low accuracy of the obtained thermal boundary conditions.

[0005] This invention provides a method for calculating thermal boundary conditions. The method includes: acquiring the ambient temperature and temperature change parameters of steel at the ambient temperature, and dividing the temperature change parameters into test sample data and training sample data; obtaining multiple candidate heat transfer coefficients based on preset heat transfer coefficient conditions; constructing temperature prediction models based on the training sample data and the multiple candidate heat transfer coefficients respectively, obtaining multiple candidate temperature prediction models, and verifying each candidate temperature prediction model based on the test sample data to obtain a target temperature prediction model; determining the candidate heat transfer coefficient corresponding to the target temperature prediction model as the target heat transfer coefficient, and determining the target heat transfer coefficient as the thermal boundary condition of steel at the ambient temperature.

[0006] In one embodiment of this application, obtaining the ambient temperature and the temperature change parameters of steel under the ambient temperature includes: setting temperature sensors at different locations in the target environment to obtain multiple measured temperature parameters, and calculating all the measured temperatures based on a preset weight of each measured temperature to obtain the ambient temperature; measuring the initial temperature of the steel in the ambient temperature and the current temperature after cooling, and recording the cooling time of the steel from the initial temperature to the current temperature, and determining the initial temperature, the cooling time, and the current temperature as the temperature change parameters of the steel under the ambient temperature.

[0007] In one embodiment of this application, obtaining multiple candidate heat transfer coefficients based on preset heat transfer coefficient conditions includes: obtaining a value range of the heat transfer coefficients, and determining the number of items of the candidate heat transfer coefficients based on the preset heat transfer coefficient conditions; selecting multiple values ​​within the value range as candidate heat transfer coefficients, wherein the number of items of the multiple values ​​is the same as the number of items of the selected heat transfer coefficients.

[0008] In one embodiment of this application, a temperature prediction model is constructed based on the training sample data and the plurality of candidate heat transfer coefficients to obtain a plurality of candidate temperature prediction models, including: determining any candidate heat transfer coefficient as a specified heat transfer coefficient, and training an initial prediction model based on the specified heat transfer coefficient; using the initial temperature and current temperature in the training sample data as input information and the cooling time in the training sample data as output information; labeling the initial temperature and current temperature based on the cooling time, and training the initial prediction model based on the labeled initial temperature and labeled current temperature to obtain candidate temperature prediction models; and traversing each candidate heat transfer coefficient to obtain a plurality of candidate temperature prediction models.

[0009] In one embodiment of this application, after obtaining multiple candidate temperature prediction models, the method further includes: obtaining multiple actual cooling times for steel at the ambient temperature based on different initial temperatures and different current temperatures, and determining a set of ambient temperature, initial temperature, and current temperature as an input parameter to obtain a first mapping relationship between the input parameter and the actual cooling time; inputting any of the input parameters into each of the candidate temperature prediction models to obtain multiple predicted cooling times; obtaining a second mapping relationship between the heat transfer coefficient and the predicted cooling time based on the first correlation relationship between the predicted cooling time and the candidate temperature prediction model, and the second correlation relationship between the heat transfer coefficient and the candidate temperature prediction model; and constructing a thermal boundary condition mapping relationship table based on the first mapping relationship and the second mapping relationship.

[0010] In one embodiment of this application, the candidate temperature prediction model is validated based on the test sample data to obtain a target temperature prediction model. This includes: acquiring the initial temperature, current temperature, and actual cooling duration from the test sample; inputting the initial temperature and current temperature from the test sample data into each candidate temperature prediction model to obtain multiple predicted cooling durations; comparing the actual cooling duration with the multiple predicted cooling durations, and determining the predicted cooling duration whose difference from the actual cooling duration meets a preset standard as the standard predicted duration; and determining the candidate temperature prediction model corresponding to the standard predicted duration as the target temperature prediction model.

[0011] In one embodiment of this application, the predicted cooling time that satisfies a preset deviation from the actual cooling time is determined as the standard predicted time, which includes: calculating the actual cooling time and the predicted cooling time to obtain the prediction deviation; comparing the prediction deviation with the preset deviation, and determining the predicted cooling time as the standard predicted time when the prediction deviation is less than or equal to the preset deviation.

[0012] This application provides a thermal boundary condition calculation device, comprising: a data acquisition module for acquiring ambient temperature and temperature change parameters of steel at the ambient temperature, and dividing the temperature change parameters into test sample data and training sample data; a heat transfer coefficient determination module for obtaining multiple candidate heat transfer coefficients based on preset heat transfer coefficient conditions; a model building module for constructing temperature prediction models based on the training sample data and the multiple candidate heat transfer coefficients respectively, obtaining multiple candidate temperature prediction models, and verifying each candidate temperature prediction model based on the test sample data to obtain a target temperature prediction model; and a thermal boundary condition determination module for determining the candidate heat transfer coefficient corresponding to the target temperature prediction model as the target heat transfer coefficient, and determining the target heat transfer coefficient as the thermal boundary condition of steel at the ambient temperature.

