A data-driven artificial intelligence magnetic material prediction system and method

Abstract

The application discloses a data-driven artificial intelligence magnetic material prediction system and method, comprising: collecting performance parameters of magnetic materials; using the performance parameters of the magnetic materials to use a data-driven artificial intelligence computing gateway to perform magnetic performance prediction analysis under different use scenarios; statistically processing the magnetic entropy change and the adiabatic temperature change variation interval of the magnetic material structure design end of the processing engineer under different use scenarios; statistically processing the magnetic entropy change and the adiabatic temperature change variation interval used under different use scenarios; determining whether the magnetic entropy change and the adiabatic temperature change variation interval belong to the pre-set variation interval allowable range, and when it is determined that the magnetic entropy change and the adiabatic temperature change variation interval do not belong to the pre-set variation interval allowable range, the magnetic performance prediction analysis results under different use scenarios are respectively sent to the magnetic material structure design end of the processing engineer. The application realizes dynamic monitoring through the management of the magnetic entropy change and the adiabatic temperature change variation interval under different use scenarios, and improves the accuracy of the magnetic performance prediction results.

Description

Technical Field

[0001] The present invention relates to the field of magnetic material performance prediction, and in particular to a data-driven artificial intelligence magnetic material prediction system and method. Background Art

[0002] In the field of materials science and engineering, traditional material design methods rely on large amounts of experimental data and empirical formulas, and often require repeated trials to obtain ideal material properties. However, with the rapid development of data science and artificial intelligence (AI) technology, data-driven artificial intelligence material prediction systems have emerged. Such systems use machine learning (ML) and deep learning (DL) algorithms to efficiently predict various material performance parameters, such as magnetic properties, thermal properties, and mechanical properties, based on existing experimental data and simulation results. Especially in the design of magnetic materials, AI technology can quickly infer their performance in actual applications by analyzing the phase composition, microstructure, and processing technology of the material, reducing the manual intervention and experimental errors in traditional methods.

[0003] Although data-driven artificial intelligence material prediction systems have achieved remarkable results in many aspects, they still face some challenges in practical applications, especially in the lack of accuracy in the structural design of magnetic materials and the prediction of magnetic properties. A major drawback of existing technologies is that although AI models can provide fast performance predictions in some cases, the accuracy of the prediction results is often low when dealing with complex processing processes and material microstructures. The performance of magnetic materials is usually affected by many factors, such as saturation magnetic induction intensity, magnetic permeability, coercive force, magnetocooling, magnetostriction coefficient, magnetoelectric coupling coefficient, etc. Slight changes in these factors may lead to significant differences in the magnetic properties of the material. When simulating these complex multi-physics field coupling effects, current AI models often fail to fully consider the changes in the structure during the processing process, resulting in inaccurate predictions of magnetic properties, especially in specific material systems, where the errors may be large.

[0004] In addition, the application of AI prediction systems in the workflow of processing engineers still has the problem of low efficiency. The design of magnetic materials not only depends on the selection of composition and structure, but also requires accurate prediction of the performance of magnetic materials in the actual processing process. However, existing AI systems usually rely on relatively simple input data and ignore dynamic changes in the processing process, such as temperature, stress and phase change, which makes the system's prediction accuracy low when dealing with complex processing processes. In the application of magnetic materials, the processing technology of magnetic materials has an important influence on the final magnetic properties and functional applications, and the existing AI methods are still insufficient in this regard, resulting in processing engineers being unable to obtain completely reliable prediction results during the design and optimization process, thereby affecting the efficiency and quality of the entire design process. Therefore, how to improve the accuracy of AI prediction systems in the structural design and processing of magnetic materials, especially their performance under multi-physical field coupling conditions, is a technical problem that needs to be solved urgently. Summary of the Invention

[0005] In response to the problems existing in the background technology, the purpose of the present invention is to provide a data-driven artificial intelligence magnetic material prediction system and method.

[0006] In order to achieve the above technical objectives, the present invention provides the following technical solutions:

[0007] The first aspect of the present invention is to provide a data-driven artificial intelligence magnetic material prediction system, comprising: a magnetic material performance parameter acquisition module, a magnetic performance prediction and analysis module, a magnetic entropy change and adiabatic temperature change interval statistics module, a magnetic entropy change and adiabatic temperature change interval statistics module, a magnetic entropy change and adiabatic temperature change interval range determination module, a processing engineer magnetic material structure design terminal module, and a magnetic entropy change and adiabatic temperature change interval update module; wherein,

[0008] Magnetic material performance parameter acquisition module, used to collect the saturation magnetic induction intensity, magnetic permeability, coercive force, magnetic cooling capacity, magnetostriction coefficient, and magnetoelectric coupling coefficient of magnetic materials;

[0009] A magnetic performance prediction and analysis module, connected to the magnetic material parameter acquisition module, is used to utilize the performance parameters of the magnetic material (including saturation magnetic induction intensity, magnetic permeability, coercivity, magneto-refrigeration capacity, magnetostriction coefficient, and magneto-electric coupling coefficient) to perform magnetic performance prediction and analysis in different usage scenarios using a data-driven artificial intelligence computing gateway. The magnetic performance prediction and analysis performed by the data-driven artificial intelligence computing gateway in different usage scenarios includes prediction and analysis of the adaptability and thermal stability of the magnetic material under different magnetic field, temperature, and pressure environments;

[0010] A magnetic entropy change and adiabatic temperature change interval statistics module is connected to the magnetic performance prediction and analysis module and is used to count the magnetic entropy change and adiabatic temperature change intervals under different usage scenarios used by the magnetic performance prediction and analysis module;

[0011] a magnetic entropy change and adiabatic temperature change interval range determination module, connected to the magnetic entropy change and adiabatic temperature change interval statistics module, for determining whether the magnetic entropy change and adiabatic temperature change intervals under the different usage scenarios do not fall within a preset allowable range of the change interval;

[0012] The processing engineer's magnetic material structure design module is connected to the magnetic performance prediction and analysis module and the magnetic entropy change and adiabatic temperature change range determination module. It is used to send the magnetic performance prediction and analysis results under different usage scenarios using the data-driven artificial intelligence computing gateway to the processing engineer's magnetic material structure design terminal;

[0013] The magnetic entropy change and adiabatic temperature change interval update module is used to update the magnetic entropy change and adiabatic temperature change intervals in different usage scenarios of the magnetic entropy change and adiabatic temperature change interval statistics module, as well as to count the magnetic entropy change and adiabatic temperature change intervals of substandard data calculated by processing engineers.

