Fast and high-precision simulation method, simulator, storage medium and system for GIS electromagnetic field distribution

Abstract

The present invention discloses a method, a simulator, a storage medium and a system for rapid and high-precision simulation of electromagnetic field distribution of GIS. The method comprises the following steps: numerically solving a three-dimensional simulation model of GIS equipment by using a finite difference time domain algorithm or a finite element algorithm to obtain a GIS full-wave electromagnetic coarse grid simulation result, wherein the coarse grid simulation result comprises coarse grid structure data and coarse grid field strength data; and enhancing the coarse grid simulation result by using an enhanced model to obtain enhanced fine grid data. The present invention can realize rapid and high-precision simulation of electromagnetic field distribution of GIS.

Description

Technical Field

[0001] The present invention relates to the technical field of electric power equipment, and in particular to a fast and high-precision simulation method for GIS electromagnetic field distribution, a simulator, a storage medium and a system. Background Art

[0002] Gas Insulated Switchgear (GIS) plays a vital role in modern power systems. This equipment uses inert gas as an insulating medium to achieve safe and reliable transmission and distribution of high-voltage electricity in a relatively small space. The high performance and reliability of GIS are essential to ensure the stable operation of the power system, improve the transmission efficiency of the power grid, and ensure the security of power supply. With the rapid development of power systems and the increasing requirements for power grid safety performance, electromagnetic simulation of GIS has become one of the research focuses. Electromagnetic simulation methods can help engineers and researchers deeply understand the electromagnetic field distribution, electromagnetic interference, and its impact on GIS performance inside GIS.

[0003] The simulation research of GIS generally uses finite element simulation method or finite time domain difference method (Finite-Difference Time-Domain, abbreviated as FDTD), etc. Among them, the finite element simulation method, such as the one proposed in the document "Simulation and Optimization of Switchgear Products Based on Finite Element Analysis, Ouyang Zhenguo, Master's Thesis", uses finite element analysis software to simulate and calculate the three-dimensional electric field strength of the new vacuum circuit breaker. Finite time-domain difference method, for example, a master's thesis "Simulation and Calculation of Transient Electric Field of GIS Equipment Based on Finite Time-Domain Finite Difference Method, Yang Rui, Huazhong University of Science and Technology" proposed a FDTD method suitable for transient electric field calculation of GIS equipment. This paper selects appropriate grid generation algorithm and absorbing boundary conditions, divides GIS into two parts: coaxial bus pipeline and GIS complex equipment according to the structural characteristics during modeling, and studies key issues such as grid generation algorithm. Since GIS electromagnetic field simulation focuses on the accurate simulation of the interaction between equipment model and electromagnetic field distribution, it has high complexity and needs to consider both time cost and simulation accuracy. However, this paper mainly studies the improvement of simulation algorithm accuracy and ignores the time cost required in the actual simulation process. It pays more attention to theoretical research and lacks practical applicability. In addition, the main purpose of this paper is to analyze the electric field distribution simulation of GIS equipment under transient voltage. This simulation usually focuses on the response of equipment under voltage or current shock in a short period of time, and has weak generalization ability.

[0004] In addition, traditional numerical methods face problems such as complex coupling processing between coarse and fine grids and difficulty in establishing boundary conditions when performing electromagnetic field non-uniform grid simulation. 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, there is an urgent need for a fast and high-precision grid electromagnetic field distribution simulation technology. Summary of the invention

[0005] The technical problem to be solved by the present invention is how to realize fast and high-precision GIS electromagnetic field distribution simulation.

[0006] The present invention solves the above technical problems by the following technical means:

[0007] The present invention proposes a fast and high-precision simulation method for GIS electromagnetic field distribution, characterized in that the method comprises:

[0008] A finite-difference time-domain algorithm or a finite element algorithm is used to numerically solve a three-dimensional simulation model of the GIS equipment to obtain a GIS full-wave electromagnetic coarse-grid simulation result, wherein the coarse-grid simulation result includes coarse-grid structure data and coarse-grid field strength data;

[0009] The coarse grid simulation result is enhanced by using an enhanced model to obtain enhanced fine grid data.

[0010] Furthermore, the process of numerically solving the three-dimensional simulation model of GIS equipment using the finite difference time domain algorithm includes:

[0011] Discretize the three-dimensional simulation model of GIS equipment into spatial grids, and determine the corresponding relationship between the number and spatial coordinate data of each grid node;

[0012] The Maxwell equations used to describe the electromagnetic field of GIS are converted into a fourth-order matrix, and the four-step HIE-FDTD algorithm is used to solve the fourth-order matrix and calculate the field strength data of each grid node.

[0013] Furthermore, the Maxwell equations used to describe the electromagnetic field of the GIS are converted into a fourth-order matrix, and the fourth-order matrix is ​​solved using a four-step HIE-FDTD algorithm to calculate the field strength data of each grid node, including:

[0014] The Maxwell equations used to describe the electromagnetic field of GIS are converted into a sixth-order matrix form:

[0015]

[0016] In the formula, is the vector consisting of the components of the electric and magnetic fields in the rectangular coordinate system, is a sixth-order matrix;

[0017] Convert the sixth-order matrix form to a fourth-order rectangular form:

[0018]

[0019] In the formula, for ,

[0020] for ;

[0021] The four-step HIE-FDTD algorithm is used to solve the fourth-order matrix form and calculate the field intensity data of each grid node.

[0022] Furthermore, the sixth-order matrix The formula is expressed as:

[0023]

[0024] In the formula, is the dielectric constant, is the magnetic permeability.

[0025] Furthermore, the four-step HIE-FDTD algorithm is used to solve the fourth-order matrix form and calculate the field strength data of each grid node, including:

[0026] The four-step HIE-FDTD algorithm is decomposed into , , , Four sub-steps, for each sub-step a semi-implicit difference scheme is used to calculate the three diagonal implicits of the field strength data about the grid nodes;

[0027] The pursuit method is used to solve the three diagonal implicit equations and obtain the grid node field strength data.

[0028] Furthermore, the enhancement model adopts a differential deep learning network model, the differential deep learning network model includes an enhancement network and a structural similarity network connected in sequence, and the enhancement network includes a self-adjusting module and a differential convolution module;

[0029] The self-adjusting module and the differential convolution module are used to calculate the coarse grid structure data and the coarse grid field strength data respectively to obtain fine grid enhanced grid structure characteristics and fine grid enhanced field strength characteristics;

[0030] Using the structural similarity network, the fine grid enhanced grid structure feature and the fine grid enhanced field strength feature are matched to calculate a similarity feature;

[0031] Based on the similarity features, enhanced fine grid data is calculated.

[0032] Furthermore, the self-adjusting module includes a first convolutional layer and a second convolutional layer connected in sequence, and the output features of the first convolutional layer and the output features of the second convolutional layer are output to the activation function layer after a first addition operation;

[0033] The coarse grid structure data is used as the input of the first convolutional layer, the grid size supplementary information of the coarse grid structure data is used as the input of the second convolutional layer, the bias vector of the coarse grid structure data is used as the input of the first addition operation, and the coarse grid structure data and the grid size supplementary information of the coarse grid structure data are output to the first addition operation via residual connection.

[0034] Furthermore, the differential convolution module includes a differential convolution layer, a size integration layer, a self-attention mechanism layer and a third convolution layer connected in sequence, and the third convolution layer is connected to an activation function;

[0035] The coarse grid field intensity data is used as the input of the differential convolution layer, and the differential convolution layer is used to calculate the field intensity features of different sizes of the coarse grid field intensity data by using a differential algorithm;

[0036] The size integration layer is used to sum the field intensity features of different sizes calculated by the differential convolution layer to obtain the reorganized field intensity features.

[0037] Furthermore, the convolution kernel of the differential convolution layer adopts any one of a five-point differential convolution kernel, a weighted differential convolution kernel, a multi-scale differential convolution kernel, a directional differential convolution kernel, a nine-point differential convolution kernel, and a mixed mode differential convolution.

[0038] Furthermore, the structural similarity network includes a first branch network, a second branch network, a second addition operation and a first multilayer perceptron, the outputs of the first branch network and the second branch network are both connected to the second addition operation, the output of the second addition operation is connected to the first multilayer perceptron, and the multilayer perceptron is followed by an activation function.

[0039] Furthermore, the first branch network includes a convolutional neural network layer CNN and a batch normalization operation connected in sequence, and the regularization operation is followed by an activation function;

[0040] The second branch network includes a second multilayer perceptron, and the second multilayer perceptron is followed by an activation function.

