PU-GAN-based GIS electromagnetic field simulation data enhancement method and system

Abstract

The invention discloses a PU-GAN-based GIS electromagnetic field simulation data enhancement method and system. The method comprises the steps of obtaining real coarse grid data and real fine grid data of a GIS electromagnetic field; inputting the real coarse grid data and the real fine grid data into a generative adversarial network for training until an overall optimization loss function is minimum, and obtaining a trained generator as a data enhancement model for enhancing the real coarse grid data generated in real time; wherein the generative adversarial network comprises a generator and a discriminator, and the generator is used for performing feature extraction on the real coarse grid data and performing cyclic multiple enhancement on the extracted features to obtain fine grid generation data; according to the method, high-precision GIS electromagnetic field simulation enhancement data can be quickly obtained by using the trained model.

Description

Technical Field

[0001] The present invention relates to the technical field of power equipment, and in particular to a GIS electromagnetic field simulation data enhancement method and system based on PU-GAN. Background Art

[0002] Gas insulated switchgear (GIS) has a complex structure and an uncertain working environment. The simulation research of GIS generally uses finite element simulation methods, such as the literature "Simulation and Optimization of Switchgear Products Based on Finite Element Analysis, Ouyang Zhenguo, Master's Thesis" proposed the use of finite element analysis software to simulate and calculate the three-dimensional electric field strength of new vacuum circuit breakers. However, when performing electromagnetic field non-uniform grid simulation, traditional numerical methods face problems such as complex coupling processing between coarse and fine grids and difficulty in establishing boundary conditions; at the same time, non-uniform grid division simulation requires high computing resources. When simulating with a high number of grid divisions and sparse density, the calculation time is long and the simulation speed is slow. When dealing with high-frequency GIS partial discharge detection problems, it will seriously affect the detection time. If coarse grid simulation is used, although the time cost can be reduced, the simulation accuracy is low, which will affect the quality of partial discharge detection. Therefore, a fast and high-precision grid electromagnetic field distribution simulation technology is urgently needed.

[0003] In the related art, a patent application document with publication number CN111428407A proposed a method for calculating electromagnetic scattering based on deep learning. The scheme proposed to design and use a deep learning network as a model to complete the training prediction process, thereby characterizing the input information, that is, the relationship between the scatterer, the incident field, and the induced current. However, the premise of this scheme requires that the incident angle and intensity of the incident wave are fixed and known. When enhancing the GIS electromagnetic field data, only the coarse grid electromagnetic field information of the GIS tube can be obtained, and the location and intensity of the GIS local discharge are unknown, so this scheme is not suitable for enhancing the GIS electromagnetic field data. Summary of the invention

[0004] The technical problem to be solved by the present invention is how to quickly obtain high-precision GIS grid electromagnetic field simulation results.

[0005] The present invention solves the above technical problems by the following technical means: The present invention proposes a GIS electromagnetic field simulation data enhancement method based on PU-GAN, the method comprising: Obtain the real coarse grid data and real fine grid data of GIS electromagnetic field; Inputting the real coarse grid data and the real fine grid data into a generative adversarial network for training until the overall optimization loss function is minimized, and obtaining a trained generator as a data enhancement model for enhancing the real coarse grid data generated in real time; Among them, the generative adversarial network includes the generator and the discriminator, and the generator is used to extract features from the real coarse grid data and perform cyclic multiple enhancement on the extracted features to obtain fine grid generated data.

[0006] Furthermore, the discriminator includes a structural similarity module, a field strength consistency module and an accuracy discrimination module, wherein: The structural similarity module is used to calculate a first confidence value of the structural information contained in the fine grid generation data and the real fine grid data; The field intensity consistency module is used to calculate a second confidence value of the field intensity information included in the fine grid generation data and the real fine grid data; The accuracy determination module is used to shorten the distance between the fine grid generated data and the real fine grid data distribution.