[0014] Preferably, it also includes: a variation interval allowable range module for updating the variation interval allowable range used by the magnetic entropy change and adiabatic temperature change variation interval range determination module to compare the magnetic entropy change and adiabatic temperature change variation intervals.

[0015] Preferably, the magnetic entropy change and adiabatic temperature change interval update module is also used to collect first information of substandard data calculated by processing engineers;

[0016] The magnetic performance prediction and analysis module is further used to: collect data of the processing engineer's non-compliant data and use the magnetic entropy change and adiabatic temperature change intervals, the first information, and the second information to predict new magnetic entropy change and adiabatic temperature change intervals for the processing engineer's non-compliant data;

[0017] The magnetic entropy change and adiabatic temperature change interval statistics module is also used to: count the magnetic entropy change and adiabatic temperature change intervals in different usage scenarios of the magnetic material structure design end of the processing engineer, and use the magnetic entropy change and adiabatic temperature change intervals in different usage scenarios of the magnetic material structure design end of the processing engineer to count the magnetic entropy change and adiabatic temperature change intervals in different usage scenarios, wherein the magnetic entropy change and adiabatic temperature change intervals in different usage scenarios are the magnetic entropy change and adiabatic temperature change intervals and the covariance of the magnetic entropy change and adiabatic temperature change intervals in different usage scenarios of the magnetic material structure design end of the processing engineer.

[0018] Preferably, the module for determining the range of magnetic entropy change and adiabatic temperature change is specifically used to:

[0019] When it is determined that the magnetic entropy change and adiabatic temperature change intervals under the different usage scenarios are lower than the pre-set allowable range of the change interval, the magnetic material parameter acquisition module, the magnetic performance prediction and analysis module, and the magnetic entropy change and adiabatic temperature change interval statistics module are notified to re-calculate the performance parameters of the magnetic material including saturation magnetic induction intensity, magnetic permeability, coercive force, magnetocooling capacity, magnetostriction coefficient, and magnetoelectric coupling coefficient, and use a data-driven artificial intelligence computing gateway to perform magnetic performance prediction and analysis under different usage scenarios and to count the change intervals of magnetic entropy change and adiabatic temperature change.

[0020] Preferably, the processing engineer magnetic material structure design end module is specifically used to:

[0021] Record the number of times the data-driven artificial intelligence computing gateway, sent by the command of the magnetic entropy change and adiabatic temperature change variation range determination module, performs magnetic performance prediction analysis under different usage scenarios, and after receiving the command that the magnetic entropy change and adiabatic temperature change variation range determination module determines that the magnetic entropy change and adiabatic temperature change variation range under different usage scenarios does not fall within the preset allowable range of the variation range, determine whether the number of times the data-driven artificial intelligence computing gateway used by the magnetic performance prediction and analysis module performs magnetic performance prediction analysis results under different usage scenarios and sends them to the processing engineer's magnetic material structure design end within the allowable range of the variation range has reached the preset allowable range of times;

[0022] When the number of times the magnetic performance prediction analysis results are sent under different usage scenarios using the data-driven artificial intelligence computing gateway reaches a pre-set allowed range, the change interval allowed range module is notified to update the change interval allowed range; wherein, the change interval allowed range module is used to use the magnetic entropy change and adiabatic temperature change change intervals obtained by the magnetic entropy change and adiabatic temperature change change interval statistics module under each different usage scenario, and to calculate a new change interval allowed range through the initial change interval allowed range and the influencing factors of the magnetic entropy change and adiabatic temperature change change interval.

[0023] A second aspect of the present invention is to provide a data-driven artificial intelligence magnetic material prediction method, comprising the following steps:

[0024] Step S100, collecting performance parameters of the magnetic material, including: saturation magnetic induction intensity, magnetic permeability, coercive force, magnetic cooling capacity, magnetostriction coefficient, and magnetoelectric coupling coefficient;

[0025] Step S200: Using the performance parameters of the magnetic material, a data-driven artificial intelligence computing gateway is used to perform a predictive analysis of magnetic performance under different usage scenarios. The data-driven artificial intelligence computing gateway performs a predictive analysis of magnetic performance under different usage scenarios, including a predictive analysis of the adaptability and thermal stability of the magnetic material under different magnetic field, temperature, and pressure environments.

[0026] Step S300: Counting the magnetic entropy change and adiabatic temperature change ranges under different usage scenarios of the magnetic material structure design end of the processing engineer;

[0027] Step S400: Counting the variation ranges of magnetic entropy change and adiabatic temperature change in different usage scenarios used by the data-driven artificial intelligence computing gateway to perform magnetic performance prediction analysis in different usage scenarios;

[0028] Step S500: determining whether the magnetic entropy change and adiabatic temperature change ranges under the different usage scenarios do not fall within a preset allowable range of the change range;

[0029] Step S600: When it is determined that the magnetic entropy change and adiabatic temperature change ranges under different usage scenarios do not fall within the pre-set allowable range of the change range, the data-driven artificial intelligence computing gateway used is used to perform magnetic performance prediction and analysis results under different usage scenarios and send them to the magnetic material structure design end of the processing engineer.

[0030] Preferably, it also includes: when it is determined that the magnetic entropy change and adiabatic temperature change intervals under the different usage scenarios are lower than the preset allowable range of the change interval, saving the current data-driven artificial intelligence computing gateway to perform magnetic performance prediction and analysis results under different usage scenarios and the corresponding magnetic entropy change and adiabatic temperature change intervals under different usage scenarios of the magnetic material structure design end of the processing engineer; determining whether the performance parameters of the magnetic material including saturation magnetic induction intensity, magnetic permeability, coercive force, magnetocooling capacity, magnetostriction coefficient, and magnetoelectric coupling coefficient are re-performed after the last sending of the magnetic performance prediction and analysis results under different usage scenarios using the data-driven artificial intelligence computing gateway, and whether the number of repetitions of using the data-driven artificial intelligence computing gateway to perform magnetic performance prediction and analysis under different usage scenarios and statistics on the magnetic entropy change and adiabatic temperature change intervals reaches the preset allowable range of repetitions;

[0031] When it is determined that the number of repetitions has reached a preset permissible repetition range, the stored magnetic entropy change and adiabatic temperature change in different usage scenarios with the largest change ranges of the magnetic entropy change and adiabatic temperature change are counted;

[0032] When it is determined that the number of repetitions does not reach the preset allowable repetition range, the performance parameters of the magnetic material including saturation magnetic induction intensity, magnetic permeability, coercive force, magneto-cooling capacity, magnetostriction coefficient, and magneto-electric coupling coefficient are re-calculated, and a data-driven artificial intelligence computing gateway is used to perform magnetic performance prediction analysis under different usage scenarios and to calculate the magnetic entropy change and adiabatic temperature change range.