[0013] This application provides an electronic device, which includes: one or more processors; and a storage device for storing one or more programs, which, when executed by the one or more processors, enable the electronic device to implement the thermal boundary condition calculation method as described above.

[0014] This application provides a computer-readable storage medium storing a computer program that, when executed by a computer's processor, causes the computer to perform the thermal boundary condition calculation method described above.

[0015] The beneficial effects of this invention are as follows: This invention provides a method, apparatus, device, and storage medium for calculating thermal boundary conditions. The method includes: acquiring ambient temperature and temperature change parameters, dividing the temperature change parameters into test sample data and training sample data, obtaining multiple candidate heat transfer coefficients based on preset heat transfer coefficient conditions, constructing temperature prediction models based on the training sample data and the multiple candidate heat transfer coefficients respectively, obtaining multiple candidate temperature prediction models, and verifying each candidate temperature prediction model based on the test sample data to obtain a target temperature prediction model. The candidate heat transfer coefficient corresponding to the target temperature prediction model is determined as the thermal boundary condition for steel at that ambient temperature. By equating the thermal boundary condition to a heat transfer coefficient and obtaining a temperature prediction model that meets the conditions based on the heat transfer coefficient, the temperature change law of steel at that ambient temperature is determined based on a simple temperature change environment, which is beneficial for predicting the temperature change of steel in other complex environments.

[0016] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0017] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application. It is obvious that the drawings described below are merely some embodiments of this application, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort. In the drawings:

[0018] Figure 1 This is a schematic diagram illustrating the implementation environment of the thermal boundary condition calculation method in an exemplary embodiment of this application;

[0019] Figure 2 This is a flowchart illustrating a thermal boundary condition calculation method in an exemplary embodiment of this application;

[0020] Figure 3 This is a schematic diagram of a thermal boundary condition calculation system shown in an exemplary embodiment of this application;

[0021] Figure 4 This is an exemplary embodiment of the present application illustrating a deep learning model for predicting heat transfer coefficients, including training and prediction models.

[0022] Figure 5 This is a schematic diagram illustrating the thermal boundary condition calculation steps in an exemplary embodiment of this application;

[0023] Figure 6 This is an exemplary embodiment of the present application illustrating a flowchart of generating a temperature-heat transfer coefficient database using the finite element method;

[0024] Figure 7 This is a block diagram illustrating a thermal boundary condition calculation device according to an exemplary embodiment of this application;

[0025] Figure 8 A schematic diagram of the structure of a computer system suitable for implementing the electronic device of the present application is shown. Detailed Implementation

[0026] The embodiments of the present invention will be described below with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be understood that the preferred embodiments are only for illustrating the present invention and not for limiting the scope of protection of the present invention.

[0027] It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of the present invention. Therefore, the drawings only show the components related to the present invention and are not drawn according to the actual number, shape and size of the components in the actual implementation. In the actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.

[0028] In the following description, numerous details are explored to provide a more thorough explanation of embodiments of the invention. However, it will be apparent to those skilled in the art that embodiments of the invention may be practiced without these specific details. In other embodiments, well-known structures and devices are shown in block diagram form rather than in detail to avoid obscuring embodiments of the invention.

[0029] First, it should be noted that interpolation is a method of adding a continuous function to discrete data so that the continuous curve passes through all the given discrete data points. It is an important method for approximating discrete functions, and can be used to estimate the approximate value of the function at other points by observing the value of the function at a finite number of points.

[0030] Figure 1 This is a schematic diagram illustrating the implementation environment of the thermal boundary condition calculation method, as shown in an exemplary embodiment of this application. Figure 1As shown, the real-time environment for calculating thermal boundary conditions includes a data acquisition device 101 and a computer device 102. The data acquisition device 101 is used to collect relevant parameters, including but not limited to ambient temperature, initial temperature of the steel, current temperature of the steel, cooling time, and the range and rules for the heat transfer coefficient. The data acquisition device 101 sends the collected data to the computer device 102. It should be noted that the data acquisition device 101 can be a thermometer, timer, or any other type of data acquisition device, such as digital information acquisition. This application does not impose any restrictions on this. The computer device 102 is used to organize and analyze the relevant data collected by the data acquisition device 101, construct a temperature prediction model, and verify multiple constructed temperature prediction models to obtain a target temperature prediction model that meets the requirements. Based on the construction data of the target temperature prediction model, the corresponding heat transfer coefficient is obtained, which is the thermal boundary condition of the steel at ambient temperature. The computer device 102 may be at least one of a desktop graphics processing unit (GPU) computer, a GPU computing cluster, a neural network computer, etc., or it may be an intelligent processor integrated into the current vehicle. This application does not impose any restrictions on this.