[0007] Furthermore, the structural similarity module includes a first structural branch network, a second structural branch network and a first regression network, the enhanced structural information contained in the fine grid generation data and the real fine structural information contained in the real fine grid data are respectively used as inputs of the first structural branch network and the second structural branch network, and the outputs of the first structural branch network and the second structural branch network are output as structural feature matrices after matrix multiplication operations; The structural feature matrix is ​​used as an input of the first regression network to obtain a first confidence value between the enhanced structural information and the real fine structural information.

[0008] Furthermore, the field intensity consistency module includes a first enhanced branch network, a second enhanced branch network, and a second regression network, the enhanced field intensity information contained in the fine grid generation data and the real fine field intensity information contained in the real fine grid data are respectively used as inputs of the first enhanced branch network and the second enhanced branch network, and the outputs of the first enhanced branch network and the second enhanced branch network are subjected to matrix multiplication operation to output a field intensity feature matrix; The field strength characteristic matrix is ​​used as the input of the second regression network to obtain a second confidence value between the enhanced field strength information and the real fine field strength information.

[0009] Furthermore, the first structure branch network and the second structure branch network both include a multi-layer perceptron and a maximum pooling layer connected in sequence, and the outputs of the first structure branch network and the second structure branch network are subjected to matrix multiplication operations to output a structural feature matrix as follows:

[0010] In the formula, is the structural feature matrix, The structural characteristics of the data for the fine grid generation, is the structural feature of the real fine grid data, , respectively , The modulation weight.

[0011] Furthermore, the first regression network includes a first self-attention unit, a multi-layer perceptron and a fully connected layer connected in sequence, the first self-attention unit is used to generate a structural attention weight based on the structural feature matrix, and the structural attention weight outputs a first confidence value after passing through the multi-layer perceptron and the fully connected layer.

[0012] Furthermore, the first enhanced branch network and the second enhanced branch network both include a multi-layer perceptron and an activation function connected in sequence, and the outputs of the first enhanced branch network and the second enhanced branch network are subjected to matrix multiplication operations to output a field intensity feature matrix as follows:

[0013] In the formula, is the field strength characteristic matrix, The field strength characteristics of the data generated for the fine grid, is the field intensity characteristic of the real fine grid data, '、 respectively , The modulation weight.

[0014] Furthermore, the second regression network includes a second self-attention unit, a multi-layer perceptron and a fully connected layer connected in sequence, the second self-attention unit is used to generate a field intensity attention weight based on the field intensity feature matrix, and the field intensity attention weight outputs a second confidence value after passing through the multi-layer perceptron and the fully connected layer.

[0015] Furthermore, the formula of the overall optimization loss function is expressed as:

[0016] In the formula, For the overall optimization loss function, A first confidence value of the structural information contained in the fine grid generation data and the true fine grid data, a second confidence value for the field strength information contained in the fine grid generation data and the real fine grid data, is the adversarial loss between the fine grid generated data and the true fine grid data, and is the weight parameter.

[0017] Furthermore, the generator includes a plurality of cascaded feature extraction and expansion networks, each of which is connected to a multi-layer perceptron; The feature extraction and expansion network includes a feature extraction module and a feature expansion module connected in sequence, and the output of the feature extraction module in the feature extraction and expansion network of the previous level is connected to the output of the feature extraction module in the feature extraction and expansion network of the next level; The feature extraction module includes a first MLPs layer, a KNN layer, a second MLPs layer, a maximum pooling layer maxpooling and a data compression layer connected in sequence, the real coarse grid data is used as the input of the first MLPs layer, the output of the first MLPs layer and the output of the second MLPs layer are spliced ​​and output to the maximum pooling layer maxpooling, the real coarse grid data and the output of the maximum pooling layer maxpooling are spliced ​​and used as the input of the data compression layer, and the output of the data compression layer is connected to the feature expansion module; The feature expansion module is used to add a vector coded as 1 or -1 to each feature output by the feature extraction module to generate position disturbance.

