Prediction method and platform for magnetic domain structure of magnetic material

Abstract

The invention discloses a prediction method and platform for a magnetic domain structure of a magnetic material, and the method comprises the steps: carrying out the parameter processing of crystal structures, chemical compositions and intrinsic properties of different use scenes, and obtaining the parameters of a target magnetic material; judging the parameters of the target magnetic material and the temperature dependence thereof, counting the temperature stability, and generating phase change behavior parameters of the magnetic material and local magnetic parameters of the magnetic material; performing phase change behavior characteristic clustering on the magnetic material phase change behavior parameters to obtain phase change behavior category information; the phase change behavior category information is input into a phase change behavior magnetic domain structure judgment model set for magnetic domain structure judgment, and a magnetic domain structure judgment result is obtained; inputting the local magnetic category information into a magnetic material category analysis model set for magnetic material domain structure category analysis to obtain a magnetic material domain structure analysis result; according to the magnetic domain structure prediction method, the magnetic domain structure prediction accuracy is improved.

Description

Technical Field

[0001] The present invention relates to the field of magnetic material magnetic domain structure prediction, and in particular to a method and platform for predicting the magnetic domain structure of a magnetic material. Background Art

[0002] With the widespread application of magnetic materials in energy, information storage, sensors and other fields, accurately predicting their magnetic domain structure has become a hot topic of research. However, the magnetic domain structure of magnetic materials is not only affected by the crystal structure and elemental composition, but also closely related to various factors such as the microscopic defects of the material and the external environment. Therefore, how to accurately predict the magnetic domain structure of magnetic materials is of great significance to improving material performance and accelerating the discovery of new materials. Existing methods for predicting magnetic domain structure mainly rely on experimental measurements and computational simulations, but these methods are usually limited by sample preparation, experimental conditions and computational models, and it is difficult to provide high-throughput and accurate predictions.

[0003] At present, commonly used methods for predicting magnetic domain structure include calculations based on micromagnetic principles and empirical models. The calculation method based on the micromagnetic principle obtains the microstructure and magnetic characteristics of magnetic materials by solving the Landau-Lifshitz-Gilbert equation, which has high accuracy. However, due to its high computational cost and limited applicability to large-scale samples, it is difficult to meet the needs of high throughput. The empirical model is based on existing magnetic data and establishes the relationship between magnetism and structure through regression analysis and other methods. Although the calculation efficiency is high, due to the lack of complete data support, the prediction ability and universality of the model are greatly limited. Especially when facing new magnetic materials, existing methods often find it difficult to fully capture the complex changes in magnetic domain structure, and the prediction results are less accurate.

[0004] The problem of accuracy in predicting the magnetic domain structure of magnetic materials often stems from the incomplete data statistics of magnetic materials. Most of the existing experimental data focus on the magnetic measurements of common materials, and lack high-quality experimental data for new materials and complex material systems. In addition, although existing computational simulations can provide theoretical predictions, they often ignore the noise, errors and uncertainties in the experimental data, making the model's generalization ability insufficient in complex situations. Therefore, although existing methods have achieved certain results in certain specific material systems, the lack of comprehensive and accurate experimental data and efficient statistical learning methods has led to low accuracy in predicting the magnetic domain structure of magnetic materials, especially when dealing with new and complex magnetic materials, which still faces great challenges. Summary of the invention

[0005] The present invention provides a method and platform for predicting the magnetic domain structure of a magnetic material, which are used to improve the accuracy of magnetic domain structure prediction.

[0006] A first aspect of the present invention provides a method for predicting the magnetic domain structure of a magnetic material, comprising:

[0007] The magnetic material parameter acquisition unit of the multi-modal hardware sensor device performs parameter processing on the crystal structure, chemical composition, and intrinsic properties of different usage scenarios to obtain the target magnetic material parameters;

[0008] The target magnetic material parameters are judged in different usage scenarios and the temperature stability of the magnetic material is statistically analyzed to generate phase change behavior parameters of the magnetic material, and the magnetic domain structure is judged and the temperature stability of the magnetic material is statistically analyzed to generate local magnetic parameters of the magnetic material;

[0009] Performing phase change behavior feature clustering on the phase change behavior parameters of the magnetic material to obtain phase change behavior category information, and performing local magnetic feature clustering on the local magnetic parameters of the magnetic material to obtain local magnetic category information;

[0010] Inputting the phase change behavior category information into a preset phase change behavior magnetic domain structure determination model set to perform magnetic domain structure determination to obtain a magnetic domain structure determination result;

[0011] Inputting the local magnetic category information into a preset magnetic material category analysis model set to perform magnetic material magnetic domain structure category analysis to obtain a magnetic material magnetic domain structure analysis result;

[0012] A magnetic material magnetic domain structure category prediction result is generated based on the magnetic domain structure determination result and the magnetic material magnetic domain structure analysis result.

[0013] Preferably, the magnetic material parameter acquisition unit of the multimodal hardware sensor device performs parameter processing on the crystal structure, chemical composition, and intrinsic properties of different usage scenarios to obtain the target magnetic material parameters, including:

[0014] The magnetic material parameter acquisition unit of the multi-modal hardware sensor device collects the crystal structure, chemical composition, and intrinsic properties of magnetic materials in different usage scenarios to obtain the original magnetic material parameters;

[0015] Based on the field test technology, a magnetic material field test is performed on the original magnetic material parameters to obtain the field test magnetic material parameters, and the field test magnetic material parameters are transmitted to a preset parameter processing server through a data sending component in a target magnetic material parameter acquisition unit of the multimodal hardware sensor device;

[0016] The parameter processing server performs data denoising and data feature extraction on the field test magnetic material parameters to obtain target magnetic material parameters.

[0017] Preferably, the step of judging the target magnetic material parameters in different usage scenarios and performing statistics on the temperature stability of the magnetic material to generate the phase change behavior parameters of the magnetic material, and judging the magnetic domain structure and performing statistics on the temperature stability of the magnetic material to generate the local magnetic parameters of the magnetic material includes:

[0018] The magnetization intensity phase change behavior of the target magnetic material parameters is judged to obtain the magnetization intensity phase change behavior of different use environments, and the magnetic material density data is used in the target magnetic material parameters to perform statistics on the regional magnetic material temperature stability and critical temperature calculation on the magnetization intensity phase change behavior of different use environments to obtain the magnetic material parameters with magnetization intensity calculation information;

[0019] Performing topological phase change behavior detection on the magnetic material parameters with magnetization intensity calculation information to obtain topological phase change behaviors in different usage environments, and using magnetic material specific heat capacity data in the magnetic material parameters with magnetization intensity calculation information to perform statistics on regional magnetic material temperature stability and critical temperature calculation on the topological phase change behaviors in different usage environments to generate magnetic material phase change behavior parameters;

[0020] The magnetic domain structure of the target magnetic material parameters is judged to obtain the magnetic domain structures of different usage environments, and the magnetic material data is used in the target magnetic material parameters to perform statistics on the temperature stability of the regional magnetic materials and calculate the grain boundary effect information of the magnetic domain structures of different usage environments to generate local magnetic parameters of the magnetic materials.