[0031] Figure 2 This is a flowchart illustrating a thermal boundary condition calculation method in an exemplary embodiment of this application.

[0032] like Figure 2 As shown, in an exemplary embodiment, the thermal boundary condition calculation method includes at least steps S210 to S240, which are described in detail below:

[0033] Step S210: Obtain the ambient temperature and the temperature change parameters of the steel under the ambient temperature, and divide the temperature change parameters into test sample data and training sample data.

[0034] Figure 3 This is a schematic diagram of a thermal boundary condition calculation system illustrated in an exemplary embodiment of this application. Figure 3 As shown, the thermal boundary condition calculation system includes steel, temperature sensors, and computer equipment.

[0035] In one embodiment of this application, the ambient temperature of the steel production environment, the initial temperature and current temperature of the steel, and the cooling time taken to cool down from the initial temperature to the current temperature are collected by a temperature sensor, and all the obtained parameters are sent to a computer device so that the computer device can obtain the heat transfer coefficient of the steel at the ambient temperature based on a preset neural network prediction model.

[0036] In one embodiment of this application, obtaining the ambient temperature and the temperature change parameters of steel under the ambient temperature includes: setting temperature sensors at different locations in the target environment to obtain multiple measured temperature parameters, and calculating all measured temperatures based on the preset weights of each measured temperature to obtain the ambient temperature; measuring the initial temperature of the steel in the ambient temperature and the current temperature after cooling, and recording the cooling time of the steel from the initial temperature to the current temperature, and determining the initial temperature, cooling time, and current temperature as the temperature change parameters of the steel under the ambient temperature.

[0037] In one embodiment of this application, multiple temperature observation points are first determined in the steel production workshop, and different weights, x1, x2, x3…x, are assigned to the temperature parameters of each observation point based on their different locations. n This includes ambient temperature observation points and steel temperature observation points; based on different ambient temperature observation points, multiple measured ambient temperatures were obtained, namely T1, T2, T3…T n Then, the ambient temperature is calculated based on the observed temperature obtained from each observation point and the weight of that observation point, using the following formula:

[0038]

[0039] Where T is the ambient temperature, T1, T2, T3…T n The measured temperatures at a single detection point are x1, x2, x3…x n Each of these is a weighting coefficient for a measured temperature.

[0040] In addition, the initial temperature, current temperature, and recording time of the steel are recorded by temperature sensors and timers respectively, so as to obtain the cooling time of the steel from the initial temperature to the current temperature.

[0041] Step S220: Obtain multiple candidate heat transfer coefficients based on preset heat transfer coefficient conditions.

[0042] In one embodiment of this application, multiple candidate heat transfer coefficients are obtained based on preset heat transfer coefficient conditions, including: obtaining the value range of the heat transfer coefficient, and determining the number of items of the candidate heat transfer coefficients based on the preset heat transfer coefficient conditions; selecting multiple values ​​as candidate heat transfer coefficients within the value range, wherein the number of items of the multiple values ​​is the same as the number of items of the candidate heat transfer coefficients.

[0043] It should be noted that, based on prior knowledge, when the initial ambient temperature range is 20℃ to 100℃, the heat transfer coefficient between the steel billet and the environment is usually between 0 and 100W.

[0044] In one specific embodiment of this application, taking an ambient temperature of 2°C and a preset heat transfer coefficient condition of 2W / (m2*K) for uniform sampling as an example, the heat transfer coefficient is first sampled based on a sampling interval of 2W, resulting in 200 different heat transfer coefficient values, i.e., 200 candidate heat transfer coefficients as described above.

[0045] Step S230: Based on the training sample data and multiple candidate heat transfer coefficients, construct temperature prediction models to obtain multiple candidate temperature prediction models, and verify each candidate temperature prediction model based on the test sample data to obtain the target temperature prediction model.

[0046] In one embodiment of this application, a temperature prediction model is constructed based on training sample data and multiple candidate heat transfer coefficients to obtain multiple candidate temperature prediction models. The process includes: determining any candidate heat transfer coefficient as a specified heat transfer coefficient, and training an initial prediction model based on the specified heat transfer coefficient; using the initial temperature and current temperature in the training sample data as input information and the cooling time in the training sample data as output information; labeling the initial temperature and current temperature based on the cooling time, and training the initial prediction model based on the labeled initial temperature and labeled current temperature to obtain candidate temperature prediction models; and traversing each candidate heat transfer coefficient to obtain multiple candidate temperature prediction models.