[0018] Furthermore, when the features output by the feature extraction module in the feature extraction and expansion network at the previous level are copied to the output of the feature extraction module in the feature extraction and expansion network at the next level, interpolation technology is used to match features at different levels.

[0019] Furthermore, the method further comprises: using bilateral interpolation to match features at different levels, The interpolation of the feature values ​​output by the previous feature extraction module is:

[0020] in, It is The coordinates and field strength of each point, It is The coordinates and field strength of each point, It is The eigenvalues ​​corresponding to the points are It is The eigenvalues ​​corresponding to the points are is the set of data points that need to be inserted, where the joint weighted function is expressed as follows:

[0021]

[0022] Among them, the width parameter and is the average distance from a point to its nearest neighbor, Represents the magnitude of a vector.

[0023] In addition, the present invention also proposes a GIS electromagnetic field simulation data enhancement system based on PU-GAN, the system comprising: A data acquisition unit, used to acquire real coarse grid data and real fine grid data of GIS electromagnetic field; A training unit, used for inputting the real coarse grid data and the real fine grid data into a generative adversarial network for training until the overall optimization loss function is minimized, and obtaining a trained generator as a data enhancement model for enhancing the real coarse grid data generated in real time; Among them, the generative adversarial network includes the generator and the discriminator, and the generator is used to extract features from the real coarse grid data and perform cyclic multiple enhancement on the extracted features to obtain fine grid generated data.

[0024] The advantages of the present invention are: (1) The present invention trains a generative adversarial network by using real coarse grid data and real fine grid data obtained by simulation. The trained generator can be used to enhance the real coarse grid data obtained by real-time simulation to generate GIS electromagnetic field fine data. In addition, since GIS equipment has a certain physical structure, the data points of electromagnetic field simulation cannot exceed a certain range. The generator designed by the present invention adopts cyclic multiple enhancement to enhance the electromagnetic field between coarse grid data points, which ensures that it does not exceed the physical structure of GIS to a certain extent, thereby improving the accuracy of GIS electromagnetic field simulation data enhancement.

[0025] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 It is a flowchart of a GIS electromagnetic field simulation data enhancement method based on PU-GAN proposed in one embodiment of the present invention; Figure 2It is a principle block diagram of GIS electromagnetic field simulation data enhancement based on PU-GAN proposed in one embodiment of the present invention; Figure 3 is a schematic diagram of the structure of a generator in one embodiment of the present invention; Figure 4 is a schematic diagram of the structure of a feature extraction module in one embodiment of the present invention; Figure 5 is a schematic diagram of a structurally similar module in one embodiment of the present invention; Figure 6 is a schematic diagram of the structure of a field strength consistency module in one embodiment of the present invention; Figure 7 is a schematic diagram of the structure of a self-attention unit in one embodiment of the present invention; Figure 8 It is a structural schematic diagram of a GIS electromagnetic field simulation data enhancement system based on PU-GAN proposed in one embodiment of the present invention. DETAILED DESCRIPTION

[0027] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in combination with the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0028] like Figure 1 to Figure 2 As shown, the first embodiment of the present invention proposes a GIS electromagnetic field simulation data enhancement method based on PU-GAN, and the method includes the following steps: S10, obtaining real coarse grid data and real fine grid data of GIS electromagnetic field; It should be noted that, in this embodiment, the electromagnetic field coarse grid data and fine grid data can be obtained by establishing a GIS spatial topology model and an electromagnetic field mathematical model, and solving the electromagnetic field model based on a finite difference method or a finite element method.

[0029] It should be noted that the acquired mesh data includes three-dimensional space coordinate data and field strength values ​​of each mesh vertex.