[0021] Preferably, clustering the phase change behavior characteristics of the first magnetic material number to obtain phase change behavior category information, and clustering the local magnetic characteristics of the local magnetic parameters of the magnetic material to obtain body category information, includes:

[0022] Performing phase change behavior magnetic anisotropy clustering on the phase change behavior parameters of the magnetic material to obtain phase change behavior magnetic anisotropy data, performing Curie temperature clustering on the phase change behavior parameters of the magnetic material to obtain Curie temperature data, and performing phase change behavior Neel temperature clustering on the phase change behavior parameters of the magnetic material;

[0023] The phase transition behavior magnetic anisotropy data, the Curie temperature data and the phase transition behavior Neel temperature data are used as phase transition behavior category information;

[0024] Performing Nye temperature classification on magnetic domain structures in different use environments in the local magnetic parameters of the magnetic material to obtain antiferromagnetic local magnetic categories of different magnetic materials with the same external magnetic field and superparamagnetic local magnetic categories within the same magnetic material;

[0025] The local magnetic category information is generated according to the antiferromagnetic local magnetic category of the different magnetic materials under the same external magnetic field and the superparamagnetic local magnetic category within the same magnetic material.

[0026] Preferably, the step of inputting the phase change behavior category information into a preset phase change behavior magnetic domain structure determination model set to perform magnetic domain structure determination to obtain a magnetic domain structure determination result includes:

[0027] Inputting the phase change behavior category information into a preset phase change behavior magnetic domain structure determination model set, wherein the phase change behavior magnetic domain structure determination model set includes different models, namely, a magnetic domain structure classification model, a magnetic domain structure determination model for different use environments, and an edge computing gateway;

[0028] Classifying the magnetic domain structure type of the phase change behavior category information through a classification model to obtain classification information of different magnetic domain structure types;

[0029] According to the classification information of different magnetic domain structure types, the phase change behavior category information is input into a magnetic domain structure determination model to perform magnetic domain structure determination, and obtain a corresponding magnetic domain structure determination probability, wherein the magnetic domain structure determination model includes: a magnetic domain structure magnetic susceptibility determination model, a magnetic domain structure magnetic energy determination model, a magnetic domain structure magnetic moment determination model and a fluctuation range determination model;

[0030] Through the edge computing gateway, the magnetic domain structure determination probability is determined and the magnetic domain structure determination result is output.

[0031] Preferably, the inputting the local magnetic category information into a preset magnetic material category analysis model set to perform magnetic material magnetic domain structure category analysis to obtain a magnetic material magnetic domain structure analysis result includes:

[0032] Inputting the local magnetic category information into a preset magnetic material category analysis model set, wherein the magnetic material category analysis model set includes a magnetic domain structure spin arrangement detection model and an electronic structure analysis model;

[0033] Using the magnetic domain structure spin alignment detection model, the local magnetic category information is subjected to magnetic domain structure classification and clustering to obtain a magnetic domain structure spin alignment detection result;

[0034] Performing electronic structure analysis on the local magnetic category information by using the electronic structure analysis model to obtain an electronic structure analysis result;

[0035] The magnetic domain structure analysis result of the magnetic material is outputted according to the magnetic domain structure spin arrangement detection result and the electronic structure analysis result.

[0036] Preferably, generating a magnetic material magnetic domain structure category prediction result according to the magnetic domain structure determination result and the magnetic material magnetic domain structure analysis result comprises:

[0037] Performing result division on the magnetic domain structure determination result to obtain initial division data, and performing result division on the magnetic material magnetic domain structure analysis result to obtain secondary division data;

[0038] Acquire a preset local abnormal magnetic material category local non-magnetic region, and match the local abnormal magnetic material magnetic domain structure category prediction result from the local abnormal magnetic material category local non-magnetic region according to the initial division data;

[0039] Acquire a preset local non-magnetic region of a high-dimensional magnetic material category, and match a prediction result of a high-dimensional magnetic material magnetic domain structure category from the local non-magnetic region of the high-dimensional magnetic material category according to the re-divided data;

[0040] According to the prediction results of the magnetic domain structure category of the local anomalous magnetic material and the prediction results of the magnetic domain structure category of the high-dimensional magnetic material, a prediction result of the magnetic domain structure category of the magnetic material is generated, and the prediction result of the magnetic domain structure category of the magnetic material is sent to a parameter processing server for processing.

[0041] The second aspect of the present invention provides a prediction platform for the magnetic domain structure of a magnetic material, comprising:

[0042] A target magnetic material parameter acquisition unit is used to perform parameter processing on the crystal structure, chemical composition, and intrinsic properties of different usage scenarios through the magnetic material parameter acquisition unit of the multimodal hardware sensor device to acquire the target magnetic material parameters;

[0043] A magnetic material local magnetic parameter generating unit is used to judge the target magnetic material parameters in different usage scenarios and to collect statistics on the temperature stability of the magnetic material, to generate magnetic material phase change behavior parameters, and to judge the magnetic domain structure and to collect statistics on the temperature stability of the magnetic material, to generate magnetic material local magnetic parameters;

[0044] A phase change behavior characteristic clustering unit is used to perform phase change behavior characteristic clustering on the phase change behavior parameters of the magnetic material to obtain phase change behavior category information, and to perform local magnetic characteristic clustering on the local magnetic parameters of the magnetic material to obtain local magnetic category information;

[0045] A magnetic domain structure determination unit, used for inputting the phase change behavior category information into a preset phase change behavior magnetic domain structure determination model set to perform magnetic domain structure determination and obtain a magnetic domain structure determination result;

[0046] A magnetic material magnetic domain structure analysis unit, used for inputting the local magnetic category information into a preset magnetic material category analysis model set to perform magnetic material magnetic domain structure category analysis to obtain a magnetic material magnetic domain structure analysis result;

[0047] The magnetic material magnetic domain structure category prediction unit is used to generate a magnetic material magnetic domain structure category prediction result according to the magnetic domain structure determination result and the magnetic material magnetic domain structure analysis result.