[0047] In one specific embodiment of this application, the aforementioned 200 candidate heat transfer coefficients are used as an example. After obtaining the aforementioned 200 candidate heat transfer coefficients, each heat transfer coefficient is determined as a specific operating condition. Using these 200 operating conditions, combined with the initial temperature, current temperature, and cooling time in the training sample data, the initial prediction model is trained to obtain 200 different candidate temperature prediction models. Then, based on the initial temperature, current temperature, and cooling time in the test sample data, the aforementioned 200 candidate temperature prediction models are verified to obtain a target temperature prediction model that meets the preset accuracy requirements.

[0048] It should be noted that in the process of determining the target temperature candidate model based on the candidate temperature prediction model, the test results and test errors of the candidate temperature prediction models corresponding to the heat transfer coefficients other than the above 200 candidate heat transfer coefficients can be calculated by interpolation, and the target temperature prediction model can be obtained based on the test error.

[0049] In one embodiment of this application, each candidate temperature prediction model is validated based on test sample data to obtain a target temperature prediction model. This includes: obtaining the initial temperature, current temperature, and actual cooling duration from the test sample; inputting the initial temperature and current temperature from the test sample data into each candidate temperature prediction model to obtain multiple predicted cooling durations; comparing the actual cooling duration with the multiple predicted cooling durations, and determining the predicted cooling duration whose difference from the actual cooling duration meets a preset standard as the standard predicted duration; and determining the candidate temperature prediction model corresponding to the standard predicted duration as the target temperature prediction model.

[0050] In one specific embodiment of this application, firstly, 200 different heat transfer coefficient conditions are obtained based on the above method, and 200 candidate temperature prediction models are obtained by training the initial prediction model based on these 200 conditions; then, test sample data is input into the 200 candidate temperature prediction models to obtain 200 predicted cooling times, and prediction results of other temperature prediction models corresponding to multiple heat transfer coefficients other than the above 200 candidate heat transfer coefficients are calculated based on the above interpolation method; finally, all the above prediction results are compared with the standard prediction time to obtain the target temperature prediction model that meets the accuracy requirements.

[0051] In one embodiment of this application, the predicted cooling time that satisfies a preset deviation from the actual cooling time is determined as the standard predicted time. This includes: calculating the actual cooling time and the predicted cooling time to obtain the prediction deviation; comparing the prediction deviation with the preset deviation; and determining that the predicted cooling time is determined as the standard predicted time when the prediction deviation is less than or equal to the preset deviation.

[0052] In one specific embodiment of this application, after obtaining the difference between all prediction results and the standard prediction duration, the difference is compared with a preset standard deviation. The predicted cooling duration of the candidate temperature prediction model that is less than or equal to the preset standard deviation is determined as the standard cooling duration. The candidate temperature prediction model corresponding to the standard cooling duration is determined as the intended temperature prediction model. Based on the increasing order of the difference between the test results of all intended temperature prediction models and the standard prediction duration, all intended temperature prediction models are sorted. The intended temperature prediction models with the highest preset number of items are selected as the proposed temperature prediction models. Finally, the proposed temperature prediction models are verified multiple times, and the proposed temperature prediction model with the predicted cooling duration closest to the actual cooling duration is obtained as the target temperature prediction model.

[0053] It should be noted that the target temperature prediction models are all determined based on actual production needs. This application does not impose any limitations on their determination methods and processes. The above-mentioned determination method based on prediction differences is only an example and does not impose any restrictions on this application.

[0054] In one embodiment of this application, after obtaining multiple candidate temperature prediction models, the method further includes: obtaining multiple actual cooling times of steel at ambient temperature based on different initial temperatures and different current temperatures, and determining a set of ambient temperature, initial temperature, and current temperature as an input parameter to obtain a first mapping relationship between the input parameter and the actual cooling time; inputting any input parameter into each candidate temperature prediction model to obtain multiple predicted cooling times; obtaining a second mapping relationship between the heat transfer coefficient and the predicted cooling time based on the first correlation between the predicted cooling time and the candidate temperature prediction models, and the second correlation between the heat transfer coefficient and the candidate temperature prediction models; and constructing a thermal boundary condition mapping relationship table based on the first mapping relationship and the second mapping relationship.