[0033] Preferably, after determining that the magnetic entropy change and adiabatic temperature change ranges in different usage scenarios do not fall within a preset allowable range of the change range, the method further includes:

[0034] Determine whether the number of times the magnetic performance prediction analysis results under different usage scenarios of the data-driven artificial intelligence computing gateway used have been sent to the magnetic material structure design end of the processing engineer within the allowable range of the variation interval has reached a preset allowable range;

[0035] When it is determined that the number of times sent has reached the preset allowable range, a new allowable range of the change interval is counted; the new allowable range of the change interval is counted including:

[0036] Statistics initial change interval allowable range;

[0037] Calculate the factors affecting the magnetic entropy change and adiabatic temperature change range in different usage scenarios during each transmission;

[0038] A new allowable range of the change interval is calculated based on the allowable range of the initial change interval and the influencing factors of the magnetic entropy change and adiabatic temperature change change interval, wherein the new allowable range of the change interval is the influencing factors of the allowable range of the initial change interval and the magnetic entropy change and adiabatic temperature change change interval.

[0039] Preferably, the data-driven artificial intelligence computing gateway is used to predict and analyze the magnetic performance under different usage scenarios, including the following steps:

[0040] Calculate the range of magnetic entropy change and adiabatic temperature change in different usage scenarios for magnetic material structure design by processing engineers;

[0041] The magnetic entropy change and adiabatic temperature change intervals and the covariance of the magnetic entropy change and adiabatic temperature change intervals under different usage scenarios of the magnetic material structure design end of the processing engineer are used as the magnetic entropy change and adiabatic temperature change intervals under different usage scenarios;

[0042] Preferably, before sending the magnetic performance prediction analysis results of the data-driven artificial intelligence computing gateway used in different usage scenarios to the magnetic material structure design end of the processing engineer, it also includes:

[0043] The statistical data-driven artificial intelligence computing gateway performs magnetic performance prediction and analysis results in different usage scenarios, including the corresponding magnetic entropy change and adiabatic temperature change ranges of the non-compliant data measured by the processing engineer and the first information, where the first information is the predetermined frequency of occurrence of the non-compliant data measured by the corresponding processing engineer;

[0044] After the data-driven artificial intelligence computing gateway sends the magnetic performance prediction analysis results under different usage scenarios a predetermined number of times, second information of the non-compliant data measured by the processing engineer is collected, wherein the second information is the probability of occurrence of the non-compliant data measured by the corresponding processing engineer when the data-driven artificial intelligence computing gateway sends the magnetic performance prediction analysis results under different usage scenarios a predetermined number of times;

[0045] Using the magnetic entropy change and adiabatic temperature change intervals, the first information, and the second information, calculating new magnetic entropy change and adiabatic temperature change intervals for the data that does not meet the standards measured by the processing engineer;

[0046] The data-driven artificial intelligence computing gateway performs magnetic performance prediction and analysis results under different usage scenarios, including substandard data calculated by processing engineers, and the magnetic entropy change and adiabatic temperature change ranges under different usage scenarios are statistically analyzed using substandard data calculated by processing engineers.

[0047] Beneficial effects:

[0048] (1) The present invention proposes a data-driven artificial intelligence magnetic material prediction system and method, which counts the magnetic entropy change and adiabatic temperature change intervals in different usage scenarios and compares them with the pre-set allowable range of the change interval. By managing the magnetic entropy change and adiabatic temperature change intervals in different usage scenarios, the data-driven artificial intelligence computing gateway is managed to perform magnetic performance prediction analysis in different usage scenarios, which solves the problem of cumbersome prediction process and low accuracy caused by the prior art of randomly sending data-driven artificial intelligence computing gateways to perform magnetic performance prediction analysis in different usage scenarios.

[0049] (2) The present invention manages the dynamic magnetic entropy change and adiabatic temperature change by managing the change ranges of magnetic entropy change and adiabatic temperature change in different usage scenarios, and manages the lateral differences of the magnetic performance prediction analysis in different usage scenarios through the operation and operability of the data-driven artificial intelligence computing gateway, thereby improving the work efficiency of the magnetic material structure design end module of the processing engineer and further improving the accuracy of the magnetic performance prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0051] Figure 1 This is a module composition diagram of a data-driven artificial intelligence magnetic material prediction system proposed in the present invention;

[0052] Figure 2 This is a flow chart of a data-driven artificial intelligence magnetic material prediction method proposed in the present invention. DETAILED DESCRIPTION

[0053] It should be noted that, unless there is a conflict, the embodiments and features in the embodiments of this application can be combined with each other. The present application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0054] like Figure 1 As shown in FIG, it is a module composition diagram of a data-driven artificial intelligence magnetic material prediction system according to an embodiment of the present invention. The system includes: a magnetic material performance parameter acquisition module, a magnetic performance prediction and analysis module, a magnetic entropy change and adiabatic temperature change interval statistics module, a magnetic entropy change and adiabatic temperature change interval statistics module, a magnetic entropy change and adiabatic temperature change interval range determination module, a processing engineer magnetic material structure design terminal module, and a magnetic entropy change and adiabatic temperature change interval update module; wherein,

[0055] The magnetic material parameter acquisition module is used to collect the performance parameters of magnetic materials, including saturation magnetic induction intensity, magnetic permeability, coercive force, magneto-refrigeration capacity, magnetostriction coefficient, and magneto-electric coupling coefficient.

[0056] For dynamic magnetic entropy change and adiabatic temperature change management with specific content, the adaptability and thermal stability of magnetic materials in different usage scenarios, such as different magnetic field, temperature, and pressure environments, are the factors with the greatest influence on dynamic magnetic entropy change and adiabatic temperature change management, which are statistically analyzed using the dynamic magnetic entropy change and adiabatic temperature change management content. Generally, obtaining the adaptability and thermal stability of magnetic materials in different magnetic field, temperature, and pressure environments should be conducive to completing the non-standard data calculated by processing engineers based on the dynamic magnetic entropy change and adiabatic temperature change management content. For example, for antagonistic dynamic magnetic entropy change and adiabatic temperature change management, the adaptability and thermal stability of the magnetic material in different magnetic field, temperature, and pressure environments can be set as target features or roles with maximum processing power. The saturation magnetic induction intensity, magnetic permeability, coercive force, magnetic cooling capacity, magnetostriction coefficient, and magnetoelectric coupling coefficient of the magnetic material may include: change values, thresholds, etc. of the adaptability and thermal stability of the magnetic material in different magnetic field, temperature, and pressure environments.