[0030] S20, inputting the real coarse grid data and the real fine grid data into a generative adversarial network for training until the overall optimization loss function is minimized, and obtaining a trained generator as a data enhancement model for enhancing the real coarse grid data generated in real time; Among them, the generative adversarial network includes the generator and the discriminator, and the generator is used to extract features from the real coarse grid data and perform cyclic multiple enhancement on the extracted features to obtain fine grid generated data.

[0031] It should be noted that the generator network is responsible for learning the potential distribution characteristics of real samples and synthesizing new samples; the role of the discriminator network is to distinguish between real samples and generated new samples. The generator and the discriminator achieve the effect of confrontation through alternating training, continuously improving their respective generation and discrimination capabilities, and finally making the confrontation between the generator network and the discriminator network reach Nash equilibrium.

[0032] Since GIS equipment has a certain physical structure, the data points of electromagnetic field simulation cannot exceed a certain range. The PU-GAN (Projection Upsampling Generative Adversarial Network) designed in the embodiment of the present invention multiplies the coarse grid data points by upsampling. The generator adopts cyclic multiplication enhancement to enhance the electromagnetic field between coarse grid data points, which ensures that it does not exceed the physical structure of GIS to a certain extent, thereby improving the accuracy of GIS electromagnetic field simulation data enhancement.

[0033] As a further preferred technical solution, Figure 3 As shown, the generator includes several cascaded feature extraction and expansion networks, each of which is connected to a multi-layer perceptron; The feature extraction and expansion network includes a feature extraction module Featuer Extraction and a feature expansion module connected in sequence, and the output of the feature extraction module Featuer Extraction in the feature extraction and expansion network of the previous level is connected to the output of the feature extraction module Featuer Extraction in the feature extraction and expansion network of the next level; like Figure 4 As shown, the feature extraction module Featuer Extraction includes a first MLPs layer, a KNN layer, a second MLPs layer, a maximum pooling layer maxpooling and a data compression layer compression which are connected in sequence, the real coarse grid data is used as the input of the first MLPs layer, the output of the first MLPs layer and the output of the second MLPs layer are spliced ​​and output to the maximum pooling layer maxpooling, the real coarse grid data and the output of the maximum pooling layer maxpooling are spliced ​​and used as the input of the data compression layer compression, and the output of the data compression layer compression is connected to the feature expansion module; The feature expansion module is used to add a vector coded as 1 or -1 to each feature output by the feature extraction module to generate position disturbance.

[0034] It should be noted that the function of the generator designed in this embodiment is to enhance the coarse grid data of GIS and generate the required GIS fine grid data; the designed generator adopts a cyclic multiple enhancement design, and can autonomously adjust the coarse grid enhancement multiple according to demand, and the multiple enhancement can better retain the characteristics of the coarse grid data.

[0035] Specifically, the working process of the feature extraction module in this embodiment is as follows: first, the N×4-dimensional information composed of the three-dimensional spatial coordinates (x, y, z) and the field strength value v of each input sampling point is extracted as a fixed-scale feature C' through the first MLPs layer, and then the features are grouped by the KNN layer to obtain N×K groups, and the group features are further optimized by the second MLPs layer to obtain the features of the G channel. The features output by the second MLPs layer are combined with the features output by the first MLPs layer to obtain a new G channel feature (a total of N×K×(2G+C')). Finally, the group information is condensed by maxpooling to obtain the final N×(2G+C'), and the N×4-dimensional features of the sampling points initially output are added. This feature will be fed into the subsequent modules for reuse as a module multi-scale feature aggregation to improve the reconstruction accuracy while also improving the parameter efficiency and reducing the model size. The N×C features are obtained under the compression of the last layer of data compression layer compression. After copying the obtained N×C features, a vector encoded as 1 or -1 is added after each feature to generate position perturbations, and then the subsequent multi-layer perceptron MLP is used to regress the 2N×(C+1) features into 2N×4 data.

[0036] It should be noted that after multiple cycles of feature extraction and expansion, a 2 r The N×C features are finally regressed to four-dimensional data by a multi-layer perceptron MLP2 r N×4.