[0055] In one embodiment of this application, the ambient temperature is first determined, and the initial temperature of the steel is measured at that ambient temperature. Simultaneously, the measurement time of the initial temperature is recorded, the cooling time of the steel at that initial temperature is tracked, and the current temperature after the cooling time is recorded. The aforementioned first mapping relationship is then generated, thereby constructing a temperature information table as shown in Table 1.

[0056] Table 1

[0057]

[0058]

[0059] As can be seen from the table above, under the same ambient temperature, different initial temperatures and current temperatures correspond to different cooling times. Therefore, when the ambient temperature, initial temperature, and current temperature are all determined, a unique cooling time will be obtained.

[0060] Then, the arbitrarily determined ambient temperature, initial temperature, and current temperature are set as input parameters. These input parameters are then input into different candidate temperature values ​​to obtain different predicted cooling times. Based on the above data, a second mapping relationship is constructed, resulting in the heat transfer coefficient comparison table shown in Table 2.

[0061] Table 2

[0062]

[0063] As shown in Table 2, each heat transfer coefficient corresponds to a candidate temperature prediction model, and a unique predicted cooling time is obtained based on the same input parameters. Furthermore, the prediction deviation is obtained based on the difference between the predicted cooling time and the actual cooling time.

[0064] In one specific embodiment of this application, based on Table 1 and Table 2 above, the following thermal boundary condition mapping relationship table is generated:

[0065] Table 3

[0066]

[0067]

[0068] As shown in Table 3, when the input parameters of the candidate temperature prediction model are processed, a unique predicted cooling time can be obtained. Based on the relationship between the parameters and the actual cooling time, the correlation between the actual cooling time and the predicted cooling time can be obtained. Therefore, based on the difference between the actual cooling time and the predicted cooling time, the candidate temperature prediction model that meets the difference requirement can be determined as the target temperature prediction model. Thus, based on the relationship between the candidate temperature prediction model and the heat transfer coefficient, the heat transfer coefficient corresponding to the target temperature prediction model can be obtained.

[0069] Step S240: The candidate heat transfer coefficient corresponding to the target temperature prediction model is determined as the target heat transfer coefficient, and the target heat transfer coefficient is determined as the thermal boundary condition of steel at ambient temperature.

[0070] In one embodiment of this application, parameter 2 is used as a test parameter and input into each candidate temperature prediction model to obtain multiple predicted cooling times, namely t y1 t y2 t y3 ... and t yn The predicted cooling time and the actual cooling time t2 corresponding to the input parameter 2 are compared respectively to obtain the target temperature prediction model as model y2. Therefore, the heat transfer coefficient β2 corresponding to model y2 is determined as the thermal boundary condition of steel at ambient temperature T1.

[0071] Figure 4 This application illustrates a deep learning model for heat transfer coefficient prediction training and prediction, as shown in an exemplary embodiment. Figure 4 As shown, a database is generated based on the ambient temperature, the initial temperature and current temperature of the steel, and the cooling time from the initial temperature to the current temperature. Then, a deep learning algorithm model is constructed based on the parameters in the database, and its loss function is calculated to determine whether the algorithm model meets the requirements. If it does not meet the requirements, it is retrained. If it meets the requirements, the algorithm model is determined as a neural network prediction model, which is used to predict the cooling time of steel from a certain initial temperature to a specific target temperature under a certain ambient temperature.

[0072] In one embodiment of this application, the thermal boundary conditions such as convective heat transfer and thermal radiation between the rolled piece and the external environment during the rolling process are first equivalent to a heat transfer coefficient. The ambient temperature and the equivalent heat transfer coefficient are used as parameters to establish a parameterized numerical simulation model for heat transfer analysis of the rolled piece. The advantages of the parameterized model are used to carry out large-scale numerical calculations to obtain calculation results. Then, the number and arrangement of observation points are determined, and the temperature of the observation points in the calculation results is extracted. The initial ambient temperature and the equivalent heat transfer coefficient are correlated with the calculated temperature of the observation points to form a temperature-boundary mapping dataset. Finally, the dataset is divided into a training dataset and a test dataset. The temperature of the observation points and the ambient temperature are used as inputs, and the thermal boundary condition parameters are used as outputs to establish a physical information deep learning model. The training dataset is used for training, and the test dataset is used for testing. The model that meets the accuracy requirements is stored as a prediction model.

[0073] In one specific embodiment of this application, the thermal boundary conditions such as convective heat transfer, contact heat transfer, and thermal radiation between the workpiece and the external environment during the rolling process are first equivalent to a heat transfer coefficient; then, the ambient temperature and the equivalent heat transfer coefficient are used as design parameters to establish a parameterized numerical simulation model of the workpiece rolling, and parameters that can cover all ambient temperatures and equivalent heat transfer coefficients are set. The advantages of the parameterized model are utilized to carry out large-scale calculations.