[0041] Furthermore, the using the structural similarity network to match the fine grid enhanced grid structure feature and the fine grid enhanced field strength feature to calculate the similarity feature includes:

[0042] The structural feature information of the fine grid enhanced grid structure feature is extracted by using the first branch network, and the formula is expressed as:

[0043]

[0044] In the formula, For the The fine grid enhances the characteristic information of the grid structure characteristics, Enhance the grid structure characteristics for the fine grid, is a stacked convolution operation, is the batch normalization operation, is the activation function;

[0045] The second branch network is used to extract the field intensity feature information of the fine grid enhanced field intensity feature, and the formula is expressed as:

[0046]

[0047] In the formula, For the The characteristic information of the fine grid enhanced field strength characteristics, Enhance the field strength characteristics for the fine grid, Operations performed by the second multilayer perceptron;

[0048] The field strength and structure combination feature is calculated by using the modulation weights corresponding to the feature information of the fine grid enhanced grid structure feature and the feature information of the fine grid enhanced field strength feature. The formula is expressed as:

[0049]

[0050] In the formula, is the field strength and structure combination feature, and The modulation weights corresponding to the feature information of the fine grid enhanced grid structure feature and the feature information of the fine grid enhanced field strength feature are respectively represented;

[0051] Based on the field strength and structure combination characteristics, the similarity characteristics are calculated, and the formula is expressed as:

[0052]

[0053] In the formula, For the similarity feature, Operations performed by the first multilayer perceptron.

[0054] Further, the calculating enhanced fine grid data based on the similarity feature includes:

[0055] Calculating regularized coarse grid structure data, regularized coarse grid field intensity data, regularized fine grid enhanced grid structure characteristics, and regularized fine grid enhanced field intensity characteristics based on the coarse grid structure data, the coarse grid field intensity data, the fine grid enhanced grid structure characteristics, and the fine grid enhanced field intensity characteristics, respectively;

[0056] Calculating grid structure consistency based on the regularized coarse grid structure data and the regularized fine grid enhanced grid structure features;

[0057] Calculating grid field strength consistency based on the regularized coarse grid field strength data and the regularized fine grid enhanced field strength characteristics;

[0058] Calculating grid field strength loss compensation based on the grid structure consistency and the grid field strength consistency;

[0059] Calculating fine grid enhancement structure data based on the fine grid enhancement grid structure characteristics, the grid field strength loss compensation and the similarity characteristics;

[0060] Based on the fine grid enhanced field strength characteristics, the grid field strength loss compensation and the similarity characteristics, fine grid enhanced field strength data is calculated.

[0061] Furthermore, the enhancement model adopts a generative adversarial network model, which includes a generator and a discriminator. The generator is used to extract features from the coarse grid simulation results and perform cyclic multiple enhancement on the extracted features to obtain enhanced fine grid data.

[0062] The discriminator includes a structural similarity module, a field strength consistency module and an accuracy discrimination module, wherein:

[0063] The structural similarity module is used to calculate a first confidence value of structural information contained in the enhanced fine grid data and the real fine grid data obtained by simulation;

[0064] The field intensity consistency module is used to calculate a second confidence value of the field intensity information contained in the enhanced fine grid data and the real fine grid data obtained by simulation;

[0065] The accuracy determination module is used to shorten the distance between the enhanced fine grid data and the real fine grid data distribution obtained by simulation.

[0066] 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 enhanced fine grid 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;

[0067] 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.

[0068] Further, 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 enhanced fine grid 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 output as a field intensity feature matrix after matrix multiplication operation;

[0069] 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.

[0070] Furthermore, the generator includes a plurality of cascaded feature extraction and expansion networks, each of which is connected to a multi-layer perceptron;

[0071] 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;

[0072] 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 coarse grid simulation result 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 coarse grid simulation result 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;

[0073] 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.

[0074] 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.

[0075] Furthermore, when the finite element algorithm is used to numerically solve the three-dimensional simulation model of the GIS equipment, it includes:

[0076] The simulation model of the GIS equipment is discretized into a plurality of tetrahedral units by using the finite element method, and the GIS full-wave electromagnetic coarse grid simulation result is obtained by simulation, wherein each of the tetrahedral units includes a plurality of nodes.

[0077] Furthermore, the method of using the enhanced model to enhance the coarse grid simulation result to obtain enhanced fine grid data also includes:

[0078] Abstract the simulation model of GIS equipment into a network topology , and any two adjacent free tetrahedrons in the network topology are regarded as a sheet unit, where Represents a collection of nodes. Represents an edge set, where the lines between mesh vertices are considered edges;

[0079] Using the coarse grid simulation results as the initial benchmark features, the GraphSAGE algorithm is used to perform an aggregation process on the neighboring nodes of each node in each slice unit to generate the initial benchmark features of the newly added nodes;

[0080] The GraphSAGE algorithm is used to perform secondary aggregation on the neighbor nodes of the newly added nodes to generate the feature vector representation of the new nodes.

[0081] Furthermore, the coarse grid simulation result is used as the initial benchmark feature, and the neighbor nodes of each node in each slice unit are aggregated by using the GraphSAGE algorithm to generate the initial benchmark feature of the newly added node, including:

[0082] The coarse grid simulation results of each node are used as the initial benchmark features of each node;

[0083] Traverse each node in each of the slice units , taking all the adjacent nodes of each node as sampling points, obtain the node The neighbor set of , and use the aggregation function to aggregate nodes Corresponding to the initial baseline features of all nodes in the neighbor set, an aggregated neighbor feature is obtained ;

[0084] Connect the initial reference features and aggregated neighbor features Get the first joint feature, perform matrix multiplication on the first weight matrix and the first joint feature, and then use a nonlinear transformation to get the node feature after one traversal ;

[0085] The initial datum features of the common nodes of the two free tetrahedrons in each sheet element are aggregated using an aggregation function to obtain the initial datum features of the newly added nodes.

[0086] Furthermore, the GraphSAGE algorithm is used to perform secondary aggregation processing on the neighbor nodes of the newly added node to generate a feature vector representation of the newly added node, including:

[0087] The node features after a traversal As a new benchmark feature for the corresponding node;

[0088] Each node in each of the slice units As the neighbor sampling point of the newly added node, and using the aggregation function to aggregate the new benchmark features of all nodes in each slice unit, obtain the secondary aggregated neighbor feature ;

[0089] The initial reference feature of the newly added node and the secondary aggregated neighbor feature are connected to obtain a second joint feature, and a second weight matrix is ​​multiplied by the second joint feature to obtain a feature vector representation of the newly added node through a nonlinear transformation.

[0090] Furthermore, a new node is generated corresponding to the overlapping faces of any two adjacent free tetrahedrons.

[0091] In addition, the present invention also proposes a fast and high-precision simulator for GIS electromagnetic field distribution, which includes a memory and a processor; wherein the processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, so as to implement the fast and high-precision simulation method for GIS electromagnetic field distribution as described above.

[0092] In addition, the present invention also proposes a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the above-mentioned fast and high-precision simulation method for GIS electromagnetic field distribution is implemented.

[0093] In addition, the present invention also proposes a multi-structure adaptive GIS field-electric fusion real-time status perception and early warning system, including a signal synchronous acquisition and measurement embedded device and an industrial computer, the industrial computer is provided with the simulator as described above, the simulator is connected to the signal synchronous acquisition and measurement embedded device, the signal synchronous acquisition and measurement embedded device is used to collect the time domain full waveform data of GIS local discharge, the simulator is used to obtain enhanced fine grid data based on the time domain full waveform data, and the industrial computer is used to search for the actual discharge position of the GIS local discharge source based on the time domain full waveform data and the enhanced fine grid data.

[0094] The advantages of the present invention are:

[0095] (1) The present invention first uses a finite-difference time-domain algorithm or a finite element algorithm to numerically solve the three-dimensional simulation model of the GIS equipment, which can quickly obtain a coarse grid simulation result, and uses the coarse grid simulation result as a data basis to perform data enhancement, thereby obtaining fine grid data with enhanced GIS electromagnetic field distribution, that is, high-precision grid data. Therefore, the present invention can quickly obtain high-precision GIS electromagnetic field distribution data.

[0096] (2) The present invention can significantly improve the accuracy and stability of the numerical solution by introducing a higher-order time integration scheme and a space integration scheme. The traditional FDTD method may be affected by numerical dissipation and numerical dispersion, and the present invention can reduce these problems through a more accurate integration method, which is particularly effective when dealing with long-term simulation or high-frequency electromagnetic wave propagation. For electromagnetic field simulation of complex structures, such as dielectrics, inhomogeneous media or inhomogeneous structures, this embodiment adopts a four-step hybrid implicit explicit finite-difference time-domain (HIE-FDTD) method to better handle these complexities. Its accurate integration and numerical methods can effectively simulate the electromagnetic field propagation and interaction between different media.

[0097] (3) Since GIS electromagnetic field simulation focuses more on the accurate simulation of the detailed interaction between equipment and electromagnetic fields, the present invention designs and constructs a differential deep learning network model, which uses convolution combined with a differential algorithm to process coarse grid field strength data. This model can accurately simulate the electromagnetic field distribution of GIS, especially when dealing with complex geometric structures and boundary conditions. In addition, the deep learning network is used to optimize the simulation process, improve the simulation accuracy, and accelerate the simulation process, effectively shortening the design and evaluation cycle, thereby taking into account both the accuracy and efficiency of GIS electromagnetic simulation.

[0098] (4) The generative adversarial network is trained by using the real coarse grid data and the 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 in 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.