[0037] It should be noted that the value of r depends on the difference in precision between the input simulation coarse grid and fine grid, and is not specifically limited in this embodiment.

[0038] Specifically, if it is necessary to pass the previous feature to the next layer, a good interpolation technology is needed to match the features of different levels. In this embodiment, when copying the features output by the feature extraction module in the feature extraction and expansion network of the previous level to the output of the feature extraction module in the feature extraction and expansion network of the next level, the interpolation technology is used to match the features of different levels.

[0039] As a further preferred technical solution, this embodiment uses the bilateral interpolation technology to interpolate the points using the features around the target point. The interpolation of the feature values ​​output by the previous feature extraction module is:

[0040] in, It is The coordinates and field strength of each point, It is The coordinates and field strength of each point, It is The eigenvalues ​​corresponding to the points are It is The eigenvalues ​​corresponding to the points are is the set of data points that need to be inserted, where the joint weighted function is expressed as follows:

[0041]

[0042] Among them, the width parameter and is the average distance from a point to its nearest neighbor, Represents the magnitude of a vector.

[0043] This embodiment is for coarse grid data enhancement. The use of bilateral interpolation can effectively avoid the overlap of generated grid data with source grid data, thus avoiding waste.

[0044] As a further preferred technical solution, Figure 2 As shown, the discriminator includes a structural similarity module, a field strength consistency module and an accuracy discrimination module, wherein: The structural similarity module is used to calculate a first confidence value of the structural information contained in the fine grid generation data and the real fine grid data; The field intensity consistency module is used to calculate a second confidence value of the field intensity information included in the fine grid generation data and the real fine grid data; The accuracy determination module is used to shorten the distance between the fine grid generated data and the real fine grid data distribution.

[0045] It should be noted that the discriminator designed in this embodiment is used to determine whether the input data meets the requirements. The discriminator consists of a structural similarity module, a field strength consistency module and an accuracy discrimination module. The grid data is divided into structural data and field strength data for comparative analysis, which can effectively improve the discrimination accuracy.

[0046] As a further preferred technical solution, Figure 5As shown, the structural similarity module includes a first structural branch network, a second structural branch network and a first regression network, the enhanced structural information contained in the fine grid generation data and the real fine structural information contained in the real fine grid data are respectively used as inputs of the first structural branch network and the second structural branch network, and the outputs of the first structural branch network and the second structural branch network are output as structural feature matrices after matrix multiplication operations; The structural feature matrix is ​​used as an input of the first regression network to obtain a first confidence value between the enhanced structural information and the real fine structural information.

[0047] Specifically, Figure 5 As shown, the first structure branch network and the second structure branch network both include a multi-layer perceptron and a maximum pooling layer connected in sequence, and the output of the first structure branch network and the second structure branch network is subjected to a matrix multiplication operation to output a structural feature matrix:

[0048]

[0049]

[0050] In the formula, is the structural feature matrix, The structural characteristics of the data for the fine grid generation, is the structural feature of the real fine grid data, , respectively , The modulation weight, represents the multi-layer perceptron operation, represents the maximum pooling operation, Generate data for the fine grid The structural information of each point, is the real fine grid data The structural information of each point.

[0051] Specifically, Figure 5 As shown, the first regression network includes a first self-attention unit, a multi-layer perceptron and a fully connected layer connected in sequence, the first self-attention unit is used to generate a structural attention weight based on the structural feature matrix, and the structural attention weight outputs a first confidence value after passing through the multi-layer perceptron and the fully connected layer.

[0052] As a further preferred technical solution, Figure 6As shown, the field strength consistency module includes a first enhanced branch network, a second enhanced branch network and a second regression network, the enhanced field strength information contained in the fine grid generation data and the real fine field strength information contained in the real fine grid data are respectively used as inputs of the first enhanced branch network and the second enhanced branch network, and the outputs of the first enhanced branch network and the second enhanced branch network are output as a field strength feature matrix after matrix multiplication operation; The field strength characteristic matrix is ​​used as the input of the second regression network to obtain a second confidence value between the enhanced field strength information and the real fine field strength information.