[0074] Figure 5 This is a schematic diagram illustrating the generation of a temperature-heat transfer coefficient database using the finite element method, as shown in an exemplary embodiment of this application; Figure 5 As shown, the temperature-heat transfer coefficient database includes the initial temperature of the billet, the ambient temperature, and the heat transfer coefficient. After processing the initial temperature of the billet, the ambient temperature, and the heat transfer coefficient through the finite element model, new billet temperature, ambient temperature, and heat transfer coefficient are obtained, and the database is generated based on the new billet temperature, ambient temperature, and heat transfer coefficient.

[0075] In one embodiment of this application, after generating the temperature-heat transfer coefficient database, a temperature-boundary mapping dataset can be constructed based on the database. First, the number and arrangement of observation points are determined, with the principle that the observation points can cover all different thermal boundary condition regions of the rolled piece. Then, the temperatures of the observation points are extracted from the calculation results, and the initial ambient temperature and equivalent heat transfer coefficient are correlated with the observation point temperatures to form a temperature-boundary mapping dataset.

[0076] Furthermore, after obtaining the aforementioned temperature-heat transfer coefficient database, the data in this database can be divided into training sample data and test sample data. In one embodiment of this application, the data is divided using a temperature-boundary database, with one part serving as training data for the deep learning model and the other part as test data. The division method is random selection. In addition, the amount of test sample data can be limited, for example, the test data cannot be less than 20% of the total data.

[0077] Figure 6 This is a schematic diagram illustrating the thermal boundary condition calculation steps in an exemplary embodiment of this application, as shown below. Figure 5 As shown, a numerical simulation model is first established; then, the correlation between temperature parameters and heat transfer coefficients is established, and a temperature-heat transfer coefficient database is generated; then, a deep learning model is generated based on this database, and the convergence of its output data is judged. When the output results converge, it is determined as the target prediction model, namely the above-mentioned target temperature prediction model, and the currently collected actual temperature data is input into the target prediction model to obtain the corresponding target heat transfer coefficient.

[0078] In one embodiment of this application, determining the heat transfer coefficient based on the target prediction model includes the following steps: First, temperature data is collected using a temperature sensor and transmitted to a storage device for storage. The temperature sensor should be arranged to take into account the area of ​​interest. Then, the measured temperature data is read from the storage device using a computer as input, and a deep learning prediction model is used to make a prediction to obtain the equivalent heat transfer coefficient that matches the actual temperature boundary conditions.

[0079] It should be noted that the thermal boundary condition calculation method proposed in this application avoids the technical problems of difficult and costly testing of relevant temperature parameters in the steel production environment by equating the thermal boundary condition with a specific heat transfer coefficient. In addition, equating all thermal boundary conditions with a heat transfer coefficient also avoids the problem of difficulty in setting relevant parameters such as convective heat transfer coefficient and thermal emissivity, which leads to the great difficulty in obtaining heat transfer boundary condition parameters in the process of heat transfer analysis or thermo-mechanical coupling analysis of rolled parts. Furthermore, equating the thermal boundary condition in the rolling process of rolled parts with an equivalent heat transfer coefficient can greatly simplify the numerical model and effectively improve the calculation efficiency of the prediction model.

[0080] Figure 7 This is a block diagram illustrating a thermal boundary condition calculation apparatus according to an exemplary embodiment of this application. The apparatus can be applied to... Figure 1 The implementation environment shown is not limited to this embodiment. This device can also be applied to other exemplary implementation environments and specifically configured in other devices. This embodiment does not limit the implementation environment to which the device is applicable.

[0081] like Figure 7As shown, the exemplary thermal boundary condition calculation device includes: a data acquisition module 710, a heat transfer coefficient determination module 720, a model building module 730, and a thermal boundary condition determination module 740.

[0082] The data acquisition module 710 is used to acquire the ambient temperature and the temperature change parameters of the steel under the ambient temperature, and divides the temperature change parameters into test sample data and training sample data; the heat transfer coefficient determination module 720 is used to obtain multiple candidate heat transfer coefficients based on preset heat transfer coefficient conditions; the model building module 730 is used to build temperature prediction models based on the training sample data and multiple candidate heat transfer coefficients respectively, obtain multiple candidate temperature prediction models, and verify each candidate temperature prediction model based on the test sample data to obtain the target temperature prediction model; the thermal boundary condition determination module 740 is used to determine the candidate heat transfer coefficient corresponding to the target temperature prediction model as the target heat transfer coefficient, and determine the target heat transfer coefficient as the thermal boundary condition of the steel under the ambient temperature.