[0048] Beneficial effects:

[0049] The present invention proposes a method and platform for predicting the magnetic domain structure of a magnetic material. Based on a target magnetic material parameter acquisition unit of a multimodal hardware sensor device, parameter processing is performed on the crystal structure, chemical composition, and intrinsic properties of different usage scenarios to obtain target magnetic material parameters; judgment is performed based on the target magnetic material parameters and statistics are performed on the temperature stability of the magnetic material to generate phase change behavior parameters of the magnetic material and local magnetic parameters of the magnetic material; phase change behavior characteristics of the phase change behavior parameters of the magnetic material are clustered to obtain phase change behavior category information, and local magnetic characteristics of the local magnetic parameters of the magnetic material are clustered to obtain local magnetic category information; the phase change behavior category information is input into a phase change behavior magnetic domain structure judgment model set to perform magnetic domain structure judgment to obtain a magnetic domain structure judgment result; the local magnetic category information is input into a magnetic material category analysis model set to perform magnetic domain structure category analysis of the magnetic material to obtain a magnetic domain structure analysis result of the magnetic material; a magnetic domain structure category prediction result of the magnetic material is generated based on the magnetic domain structure judgment result and the magnetic domain structure analysis result of the magnetic material. The present invention judges and predicts the magnetic domain structure of the magnetic material through real-time parameter processing and prediction, and can improve the accuracy of magnetic domain structure prediction through the combination of high-throughput calculation and large-scale experimental data. The platform integrates rich experimental data and systematically analyzes the magnetic behavior of materials to provide accurate predictions for different magnetic materials. By continuously updating and optimizing the data set, the platform can more comprehensively capture the changes in the magnetic domain structure of magnetic materials under various conditions. Due to the improvement of data statistics, this method can effectively overcome the problems of data scarcity and inaccuracy in traditional prediction methods, and can provide more accurate prediction results when faced with new materials. In addition, through data-driven model optimization, the platform can quickly adapt to the magnetic characteristics of new materials, significantly improve the accuracy and reliability of predictions, and promote the rapid screening and design of magnetic materials. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 A flow chart of a method for predicting the magnetic domain structure of a magnetic material according to the present invention;

[0051] Figure 2 This is a composition diagram of a prediction platform for the magnetic domain structure of a magnetic material of the present invention. DETAILED DESCRIPTION

[0052] It should be noted that, in the absence of conflict, the embodiments in this application and the categories in the embodiments can be combined with each other. The present application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0053] For ease of understanding, the specific process of the embodiment of the present invention is described below. Figure 1 , an embodiment of a method for predicting a magnetic domain structure of a magnetic material in an embodiment of the present invention includes:

[0054] S101, performing parameter processing on the crystal structure, chemical composition, and intrinsic properties of different usage scenarios through a magnetic material parameter acquisition unit of a multimodal hardware sensing device to obtain target magnetic material parameters;

[0055] It is understandable that the execution subject of the present invention may be a prediction platform for the magnetic domain structure of a magnetic material, or a terminal or a server, which is not limited here. The embodiment of the present invention is described by taking a server as the execution subject as an example.

[0056] Specifically, the server uses a camera or other sensors to collect magnetic materials for crystal structures, chemical compositions, and intrinsic properties of different usage scenarios through a multimodal hardware sensor device target magnetic material parameter acquisition unit, and obtains the original magnetic material parameters. In order to reduce the overhead of data transmission and improve transmission efficiency, the magnetic material field test technology is used to perform field test processing on the original magnetic material parameters. The field test magnetic material parameters occupy less storage space and can be transmitted to the parameter processing server more quickly. Through the data sending component in the preset multimodal hardware sensor device target magnetic material parameter acquisition unit, the magnetic material parameters after the field test are transmitted to the preset parameter processing server. This data sending component can be a wired or wireless network, such as a local area network, a wireless sensor network, etc. The establishment of the data sending component needs to ensure the reliable transmission and confidentiality of the magnetic material parameters. On the parameter processing server, the received field test magnetic material parameters are processed for data denoising and data feature extraction. After data denoising and data feature extraction, the target magnetic material data is obtained. These target magnetic material parameters can provide clearer and more accurate crystal structures, chemical compositions, and intrinsic properties for different usage scenarios, and provide better input for subsequent phase change behavior judgments, statistical analysis of magnetic material temperature stability, and other steps. For example, after field tests, the collected original magnetic material parameters are transmitted to a preset parameter processing server via a wireless network. On the parameter processing server, data denoising and data feature extraction are performed on the received field test magnetic material parameters. The processed target magnetic material parameters can be used for further phase change behavior judgments, statistical analysis of magnetic material temperature stability, and other analyses, to achieve parameter processing and prediction for different usage scenarios.

[0057] S102, judging different usage scenarios of target magnetic material parameters and performing statistics on the temperature stability of magnetic materials to generate phase change behavior parameters of magnetic materials, and judging magnetic domain structure of target magnetic material parameters and performing statistics on the temperature stability of magnetic materials to generate local magnetic parameters of magnetic materials;

[0058] Specifically, the server judges the magnetization phase change behavior for the target magnetic material parameters. Using magnetic material processing and machine learning algorithms, the server trains a magnetization phase change behavior judgment model. The model can judge the magnetization phase change behavior in magnetic materials and cluster their categories. By processing the target magnetic material parameters, the server detects the magnetization phase change behavior in different usage environments. The server calculates these phase change behaviors using magnetic material density data and performs statistics on the temperature stability of regional magnetic materials. Secondly, the topological phase change behavior detection is performed for the magnetic material parameters with magnetization calculation information. Through the topological phase change behavior detection algorithm, the server further screens out the topological phase change behavior in the magnetic material. These phase change behaviors are calculated using the magnetic material specific heat capacity data, and the regional magnetic material temperature stability is statistically analyzed to cluster the phase change behavior areas. Through the topological phase change behavior detection, the specific heat capacity data of magnetic materials are used to calculate them and the temperature stability is statistically analyzed. The server clusters the critical temperature data of these phase change behaviors. Through the magnetic domain structure judgment, the magnetic material data are used to calculate them and the temperature stability is statistically analyzed to cluster their grain boundary effect information.