[0053] Specifically, the first enhanced branch network and the second enhanced branch network both include a multi-layer perceptron and an activation function connected in sequence, and the output of the first enhanced branch network and the second enhanced branch network is subjected to a matrix multiplication operation to output a field intensity feature matrix as follows:

[0054]

[0055]

[0056] In the formula, is the field strength characteristic matrix, The field strength characteristics of the data generated for the fine grid, is the field intensity characteristic of the real fine grid data, '、 respectively , The modulation weight, Generate data for the fine grid Field strength information of each point, is the real fine grid data Field strength information of each point.

[0057] Specifically, the second regression network includes a second self-attention unit, a multi-layer perceptron and a fully connected layer connected in sequence, the second self-attention unit is used to generate a field intensity attention weight based on the field intensity feature matrix, and the field intensity attention weight outputs a second confidence value after passing through the multi-layer perceptron and the fully connected layer.

[0058] As a further preferred technical solution, Figure 7 As shown, the self-attention unit used in this embodiment is used to perform enhanced feature integration. Specifically, the input features are converted into G, H and F through three independent MLPs, and then the attention weights are generated by G and H: M

[0059] in, Represents the softmax function.

[0060] Then the weighted feature M is obtained, and finally the output feature is generated, which is the sum of the input feature and the weighted feature.

[0061] As a further preferred technical solution, in this embodiment, the outputs of the structural similarity module and the field strength consistency module are both connected to the accuracy discrimination module, which is used to control the generated grid structure and field strength data and distinguish the accuracy of the generated results. The accuracy discrimination module can be defined as a regional-level fully convolutional binary classifier, which can narrow the distance between the generated fine grid simulation data and the fine grid simulation data distribution of the numerical method, and use the least squares adversarial loss to ensure the stability of the training process.

[0062] The adversarial loss between the fine mesh generated data and the true fine mesh data is defined as follows:

[0063] In the formula, and They are respectively the discriminator D generating data from the fine grid output of the generator With real fine grid data Confidence value of the prediction in .

[0064] As a further preferred technical solution, the formula of the overall optimization loss function is expressed as:

[0065] In the formula, For the overall optimization loss function, A first confidence value of the structural information contained in the fine grid generation data and the true fine grid data, a second confidence value for the field strength information contained in the fine grid generation data and the real fine grid data, is the adversarial loss between the fine grid generated data and the true fine grid data, and is the weight parameter.

[0066] The overall optimization loss function set in this embodiment comprehensively considers the structure and field strength confidence of the generated fine grid and the real fine grid, and has the advantages of: (1) Promoting the generator to generate realistic data: By optimizing the loss function, the generator is forced to generate samples that are as close to the real data distribution as possible. (2) Improving the accuracy of the discriminator: The discriminator improves its ability to distinguish between real data and generated data by optimizing the loss function. This includes enabling the discriminator to more accurately identify the data generated by the generator, and better distinguishing between generated data and real data. (3) Achieving a balance between the generator and the discriminator: Optimizing the loss function ensures that there is a balance between the generator and the discriminator, avoiding over-optimization of one of them and causing unstable training. This balance helps the generator generate more realistic data while ensuring that the discriminator can effectively distinguish between real data and generated data.

[0067] In addition, if Figure 8 As shown, the second embodiment of the present invention proposes a GIS electromagnetic field simulation data enhancement system based on PU-GAN, and the system includes: A data acquisition unit 10 is used to acquire real coarse grid data and real fine grid data of the GIS electromagnetic field; A training unit 20 is used to input the real coarse grid data and the real fine grid data into a generative adversarial network for training until the overall optimization loss function is minimized, and obtain a trained generator as a data enhancement model for enhancing the real coarse grid data generated in real time; Among them, the generative adversarial network includes the generator and the discriminator, and the generator is used to extract features from the real coarse grid data and perform cyclic multiple enhancement on the extracted features to obtain fine grid generated data.