[0099] (5) The GraphSAGE algorithm is used to enhance the coarse mesh data of GIS equipment obtained by finite element method simulation. After the GraphSAGE algorithm is used, a new node data generated by the neighboring node update iteration will be obtained between each two adjacent free tetrahedrons in the coarse mesh data, thereby generating more new node data based on the original mesh node data, completing the enhancement and refinement of the mesh node data generated by the simulation calculation.

[0100] (6) When simulating multi-structure GIS equipment, while ensuring accuracy, the time required for simulation will inevitably increase with the fineness of the grid. The present invention first obtains a data solution for a relatively coarse grid through a simulation method, and then enhances the obtained data through a designed grid data enhancement method, thereby achieving a data result that is similar to a simulation of a finer grid, thereby reducing the time cost without sacrificing accuracy as much as possible. Compared with traditional simulation methods, there is a contradiction between time and accuracy when simulating more complex equipment models such as multi-structure GIS equipment. This solution is more adaptable.

[0101] 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

[0102] Figure 1 It is a schematic diagram of a process of a fast and high-precision simulation method for GIS electromagnetic field distribution proposed in the first embodiment of the present invention;

[0103] Figure 2 It is a schematic diagram of a process of enhancing the coarse grid simulation results by using a differential deep learning network model in the second embodiment of the present invention;

[0104] Figure 3 It is a principle block diagram of GIS electromagnetic field coarse grid data enhancement based on differential network in the second embodiment of the present invention;

[0105] Figure 4 is a schematic diagram of the structure of the enhanced network in the differential deep learning network model in the second embodiment of the present invention;

[0106] Figure 5 Schematic diagram of the design principle of the differential convolution module in the second embodiment of the present invention;

[0107] Figure 6 is a schematic diagram of the structure of a structural similarity network in a differential deep learning network model in the second embodiment of the present invention;

[0108] Figure 7 It is a principle block diagram of GIS electromagnetic field simulation data enhancement based on PU-GAN in the third embodiment of the present invention;

[0109] Figure 8 is a schematic diagram of the structure of a generator in a third embodiment of the present invention;

[0110] Fig. 9 is a schematic diagram of the structure of a feature extraction module in a third embodiment of the present invention;

[0111] Fig.10 is a schematic diagram of a structure of a module with similar structure in the third embodiment of the present invention;

[0112] Fig.11 is a schematic structural diagram of a field strength consistency module in a third embodiment of the present invention;

[0113] Fig.12 is a schematic diagram of the structure of a self-attention unit in a third embodiment of the present invention;

[0114] Fig.13 It is a principle block diagram of GIS simulation data enhancement based on GraphSAGE algorithm in the fourth embodiment of the present invention;

[0115] Fig.14 is a schematic diagram of a process for enhancing GIS electromagnetic field coarse grid data in a fourth embodiment of the present invention;

[0116] Fig.15 is a schematic diagram of the principle of implementing two-layer aggregation using the GraphSAGE algorithm in the fourth embodiment of the present invention;

[0117] Fig.16 It is a structural schematic diagram of a fast and high-precision simulator for GIS electromagnetic field distribution proposed in the fifth embodiment of the present invention. DETAILED DESCRIPTION

[0118] 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.

[0119] Embodiment 1

[0120] like Figure 1 As shown, the first embodiment of the present invention proposes a fast and high-precision simulation method for GIS electromagnetic field distribution, the method comprising:

[0121] S101, using a finite-difference time-domain algorithm or a finite element algorithm to numerically solve a three-dimensional simulation model of the GIS equipment to obtain a GIS full-wave electromagnetic coarse grid simulation result, wherein the coarse grid simulation result includes coarse grid structure data and coarse grid field strength data;

[0122] S102, using an enhanced model to perform enhancement processing on the coarse grid simulation result to obtain enhanced fine grid data.

[0123] This embodiment first uses a time-domain finite difference algorithm or a finite element algorithm to numerically solve the three-dimensional simulation model of the GIS equipment, which can quickly obtain a coarse grid simulation result, and uses the coarse grid simulation result as a data basis to perform data enhancement, and obtains fine grid data with enhanced GIS electromagnetic field distribution, that is, high-precision grid data, so that high-precision GIS electromagnetic field distribution data can be quickly obtained.

[0124] As a further preferred technical solution, in step S101, the process of numerically solving the three-dimensional simulation model of the GIS equipment using the finite difference time domain algorithm includes the following steps:

[0125] S111, discretizing the three-dimensional simulation model of the GIS device into a spatial grid, and determining the corresponding relationship between the number and spatial coordinate data of each grid node;

[0126] Specifically, this embodiment discretizes the three-dimensional simulation model of the GIS device into rectangular space grids, and uses the Yee grid concept to number each grid node; and determines the corresponding relationship between the number of each grid node and its spatial coordinate data.

[0127] S112. Convert the Maxwell equations used to describe the electromagnetic field of GIS into a fourth-order matrix, and use the four-step HIE-FDTD algorithm to solve the fourth-order matrix and calculate the field strength data of each grid node.

[0128] As a further preferred technical solution, the step S112: converting the Maxwell equations used to describe the GIS electromagnetic field into a fourth-order matrix, and using a four-step HIE-FDTD algorithm to solve the fourth-order matrix, and calculating the field strength data of each grid node, specifically includes the following steps:

[0129] S1121. Convert the Maxwell equations used to describe the electromagnetic field of GIS into a sixth-order matrix form:

[0130]

[0131] In the formula, is the vector consisting of the components of the electric and magnetic fields in the rectangular coordinate system, ,in:

[0132]

[0133]

[0134]

[0135]

[0136]

[0137]

[0138] in, is a sixth-order matrix, expressed as:

[0139]

[0140] In the formula, is the dielectric constant, is the magnetic permeability.

[0141] S1122, convert the sixth-order matrix form into a fourth-order rectangular form:

[0142]

[0143] In the formula, and The representation forms are:

[0144]

[0145]

[0146] S1123. Use the four-step HIE-FDTD algorithm to solve the fourth-order matrix form and calculate the field strength data of each grid node.

[0147] This embodiment can significantly improve the accuracy and stability of the numerical solution by introducing a higher-order time integration scheme and a space integration scheme. The traditional FDTD method may be affected by numerical dissipation and numerical dispersion, and this embodiment can reduce these problems through a more accurate integration method, which is particularly effective when dealing with long-term simulations or high-frequency electromagnetic wave propagation. For electromagnetic field simulations of complex structures, such as those with media, inhomogeneous media or inhomogeneous structures, this embodiment can better handle these complexities. Its accurate integration and numerical methods can effectively simulate electromagnetic field propagation and interaction between different media.

[0148] Specifically, the step S1123: using a four-step HIE-FDTD algorithm to solve the fourth-order matrix form and calculate the field strength data of each grid node specifically includes:

[0149] The four-step HIE-FDTD algorithm is decomposed into , , , Four steps, including:

[0150] (1) :

[0151]

[0152] (2) :

[0153]

[0154] (3) :

[0155]

[0156] (4) Step by step:

[0157]

[0158] for Step by step: Using semi-implicit difference scheme to introduce auxiliary vectors , keeping the stability condition of the algorithm unchanged, we can get:

[0159]

[0160] in and is the mutual coupling equation, and the substitution method is used to eliminate The tridiagonal implicit equations are as follows:

[0161]

[0162] In the formula, is the point loss parameter of the medium, , , is the time step, represents the electric field components in the x, y, and z directions, The magnetic field components in the x, y, and z directions. The superscripts indicate the time step, e.g. Represents the time step n E x , represents the electric field Ex at the 1 / 4 position between time steps n and n+1, is the sixth-order identity matrix.

[0163] for , the auxiliary vector Substitute the expression into the expansion and get:

[0164]

[0165] for , the auxiliary vector Substitute the expression into the expansion and get:

[0166]

[0167] for , the auxiliary vector Substitute the expression into the expansion and get:

[0168]

[0169] According to the above equations, the components of the electric field and magnetic field in the x, y, and z directions at each step can be solved.

[0170] It should be noted that the simulation calculation results can be obtained through calculation in this embodiment, and the results are shown as the spatial coordinates corresponding to each grid node and the distribution data of the electromagnetic field at that point. Since the coarseness of the simulation grid division is proportional to the calculation accuracy and inversely proportional to the calculation time, in order to resolve the contradiction between accuracy and time, it is necessary to design a real-time enhancement simulation method for grid data to enhance the coarse grid simulation electromagnetic field distribution results and achieve the results of finer grid simulation.

[0171] As a further preferred technical solution, in step S101, the process of numerically solving the three-dimensional simulation model of the GIS equipment using the finite element algorithm specifically includes:

[0172] The simulation model of the GIS equipment is discretized into a plurality of tetrahedral units by using the finite element method, and the GIS full-wave electromagnetic coarse grid simulation result is obtained by simulation, wherein each of the tetrahedral units includes a plurality of nodes.

[0173] It should be noted that, according to the structural parameters of the GIS equipment, this embodiment can use simulation software such as COMSOL Multiphysics to establish a simulation model of three-dimensional data, and discretize the three-dimensional data model into multiple tetrahedral units through the finite element method, and perform simulation calculations to obtain the coarse mesh simulation data to be processed. The results obtained by the simulation calculation are exported to obtain each node Simulation feature data As the feature vector of the node, Represents the three-dimensional space coordinates of the node, Represents the electric field strength of the node.