[0059] S103, performing phase change behavior feature clustering on the phase change behavior parameters of the magnetic material to obtain phase change behavior category information, and performing local magnetic feature clustering on the local magnetic parameters of the magnetic material to obtain local magnetic category information;

[0060] It should be noted that the phase change behavior characteristics are clustered for the phase change behavior parameters of the magnetic materials. The server uses computer vision and magnetic material processing technology to cluster the category information of the phase change behavior. By processing the phase change behavior parameters of the magnetic materials, such as target detection and tracking, the server determines the magnetic anisotropy of the phase change behavior in the magnetic material and clusters the grain boundary effect information. The server obtains the magnetic anisotropy data of the phase change behavior and the Née temperature data of the phase change behavior. In addition, the server can also use technologies such as optical flow estimation to calculate the moving distance of the phase change behavior in the magnetic material to obtain the Curie temperature data. These data can be used as phase change behavior category information for subsequent flow calculations, phase change behavior analysis and other applications. Secondly, local magnetic feature clustering is performed for the local magnetic parameters of the magnetic material. The server uses magnetic material processing and machine learning algorithms to perform Née temperature classification and feature clustering on the magnetic domain structures in different usage environments. Through target detection and statistical technology of magnetic material temperature stability, the server counts the temperature stability of magnetic domain structures in different use environments in magnetic materials and classifies them by Nye temperature. In this embodiment, the server realizes the phase change behavior characteristic clustering of magnetic material phase change behavior parameters, including phase change behavior magnetic anisotropy, Curie temperature and phase change behavior grain boundary effect information. Local magnetic characteristic clustering is performed on local magnetic parameters of magnetic materials.

[0061] S104, inputting the phase change behavior category information into a preset phase change behavior magnetic domain structure determination model set to perform magnetic domain structure determination to obtain a magnetic domain structure determination result;

[0062] Specifically, the server inputs the phase change behavior category information into a preset phase change behavior magnetic domain structure determination model set. The model set includes different models: a magnetic domain structure classification model, a magnetic domain structure determination model, and an edge computing gateway. The magnetic domain structure classification model is used to classify the phase change behavior category information into magnetic domain structure types. The model can divide the phase change behavior category information into different magnetic domain structure types, such as illegal driving, magnetic domain structure source, magnetic domain structure magnetic moment, and fluctuation range. Through the classification model, the server obtains different types of magnetic domain structure type classification information. According to the obtained magnetic domain structure type classification information, the phase change behavior category information is input into the magnetic domain structure determination model. These magnetic domain structure determination models include a magnetic domain structure magnetic susceptibility determination model, a magnetic domain structure magnetic energy determination model, a magnetic domain structure magnetic moment determination model, and a fluctuation range determination model. Each magnetic domain structure determination model determines a specific magnetic domain structure type and outputs a corresponding magnetic domain structure determination probability. In the edge computing gateway, the obtained magnetic domain structure determination probability is processed to obtain a final constant determination result. According to the size of the magnetic domain structure determination probability, the possibility of the occurrence of the magnetic domain structure can be determined. In this embodiment, the server inputs the phase change behavior category information into the preset phase change behavior magnetic domain structure determination model set, and obtains the magnetic domain structure determination result after magnetic domain structure classification, magnetic domain structure determination and result output. This process can help the server quickly and accurately determine whether the phase change behavior has a magnetic domain structure, providing an important reference for management and security.

[0063] S105, inputting the local magnetic category information into a preset magnetic material category analysis model set to perform magnetic material magnetic domain structure category analysis to obtain a magnetic material magnetic domain structure analysis result;

[0064] Specifically, the server obtains a preset magnetic material category analysis model set, which includes a magnetic domain structure spin arrangement detection model and an electronic structure analysis model. The local magnetic category information to be analyzed is input into the model set. The local magnetic category information may include the spin arrangement type, size, and Neel temperature detected in the magnetic material. In the first part of the model set, the magnetic domain structure spin arrangement detection model is used to classify and cluster the local magnetic category information into magnetic domain structures. The model is obtained through training and learning, and can determine the spin arrangement of the magnetic domain structure in the magnetic material. Performing magnetic material magnetic domain structure category analysis through a preset magnetic material category analysis model set can help the server better understand and evaluate the condition of the surrounding rock, and take corresponding measures to deal with it in a timely manner.

[0065] S106, generating a magnetic material magnetic domain structure category prediction result according to the magnetic domain structure determination result and the magnetic material magnetic domain structure analysis result.

[0066] Specifically, the magnetic domain structure determination results are divided, and different magnetic domain structure types are divided by numbers or symbols. In this embodiment, based on the magnetic domain structure determination results and the magnetic material magnetic domain structure analysis results, the server can formulate magnetic material magnetic domain structure category prediction results for specific problems, thereby effectively solving the magnetic domain structure situation on the surrounding rock.

[0067] In an embodiment of the present invention, a target magnetic material parameter acquisition unit based on a multimodal hardware sensing device performs parameter processing on the crystal structure, chemical composition, and intrinsic properties of different usage scenarios to obtain target magnetic material parameters; a judgment is made based on the target magnetic material parameters and statistics are performed on the temperature stability of the magnetic material to generate phase change behavior parameters of the magnetic material and local magnetic parameters of the magnetic material; phase change behavior characteristics of the phase change behavior parameters of the magnetic material are clustered to obtain phase change behavior category information, and local magnetic characteristics of the local magnetic parameters of the magnetic material are clustered to obtain local magnetic category information; the phase change behavior category information is input into a phase change behavior magnetic domain structure determination model set to perform magnetic domain structure determination to obtain a magnetic domain structure determination result; the local magnetic category information is input into a magnetic material category analysis model set to perform magnetic domain structure category analysis of the magnetic material to obtain a magnetic domain structure analysis result of the magnetic material; and a magnetic material magnetic domain structure category prediction result is generated based on the magnetic domain structure determination result and the magnetic material magnetic domain structure analysis result.

[0068] In a specific embodiment, the process of executing step S101 may specifically include the following steps:

[0069] The magnetic material parameter acquisition unit of the multi-modal hardware sensor device collects the crystal structure, chemical composition, and intrinsic properties of magnetic materials in different usage scenarios to obtain the original magnetic material parameters;

[0070] Based on the field test technology, the original magnetic material parameters are subjected to a field test to obtain the field test magnetic material parameters, and the field test magnetic material parameters are transmitted to a preset parameter processing server through a data sending component in a target magnetic material parameter acquisition unit of a multi-modal hardware sensor device;

[0071] Through the parameter processing server, data denoising and data feature extraction are performed on the magnetic material parameters of the field test to obtain the target magnetic material parameters.

[0072] In a specific embodiment, the process of executing step S102 may specifically include the following steps:

[0073] The magnetization intensity phase change behavior of the target magnetic material parameters is judged to obtain the magnetization intensity phase change behavior of different use environments, and the magnetic material density data is used in the target magnetic material parameters to perform statistics on the temperature stability of the regional magnetic materials and calculate the critical temperature of the magnetization intensity phase change behavior of different use environments, and obtain the magnetic material parameters with magnetization intensity calculation information;

[0074] The topological phase transition behavior of magnetic material parameters with magnetization intensity calculation information is detected to obtain topological phase transition behaviors in different use environments. The specific heat capacity data of magnetic materials are used in the magnetic material parameters with magnetization intensity calculation information to perform statistics on the temperature stability of regional magnetic materials and calculate the critical temperature of topological phase transition behaviors in different use environments, and generate magnetic material phase transition behavior parameters;

[0075] The magnetic domain structure of the target magnetic material parameters is judged to obtain the magnetic domain structures in different usage environments. The magnetic material data is used in the target magnetic material parameters to perform statistics on the temperature stability of the regional magnetic materials and calculate the grain boundary effect information for the magnetic domain structures in different usage environments to generate the local magnetic parameters of the magnetic materials.