[0083] It should be noted that the thermal boundary condition calculation device and the thermal boundary condition calculation method provided in the above embodiments belong to the same concept. The specific operation methods of each module and unit have been described in detail in the method embodiments and will not be repeated here. In practical applications, the thermal boundary condition calculation device provided in the above embodiments can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. This is not a limitation here.

[0084] Embodiments of this application also provide an electronic device, including: one or more processors; and a storage device for storing one or more programs, which, when executed by the one or more processors, cause the electronic device to implement the thermal boundary condition calculation method provided in the above embodiments.

[0085] Figure 8 A schematic diagram of a computer system suitable for implementing the embodiments of this application is shown. It should be noted that... Figure 8 The computer system 800 of the electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0086] like Figure 8As shown, the computer system 800 includes a Central Processing Unit (CPU) 801, which can perform various appropriate actions and processes based on programs stored in Read-Only Memory (ROM) 802 or programs loaded from storage portion 808 into Random Access Memory (RAM) 803, such as performing the methods described in the above embodiments. The RAM 803 also stores various programs and data required for system operation. The CPU 801, ROM 802, and RAM 803 are interconnected via a bus 804. An Input / Output (I / O) interface 805 is also connected to the bus 804.

[0087] The following components are connected to I / O interface 805: an input section 806 including a keyboard, mouse, etc.; an output section 807 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 808 including a hard disk, etc.; and a communication section 809 including a network interface card such as a LAN (Local Area Network) card, modem, etc. The communication section 809 performs communication processing via a network such as the Internet. A drive 810 is also connected to I / O interface 805 as needed. A removable medium 811, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 810 as needed so that computer programs read from it can be installed into storage section 808 as needed.

[0088] Specifically, according to embodiments of this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program including a computer program for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 809, and / or installed from removable medium 811. When the computer program is executed by central processing unit (CPU) 801, it performs various functions defined in the system of this application.

[0089] It should be noted that the computer-readable medium shown in the embodiments of this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, portable compact disc read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying a computer-readable computer program. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The computer program contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to wireless, wired, etc., or any suitable combination thereof.

[0090] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. Each block in a flowchart or block diagram may represent a module, segment, or portion of code, which contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0091] The units described in the embodiments of this application can be implemented in software or hardware, and the described units can also be located in a processor. The names of these units do not necessarily limit the specific unit itself.

[0092] Another aspect of this application provides a computer-readable storage medium storing a computer program thereon, which, when executed by a computer's processor, causes the computer to perform the thermal boundary condition calculation method as described above. This computer-readable storage medium may be included in the electronic device described in the above embodiments, or it may exist independently and not assembled into the electronic device.

[0093] Another aspect of this application provides a computer program product or computer program including computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the thermal boundary condition calculation method provided in the various embodiments described above.

[0094] The above embodiments are merely illustrative of the principles and effects of the present invention and are not intended to limit the invention. Any person skilled in the art can modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical concept disclosed in the present invention should still be covered by the claims of the present invention.

Claims

1. A method of calculating a thermal boundary condition, characterized by, The method includes: The ambient temperature and the temperature change parameters of the steel at the ambient temperature are obtained, and the temperature change parameters are divided into test sample data and training sample data. Multiple candidate heat transfer coefficients are obtained based on preset heat transfer coefficient conditions; wherein, the value range of the heat transfer coefficient is obtained, and the number of items of the candidate heat transfer coefficient is determined based on the preset heat transfer coefficient conditions; multiple values ​​are selected as candidate heat transfer coefficients within the value range, and the number of items of the multiple values ​​is the same as the number of items of the candidate heat transfer coefficient. Temperature prediction models are constructed based on the training sample data and the multiple candidate heat transfer coefficients to obtain multiple candidate temperature prediction models. Each candidate temperature prediction model is then validated based on the test sample data to obtain a target temperature prediction model. The process of constructing temperature prediction models based on the training sample data and the multiple candidate heat transfer coefficients to obtain multiple candidate temperature prediction models includes: determining any candidate heat transfer coefficient as a specified heat transfer coefficient; training an initial prediction model based on the specified heat transfer coefficient; using the initial temperature and current temperature from the training sample data as input information and the cooling time from the training sample data as output information; labeling the initial temperature and current temperature based on the cooling time; and training the initial prediction model based on the labeled initial temperature and labeled current temperature to obtain candidate temperature prediction models; and iterating through each candidate heat transfer coefficient to obtain multiple candidate temperature prediction models. The candidate heat transfer coefficient corresponding to the target temperature prediction model is determined as the target heat transfer coefficient, and the target heat transfer coefficient is determined as the thermal boundary condition of steel at the ambient temperature.