[0174] Embodiment 2

[0175] Based on the content disclosed in the above embodiment 1, this embodiment specifically uses a differential deep learning network model to enhance the coarse grid simulation results to obtain enhanced fine grid data. The specific implementation process is as follows: Figures 2 to 3 As shown:

[0176] S201, inputting the coarse grid simulation result into a differential deep learning network model, wherein the differential deep learning network model comprises an enhanced network and a structural similarity network connected in sequence, wherein the enhanced network comprises a self-adjusting module and a differential convolution module;

[0177] S202, using the self-adjusting module and the differential convolution module to respectively calculate the coarse grid structure data and the coarse grid field strength data to obtain fine grid enhanced grid structure features and fine grid enhanced field strength features;

[0178] S203, using the structural similarity network to match the fine grid enhanced grid structure feature and the fine grid enhanced field strength feature, and calculating a similarity feature;

[0179] S204: Calculate enhanced fine grid data based on the similarity features.

[0180] This embodiment designs and constructs a differential deep learning network model, in which convolution combined with a differential algorithm is used to process coarse grid field strength data, which can accurately simulate the electromagnetic field distribution of GIS, especially when dealing with complex geometric structures and boundary conditions; and uses a deep learning network to optimize the simulation process, improve the simulation accuracy, and accelerate the simulation process, effectively shortening the design and evaluation cycle, thereby taking into account both the accuracy and efficiency of GIS electromagnetic simulation.

[0181] As a further preferred technical solution, Figure 4 As shown, the self-adjusting module includes a first convolutional layer Conv1 and a second convolutional layer Conv2 connected in sequence, and the outputs of the first convolutional layer Conv1 and the second convolutional layer Conv2 are connected through a first addition operation and then output to the activation function layer;

[0182] The coarse grid structure data is used as the input of the first convolution layer Conv1, the grid size supplementary information of the coarse grid structure data is used as the input of the second convolution layer Conv2, the deviation vector of the coarse grid structure data is used as the input of the first addition operation, and the coarse grid structure data and the grid size supplementary information of the coarse grid structure data are connected via residual Output to the first adding operation.

[0183] It should be noted that this embodiment realizes the refined enhancement of the coarse grid structure data by designing a self-adjusting module. The self-adjusting module realizes the refined enhancement of the electromagnetic field coarse grid data of the GIS equipment by combining convolution operations, residual connections and sigmoid activation functions. This method not only improves the detail expression of the grid data, but also can adaptively adjust the enhancement strategy according to the original grid data through the self-adjusting mechanism, thereby ensuring the accuracy and adaptability of the enhanced grid structure.

[0184] As a further preferred technical solution, the function of the self-adjusting module is to perform fine enhancement of the grid structure. GIS equipment electromagnetic field coarse grid data Input the self-adjusting module in the enhancement module to obtain the fine grid enhancement grid structure characteristics , the formula is:

[0185]

[0186] In the formula, Enhance the mesh structure features for fine meshes, represents the grid-enhanced convolution operation, represents the fine-tuning convolution operation, is the coarse grid structure data, Supplementary information for the grid size of the coarse grid structure data, is the deviation vector of the coarse grid structure data, is the residual link, is the activation function.

[0187] As a further preferred technical solution, Figure 4 As shown, the differential convolution module includes differential convolution layers connected in sequence , Size Integration Layer , self-attention mechanism layer And the third convolutional layer Conv3, the third convolutional layer Conv3 is connected with Activation function;

[0188] The coarse grid field strength data is used as the differential convolution layer The input of the differential convolution layer Used to calculate field intensity characteristics of different sizes of the coarse grid field intensity data by using a differential algorithm;

[0189] The size integration layer Used to sum the field intensity features of different sizes calculated by the differential convolution layer to obtain a reshaped field intensity feature;

[0190] The reshaped field strength features are passed through the self-attention mechanism layer , after the third convolutional layer Conv3, the fine grid enhanced field strength features are output.

[0191] It should be noted that this embodiment designs a differential convolution module for accurate extraction of field intensity data. The differential convolution module can accurately extract electromagnetic field intensity features through specially designed differential convolution operations, effectively simulate the physical distribution of the electromagnetic field, and combine the self-attention mechanism. This module can highlight important field intensity features and improve the extraction accuracy of field intensity data and the attention concentration of the model. And by extracting and summing features with convolution kernels of different sizes, it is possible to capture the multi-scale features of electromagnetic field data, which is particularly important for understanding and simulating the complex changes of electromagnetic fields. This method improves the generalization ability of the model, enabling it to better adapt to changes in electromagnetic fields of different scales.

[0192] As a further preferred technical solution, the convolution kernel of the differential convolution layer adopts any one of a five-point differential convolution kernel, a weighted differential convolution kernel, a multi-scale differential convolution kernel, a directional differential convolution kernel, a nine-point differential convolution kernel, and a mixed mode differential convolution.

[0193] It should be noted that those skilled in the art may also select other differential algorithms to be combined with the deep learning network according to actual application requirements, and this embodiment does not specifically limit this.

[0194] Further, taking the five-point difference as an example, Figure 5 As shown, the differential convolution layer The design is as follows:

[0195] Design the basic convolution kernel based on the five-point difference algorithm :

[0196]

[0197] Considering the data enhancement for 3D GIS electromagnetic field simulation, the dimensionality transformation kernel Get the three-dimensional difference convolution kernel :

[0198]

[0199]

[0200] Among them, ⊙ represents the corresponding multiplication of elements.

[0201] Using 3D differential convolution kernel Extraction of coarse grid field intensity gradient information (extracting coarse grid electromagnetic field gradient changes to guide fine grid data generation):

[0202]

[0203] Among them, ∗ represents the convolution operation, For application The gradient information data obtained later;

[0204] The coarse grid field intensity data is enhanced by upsampling to obtain the upsampled fine grid field intensity data U (obtaining refined coarse grid data):

[0205]

[0206] in, The upsampling convolution kernel is obtained with network training;

[0207] Combined with the coarse grid field intensity gradient information G, preliminary fine grid field intensity data is obtained

[0208] .

[0209] This embodiment directly uses the form of the differential algorithm to define the convolution kernel, ensuring that the physical principles can be accurately mapped to the convolution operation. This is achieved by taking the core calculation formula of the differential algorithm and converting it into the form of the convolution kernel, thereby ensuring the correct application of continuous physical laws to discrete data. In addition, this embodiment takes scale transformation into account when designing the differential convolution kernel, allowing the electromagnetic field to be analyzed at different resolutions. By adjusting the size and shape of the convolution kernel, different physical resolutions can be simulated to capture multi-scale features.

[0210] By extending the two-dimensional convolution kernel to three-dimensional space through a certain transformation, the key step of applying the traditional differential method to the three-dimensional GIS electromagnetic field simulation is that this dimensional transformation takes into account the physical effects in each direction in the three-dimensional space. The rotational invariance problem can be solved by designing a symmetrical three-dimensional convolution kernel. A symmetrical kernel will produce a consistent response in all directions, which can solve the isotropy problem in electromagnetic field simulation.

[0211] It should be noted that the special differential convolution operation designed in this implementation is based on a method for solving numerical partial differential equations, such as the five-point difference method, which is often used to approximate the solution of partial differential equations in numerical analysis. In deep learning, traditional convolution layers are usually used to extract features of input data, while special differential convolution kernels can be designed to be more suitable for the simulation of specific physical phenomena, such as electromagnetic field simulation. The design of such convolution kernels is usually based on the discrete approximation of the second-order derivative of the function space in the differential algorithm, so that the network can capture the physical characteristics of the data while learning the data.

[0212] Compared with traditional convolutional layers, differential convolution can maintain high-quality data while ensuring that the data conforms to specific physical laws, making the data generated by the network more physically credible. This combination makes the model perform better when dealing with problems that require precise physical modeling, such as electromagnetic field simulation and climate change simulation.

[0213] Furthermore, the function of the differential convolution module set in this embodiment is to obtain accurate fine grid field strength data, and use the differential convolution module to Coarse grid field strength data of electromagnetic field of GIS equipment Processing is performed to obtain the fine grid enhanced field strength characteristics , the formula is:

[0214]

[0215]

[0216]

[0217] In the formula, is the field intensity feature generated by differential convolution, is the differential convolution operation, is the coarse grid field strength data, is the field strength characteristic after reorganization, Indicates the application of convolution kernels of different sizes. Enhance the field strength characteristics for the fine grid, For the self-attention mechanism operation, is the convolution operation, is the activation function.

[0218] Furthermore, this embodiment optimizes the computational efficiency and accuracy of the simulation by combining the self-adjusting module and the differential convolution module. The self-adjusting module reduces unnecessary calculations through intelligent enhancement strategies, while the differential convolution module ensures high-precision extraction of field strength data. The two work together to achieve efficient and accurate electromagnetic field simulation. In general, the design and implementation of the self-adjusting module and the differential convolution module greatly improve the accuracy, efficiency and applicability of GIS electromagnetic field simulation through intelligent enhancement, precise feature extraction and efficient calculation methods.