[0057] The magnetic performance prediction and analysis module is connected to the magnetic material parameter acquisition module and is used to utilize the performance parameters of the magnetic material, including saturation magnetic induction intensity, magnetic permeability, coercive force, magnetocooling capacity, magnetostriction coefficient, and magnetoelectric coupling coefficient, to use a data-driven artificial intelligence computing gateway to perform magnetic performance prediction and analysis under different usage scenarios; wherein, the magnetic performance prediction and analysis under the above-mentioned different usage scenarios includes the prediction and analysis of the adaptability and thermal stability of the magnetic material under different magnetic field, temperature, and pressure environments.

[0058] Specifically, the magnetic performance prediction and analysis results of the data-driven artificial intelligence computing gateway used by the magnetic performance prediction and analysis module in different usage scenarios should include the results of the adaptability and thermal stability of the magnetic material under different magnetic field, temperature, and pressure environments. The data-driven artificial intelligence computing gateway for magnetic performance prediction and analysis in different usage scenarios should include the data-driven artificial intelligence computing gateway for magnetic performance prediction and analysis in different usage scenarios, which is statistically analyzed using dynamic magnetic entropy change and adiabatic temperature change management content and is to be sent to each processing engineer's magnetic material structure design end module. The adaptability and thermal stability of the magnetic material under different magnetic field, temperature, and pressure environments are included in the magnetic performance prediction and analysis in different usage scenarios of the data-driven artificial intelligence computing gateway to be sent to one or more processing engineers' magnetic material structure design end modules. For example, the adaptability and thermal stability of the magnetic material under different magnetic field, temperature, and pressure environments should be used when the magnetic performance prediction and analysis module uses the data-driven artificial intelligence computing gateway to perform magnetic performance prediction and analysis in different usage scenarios and included in the magnetic performance prediction and analysis in different usage scenarios of the data-driven artificial intelligence computing gateway used.

[0059] The magnetic entropy change and adiabatic temperature change interval statistics module is connected to the magnetic performance prediction and analysis module, and is used to statistically calculate the magnetic entropy change and adiabatic temperature change intervals in different usage scenarios of the magnetic material structure design end of the processing engineer, as well as the magnetic entropy change and adiabatic temperature change intervals in different usage scenarios used by the magnetic performance prediction and analysis module.

[0060] Specifically, the magnetic entropy change and adiabatic temperature change interval statistics module can use the data-driven artificial intelligence computing gateway used by the magnetic performance prediction and analysis module to be sent to each processing engineer's magnetic material structure design end module to perform magnetic performance prediction and analysis under different usage scenarios, and statistics the magnetic entropy change and adiabatic temperature change intervals under different usage scenarios to be sent to the processing engineer's magnetic material structure design end module. It is understandable that the data-driven artificial intelligence computing gateway generated by the random sending method is used to perform magnetic performance prediction and analysis under different usage scenarios. The differences in difficulty, operability, etc. are also random, so that unexpected unevenness may occur in the same dynamic magnetic entropy change and adiabatic temperature change management in the same period. This unexpected unevenness is also one of the important reasons why the existing random sending principle affects the trouble and stickiness of user prediction. Using one embodiment of the present invention, the magnetic entropy change and adiabatic temperature change interval statistics module is used to count the magnetic entropy change and adiabatic temperature change intervals under different usage scenarios of the processing engineer's magnetic material structure design end, which is an important means of managing the existing random sending principle.

[0061] By using an embodiment of the present invention, the magnetic entropy change and adiabatic temperature change interval statistics module can count the magnetic entropy change and adiabatic temperature change intervals in different usage scenarios based on the statistical magnetic entropy change and adiabatic temperature change intervals in different usage scenarios of the processing engineer's magnetic material structure design end. Of course, by using other feasible implementation methods, it is also possible to perform pre-set operations on all data-driven artificial intelligence computing gateways used by the magnetic performance prediction and analysis module for magnetic performance prediction and analysis in different usage scenarios, thereby counting the magnetic entropy change and adiabatic temperature change intervals in different usage scenarios used by the magnetic performance prediction and analysis module. In this case, the magnetic entropy change and adiabatic temperature change interval statistics module may not perform statistics on the magnetic entropy change and adiabatic temperature change intervals for magnetic performance prediction and analysis in different usage scenarios for the data-driven artificial intelligence computing gateways of the magnetic material structure design end modules of each processing engineer.

[0062] In this embodiment, the magnetic entropy change and adiabatic temperature change change intervals reflect the difficulty and operability of the dynamic magnetic entropy change and adiabatic temperature change management content reflected by the data-driven artificial intelligence computing gateway in performing magnetic performance prediction and analysis in different usage scenarios, as well as the differences between the magnetic performance prediction and analysis in different usage scenarios performed by the data-driven artificial intelligence computing gateway of the magnetic material structure design end module of each processing engineer. Through the magnetic entropy change and adiabatic temperature change change intervals, the differences in the difficulty and operability of the magnetic performance prediction and analysis in different usage scenarios performed by the data-driven artificial intelligence computing gateway sent to the magnetic material structure design end module of each processing engineer can be obtained, which can be distinguished from the unexpected difficulty, operability and difference reflected in the existing random sending principle.

[0063] The magnetic entropy change and adiabatic temperature change interval range determination module is connected to the magnetic entropy change and adiabatic temperature change interval statistics module, and is used to determine whether the magnetic entropy change and adiabatic temperature change intervals in different usage scenarios do not fall within the preset allowable range of the change interval.

[0064] Specifically, the pre-set allowable range of the change interval can be set based on the desired differences between the various dynamic magnetic entropy change and adiabatic temperature change management elements included in the magnetic performance prediction analysis under different usage scenarios using the data-driven artificial intelligence computing gateway, and the magnetic performance prediction analysis under different usage scenarios using the data-driven artificial intelligence computing gateway of the magnetic material structure design end module of each processing engineer. In this embodiment, when the magnetic entropy change and adiabatic temperature change change interval range determination module determines that the magnetic entropy change and adiabatic temperature change change intervals in different usage scenarios are lower than the pre-set allowable range of the change interval, it indicates that the difficulty and operability of the overall dynamic magnetic entropy change and adiabatic temperature change management and the data-driven artificial intelligence computing gateway of the magnetic material structure design end module of each processing engineer perform magnetic performance prediction analysis in different usage scenarios. The difference is beyond expectations, and it is necessary to notify the magnetic material parameter acquisition module, the magnetic performance prediction and analysis module, and the magnetic entropy change and adiabatic temperature change change interval statistics module to perform statistics on the adaptability and thermal stability of the magnetic material under different magnetic fields, temperatures, and pressure environments, use the data-driven artificial intelligence computing gateway to perform magnetic performance prediction analysis in different usage scenarios, and count the magnetic entropy change and adiabatic temperature change change intervals again, until the magnetic entropy change and adiabatic temperature change change interval range determination module statistics the magnetic entropy change and adiabatic temperature change change intervals in different usage scenarios that meet the expected difficulty, operability and difference expectations, that is, the allowable range of the change interval does not belong to the pre-set allowable range of the change interval.