[0068] It should be noted that other embodiments or implementation methods of the generative adversarial network in the GIS electromagnetic field simulation data enhancement system based on PU-GAN described in the present invention can refer to the above-mentioned method embodiments, which will not be repeated here.

[0069] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0070] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of the present invention, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0071] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. A GIS electromagnetic field simulation data enhancement method based on PU-GAN, characterized in that: The method comprises: Obtain the real coarse grid data and real fine grid data of GIS electromagnetic field; Inputting the real coarse grid data and the real fine grid data into a generative adversarial network for training until the overall optimization loss function is minimized, and obtaining a trained generator as a data enhancement model for enhancing the real coarse grid data generated in real time; Among them, the generative adversarial network includes the generator and the discriminator, and the generator is used to extract features from the real coarse grid data and perform cyclic multiple enhancement on the extracted features to obtain fine grid generated data.

2. The GIS electromagnetic field simulation data enhancement method based on PU-GAN as claimed in claim 1, characterized in that: The discriminator includes a structural similarity module, a field strength consistency module and an accuracy discrimination module, wherein: The structural similarity module is used to calculate a first confidence value of the structural information contained in the fine grid generation data and the real fine grid data; The field intensity consistency module is used to calculate a second confidence value of the field intensity information included in the fine grid generation data and the real fine grid data; The accuracy determination module is used to shorten the distance between the fine grid generated data and the real fine grid data distribution.

3. The GIS electromagnetic field simulation data enhancement method based on PU-GAN as claimed in claim 2, characterized in that: The structural similarity module includes a first structural branch network, a second structural branch network and a first regression network, the enhanced structural information contained in the fine grid generation data and the real fine structural information contained in the real fine grid data are respectively used as inputs of the first structural branch network and the second structural branch network, and the outputs of the first structural branch network and the second structural branch network are subjected to matrix multiplication operation to output a structural feature matrix; The structural feature matrix is ​​used as an input of the first regression network to obtain a first confidence value between the enhanced structural information and the real fine structural information.

4. The GIS electromagnetic field simulation data enhancement method based on PU-GAN as claimed in claim 2, characterized in that: The field intensity consistency module comprises a first enhanced branch network, a second enhanced branch network and a second regression network, the enhanced field intensity information contained in the fine grid generation data and the real fine field intensity information contained in the real fine grid data are respectively used as inputs of the first enhanced branch network and the second enhanced branch network, and the outputs of the first enhanced branch network and the second enhanced branch network are subjected to matrix multiplication operation to output a field intensity feature matrix; The field strength characteristic matrix is ​​used as the input of the second regression network to obtain a second confidence value between the enhanced field strength information and the real fine field strength information.

5. The GIS electromagnetic field simulation data enhancement method based on PU-GAN as claimed in claim 3 is characterized in that: The first structure branch network and the second structure branch network both include a multi-layer perceptron and a maximum pooling layer connected in sequence. The outputs of the first structure branch network and the second structure branch network are subjected to matrix multiplication operations to output a structural feature matrix: In the formula, is the structural feature matrix, The structural characteristics of the data for the fine grid generation, is the structural feature of the real fine grid data, , respectively , The modulation weight.

6. The GIS electromagnetic field simulation data enhancement method based on PU-GAN as claimed in claim 3, characterized in that: The first regression network includes a first self-attention unit, a multi-layer perceptron and a fully connected layer connected in sequence, the first self-attention unit is used to generate a structural attention weight based on the structural feature matrix, and the structural attention weight outputs a first confidence value after passing through the multi-layer perceptron and the fully connected layer.