[0076] The server uses computer vision technology and deep learning models to judge the magnetization phase change behavior in the target magnetic material parameters. By training a magnetization phase change behavior judgment model, the server uses this model to automatically judge and locate the target magnetic material parameters and find out the magnetization phase change behavior. Once the magnetization phase change behavior is judged, the server uses similar methods to detect the topological phase change behavior in the magnetic material parameters with magnetization calculation information.

[0077] In a specific embodiment, the process of executing step S103 may specifically include the following steps:

[0078] Performing phase change behavior magnetic anisotropy clustering on the phase change behavior parameters of the magnetic material to obtain phase change behavior magnetic anisotropy data, and performing Curie temperature clustering on the phase change behavior parameters of the magnetic material to obtain Curie temperature data, and performing phase change behavior Nye temperature clustering on the phase change behavior parameters of the magnetic material to obtain phase change behavior Nye temperature data;

[0079] The phase transition behavior magnetic anisotropy data, Curie temperature data and Nel temperature data of the phase transition behavior are used as the phase transition behavior category information;

[0080] The magnetic domain structures in different use environments in the local magnetic parameters of magnetic materials are classified by Nye temperature, and the antiferromagnetic local magnetic categories of different magnetic materials with the same external magnetic field and the superparamagnetic local magnetic categories within the same magnetic material are obtained;

[0081] Characteristic information is generated based on the antiferromagnetic local magnetic types of different magnetic materials under the same external magnetic field and the superparamagnetic local magnetic types within the same magnetic material.

[0082] Specifically, the server can use a series of magnetic material processing and computer vision algorithms to achieve phase change behavior magnetic anisotropy clustering, Curie temperature clustering and phase change behavior Nye temperature clustering of magnetic material phase change behavior parameters. For phase change behavior magnetic anisotropy clustering of magnetic material phase change behavior parameters, a target detection algorithm, such as a target detection model based on deep learning, can be used. This model can accurately detect phase change behavior in magnetic materials and provide information on its grain boundary effects. The server obtains the following data: phase change behavior magnetic anisotropy data, Curie temperature data, phase change behavior Nye temperature data, antiferromagnetic local magnetic categories of different magnetic materials with the same external magnetic field, and superparamagnetic local magnetic categories within the same magnetic material. These data will serve as phase change behavior category information and local magnetic category information, and play an important role in subsequent magnetic domain structure determination and magnetic material category analysis. By processing and analyzing magnetic material parameters, the server clusters key information and provides valuable reference for management and decision-making.

[0083] In a specific embodiment, the process of executing step S104 may specifically include the following steps:

[0084] Inputting the phase change behavior category information into a preset phase change behavior magnetic domain structure determination model set, wherein the phase change behavior magnetic domain structure determination model set includes different models, namely, a magnetic domain structure classification model, a magnetic domain structure determination model for different use environments, and an edge computing gateway;

[0085] The magnetic domain structure type is classified by the classification model based on the phase change behavior category information to obtain the classification information of different magnetic domain structure types;

[0086] According to the classification information of different magnetic domain structure types, the phase change behavior category information is input into the magnetic domain structure determination model to perform magnetic domain structure determination, and the corresponding magnetic domain structure determination probability is obtained, wherein the magnetic domain structure determination model includes: a magnetic domain structure magnetic susceptibility determination model, a magnetic domain structure magnetic energy determination model, a magnetic domain structure magnetic moment determination model and a fluctuation range determination model;

[0087] Through the edge computing gateway, the magnetic domain structure determination probability is output to obtain the magnetic domain structure determination result.

[0088] Specifically, in order to input the phase change behavior category information into the preset phase change behavior magnetic domain structure determination model set and obtain the magnetic domain structure determination result, the server can adopt a multi-layer model structure. The phase change behavior magnetic domain structure determination model set consists of different models: magnetic domain structure classification model, magnetic domain structure determination model and edge computing gateway. In the magnetic domain structure classification model, the server uses machine learning or deep learning algorithms to classify the magnetic domain structure type of the phase change behavior category information. This model learns different types of magnetic domain structure patterns based on training data, such as magnetic domain structure level, magnetic domain structure source, magnetic domain structure magnetic moment and fluctuation range. Through this model, the server divides the phase change behavior category information into different magnetic domain structure types. According to different types of magnetic domain structure type classification information, the server inputs the phase change behavior category information into the corresponding magnetic domain structure determination model. These magnetic domain structure determination models are specifically used for specific types of magnetic domain structure determination, such as magnetic domain structure magnetic susceptibility determination model, magnetic domain structure magnetic energy determination model, magnetic domain structure magnetic moment determination model and fluctuation range determination model. Each model will further analyze and process the input phase change behavior category information to determine whether there is a corresponding magnetic domain structure. At the edge computing gateway, the server processes the magnetic domain structure determination probability based on the output of the magnetic domain structure determination model and generates the final magnetic domain structure determination result. This process can include mapping the magnetic domain structure determination probability to a specific magnetic domain structure category, setting a threshold to determine the boundary between the magnetic domain structure and the normal, and generating the corresponding determination result based on demand.

[0089] In a specific embodiment, the process of executing step S105 may specifically include the following steps:

[0090] Inputting the local magnetic category information into a preset magnetic material category analysis model set, wherein the magnetic material category analysis model set includes a magnetic domain structure spin arrangement detection model and an electronic structure analysis model;

[0091] Through the magnetic domain structure spin alignment detection model, the local magnetic category information is classified and clustered into magnetic domain structures to obtain the magnetic domain structure spin alignment detection results;

[0092] Through the electronic structure analysis model, the electronic structure analysis is performed on the local magnetic category information to obtain the electronic structure analysis result;

[0093] The magnetic domain structure analysis results of the magnetic material are output based on the magnetic domain structure spin arrangement detection results and the electronic structure analysis results.

[0094] Specifically, in order to input the local magnetic category information into the preset magnetic material category analysis model set and obtain the magnetic material magnetic domain structure analysis results, the server adopts a multi-model structure. The magnetic material category analysis model set consists of two key models: the magnetic domain structure spin arrangement detection model and the electronic structure analysis model. These models are designed to comprehensively analyze the magnetic material category in order to provide the detection and analysis results of the magnetic domain structure of the magnetic material. Through the magnetic domain structure spin arrangement detection model, the server classifies and clusters the local magnetic category information into magnetic domain structures. The model uses machine learning or deep learning algorithms to learn different types of magnetic domain structure spin arrangement patterns through training data.