[0219] As a further preferred technical solution, Figure 6 As shown, the structural similarity network includes a first branch network, a second branch network, a second addition operation and a first multilayer perceptron, the outputs of the first branch network and the second branch network are both connected to the second addition operation, and the output of the second addition operation is connected to the first multilayer perceptron , the multilayer perceptron Followed by an activation function .

[0220] Specifically, the first branch network includes a convolutional neural network layer CNN and a batch normalization operation connected in sequence. , the regularization operation Then there is an activation function ;

[0221] The second branch network includes a second multilayer perceptron , the second multi-layer perceptron Then there is an activation function .

[0222] Furthermore, the function of the structural similarity network is to match the enhanced grid data with the field strength data for the first The fine grid structure characteristics of the electromagnetic field of GIS equipment with coarse grid number Enhanced field strength characteristics with fine grids The field strength and structural characteristics of:

[0223]

[0224]

[0225]

[0226]

[0227] In the formula, For the Extraction information of fine grid structure features corresponding to the coarse grid number of electromagnetic field of GIS equipment; For the Extraction information of the fine grid-enhanced field strength characteristics corresponding to the coarse grid number of the electromagnetic field of the GIS equipment; and Respectively represent the fine grid enhanced grid structure feature extraction information Enhanced field strength feature extraction information with fine grid The modulation weight of It is the comprehensive feature of information extraction of fine grid enhanced grid structure feature and fine grid enhanced field strength feature; For similarity characteristics; is the batch normalization operation, is the convolution operation, is a multi-layer perceptron of the structural similarity module, It is the combined characteristic of field strength and structure.

[0228] It should be noted that the functions of the structural similarity network designed in this embodiment are: (1) Preserving physical structure: The structural similarity module ensures that the enhanced data retains its physical accuracy while maintaining structural integrity and coherence by focusing on the structural properties of the data. This is particularly important in the field of simulation because the physical behavior of the electromagnetic field strongly depends on its spatial structural characteristics. (2) Improving the quality of data enhancement: This module helps to generate higher quality data, especially in restoration and super-resolution tasks, and can ensure that the details of the generated data have a high structural similarity with the original coarse grid data. (3) Enhanced feature representation: The structural similarity module provides an effective mechanism to enhance and significantly characterize key features in electromagnetic field data, especially in terms of field strength and grid structure, by fusing features extracted by CNN and MLP.

[0229] As a further preferred technical solution, the step S204: calculating GIS fine grid enhancement data based on the similarity features, specifically includes the following steps:

[0230] S241, calculating regularized coarse grid structure data, regularized coarse grid field intensity data, regularized fine grid enhanced grid structure characteristics, and regularized fine grid enhanced field intensity characteristics based on the coarse grid structure data, the coarse grid field intensity data, the fine grid enhanced grid structure characteristics, and the fine grid enhanced field intensity characteristics, respectively;

[0231] It should be noted that this embodiment specifically uses a field strength consistency module to process the coarse grid structure data, the coarse grid field strength data, the fine grid enhanced grid structure features, the fine grid enhanced field strength features and the similarity features, so as to converge the difference between the fine grid enhanced data and the coarse grid data.

[0232] Use the following formula to calculate the Electromagnetic field fine grid enhancement grid structure characteristics of strip GIS equipment and fine grid enhanced field strength characteristics With GIS equipment electromagnetic field coarse grid data and coarse grid field strength data Fine grid enhanced data after comprehensive compensation :

[0233]

[0234]

[0235]

[0236]

[0237] In the formula, , , and They are regularized electromagnetic field fine grid enhanced grid structure characteristics, regularized fine grid enhanced field strength characteristics, regularized electromagnetic field coarse grid data and regularized coarse grid field strength data; is the matrix 2-norm.

[0238] S242, calculating grid structure consistency based on the regularized coarse grid structure data and the regularized fine grid enhanced grid structure features;

[0239] Specifically, the calculation formula for grid structure consistency is:

[0240]

[0241] In the formula, The grid structure is consistent.

[0242] S243, calculating grid field intensity consistency based on the regularized coarse grid field intensity data and the regularized fine grid enhanced field intensity characteristics;

[0243] Specifically, the calculation formula for grid field strength consistency is:

[0244]

[0245] In the formula, is the grid field strength consistency.

[0246] S244, calculating grid field strength loss compensation based on the grid structure consistency and the grid field strength consistency;

[0247] Specifically, the calculation formula for grid field strength loss compensation is:

[0248]

[0249] In the formula, Compensate for grid field strength loss.

[0250] S245, calculating fine grid enhancement structure data based on the fine grid enhancement grid structure characteristics, the grid field strength loss compensation and the similarity characteristics;

[0251] Specifically, the calculation formula for fine grid enhanced structure data is:

[0252]

[0253] In the formula, Enhance structural data for fine meshes.

[0254] S246, calculating fine grid enhanced field strength data based on the fine grid enhanced field strength characteristics, the grid field strength loss compensation and the similarity characteristics;

[0255] Specifically, the calculation formula for fine grid enhanced field strength data is:

[0256]

[0257] In the formula, Enhance field strength data for fine grids; and is the scale factor.

[0258] As a further preferred technical solution, the differential deep learning network model used in this embodiment is a pre-trained model that can be used to calculate the similarity between the grid structure and the grid field strength. Before the step S201: inputting the coarse grid simulation result into the differential deep learning network model, the method further includes the following steps:

[0259] A GIS electromagnetic field coarse grid historical simulation data set is used, and the differential deep learning network model is trained using the historical simulation data set until the total loss function of the model is minimized, wherein the total loss function includes a constraint loss function based on Maxwell's equations and a field strength and structural consistency loss function, and the formula is expressed as:

[0260]

[0261] In the formula, is the total loss function, is the field strength and structure consistency loss function, is the Maxwell constraint loss function, and is the weight parameter.

[0262] It should be noted that this embodiment has carried out a multi-dimensional loss function design. By combining structural similarity loss, field strength consistency loss and physical constraint loss, multiple important characteristics of simulation data are comprehensively considered. The design of this multi-dimensional loss function is beneficial to ensure the accuracy of the simulation while being able to adjust the weights between different losses to adapt to specific simulation needs and optimization goals.

[0263] Furthermore, the formula of the field strength and structure consistency loss function is expressed as:

[0264]

[0265]

[0266]

[0267] In the formula, represents the gradient obtained by applying the difference method, is the structural similarity loss, is the field strength consistency loss, and is the scale factor, Enhance the mesh structure features for fine meshes, is the coarse grid structure data, To enhance the field strength characteristics for fine grids, is the coarse grid field strength data, is the 2-norm of the vector.

[0268] It should be noted that this embodiment ensures that the enhanced electromagnetic field data is highly consistent with the original data in structure and field strength through structural similarity loss and field strength consistency loss. This consistency not only promotes the convergence of simulation data, but also ensures the physical authenticity of simulation results and improves the reliability of simulation.

[0269] And by introducing the scaling factor, a flexible loss function adjustment mechanism is provided. This mechanism can not only adjust the importance of different parts of the loss function according to specific tasks, but also improve the generalization ability and adaptability of the model when processing different types of electromagnetic field data.

[0270] Furthermore, the formula of the constraint loss function based on Maxwell equations is expressed as:

[0271]

[0272]

[0273]

[0274]

[0275]

[0276]

[0277] In the formula, is the magnetic field component, is the Gaussian law loss, is Gauss's magnetic law loss, is the loss due to Faraday's law of electromagnetic induction, is the Ampere's law loss, The proportionality constant, , , , is the scale factor, represents the curl, is the vector 2 norm; is the magnetic permeability of vacuum, is the permittivity of vacuum, It is the fine grid enhanced field strength data.

[0278] It should be noted that the physical constraint loss function ensures that the enhanced electromagnetic field data strictly follows the basic laws of electromagnetism through the key components of Maxwell's equations - Gauss's law, Gauss's law of magnetism, Faraday's law of electromagnetic induction, and Ampere's law. This constraint makes the electromagnetic field data output by the model not only numerically accurate, but also strict in physical laws, which increases the scientificity and practicality of the model.

[0279] It should be noted that when the differential method is combined with the generative adversarial network to form a differentially enhanced generative adversarial network, the differential convolution kernel is directly integrated into the generator architecture, thereby introducing differential enhancement of spatial features. The adversarial here is mainly reflected in the loss of the model, that is, when using the generative adversarial network, the total loss function of the model includes not only the physical constraint loss function and the field strength and structural consistency loss function, but also the adversarial loss part.

[0280] In summary, the loss function designed in this embodiment combines the advantages of traditional physical models and deep learning. Through precise mathematical expressions and physical constraints, it helps to optimize the stability and convergence speed of the algorithm and improve training efficiency. The total loss function combines electromagnetic field theory and deep learning technology, which not only enhances the model's ability to process electromagnetic field simulation data, but also ensures the accuracy and physical authenticity of the simulation results, providing an effective optimization strategy for electromagnetic field simulation.