[0065] The processing engineer's magnetic material structure design end module is connected to the magnetic performance prediction and analysis module and the magnetic entropy change and adiabatic temperature change range determination module. It is used to send the magnetic performance prediction and analysis results under different usage scenarios using the data-driven artificial intelligence computing gateway to the processing engineer's magnetic material structure design end.

[0066] In this embodiment, the magnetic entropy change and adiabatic temperature change variation intervals under different usage scenarios reflect the overall difficulty, operability and individual differences of the data-driven artificial intelligence computing gateway to be sent to the magnetic material structure design end module of each processing engineer for magnetic performance prediction analysis under different usage scenarios. If the magnetic entropy change and adiabatic temperature change variation intervals do not fall within the pre-set allowable range of the variation interval, it indicates that the overall difficulty, operability and individual differences of the data-driven artificial intelligence computing gateway of the magnetic material structure design end module of each processing engineer for magnetic performance prediction analysis under different usage scenarios meet the required expectations. Each processing engineer magnetic material structure design end module can use the data-driven artificial intelligence computing gateway to perform magnetic performance prediction analysis under different usage scenarios and start dynamic magnetic entropy change and adiabatic temperature change management.

[0067] The magnetic entropy change and adiabatic temperature change interval update module is used to update the magnetic entropy change and adiabatic temperature change intervals in different usage scenarios of the magnetic entropy change and adiabatic temperature change interval statistics module, as well as to count the magnetic entropy change and adiabatic temperature change intervals of substandard data calculated by processing engineers.

[0068] In an optional embodiment, the system further includes a register, which is connected to the magnetic performance prediction and analysis module and is used to store the magnetic performance prediction and analysis results of the data-driven artificial intelligence computing gateway used by the magnetic performance prediction and analysis module in different usage scenarios. Thus, when the magnetic entropy change and adiabatic temperature change variation interval determination module calculates that the magnetic entropy change and adiabatic temperature change variation intervals in different usage scenarios do not fall within the pre-set variation interval allowable range, the processing engineer magnetic material structure design end module can retrieve the stored data-driven artificial intelligence computing gateway from the register to perform magnetic performance prediction and analysis in different usage scenarios, and send the magnetic performance prediction and analysis results of the data-driven artificial intelligence computing gateway in different usage scenarios to the processing engineer magnetic material structure design end.

[0069] In an optional embodiment, the processing engineer magnetic material structure design end module can directly send the magnetic performance prediction analysis results of the data-driven artificial intelligence computing gateway used by the magnetic performance prediction and analysis module under different usage scenarios or the magnetic performance prediction analysis results of the data-driven artificial intelligence computing gateway stored in the register under different usage scenarios to each processing engineer magnetic material structure design end module without relying on the instruction signal of the magnetic entropy change and adiabatic temperature change range determination module. Thus, when the magnetic entropy change and adiabatic temperature change range determination module calculates that the magnetic entropy change and adiabatic temperature change range under different usage scenarios are lower than the preset change range allowable range and it is necessary to re-calculate the saturation magnetic induction intensity, magnetic permeability, coercive force, magnetocooling capacity, magnetostriction coefficient, and magnetoelectric coupling coefficient of the magnetic material and use the data-driven artificial intelligence computing gateway to perform magnetic performance prediction analysis under different usage scenarios, the processing engineer magnetic material structure design end module needs to issue a command to the processing engineer magnetic material structure design end to delete or withdraw the sent data-driven artificial intelligence computing gateway for magnetic performance prediction analysis under different usage scenarios from each processing engineer magnetic material structure design end module.

[0070] like Figure 2 As shown, a data-driven artificial intelligence magnetic material prediction method according to one embodiment of the present invention includes the following steps:

[0071] Step S100, collecting the performance parameters of the magnetic material, including: saturation magnetic induction intensity, magnetic permeability, coercive force, magneto-cooling capacity, magnetostriction coefficient, magneto-electric coupling coefficient. For dynamic magnetic entropy change and adiabatic temperature change management with specific content, the adaptability and thermal stability of the magnetic material under different magnetic field, temperature and pressure environments are preferably the factors with the greatest influence on the dynamic magnetic entropy change and adiabatic temperature change management calculated by using the dynamic magnetic entropy change and adiabatic temperature change management content. Generally, obtaining the adaptability and thermal stability of the magnetic material under different magnetic field, temperature and pressure environments should be conducive to completing the calculation of non-standard data by the processing engineer based on the dynamic magnetic entropy change and adiabatic temperature change management content. For example, for confrontation-type dynamic magnetic entropy change and adiabatic temperature change management, the adaptability and thermal stability of the magnetic material under different magnetic field, temperature and pressure environments can be set as the target feature or role with the greatest combat effectiveness. The saturation magnetic induction intensity, magnetic permeability, coercive force, magnetocooling capacity, magnetostriction coefficient, and magnetoelectric coupling coefficient of the magnetic material can include: the adaptability and thermal stability of the magnetic material under different magnetic field, temperature, and pressure environments.

[0072] Step S200: Using the performance parameters of the magnetic material (including saturation magnetic induction, magnetic permeability, coercivity, magneto-refrigeration, magnetostriction coefficient, and magneto-electric coupling coefficient), a data-driven artificial intelligence computing gateway is used to perform magnetic performance prediction analysis under different usage scenarios. The data-driven artificial intelligence computing gateway performs magnetic performance prediction analysis under different usage scenarios, including prediction analysis of the adaptability and thermal stability of the magnetic material under different magnetic field, temperature, and pressure environments.

[0073] Specifically, the data-driven artificial intelligence computing gateway used in the prediction and analysis of magnetic performance in different usage scenarios should include the adaptability and thermal stability of the magnetic material in different magnetic field, temperature, and pressure environments. The data-driven artificial intelligence computing gateway used in the prediction and analysis of magnetic performance in different usage scenarios should include the data-driven artificial intelligence computing gateway to be sent to the magnetic material structure design end module of each processing engineer based on the statistics of dynamic magnetic entropy change and adiabatic temperature change management content, wherein the adaptability and thermal stability of the magnetic material in different magnetic field, temperature, and pressure environments are included in the data-driven artificial intelligence computing gateway to be sent to one or more processing engineers' magnetic material structure design end module for predicting and analyzing magnetic performance in different usage scenarios.