[0095] In a specific embodiment, the process of executing step S106 may specifically include the following steps:

[0096] The results of the magnetic domain structure determination are divided to obtain initial division data, and the results of the magnetic domain structure analysis of the magnetic material are divided to obtain re-divided data;

[0097] Obtaining a preset local anomalous magnetic material category local non-magnetic region, and matching the local anomalous magnetic material magnetic domain structure category prediction result from the local anomalous magnetic material category local non-magnetic region according to the initial division data;

[0098] Obtaining a preset local non-magnetic region of a high-dimensional magnetic material category, and matching a prediction result of a magnetic domain structure category of a high-dimensional magnetic material from the local non-magnetic region of the high-dimensional magnetic material category according to the re-divided data;

[0099] According to the prediction results of the magnetic domain structure category of the local anomalous magnetic material and the prediction results of the magnetic domain structure category of the high-dimensional magnetic material, the prediction results of the magnetic domain structure category of the magnetic material are generated, and the prediction results of the magnetic domain structure category of the magnetic material are sent to the parameter processing server for processing.

[0100] Specifically, the server divides the results of the magnetic domain structure determination and the magnetic material magnetic domain structure analysis, and converts these results into computer-processable data through a suitable division method.

[0101] The above describes a method for predicting the magnetic domain structure of a magnetic material in an embodiment of the present invention. The following describes a prediction platform for the magnetic domain structure of a magnetic material in an embodiment of the present invention. Figure 2 , an embodiment of a prediction platform for magnetic domain structure of a magnetic material in an embodiment of the present invention includes:

[0102] A target magnetic material parameter acquisition unit is used to perform parameter processing on the crystal structure, chemical composition, and intrinsic properties of different usage scenarios through the magnetic material parameter acquisition unit of the multi-modal hardware sensor device to obtain the target magnetic material parameters;

[0103] A magnetic material local magnetic parameter generating unit is used to judge the target magnetic material parameters in different usage scenarios and to collect statistics on the temperature stability of the magnetic material, to generate the phase change behavior parameters of the magnetic material, and to judge the magnetic domain structure of the target magnetic material parameters and to collect statistics on the temperature stability of the magnetic material, to generate the local magnetic parameters of the magnetic material;

[0104] A phase change behavior characteristic clustering unit is used to perform phase change behavior characteristic clustering on the phase change behavior parameters of the magnetic material to obtain phase change behavior category information, and to perform local magnetic characteristic clustering on the local magnetic parameters of the magnetic material to obtain local magnetic category information;

[0105] A magnetic domain structure determination unit, used for inputting the phase change behavior category information into a preset phase change behavior magnetic domain structure determination model set to perform magnetic domain structure determination and obtain a magnetic domain structure determination result;

[0106] A magnetic material magnetic domain structure analysis unit, used for inputting local magnetic category information into a preset magnetic material category analysis model set to perform magnetic material magnetic domain structure category analysis to obtain a magnetic material magnetic domain structure analysis result;

[0107] The magnetic material magnetic domain structure category prediction unit is used to generate a magnetic material magnetic domain structure category prediction result based on the magnetic domain structure determination result and the magnetic material magnetic domain structure analysis result.

[0108] Optionally, the target magnetic material parameter acquisition unit is specifically used for:

[0109] The magnetic material parameter acquisition unit of the multi-modal hardware sensor device collects the crystal structure, chemical composition, and intrinsic properties of magnetic materials in different usage scenarios to obtain the original magnetic material parameters;

[0110] Based on the field test technology, the original magnetic material parameters are subjected to a field test to obtain the field test magnetic material parameters, and the field test magnetic material parameters are transmitted to a preset parameter processing server through a data sending component in a target magnetic material parameter acquisition unit of a multi-modal hardware sensor device;

[0111] Through the parameter processing server, data denoising and data feature extraction are performed on the magnetic material parameters of the field test to obtain the target magnetic material parameters.

[0112] Optionally, the magnetic material local magnetic parameter generating unit is specifically used for:

[0113] The magnetization intensity phase change behavior of the target magnetic material parameters is judged to obtain the magnetization intensity phase change behavior of different use environments, and the magnetic material density data is used in the target magnetic material parameters to perform statistics on the temperature stability of the regional magnetic materials and calculate the critical temperature of the magnetization intensity phase change behavior of different use environments, and obtain the magnetic material parameters with magnetization intensity calculation information;

[0114] The topological phase transition behavior of magnetic material parameters with magnetization intensity calculation information is detected to obtain topological phase transition behaviors in different use environments. The specific heat capacity data of magnetic materials are used in the magnetic material parameters with magnetization intensity calculation information to perform statistics on the temperature stability of regional magnetic materials and calculate the critical temperature of topological phase transition behaviors in different use environments, and generate magnetic material phase transition behavior parameters;

[0115] The magnetic domain structure of the target magnetic material parameters is judged to obtain the magnetic domain structures in different usage environments. The magnetic material data is used in the target magnetic material parameters to perform statistics on the temperature stability of the regional magnetic materials and calculate the grain boundary effect information for the magnetic domain structures in different usage environments to generate the local magnetic parameters of the magnetic materials.

[0116] Optionally, the phase change behavior feature clustering unit is specifically used for:

[0117] Performing phase change behavior magnetic anisotropy clustering on the phase change behavior parameters of the magnetic material to obtain phase change behavior magnetic anisotropy data, and performing Curie temperature clustering on the phase change behavior parameters of the magnetic material to obtain Curie temperature data, and performing phase change behavior Nye temperature clustering on the phase change behavior parameters of the magnetic material to obtain phase change behavior Nye temperature data;

[0118] The phase transition behavior magnetic anisotropy data, Curie temperature data and Nel temperature data of the phase transition behavior are used as the phase transition behavior category information;

[0119] The magnetic domain structures in different use environments in the local magnetic parameters of magnetic materials are classified by Nye temperature, and the antiferromagnetic local magnetic categories of different magnetic materials with the same external magnetic field and the superparamagnetic local magnetic categories within the same magnetic material are obtained;

[0120] The local magnetic category information is generated according to the antiferromagnetic local magnetic categories of different magnetic materials with the same external magnetic field and the superparamagnetic local magnetic categories within the same magnetic material.