[0281] Embodiment 3

[0282] Based on the content disclosed in the above embodiment 1, this embodiment specifically adopts a generative adversarial network model to enhance the coarse grid simulation results to obtain enhanced fine grid data. Figure 7 As shown:

[0283] The enhancement model adopts a generative adversarial network model, which includes a generator and a discriminator. The generator is used to extract features from the coarse grid simulation results and perform cyclic multiple enhancement on the extracted features to obtain enhanced fine grid data.

[0284] The discriminator includes a structural similarity module, a field strength consistency module and an accuracy discrimination module, wherein:

[0285] The structural similarity module is used to calculate a first confidence value of structural information contained in the enhanced fine grid data and the real fine grid data obtained by simulation;

[0286] The field intensity consistency module is used to calculate a second confidence value of the field intensity information contained in the enhanced fine grid data and the real fine grid data obtained by simulation;

[0287] The accuracy determination module is used to shorten the distance between the enhanced fine grid data and the real fine grid data distribution obtained by simulation.

[0288] It should be noted that in this embodiment, the real coarse grid data and the real fine grid data are input into the generative adversarial network for training in advance until the overall optimization loss function is minimized, and the trained generator is used as a data enhancement model to enhance the real coarse grid data generated in real time, wherein the generator network is responsible for learning the potential distribution characteristics of the real samples and synthesizing new samples; the role of the discriminator network is to distinguish between the real samples and the generated new samples. The generator and the discriminator achieve the adversarial effect through alternating training, continuously improving their respective generation and discrimination capabilities, and finally making the adversarial generator network and the discriminator network reach a Nash equilibrium.

[0289] Among them, 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.

[0290] 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.

[0291] As a further preferred technical solution, Figure 8 As shown, the generator includes several cascaded feature extraction and expansion networks, each of which is connected to a multi-layer perceptron;

[0292] 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;

[0293] like Fig. 9 As shown, the feature extraction module Featur 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 coarse grid simulation result 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 coarse grid simulation result 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;

[0294] 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.

[0295] It should be noted that the function of the generator designed in this embodiment is to enhance the GIS coarse grid data 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.

[0296] Specifically, the working process of the feature extraction module in this embodiment is as follows: first, the three-dimensional space coordinates of each sampling point are input and field strength values The N×4-dimensional information composed of the information is extracted as a fixed-scale feature C' through the first MLPs layer, and then the features are grouped into N×K groups using the KNN layer, and the group features are further optimized using 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 as a module multi-scale feature aggregation to improve the reconstruction accuracy while also improving the parameter efficiency and reducing the model size. Under the compression of the last layer of data compression layer compression, N×C features are obtained. After the obtained N×C features are copied, 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.

[0297] 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 MLP. .

[0298] It should be noted that The value of depends on the accuracy difference between the input simulation coarse grid and fine grid, which is not specifically limited in this embodiment.

[0299] Specifically, different modules target data accuracy. If the previous feature needs to be passed to the next layer, good interpolation technology is required 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, interpolation technology is used to match the features of different levels.

[0300] 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:

[0301]

[0302] in, It is The coordinates and field strength of the points, It is The coordinates and field strength of the points, 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:

[0303]

[0304]

[0305] Among them, the width parameter and is the average distance from a point to its nearest neighbor, Represents the magnitude of a vector.

[0306] 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.

[0307] As a further preferred technical solution, Fig.10 As 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;

[0308] 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.

[0309] Specifically, Fig.10 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:

[0310]

[0311]

[0312]

[0313] 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.

[0314] Specifically, Fig.10 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.

[0315] As a further preferred technical solution, Fig.11 As 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;

[0316] 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.

[0317] 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:

[0318]

[0319]

[0320]

[0321] 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.

[0322] 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.

[0323] As a further preferred technical solution, Fig.12 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:

[0324] M

[0325] in, Represents the softmax function.

[0326] 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.

[0327] 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.

[0328] The adversarial loss between the fine mesh generated data and the true fine mesh data is defined as follows:

[0329]

[0330] 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 .

[0331] As a further preferred technical solution, the formula of the overall optimization loss function is expressed as:

[0332]

[0333] 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.

[0334] 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 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.

[0335] Embodiment 4

[0336] Based on the content disclosed in the first embodiment, this embodiment enhances the coarse grid simulation result obtained by numerically solving the three-dimensional simulation model of the GIS equipment using the finite element method, such as Figure 13 to Figure 14 As shown, the following steps are included:

[0337] S301. Abstract the simulation model of GIS equipment into a network topology structure , and any two adjacent free tetrahedrons in the network topology are regarded as a sheet unit, where Represents a collection of nodes. Represents an edge set, where the lines between mesh vertices are considered edges;

[0338] Specifically, in order to adopt a fixed-size neighbor set, this embodiment regards any two adjacent free tetrahedrons M and N as a sheet unit, and the free tetrahedron M and the free tetrahedron N respectively include nodes A, B, C, D and nodes B, C, D, E. Among them, the two adjacent free tetrahedrons have three repeated nodes, namely nodes B, C, and D.

[0339] S302, using the coarse grid simulation result as the initial benchmark feature, using the GraphSAGE algorithm to perform an aggregation process on the neighbor nodes of each node in each slice unit, and generating the initial benchmark feature of the newly added node;

[0340] It should be noted that when the present embodiment uses the GraphSAGE algorithm to perform aggregation once, the information of the adjacent nodes of all nodes in each slice unit is aggregated, so that a new node is generated for the overlapping faces of any two adjacent tetrahedrons.

[0341] S303, using the GraphSAGE algorithm to perform secondary aggregation processing on the neighboring nodes of the newly added node to generate a feature vector representation of the newly added node.

[0342] It should be noted that, for the newly added nodes generated by the overlapping faces of any two adjacent free tetrahedrons, each node in the sheet unit composed of the two free tetrahedrons can be used as the neighbor nodes of the newly added node. The GraphSAGE algorithm is used to perform secondary aggregation processing on the neighbor nodes of the newly added node to generate a feature vector representation of the newly added node, that is, the three-dimensional spatial coordinate data and electric field strength of the newly added node are obtained, thereby generating more new node data based on the original grid node data, completing the enhanced refinement of the grid node data generated by the simulation calculation.

[0343] In detail, in the GraphSAGE algorithm, random sampling of neighbor nodes is usually used to update the representation of the target node. However, in GIS simulation, the selection of neighbor nodes needs to consider more factors, such as the physical distance between nodes, the similarity of nodes, etc. Therefore, this embodiment regards two free tetrahedral units as a sheet unit, and aggregates the neighbors of the newly added node in a sheet unit, so that the similarity and correlation between nodes are higher. At the same time, considering that there are many types of node features in GIS simulation data, the spatial coordinates and electric field strength of the node are used as node features, which is more in line with the data connection of GIS simulation. In addition, this embodiment adjusts the depth of the model of the GraphSAGE algorithm, that is, the number of aggregation layers, according to the complexity and scale of GIS simulation data, and improves the algorithm's ability to express data in order to obtain better performance.

[0344] As a further preferred technical solution, Fig.15 As shown, the step S302: using the simulation feature data of the node as the initial benchmark feature, using the GraphSAGE algorithm to perform an aggregation process on the neighbor nodes of each node in each slice unit to generate the benchmark feature of the newly added node, includes the following steps:

[0345] S321, using the simulation feature data of each node as the initial reference feature of each node;

[0346] S322, traverse each node in each of the slice units , taking all the adjacent nodes of each node as sampling points, obtain the node The neighbor set of , and use the aggregation function to aggregate nodes Corresponding to the initial baseline features of all nodes in the neighbor set, an aggregated neighbor feature is obtained ;

[0347] Specifically, each node in the network topology ( ) is the characteristic vector of the simulation feature data as the reference feature corresponding to each node For each slice unit, traverse each node in the slice unit in the first aggregation ( ), for the node , first get its neighbor set ,node The feature vector of .

[0348] Specifically, the nodes are aggregated using the aggregation function through the aggregator Corresponding to the initial baseline features of all nodes in the neighbor set, an aggregated neighbor feature is obtained for:

[0349]

[0350] In the formula, Represents an aggregate function.

[0351] S323, connecting the initial reference feature and the aggregated neighbor feature Get the first joint feature, perform matrix multiplication on the first weight matrix and the first joint feature, and then use a nonlinear transformation to get the node feature after one traversal ;

[0352] Specifically, this embodiment uses the feature of each node after a traversal As the new feature vector representation of the node, and as the benchmark feature of each node in the secondary traversal process, where:

[0353]

[0354] In the formula, is the concatenation function, is the first weight matrix, yes function.

[0355] Furthermore, in this embodiment, the aggregation function uses the average aggregation function MEAN ,Right now .

[0356] S324. Use an aggregation function to aggregate the initial reference features of the common nodes of the two free tetrahedrons in each sheet unit to obtain the initial reference features of the newly added nodes.

[0357] Specifically, since the newly added node generated by the common face of two adjacent free tetrahedrons has no initial reference feature, this embodiment aggregates the initial reference features of the common nodes of the two adjacent free tetrahedrons using an aggregation function to obtain the initial reference feature of the newly added node P. , the formula is:

[0358]

[0359] In the formula, is the initial datum feature of the common node of two adjacent free tetrahedrons,

[0360] Furthermore, the aggregation function in this embodiment adopts the average aggregation function, so .