[0074] Step S300: Counting the magnetic entropy change and adiabatic temperature change ranges under different usage scenarios of the magnetic material structure design end of the processing engineer;

[0075] Specifically, the artificial intelligence computing gateway driven by the data to be sent to the magnetic material structure design end module of each processing engineer can be used to predict and analyze the magnetic performance under different usage scenarios, and the magnetic entropy change and adiabatic temperature change variation intervals under different usage scenarios of the magnetic material structure design end module to be sent to the processing engineer can be counted. It can be understood that the artificial intelligence computing gateway driven by the data generated by the random sending method is used to predict and analyze the magnetic performance under different usage scenarios. The differences in difficulty, operability, etc. are also random, so that the same dynamic magnetic entropy change and adiabatic temperature change management in the same period may cause unexpected unevenness. This unexpected unevenness is also one of the important reasons why the existing random sending principle affects the trouble and stickiness of user prediction. Using an embodiment of the present invention, the magnetic entropy change and adiabatic temperature change variation intervals under different usage scenarios of the magnetic material structure design end of the processing engineer are counted, which is an important means of managing the existing random sending principle.

[0076] Step S400: Counting the magnetic entropy change and adiabatic temperature change ranges under different usage scenarios;

[0077] By using an embodiment of the present invention, the magnetic entropy change and adiabatic temperature change intervals can be counted based on the magnetic entropy change and adiabatic temperature change intervals in different usage scenarios of the processing engineer's magnetic material structure design end counted in step S300. Of course, by using other feasible implementation methods, it is also possible to perform pre-set operations on all the data-driven artificial intelligence computing gateways used to predict and analyze the magnetic performance in different usage scenarios, thereby counting the magnetic entropy change and adiabatic temperature change intervals in the different usage scenarios used. In this case, step S300 of performing the magnetic performance prediction analysis and magnetic entropy change and adiabatic temperature change interval statistics for the data-driven artificial intelligence computing gateway of each processing engineer's magnetic material structure design end module in different usage scenarios may not be performed.

[0078] In this embodiment, the magnetic entropy change and adiabatic temperature change change intervals reflect the difficulty and operability of the dynamic magnetic entropy change and adiabatic temperature change management content reflected by the data-driven artificial intelligence computing gateway in performing magnetic performance prediction and analysis in different usage scenarios, as well as the differences between the magnetic performance prediction and analysis in different usage scenarios performed by the data-driven artificial intelligence computing gateway of the magnetic material structure design end module of each processing engineer. Through the magnetic entropy change and adiabatic temperature change change intervals, the differences in the difficulty and operability of the magnetic performance prediction and analysis in different usage scenarios performed by the data-driven artificial intelligence computing gateway sent to the magnetic material structure design end module of each processing engineer can be obtained, which can be distinguished from the unexpected difficulty, operability and difference reflected in the existing random sending principle.

[0079] Step S500: determining whether the magnetic entropy change and adiabatic temperature change ranges under different usage scenarios do not fall within a preset allowable range of the change range;

[0080] Specifically, the pre-set allowable range of the change interval can be set based on the desired differences between the various dynamic magnetic entropy change and adiabatic temperature change management elements included in the magnetic performance prediction analysis under different usage scenarios using the data-driven artificial intelligence computing gateway, and the magnetic performance prediction analysis under different usage scenarios using the data-driven artificial intelligence computing gateway of the magnetic material structure design end module of each processing engineer. In this embodiment, when the magnetic entropy change and adiabatic temperature change variation intervals in different usage scenarios are lower than the pre-set allowable range of the variation interval, it indicates that the difficulty and operability of the overall dynamic magnetic entropy change and adiabatic temperature change management and the data-driven artificial intelligence computing gateway of the magnetic material structure design end module of each processing engineer for the magnetic performance prediction analysis in different usage scenarios are beyond expectations, and it is necessary to re-perform steps S100 to S400 to statistically analyze the adaptability and thermal stability of magnetic materials in different magnetic fields, temperatures, and pressure environments, use the data-driven artificial intelligence computing gateway to perform magnetic performance prediction analysis in different usage scenarios, and statistically analyze the magnetic entropy change and adiabatic temperature change variation intervals until the magnetic entropy change and adiabatic temperature change variation intervals in different usage scenarios meet the expected difficulty, operability and difference expectations, that is, the allowable range of the variation interval does not belong to the pre-set allowable range of the variation interval.

[0081] Step S600: If it is determined in step S500 that the magnetic entropy change and adiabatic temperature change ranges under different usage scenarios do not fall within the pre-set allowable range of the change range, the data-driven artificial intelligence computing gateway used will be used to perform magnetic performance prediction and analysis results under different usage scenarios and send them to the processing engineer's magnetic material structure design end.

[0082] In this embodiment, the magnetic entropy change and adiabatic temperature change variation intervals under different usage scenarios reflect the overall difficulty, operability and individual differences of the data-driven artificial intelligence computing gateway to be sent to the magnetic material structure design end module of each processing engineer for magnetic performance prediction analysis under different usage scenarios. If the magnetic entropy change and adiabatic temperature change variation intervals do not fall within the pre-set allowable range of the variation interval, it indicates that the overall difficulty, operability and individual differences of the data-driven artificial intelligence computing gateway of the magnetic material structure design end module of each processing engineer for magnetic performance prediction analysis under different usage scenarios meet the required expectations. Each processing engineer magnetic material structure design end module can use the data-driven artificial intelligence computing gateway to perform magnetic performance prediction analysis under different usage scenarios and start dynamic magnetic entropy change and adiabatic temperature change management.

[0083] In an optional embodiment, before the data-driven artificial intelligence computing gateway of each user performs magnetic performance prediction analysis under different usage scenarios on the magnetic entropy change and adiabatic temperature change intervals in step S300, or before the magnetic entropy change and adiabatic temperature change intervals in different usage scenarios are calculated in step S400, the magnetic performance prediction analysis results of the data-driven artificial intelligence computing gateway used in different usage scenarios are sent to the magnetic material structure design end module of each processing engineer. Thus, when it is determined that the magnetic entropy change and adiabatic temperature change intervals in different usage scenarios are lower than the pre-set allowable range of the variation interval and it is necessary to re-calculate the performance parameters of the magnetic material including saturation magnetic induction intensity, magnetic permeability, coercive force, magneto-refrigeration capacity, magnetostriction coefficient, and magneto-electric coupling coefficient, and use the data-driven artificial intelligence computing gateway to perform magnetic performance prediction analysis under different usage scenarios, it is necessary to delete or withdraw the sent data-driven artificial intelligence computing gateway from the magnetic material structure design end module of each processing engineer to perform magnetic performance prediction analysis under different usage scenarios.