[0121] Optionally, the magnetic domain structure determination unit is specifically used for:

[0122] Inputting the phase change behavior category information into a preset phase change behavior magnetic domain structure determination model set, wherein the phase change behavior magnetic domain structure determination model set includes different models, magnetic domain structure classification models, magnetic domain structure determination models for different use environments, and an edge computing gateway;

[0123] The magnetic domain structure type is classified by the classification model based on the phase change behavior category information to obtain the classification information of different magnetic domain structure types;

[0124] According to the classification information of different magnetic domain structure types, the phase change behavior category information is input into the magnetic domain structure determination model to perform magnetic domain structure determination, and the corresponding magnetic domain structure determination probability is obtained, wherein the magnetic domain structure determination model includes: a magnetic domain structure magnetic susceptibility determination model, a magnetic domain structure magnetic energy determination model, a magnetic domain structure magnetic moment determination model and a fluctuation range determination model;

[0125] Through the edge computing gateway, the magnetic domain structure determination probability is output to obtain the magnetic domain structure determination result.

[0126] Optionally, the magnetic material magnetic domain structure analysis unit is specifically used for:

[0127] Inputting the local magnetic category information into a preset magnetic material category analysis model set, wherein the magnetic material category analysis model set includes a magnetic domain structure spin arrangement detection model and an electronic structure analysis model;

[0128] Through the magnetic domain structure spin alignment detection model, the local magnetic category information is classified and clustered into magnetic domain structures to obtain the magnetic domain structure spin alignment detection results;

[0129] Through the electronic structure analysis model, the electronic structure analysis is performed on the local magnetic category information to obtain the electronic structure analysis result;

[0130] The magnetic domain structure analysis results of the magnetic material are output based on the magnetic domain structure spin arrangement detection results and the electronic structure analysis results.

[0131] Optionally, the magnetic material magnetic domain structure category prediction unit is specifically used for:

[0132] The results of the magnetic domain structure determination are divided to obtain initial division data, and the results of the magnetic domain structure analysis of the magnetic material are divided to obtain re-divided data;

[0133] Obtaining a preset local anomalous magnetic material category local non-magnetic region, and matching the local anomalous magnetic material magnetic domain structure category prediction result from the local anomalous magnetic material category local non-magnetic region according to the initial division data;

[0134] Obtaining a preset local non-magnetic region of a high-dimensional magnetic material category, and matching a prediction result of a magnetic domain structure category of a high-dimensional magnetic material from the local non-magnetic region of the high-dimensional magnetic material category according to the re-divided data;

[0135] According to the prediction results of the magnetic domain structure category of the local anomalous magnetic material and the prediction results of the magnetic domain structure category of the high-dimensional magnetic material, the prediction results of the magnetic domain structure category of the magnetic material are generated, and the prediction results of the magnetic domain structure category of the magnetic material are sent to the parameter processing server for processing.

[0136] Through the coordinated cooperation of the above-mentioned components, the target magnetic material parameter acquisition unit of the multimodal hardware sensor device performs parameter processing on the crystal structure, chemical composition, and intrinsic properties of different usage scenarios to obtain the target magnetic material parameters; the target magnetic material parameters are judged and the temperature stability of the magnetic material is statistically analyzed to generate the phase change behavior parameters of the magnetic material and the local magnetic parameters of the magnetic material; the phase change behavior parameters of the magnetic material are clustered by phase change behavior characteristics to obtain phase change behavior category information, and the local magnetic parameters of the magnetic material are clustered by local magnetic characteristics to obtain local magnetic category information; the phase change behavior category information is input into the phase change behavior magnetic domain structure determination model set to perform magnetic domain structure determination to obtain the magnetic domain structure determination result; the local magnetic category information is input into the magnetic material category analysis model set to perform magnetic domain structure category analysis of the magnetic material to obtain the magnetic domain structure analysis result of the magnetic material; the magnetic material magnetic domain structure category prediction result is generated based on the magnetic domain structure determination result and the magnetic material magnetic domain structure analysis result. The present invention provides accurate data support to the parameter processing server through real-time parameter processing and prediction, thereby improving the timeliness and accuracy of magnetic domain structure prediction of the multimodal hardware sensor device.

[0137] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0138] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods of various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc., various media that can store program codes.

[0139] 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 the 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 method for predicting the magnetic domain structure of a magnetic material, characterized in that: The method includes: Through the magnetic material parameter acquisition unit of the multi-modal hardware sensor device, the crystal structure, chemical composition, and intrinsic properties of different usage scenarios are processed to obtain the target magnetic material parameters; The target magnetic material parameters are judged in different usage scenarios and the temperature stability of the magnetic material is statistically analyzed to generate phase change behavior parameters of the magnetic material, and the magnetic domain structure is judged and the temperature stability of the magnetic material is statistically analyzed to generate local magnetic parameters of the magnetic material; specifically, the following steps are performed: the phase change behavior of the target magnetic material parameters is judged to obtain the phase change behavior of different usage environments, and the magnetization intensity data of the magnetic material is used in the target magnetic material parameters to perform temperature dependence statistics and critical temperature calculation on the magnetization intensity phase change behavior of different usage environments to obtain magnetic material parameters with magnetization intensity calculation information; the magnetization intensity data with The magnetic material parameters with the strength calculation information are used to detect the topological phase change behavior, and the topological phase change behavior in different use environments is obtained. The specific heat capacity data of the magnetic material is used in the magnetic material parameters with the magnetization strength calculation information to perform statistics on the temperature dependence of the topological phase change behavior in different use environments and calculate the critical temperature, so as to generate the magnetic material phase change behavior parameters; the magnetic domain structure is judged on the target magnetic material parameters to obtain the magnetic domain structure in different use environments, and the magnetic material data is used in the target magnetic material parameters to perform statistics on the temperature dependence of the magnetic domain structure in different use environments and calculate the grain boundary effect information, so as to generate the local magnetic parameters of the magnetic material; Performing phase change behavior feature clustering on the phase change behavior parameters of the magnetic material to obtain phase change behavior category information, and performing local magnetic feature clustering on the local magnetic parameters of the magnetic material to obtain local magnetic category information; Inputting the phase change behavior category information into a preset phase change behavior magnetic domain structure determination model set to perform magnetic domain structure determination to obtain a magnetic domain structure determination result; Inputting the local magnetic category information into a preset magnetic material category analysis model set to perform magnetic material magnetic domain structure category analysis to obtain a magnetic material magnetic domain structure analysis result; A magnetic material magnetic domain structure category prediction result is generated based on the magnetic domain structure determination result and the magnetic material magnetic domain structure analysis result.