[0361] As a further preferred technical solution, step S303: using the GraphSAGE algorithm to perform secondary aggregation processing on the neighbor nodes of the newly added node to generate a feature vector representation of the newly added node includes the following steps:

[0362] S331, the node features after a traversal As a new benchmark feature for the corresponding node;

[0363] S332, each node in each of the slice units As the neighbor sampling point of the newly added node, and using the aggregation function to aggregate the new benchmark features of all nodes in each slice unit, obtain the secondary aggregated neighbor feature ;

[0364] Specifically, this embodiment converts all nodes in the slice unit into The neighbor set of the newly added node generated by the slice unit , through the second aggregator, the aggregation function is used to aggregate the new baseline features of all nodes in the neighbor set, that is, ( ), get the aggregated neighbor features , the formula is:

[0365]

[0366] In the formula, is an aggregate function, is the new reference feature for each node in the sheet element.

[0367] S333, connecting the initial reference feature of the newly added node and the secondary aggregated neighbor feature to obtain a second joint feature, performing a matrix multiplication operation on the second weight matrix and the second joint feature, and then performing a nonlinear transformation to obtain a feature vector representation of the newly added node.

[0368] Specifically, the feature vector of the newly added node obtained in this embodiment is expressed as:

[0369]

[0370] In the formula, is the concatenation function, is the second weight matrix, yes function.

[0371] Furthermore, since there is no natural order for the neighbors of a node, the aggregator in this embodiment Using the average aggregation function, we have Thus, a new node feature vector will be generated between any sheet unit, that is, the three-dimensional space coordinates and electric field strength of the new node, thereby enhancing the grid node data of GIS finite element method simulation.

[0372] As a further preferred technical solution, the complexity of the GraphSAGE algorithm used in this embodiment is:

[0373]

[0374] in, It is the number of aggregators, the number of weight matrices, and the number of layers in the network. Aggregators , used to aggregate node neighbor information, and Weight matrix , used to propagate information between different layers. In order to achieve better sampling aggregation effect, , and perform two polymerizations.

[0375] As a further preferred technical solution, in this embodiment, the sampling of nodes is of fixed length. Indicates The number of sampling neighbors of the layer is defined in advance. , repeated sampling or negative sampling method with replacement is used to ensure that the complexity becomes stable. When the number of defined sampling neighbors is greater than the actual number of neighbors, repeated sampling is used to make up the actual number of sampling neighbors. ; When the number of defined sampled neighbors is less than the actual number of neighbors, negative sampling is used to reduce the actual number of sampled neighbors to .

[0376] Embodiment 5

[0377] like Fig.16 As shown, the fifth embodiment of the present invention proposes a fast and high-precision simulator for GIS electromagnetic field distribution, wherein the simulator comprises a processor, a memory and a network interface connected via a system bus, wherein the memory may include a non-volatile storage medium and an internal memory. The non-volatile storage medium may store an operating system and a computer program. The computer program includes program instructions, and when the program instructions are executed, the processor may execute any one of the fast and high-precision simulation methods for GIS electromagnetic field distribution in the above-mentioned embodiments 1, 2, 3 and 4.

[0378] Among them, the processor is used to provide computing and control capabilities to support the operation of the entire computer equipment.

[0379] The internal memory provides an environment for the operation of the computer program in the non-volatile storage medium. When the computer program is executed by the processor, the processor can execute any method for determining the corrected geometric factor of the quantum radar.

[0380] The network interface is used for network communication, such as sending assigned tasks, etc. Those skilled in the art will understand that Fig.16 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0381] It should be understood that the processor may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0382] Embodiment 6

[0383] The sixth embodiment of the present invention proposes a multi-structure adaptive GIS field-electric fusion real-time status perception and early warning system, the system includes a signal synchronization acquisition and measurement embedded device and an industrial computer, the industrial computer is provided with a simulator as described in the above embodiment five, the simulator is connected to the signal synchronization acquisition and measurement embedded device, the signal synchronization acquisition and measurement embedded device is used to collect the time domain full waveform data of GIS local discharge, the simulator is used to obtain enhanced fine grid data based on the time domain full waveform data, and the industrial computer is used to search for the actual discharge position of the GIS local discharge source based on the time domain full waveform data and the enhanced fine grid data.

[0384] It should be noted that other embodiments or implementation methods of the simulator described in the present invention can refer to the above-mentioned method embodiments and will not be described in detail here.

[0385] Embodiment 7

[0386] The sixth embodiment of the present invention further proposes a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the method for rapid and high-precision simulation of GIS electromagnetic field distribution as described in any of the above embodiments is implemented.

[0387] It should be noted that the logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples (non-exhaustive list) of computer-readable media include the following: an electrical connection portion with one or more wirings (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.

[0388] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0389] 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.

[0390] 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.

[0391] 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 fast and high-precision simulation method for GIS electromagnetic field distribution, characterized in that: The method comprises: A finite-difference time-domain algorithm or a finite element algorithm is used to numerically solve a three-dimensional simulation model of the GIS equipment to obtain a GIS full-wave electromagnetic coarse-grid simulation result, wherein the coarse-grid simulation result includes coarse-grid structure data and coarse-grid field strength data; The coarse grid simulation results are enhanced by using an enhancement model to obtain enhanced fine grid data, wherein the enhancement model adopts a differential deep learning network model or a generative adversarial network model, the differential deep learning network model includes an enhancement network and a structural similarity network connected in sequence, the enhancement network includes a self-adjusting module and a differential convolution module; the generative adversarial network model includes a generator and a discriminator, the generator is used to extract features from the coarse grid simulation results, and cyclically enhance the extracted features to obtain enhanced fine grid data; the discriminator includes a structural similarity module, a field strength consistency module and an accuracy discrimination module.

2. The rapid and high-precision simulation method for GIS electromagnetic field distribution according to claim 1 is characterized in that: The process of numerically solving the three-dimensional simulation model of GIS equipment using the finite difference time domain algorithm includes: Discretize the three-dimensional simulation model of GIS equipment into spatial grids, and determine the corresponding relationship between the number and spatial coordinate data of each grid node; The Maxwell equations used to describe the electromagnetic field of GIS are converted into a fourth-order matrix, and the four-step HIE-FDTD algorithm is used to solve the fourth-order matrix and calculate the field strength data of each grid node.

3. The rapid and high-precision simulation method for GIS electromagnetic field distribution according to claim 2 is characterized in that: The Maxwell equations used to describe the GIS electromagnetic field are converted into a fourth-order matrix, and the fourth-order matrix is ​​solved using a four-step HIE-FDTD algorithm to calculate the field strength data of each grid node, including: The Maxwell equations used to describe the electromagnetic field of GIS are converted into a sixth-order matrix form: In the formula, is the vector consisting of the components of the electric and magnetic fields in the rectangular coordinate system, is a sixth-order matrix; Convert the sixth-order matrix form to a fourth-order rectangular form: In the formula, and is a sixth-order matrix; The four-step HIE-FDTD algorithm is used to solve the fourth-order matrix form and calculate the field intensity data of each grid node.

4. The rapid and high-precision simulation method for GIS electromagnetic field distribution according to claim 3 is characterized in that: The four-step HIE-FDTD algorithm is used to solve the fourth-order matrix form and calculate the field strength data of each grid node, including: The four-step HIE-FDTD algorithm is decomposed into , , , Four sub-steps, for each sub-step, a semi-implicit difference scheme is used to calculate the three diagonal implicits of the field strength data of the grid nodes, where n represents the time step; The pursuit method is used to solve the three diagonal implicit equations and obtain the grid node field strength data.

5. The rapid and high-precision simulation method for GIS electromagnetic field distribution according to claim 1 is characterized in that: The enhanced model adopts a differential deep learning network model, the differential deep learning network model includes an enhanced network and a structural similarity network connected in sequence, and the enhanced network includes a self-adjusting module and a differential convolution module; the method includes: The self-adjusting module and the differential convolution module are used to calculate the coarse grid structure data and the coarse grid field strength data respectively to obtain fine grid enhanced grid structure characteristics and fine grid enhanced field strength characteristics; Using the structural similarity network, the fine grid enhanced grid structure feature and the fine grid enhanced field strength feature are matched to calculate a similarity feature; Based on the similarity features, enhanced fine grid data is calculated.

6. The rapid and high-precision simulation method for GIS electromagnetic field distribution according to claim 5 is characterized in that: The self-adjusting module includes a first convolutional layer and a second convolutional layer connected in sequence, and the output features of the first convolutional layer and the output features of the second convolutional layer are output to the activation function layer after a first addition operation; The coarse grid structure data is used as the input of the first convolutional layer, the grid size supplementary information of the coarse grid structure data is used as the input of the second convolutional layer, the bias vector of the coarse grid structure data is used as the input of the first addition operation, and the coarse grid structure data and the grid size supplementary information of the coarse grid structure data are output to the first addition operation via residual connection.