[0084] It reflects the differences between the magnetic performance prediction and analysis in different usage scenarios performed by the artificial intelligence computing gateway driven by the data to be sent by the processing engineer's magnetic material structure design end.

[0085] Utilizing a further optional embodiment of the present invention, the magnetic entropy change and adiabatic temperature change intervals for each type of processing engineer to calculate substandard data are not fixed, but can be dynamically adjusted. The process of dynamically adjusting the magnetic entropy change and adiabatic temperature change intervals for the processing engineer to calculate substandard data using one embodiment of the present invention. It should be understood that for multiple types of processing engineers to calculate substandard data, the dynamic adjustment of the magnetic entropy change and adiabatic temperature change intervals for the processing engineer to calculate substandard data in this embodiment can be applied respectively, and other possible dynamic adjustment methods are also applicable.

[0086] By utilizing the above embodiments of the present invention, the magnetic entropy change and adiabatic temperature change intervals in different usage scenarios are counted and compared with the pre-set allowable range of the change interval, so as to realize the management of the magnetic performance prediction analysis of the data-driven artificial intelligence computing gateway in different usage scenarios by managing the magnetic entropy change and adiabatic temperature change intervals in different usage scenarios. Compared with the existing problems of cumbersome prediction and low accuracy brought about by the random sending of data-driven artificial intelligence computing gateway for magnetic performance prediction analysis in different usage scenarios, the data-driven artificial intelligence computing gateway for magnetic performance prediction analysis management system in different usage scenarios of each embodiment of the present invention can realize the management of the difficulty and operability of dynamic magnetic entropy change and adiabatic temperature change management by managing the magnetic entropy change and adiabatic temperature change intervals in different usage scenarios, as well as the lateral differences of the magnetic performance prediction analysis of the data-driven artificial intelligence computing gateway in different usage scenarios, thereby improving the work efficiency of the magnetic material structure design end module of the processing engineer and improving the accuracy of the magnetic performance prediction.

[0087] Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various equivalent changes, modifications, substitutions and variations may be made to these embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A data-driven artificial intelligence magnetic material prediction system, characterized in that: include: Magnetic material performance parameter acquisition module, used to collect the performance parameters of magnetic materials, including saturation magnetic induction intensity, magnetic permeability, coercive force, magnetic cooling capacity, magnetostriction coefficient, and magnetoelectric coupling coefficient; A magnetic performance prediction and analysis module, which is used to use the performance parameters of the magnetic material using a data-driven artificial intelligence computing gateway to perform magnetic performance prediction and analysis in different usage scenarios. The magnetic performance prediction and analysis performed by the data-driven artificial intelligence computing gateway in different usage scenarios includes predictive analysis of the adaptability and thermal stability of the magnetic material under different magnetic field, temperature, and pressure environments; A module for statistically analyzing the magnetic entropy change and adiabatic temperature change intervals, for statistically analyzing the magnetic entropy change and adiabatic temperature change intervals in different usage scenarios used by the magnetic performance prediction and analysis module; A magnetic entropy change and adiabatic temperature change variation range determination module is used to determine whether the variation range of the magnetic entropy change and adiabatic temperature change in the different usage scenarios does not fall within a preset variation range; The processing engineer magnetic material structure design end module is used to send the magnetic performance prediction analysis results under different usage scenarios using the data-driven artificial intelligence computing gateway to the processing engineer magnetic material structure design end; The magnetic entropy change and adiabatic temperature change interval update module is used to update the magnetic entropy change and adiabatic temperature change intervals in different usage scenarios of the magnetic entropy change and adiabatic temperature change interval statistics module, and to count the magnetic entropy change and adiabatic temperature change intervals of substandard data calculated by processing engineers; It also includes: a variation interval allowable range module, which is used to update the variation interval allowable range used by the magnetic entropy change and adiabatic temperature change variation interval range determination module to compare the magnetic entropy change and adiabatic temperature change variation intervals; The magnetic entropy change and adiabatic temperature change interval update module is also used to collect first information of substandard data calculated by processing engineers; The magnetic performance prediction and analysis module is further used to: collect data of the processing engineer's non-compliant data and use the magnetic entropy change and adiabatic temperature change intervals, the first information, and the second information to predict new magnetic entropy change and adiabatic temperature change intervals for the processing engineer's non-compliant data; The magnetic entropy change and adiabatic temperature change interval statistics module is further used to: count the magnetic entropy change and adiabatic temperature change intervals in different usage scenarios of the magnetic material structure design end of the processing engineer, and to use the magnetic entropy change and adiabatic temperature change intervals in different usage scenarios of the magnetic material structure design end of the processing engineer to count the magnetic entropy change and adiabatic temperature change intervals in different usage scenarios, wherein the magnetic entropy change and adiabatic temperature change intervals in different usage scenarios are the magnetic entropy change and adiabatic temperature change intervals and the covariance of the magnetic entropy change and adiabatic temperature change intervals in different usage scenarios of the magnetic material structure design end of the processing engineer; The module for determining the range of magnetic entropy change and adiabatic temperature change is specifically used to: When it is determined that the magnetic entropy change and adiabatic temperature change intervals under the different usage scenarios are lower than the preset allowable range of the change interval, the magnetic material performance parameter acquisition module, the magnetic performance prediction and analysis module, and the magnetic entropy change and adiabatic temperature change interval statistics module are notified to re-calculate the performance parameters of the magnetic material including saturation magnetic induction intensity, magnetic permeability, coercive force, magneto-cooling capacity, magnetostriction coefficient, and magneto-electric coupling coefficient, and use a data-driven artificial intelligence computing gateway to perform magnetic performance prediction and analysis under different usage scenarios and to calculate the change intervals of magnetic entropy change and adiabatic temperature change; The processing engineer magnetic material structure design end module is specifically used to: Record the number of times the data-driven artificial intelligence computing gateway, sent by the command of the magnetic entropy change and adiabatic temperature change variation range determination module, performs magnetic performance prediction analysis under different usage scenarios, and after receiving the command that the magnetic entropy change and adiabatic temperature change variation range determination module determines that the magnetic entropy change and adiabatic temperature change variation range under different usage scenarios does not fall within the preset allowable range of the variation range, determine whether the number of times the data-driven artificial intelligence computing gateway used by the magnetic performance prediction and analysis module performs magnetic performance prediction analysis results under different usage scenarios and sends them to the processing engineer's magnetic material structure design end within the allowable range of the variation range has reached the preset allowable range of times; When the number of times the magnetic performance prediction analysis results are sent under different usage scenarios using the data-driven artificial intelligence computing gateway reaches a pre-set allowed range, the change interval allowed range module is notified to update the change interval allowed range; wherein, the change interval allowed range module is used to use the magnetic entropy change and adiabatic temperature change change intervals obtained by the magnetic entropy change and adiabatic temperature change change interval statistics module under each different usage scenario, and to calculate a new change interval allowed range through the initial change interval allowed range and the influencing factors of the magnetic entropy change and adiabatic temperature change change interval.