2. The method for predicting the magnetic domain structure of a magnetic material according to claim 1, characterized in that: The magnetic material parameter acquisition unit of the multi-modal hardware sensor device performs parameter processing on the crystal structure, chemical composition, and intrinsic properties of different usage scenarios to obtain target magnetic material parameters, including: The magnetic material parameter acquisition unit of the multi-modal hardware sensor device collects the crystal structure, chemical composition, and intrinsic properties of magnetic materials in different usage scenarios to obtain the original magnetic material parameters; Based on the field test technology, a magnetic material field test is performed on the original magnetic material parameters to obtain the field test magnetic material parameters, and the field test magnetic material parameters are transmitted to a preset parameter processing server through a data sending component in a target magnetic material parameter acquisition unit of the multimodal hardware sensor device; The parameter processing server performs data denoising and data feature extraction on the field test magnetic material parameters to obtain target magnetic material parameters.

3. The method for predicting the magnetic domain structure of a magnetic material according to claim 1, characterized in that: The step of clustering the phase change behavior characteristics of the phase change behavior parameters of the magnetic material to obtain the phase change behavior category information, and clustering the local magnetic characteristics of the local magnetic parameters of the magnetic material to obtain the local magnetic category information, includes: Performing phase change behavior magnetic anisotropy clustering on the phase change behavior parameters of the magnetic material to obtain phase change behavior magnetic anisotropy data, and performing Curie temperature clustering on the phase change behavior parameters of the magnetic material to obtain Curie temperature data, and performing phase change behavior Neel temperature clustering on the phase change behavior parameters of the magnetic material to obtain phase change behavior Neel temperature data; The phase transition behavior magnetic anisotropy data, the Curie temperature data and the phase transition behavior Neel temperature data are used as phase transition behavior category information; Performing Nye temperature classification on magnetic domain structures in different use environments in the local magnetic parameters of the magnetic material to obtain antiferromagnetic local magnetic categories of different magnetic materials with the same external magnetic field and superparamagnetic local magnetic categories within the same magnetic material; The local magnetic category information is generated according to the antiferromagnetic local magnetic category of the different magnetic materials under the same external magnetic field and the superparamagnetic local magnetic category within the same magnetic material.

4. The method for predicting the magnetic domain structure of a magnetic material according to claim 1, characterized in that: The step of inputting the phase change behavior category information into a preset phase change behavior magnetic domain structure determination model set to perform magnetic domain structure determination to obtain a magnetic domain structure determination result includes: Inputting the phase change behavior category information into a preset phase change behavior magnetic domain structure determination model set, wherein the phase change behavior magnetic domain structure determination model set includes different models, namely, a magnetic domain structure classification model and a magnetic domain structure determination model for different use environments; Classifying the magnetic domain structure type of the phase change behavior category information through a classification model to obtain classification information of different magnetic domain structure types; According to the classification information of different magnetic domain structure types, the phase change behavior category information is input into a magnetic domain structure determination model to perform magnetic domain structure determination, and obtain a corresponding magnetic domain structure determination probability, wherein the magnetic domain structure determination model includes: a magnetic domain structure magnetic susceptibility determination model, a magnetic domain structure magnetic energy determination model, a magnetic domain structure magnetic moment determination model and a fluctuation range determination model; Through the edge computing gateway, the magnetic domain structure determination probability is determined and the magnetic domain structure determination result is output.

5. The method for predicting the magnetic domain structure of a magnetic material according to claim 1, characterized in that: The inputting the local magnetic category information into a preset magnetic material category analysis model set to perform magnetic material magnetic domain structure category analysis to obtain a magnetic material magnetic domain structure analysis result includes: Inputting the local magnetic category information into a preset magnetic material category analysis model set, wherein the magnetic material category analysis model set includes a magnetic domain structure spin arrangement detection model and an electronic structure analysis model; Using the magnetic domain structure spin alignment detection model, the local magnetic category information is subjected to magnetic domain structure classification and clustering to obtain a magnetic domain structure spin alignment detection result; Performing electronic structure analysis on the local magnetic category information by using the electronic structure analysis model to obtain an electronic structure analysis result; The magnetic domain structure analysis result of the magnetic material is outputted according to the magnetic domain structure spin arrangement detection result and the electronic structure analysis result.

6. The method for predicting the magnetic domain structure of a magnetic material according to claim 1, characterized in that: The generating a magnetic material magnetic domain structure category prediction result according to the magnetic domain structure determination result and the magnetic material magnetic domain structure analysis result comprises: Performing result division on the magnetic domain structure determination result to obtain initial division data, and performing result division on the magnetic material magnetic domain structure analysis result to obtain secondary division data; Acquire a preset local abnormal magnetic material category local non-magnetic region, and match the local abnormal magnetic material magnetic domain structure category prediction result from the local abnormal magnetic material category local non-magnetic region according to the initial division data; Acquire a preset local non-magnetic region of a high-dimensional magnetic material category, and match a prediction result of a high-dimensional magnetic material magnetic domain structure category from the local non-magnetic region of the high-dimensional magnetic material category according to the re-divided data; According to the prediction results of the magnetic domain structure category of the local anomalous magnetic material and the prediction results of the magnetic domain structure category of the high-dimensional magnetic material, a prediction result of the magnetic domain structure category of the magnetic material is generated, and the prediction result of the magnetic domain structure category of the magnetic material is sent to a parameter processing server for processing.

7. A prediction platform for magnetic domain structure of magnetic materials, characterized in that: The platform includes: A target magnetic material parameter acquisition unit is used to perform parameter processing on the crystal structure, chemical composition, and intrinsic properties of different usage scenarios through the magnetic material parameter acquisition unit of the multi-modal hardware sensor device to obtain the target magnetic material parameters; A magnetic material local magnetic parameter generating unit is used to judge the target magnetic material parameters in different usage scenarios and to collect statistics on the temperature stability of the magnetic material, to generate magnetic material phase change behavior parameters, and to judge the magnetic domain structure and to collect statistics on the temperature stability of the magnetic material, to generate magnetic material local magnetic parameters; A phase change behavior characteristic clustering unit is used to perform phase change behavior characteristic clustering on the phase change behavior parameters of the magnetic material to obtain phase change behavior category information, and to perform local magnetic characteristic clustering on the local magnetic parameters of the magnetic material to obtain local magnetic category information; A magnetic domain structure determination unit, used for inputting the phase change behavior category information into a preset phase change behavior magnetic domain structure determination model set to perform magnetic domain structure determination and obtain a magnetic domain structure determination result; A magnetic material magnetic domain structure analysis unit, used for inputting the local magnetic category information into a preset magnetic material category analysis model set to perform magnetic material magnetic domain structure category analysis to obtain a magnetic material magnetic domain structure analysis result; The magnetic material magnetic domain structure category prediction unit is used to generate a magnetic material magnetic domain structure category prediction result according to the magnetic domain structure determination result and the magnetic material magnetic domain structure analysis result.

Images