7. The GIS electromagnetic field simulation data enhancement method based on PU-GAN as claimed in claim 4, characterized in that: The first enhanced branch network and the second enhanced branch network both include multi-layer perceptrons and activation functions connected in sequence. The outputs of the first enhanced branch network and the second enhanced branch network are subjected to matrix multiplication operations to output a field intensity feature matrix as follows: In the formula, is the field strength characteristic matrix, The field strength characteristics of the data generated for the fine grid, is the field intensity characteristic of the real fine grid data, '、 respectively , The modulation weight.

8. The GIS electromagnetic field simulation data enhancement method based on PU-GAN as claimed in claim 4, characterized in that: The second regression network includes a second self-attention unit, a multi-layer perceptron and a fully connected layer connected in sequence. The second self-attention unit is used to generate field intensity attention weights based on the field intensity feature matrix. The field intensity attention weights output a second confidence value after passing through the multi-layer perceptron and the fully connected layer.

9. The GIS electromagnetic field simulation data enhancement method based on PU-GAN according to any one of claims 1 to 8, characterized in that: The formula of the overall optimization loss function is expressed as: In the formula, For the overall optimization loss function, A first confidence value of the structural information contained in the fine grid generation data and the true fine grid data, a second confidence value for the field strength information contained in the fine grid generation data and the real fine grid data, is the adversarial loss between the fine grid generated data and the true fine grid data, and is the weight parameter.

10. The GIS electromagnetic field simulation data enhancement method based on PU-GAN according to any one of claims 1 to 8, characterized in that: The generator includes a plurality of cascaded feature extraction and expansion networks, each of which is connected to a multi-layer perceptron; The feature extraction and expansion network includes a feature extraction module and a feature expansion module connected in sequence, and the output of the feature extraction module in the feature extraction and expansion network of the previous level is connected to the output of the feature extraction module in the feature extraction and expansion network of the next level; The feature extraction module includes a first MLPs layer, a KNN layer, a second MLPs layer, a maximum pooling layer maxpooling and a data compression layer connected in sequence, the real coarse grid data is used as the input of the first MLPs layer, the output of the first MLPs layer and the output of the second MLPs layer are spliced ​​and output to the maximum pooling layer maxpooling, the real coarse grid data and the output of the maximum pooling layer maxpooling are spliced ​​and used as the input of the data compression layer, and the output of the data compression layer is connected to the feature expansion module; The feature expansion module is used to add a vector coded as 1 or -1 to each feature output by the feature extraction module to generate position disturbance.

11. The GIS electromagnetic field simulation data enhancement method based on PU-GAN as claimed in claim 10, characterized in that: When copying the features output by the feature extraction module in the feature extraction and expansion network of the previous level to the output of the feature extraction module in the feature extraction and expansion network of the next level, an interpolation technique is used to match features at different levels.

12. The GIS electromagnetic field simulation data enhancement method based on PU-GAN as claimed in claim 10, characterized in that: The method further includes: using bilateral interpolation to match features at different levels, The interpolation of the feature values ​​output by the previous feature extraction module is: in, It is The coordinates and field strength of each point, It is The coordinates and field strength of each point, It is The eigenvalues ​​corresponding to the points are It is The eigenvalues ​​corresponding to the points are , where the joint weighting function is expressed as follows: Among them, the width parameter and is the average distance from a point to its nearest neighbor, Represents the magnitude of a vector.

13. A GIS electromagnetic field simulation data enhancement system based on PU-GAN, characterized in that: The system comprises: A data acquisition unit, used to acquire real coarse grid data and real fine grid data of GIS electromagnetic field; A training unit, used for inputting the real coarse grid data and the real fine grid data into a generative adversarial network for training until the overall optimization loss function is minimized, and obtaining a trained generator as a data enhancement model for enhancing the real coarse grid data generated in real time; Among them, the generative adversarial network includes the generator and the discriminator, and the generator is used to extract features from the real coarse grid data and perform cyclic multiple enhancement on the extracted features to obtain fine grid generated data.

Images