2. A data-driven artificial intelligence magnetic material prediction method, characterized in that: The following steps are involved: Step S100, collecting performance parameters of the magnetic material, including saturation magnetic induction intensity, magnetic permeability, coercive force, magnetic cooling capacity, magnetostriction coefficient, and magnetoelectric coupling coefficient; Step S200: Using the performance parameters of the magnetic material, a data-driven artificial intelligence computing gateway is used to perform a predictive analysis of magnetic performance under different usage scenarios. The data-driven artificial intelligence computing gateway performs a predictive analysis of magnetic performance under different usage scenarios, including a predictive analysis of the adaptability and thermal stability of the magnetic material under different magnetic field, temperature, and pressure environments. Step S300: Counting the magnetic entropy change and adiabatic temperature change ranges under different usage scenarios of the magnetic material structure design end of the processing engineer; Step S400: Counting the variation ranges of magnetic entropy change and adiabatic temperature change in different usage scenarios used by the data-driven artificial intelligence computing gateway to perform magnetic performance prediction analysis in different usage scenarios; Step S500: determining whether the magnetic entropy change and adiabatic temperature change ranges under the different usage scenarios do not fall within a preset allowable range of the change range; Step S600: When it is determined that the magnetic entropy change and adiabatic temperature change ranges under different usage scenarios do not fall within the pre-set allowable ranges, the magnetic performance prediction and analysis results under different usage scenarios performed by the data-driven artificial intelligence computing gateway used are sent to the magnetic material structure design end of the processing engineer; It also includes: when it is determined that the magnetic entropy change and adiabatic temperature change variation intervals under the different usage scenarios are lower than the preset variation interval allowable range, saving the magnetic performance prediction analysis results under different usage scenarios by the current data-driven artificial intelligence computing gateway and the corresponding magnetic entropy change and adiabatic temperature change variation intervals under different usage scenarios of the magnetic material structure design end of the processing engineer; determining whether the performance parameters of the magnetic material including saturation magnetic induction intensity, magnetic permeability, coercive force, magnetocooling capacity, magnetostriction coefficient, and magnetoelectric coupling coefficient are re-performed after the last transmission of the magnetic performance prediction analysis results under different usage scenarios using the data-driven artificial intelligence computing gateway, and whether the number of repetitions of using the data-driven artificial intelligence computing gateway to perform magnetic performance prediction analysis under different usage scenarios and statistics on the magnetic entropy change and adiabatic temperature change variation intervals reaches the preset repetition allowable range; When it is determined that the number of repetitions has reached a preset permissible repetition range, the stored magnetic entropy change and adiabatic temperature change in different usage scenarios with the largest change ranges of the magnetic entropy change and adiabatic temperature change are counted; When it is determined that the number of repetitions does not reach a preset permissible repetition range, statistics of the performance parameters of the magnetic material, including saturation magnetic induction intensity, magnetic permeability, coercive force, magneto-refrigeration capacity, magnetostriction coefficient, and magneto-electric coupling coefficient, are re-calculated, and a data-driven artificial intelligence computing gateway is used to perform magnetic performance prediction analysis under different usage scenarios, as well as statistics of magnetic entropy change and adiabatic temperature change ranges; After determining that the magnetic entropy change and adiabatic temperature change ranges under different usage scenarios do not fall within the pre-set allowable ranges, the following also applies: Determine whether the number of times the magnetic performance prediction analysis results under different usage scenarios of the data-driven artificial intelligence computing gateway used have been sent to the magnetic material structure design end of the processing engineer within the allowable range of the variation interval has reached a preset allowable range; When it is determined that the number of times sent has reached the preset allowable range, a new allowable range of the change interval is counted; the new allowable range of the change interval is counted including: Statistics initial change interval allowable range; Calculate the factors affecting the magnetic entropy change and adiabatic temperature change range in different usage scenarios during each transmission; Calculating a new allowable range of the change interval based on the initial allowable range of the change interval and the influencing factors of the magnetic entropy change and the adiabatic temperature change change interval, wherein the new allowable range of the change interval is the influencing factors of the initial allowable range of the change interval and the magnetic entropy change and the adiabatic temperature change change interval; The data-driven artificial intelligence computing gateway is used to predict and analyze the magnetic performance under different usage scenarios, including the magnetic entropy change and adiabatic temperature change ranges under different usage scenarios, including: Calculate the range of magnetic entropy change and adiabatic temperature change in different usage scenarios for magnetic material structure design by processing engineers; The magnetic entropy change and adiabatic temperature change intervals and the covariance of the magnetic entropy change and adiabatic temperature change intervals under different usage scenarios of the magnetic material structure design end of the processing engineer are used as the magnetic entropy change and adiabatic temperature change intervals under different usage scenarios; Before sending the magnetic performance prediction analysis results of different usage scenarios using the data-driven artificial intelligence computing gateway to the magnetic material structure design end of the processing engineer, it also includes: The statistical data-driven artificial intelligence computing gateway performs magnetic performance prediction and analysis results in different usage scenarios, including the corresponding magnetic entropy change and adiabatic temperature change ranges of the non-compliant data measured by the processing engineer and the first information, where the first information is the predetermined frequency of occurrence of the non-compliant data measured by the corresponding processing engineer; After the data-driven artificial intelligence computing gateway sends the magnetic performance prediction analysis results under different usage scenarios a predetermined number of times, second information of the non-compliant data measured by the processing engineer is collected, wherein the second information is the probability of occurrence of the non-compliant data measured by the corresponding processing engineer when the data-driven artificial intelligence computing gateway sends the magnetic performance prediction analysis results under different usage scenarios a predetermined number of times; Using the magnetic entropy change and adiabatic temperature change intervals, the first information, and the second information, calculating new magnetic entropy change and adiabatic temperature change intervals for the data that does not meet the standards measured by the processing engineer; The data-driven artificial intelligence computing gateway performs magnetic performance prediction and analysis results under different usage scenarios, including substandard data calculated by processing engineers, and the magnetic entropy change and adiabatic temperature change ranges under different usage scenarios are statistically analyzed using substandard data calculated by processing engineers.

Images