7. The rapid and high-precision simulation method for GIS electromagnetic field distribution according to claim 5, characterized in that: The differential convolution module includes a differential convolution layer, a size integration layer, a self-attention mechanism layer and a third convolution layer connected in sequence, and an activation function is connected after the third convolution layer; The coarse grid field intensity data is used as the input of the differential convolution layer, and the differential convolution layer is used to calculate the field intensity features of different sizes of the coarse grid field intensity data by using a differential algorithm; The size integration layer is used to sum the field intensity features of different sizes calculated by the differential convolution layer to obtain the reorganized field intensity features.

8. The rapid and high-precision simulation method for GIS electromagnetic field distribution according to claim 7 is characterized in that: The convolution kernel of the differential convolution layer adopts any one of a five-point differential convolution kernel, a weighted differential convolution kernel, a multi-scale differential convolution kernel, a directional differential convolution kernel, a nine-point differential convolution kernel, and a mixed mode differential convolution.

9. The rapid and high-precision simulation method for GIS electromagnetic field distribution according to claim 5, characterized in that: The structural similarity network includes a first branch network, a second branch network, a second addition operation and a first multilayer perceptron, the outputs of the first branch network and the second branch network are both connected to the second addition operation, the output of the second addition operation is connected to the first multilayer perceptron, and the multilayer perceptron is followed by an activation function.

10. The GIS electromagnetic field distribution fast and high-precision simulation method according to claim 9, characterized in that: The first branch network includes a convolutional neural network layer CNN and a batch normalization operation connected in sequence, and the regularization operation is followed by an activation function; The second branch network includes a second multilayer perceptron, and the second multilayer perceptron is followed by an activation function.

11. The GIS electromagnetic field distribution fast and high-precision simulation method according to claim 10, characterized in that: The using the structural similarity network to match the fine grid enhanced grid structure feature and the fine grid enhanced field strength feature to calculate the similarity feature includes: The structural feature information of the fine grid enhanced grid structure feature is extracted by using the first branch network, and the formula is expressed as: In the formula, For the The fine grid enhances the characteristic information of the grid structure characteristics, Enhance the grid structure characteristics for the fine grid, is a stacked convolution operation, is the batch normalization operation, is the activation function; The second branch network is used to extract the field intensity feature information of the fine grid enhanced field intensity feature, and the formula is expressed as: In the formula, For the The characteristic information of the fine grid enhanced field strength characteristics, Enhance the field strength characteristics for the fine grid, Operations performed by the second multilayer perceptron; The field strength and structure combination feature is calculated by using the modulation weights corresponding to the feature information of the fine grid enhanced grid structure feature and the feature information of the fine grid enhanced field strength feature. The formula is expressed as: In the formula, is the field strength and structure combination feature, and The modulation weights corresponding to the feature information of the fine grid enhanced grid structure feature and the feature information of the fine grid enhanced field strength feature are respectively represented; Based on the field strength and structure combination characteristics, the similarity characteristics are calculated, and the formula is expressed as: In the formula, For the similarity feature, Operations performed by the first multilayer perceptron.

12. The GIS electromagnetic field distribution fast and high-precision simulation method according to claim 5, characterized in that: The step of calculating enhanced fine grid data based on the similarity feature comprises: Calculating regularized coarse grid structure data, regularized coarse grid field intensity data, regularized fine grid enhanced grid structure characteristics, and regularized fine grid enhanced field intensity characteristics based on the coarse grid structure data, the coarse grid field intensity data, the fine grid enhanced grid structure characteristics, and the fine grid enhanced field intensity characteristics, respectively; Calculating grid structure consistency based on the regularized coarse grid structure data and the regularized fine grid enhanced grid structure features; Calculating grid field strength consistency based on the regularized coarse grid field strength data and the regularized fine grid enhanced field strength characteristics; Calculating grid field strength loss compensation based on the grid structure consistency and the grid field strength consistency; Calculating fine grid enhancement structure data based on the fine grid enhancement grid structure characteristics, the grid field strength loss compensation and the similarity characteristics; Based on the fine grid enhanced field strength characteristics, the grid field strength loss compensation and the similarity characteristics, fine grid enhanced field strength data is calculated.

13. The GIS electromagnetic field distribution fast and high-precision simulation method according to claim 1, characterized in that: The enhancement model adopts a generative adversarial network model, which includes a generator and a discriminator. The generator is used to extract features from the coarse grid simulation results and perform cyclic multiple enhancement on the extracted features to obtain enhanced fine grid data. 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 structural information contained in the enhanced fine grid data and the real fine grid data obtained by simulation; The field strength consistency module is used to calculate a second confidence value of the field strength information contained in the enhanced fine grid data and the real fine grid data obtained by simulation; The accuracy determination module is used to shorten the distance between the enhanced fine grid data and the real fine grid data distribution obtained by simulation.

14. The GIS electromagnetic field distribution fast and high-precision simulation method according to claim 13, 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 enhanced fine grid 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.

15. The method for rapid and high-precision simulation of GIS electromagnetic field distribution according to claim 13, 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 enhanced fine grid 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.

16. The method for rapid and high-precision simulation of GIS electromagnetic field distribution according to claim 13, 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 coarse grid simulation result 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 coarse grid simulation result 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.

17. The method for rapid and high-precision simulation of GIS electromagnetic field distribution according to claim 16, 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.

18. The method for rapid and high-precision simulation of GIS electromagnetic field distribution according to claim 1, characterized in that: When using the finite element algorithm to numerically solve the three-dimensional simulation model of GIS equipment, it includes: The simulation model of the GIS equipment is discretized into a plurality of tetrahedral units by using the finite element method, and the GIS full-wave electromagnetic coarse grid simulation result is obtained by simulation, wherein each of the tetrahedral units includes a plurality of nodes.

19. The method for rapid and high-precision simulation of GIS electromagnetic field distribution according to claim 18, characterized in that: The method further comprises: using the enhanced model to enhance the coarse grid simulation result to obtain enhanced fine grid data; Abstract the simulation model of GIS equipment into a network topology , and any two adjacent free tetrahedrons in the network topology are regarded as a sheet unit, where Represents a collection of nodes. Represents an edge set, where the lines between mesh vertices are considered edges; Using the coarse grid simulation results as the initial benchmark features, the GraphSAGE algorithm is used to perform an aggregation process on the neighboring nodes of each node in each slice unit to generate the initial benchmark features of the newly added nodes; The GraphSAGE algorithm is used to perform secondary aggregation on the neighbor nodes of the newly added nodes to generate the feature vector representation of the new nodes.

20. The GIS electromagnetic field distribution fast and high-precision simulation method according to claim 19, characterized in that: The coarse grid simulation result is used as the initial benchmark feature, and the neighbor nodes of each node in each slice unit are aggregated by using the GraphSAGE algorithm to generate the initial benchmark feature of the newly added node, including: The coarse grid simulation results of each node are used as the initial benchmark features of each node; Traverse each node in each of the slice units , taking all the adjacent nodes of each node as sampling points, obtain the node The neighbor set , and use the aggregation function to aggregate nodes Corresponding to the initial baseline features of all nodes in the neighbor set, an aggregated neighbor feature is obtained ; Connect the initial reference features and aggregated neighbor features Get the first joint feature, perform matrix multiplication on the first weight matrix and the first joint feature, and then use a nonlinear transformation to get the node feature after one traversal ; The initial datum features of the common nodes of the two free tetrahedrons in each sheet element are aggregated using an aggregation function to obtain the initial datum features of the newly added nodes.

21. The GIS electromagnetic field distribution fast and high-precision simulation method according to claim 19, characterized in that: The GraphSAGE algorithm is used to perform secondary aggregation processing on the neighbor nodes of the newly added node to generate a feature vector representation of the newly added node, including: The node features after a traversal As a new benchmark feature for the corresponding node; Each node in each of the slice units As the neighbor sampling point of the newly added node, and using the aggregation function to aggregate the new benchmark features of all nodes in each slice unit, obtain the secondary aggregated neighbor feature ; The initial reference feature of the newly added node and the secondary aggregated neighbor feature are connected to obtain a second joint feature, and a second weight matrix is ​​multiplied by the second joint feature to obtain a feature vector representation of the newly added node through a nonlinear transformation.

22. The GIS electromagnetic field distribution fast and high-precision simulation method according to claim 21, characterized in that: A new node is generated for any two adjacent free tetrahedrons where their faces overlap.

23. A fast and high-precision simulator for GIS electromagnetic field distribution, characterized in that: The simulator includes a memory and a processor; wherein the processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, so as to implement the method as described in any one of claims 1-22.

24. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 22 is implemented.

25. A multi-structure adaptive GIS field-electricity fusion real-time status perception and early warning system, characterized in that: The system includes a signal synchronous acquisition and measurement embedded device and an industrial computer, wherein the industrial computer is provided with a simulator as claimed in claim 23, and the simulator is connected to the signal synchronous acquisition and measurement embedded device, the signal synchronous acquisition and measurement embedded device is used to acquire time-domain full-waveform data of GIS local discharge, the simulator is used to obtain enhanced fine-grid data based on the time-domain full-waveform data, and the industrial computer is used to search for the actual discharge position of the GIS local discharge source based on the time-domain full-waveform data and the enhanced fine-grid data.

Images