2. The method for calculating thermal boundary conditions according to claim 1, characterized in that, Acquire the ambient temperature, and the temperature change parameters of the steel at that ambient temperature, including: Temperature sensors are set at different locations in the target environment to obtain multiple measured temperature parameters. Based on the preset weights of each measured temperature, all measured temperatures are calculated to obtain the ambient temperature. The initial temperature of the steel in the ambient temperature and its current temperature after cooling are measured, and the cooling time of the steel from the initial temperature to the current temperature is recorded. The initial temperature, the cooling time, and the current temperature are determined as the temperature change parameters of the steel in the ambient temperature.

3. The method for calculating thermal boundary conditions according to claim 1, characterized in that, After obtaining multiple candidate temperature prediction models, the following is also included: The steel is obtained under the ambient temperature, based on different initial temperatures and different current temperatures, and multiple actual cooling times are obtained. A set of ambient temperature, initial temperature, and current temperature is determined as an input parameter to obtain a first mapping relationship between the input parameter and the actual cooling time. By inputting any of the input parameters into each of the candidate temperature prediction models, multiple predicted cooling durations are obtained. Based on the first correlation between the predicted cooling time and the candidate temperature prediction model, and the second correlation between the heat transfer coefficient and the candidate temperature prediction model, a second mapping relationship between the heat transfer coefficient and the predicted cooling time is obtained. A thermal boundary condition mapping table is constructed based on the first mapping relationship and the second mapping relationship.

4. The method for calculating thermal boundary conditions according to any one of claims 1-3, characterized in that, Based on the test sample data, each of the candidate temperature prediction models is validated to obtain the target temperature prediction model, including: Obtain the initial temperature, current temperature, and actual cooling time of the test sample; The initial temperature and the current temperature in the test sample data are input into each candidate temperature prediction model to obtain multiple predicted cooling durations; Compare the actual cooling time with the multiple predicted cooling times, and determine the predicted cooling time whose difference from the actual cooling time meets a preset standard as the standard predicted time. The candidate temperature prediction model corresponding to the standard prediction duration is determined as the target temperature prediction model.

5. The method for calculating thermal boundary conditions according to claim 4, characterized in that, The predicted cooling time that satisfies a preset deviation from the actual cooling time is determined as the standard predicted time, including: The actual cooling time and the predicted cooling time are calculated to obtain the prediction deviation; The predicted deviation is compared with the preset deviation. If the predicted deviation is less than or equal to the preset deviation, the predicted cooling time is determined to be the standard predicted time.

6. A thermal boundary condition calculation device, characterized in that, The device includes: The data acquisition module is used to acquire the ambient temperature and the temperature change parameters of the steel at the ambient temperature, and to divide the temperature change parameters into test sample data and training sample data. A heat transfer coefficient determination module is used to obtain multiple candidate heat transfer coefficients based on preset heat transfer coefficient conditions; wherein, the value range of the heat transfer coefficient is obtained, and the number of items of the candidate heat transfer coefficient is determined based on the preset heat transfer coefficient conditions; multiple values ​​are selected as candidate heat transfer coefficients within the value range, and the number of items of the multiple values ​​is the same as the number of items of the candidate heat transfer coefficient. The model building module is used to construct temperature prediction models based on the training sample data and the multiple candidate heat transfer coefficients, obtaining multiple candidate temperature prediction models, and to verify each candidate temperature prediction model based on the test sample data to obtain a target temperature prediction model. The process of constructing temperature prediction models based on the training sample data and the multiple candidate heat transfer coefficients to obtain multiple candidate temperature prediction models includes: determining any candidate heat transfer coefficient as a specified heat transfer coefficient, training an initial prediction model based on the specified heat transfer coefficient; using the initial temperature and current temperature in the training sample data as input information, and the cooling time in the training sample data as output information; labeling the initial temperature and current temperature based on the cooling time, and training the initial prediction model based on the labeled initial temperature and labeled current temperature to obtain candidate temperature prediction models; and iterating through each candidate heat transfer coefficient to obtain multiple candidate temperature prediction models. The thermal boundary condition determination module is used to determine the candidate heat transfer coefficient corresponding to the target temperature prediction model as the target heat transfer coefficient, and to determine the target heat transfer coefficient as the thermal boundary condition of steel at the ambient temperature.

7. An electronic device, characterized in that, The electronic device includes: One or more processors; A storage device for storing one or more programs, which, when executed by the one or more processors, cause the electronic device to implement the thermal boundary condition calculation method as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, It stores a computer program that, when executed by the computer's processor, causes the computer to perform the thermal boundary condition calculation method according to any one of claims 1 to 5.

Images