GIS simulation data enhancement method, system and storage medium based on GraphSAGE algorithm

Abstract

The invention discloses a GIS simulation data enhancement method, system and storage medium based on GraphSAGE algorithm, comprising: discretizing a simulation model of GIS equipment into a plurality of tetrahedral units by using finite element method, and simulating to obtain coarse grid data of GIS equipment, wherein each tetrahedral unit includes a plurality of nodes, and the coarse grid data includes simulation feature data of each node; abstracting the simulation model of GIS equipment into a network topology structure, and regarding any two adjacent free tetrahedrons in the network topology structure as a sheet unit; performing a primary aggregation process on the neighbor nodes of each node in each sheet unit by using GraphSAGE algorithm to generate a primary aggregation feature; performing a secondary aggregation process on all nodes of each sheet unit by using GraphSAGE algorithm to generate a secondary aggregation feature; and generating enhanced data of the coarse grid data of GIS equipment based on the primary aggregation feature and the secondary aggregation feature.

Description

Technical Field

[0001] The present invention relates to the technical field of electric power equipment, and in particular to a GIS simulation data enhancement method, system and storage medium based on a GraphSAGE algorithm. Background Art

[0002] Gas insulated switchgear (GIS) has the advantages of relatively small footprint, high reliability, and excellent breaking performance, and has been widely used in the world, especially in power systems. Years of operation experience of UHV GIS has shown that although GIS equipment has high operating reliability, due to process problems in the manufacturing and assembly process, various defects are still inevitably present inside it, such as free metal particles, needle-like protrusions, fixed particles, insulating gas, etc.

[0003] By detecting the electromagnetic field distribution in GIS, insulation faults can be discovered in time and the insulation state of GIS can be reliably evaluated, so that appropriate measures can be taken to prevent further development and accidents. In this regard, there are currently two main methods: simulation experiments and simulation calculations. Due to the particularity of GIS equipment, experimental conditions are limited and there is a lack of experimental data and characteristic research. Therefore, simulation has become an important means of studying GIS equipment failures. GIS simulation research generally uses finite element simulation methods, such as the literature "Simulation and Optimization of Switchgear Products Based on Finite Element Analysis, Ouyang Zhenguo, Master's Thesis", which proposed the use of finite element analysis software to simulate and calculate the three-dimensional electric field strength of new vacuum circuit breakers. However, during the simulation process, the coarseness of the finite element mesh division will affect the precision of the calculation results, and will also make the time cost inversely proportional to the precision, and increase exponentially. Therefore, the study of the method of enhancing the data of mesh nodes through the GIS finite element method simulation is important for GIS simulation, and can also provide a reference direction for the research and simulation of GIS equipment.

[0004] In the related art, a patent application document with publication number CN113722951A proposed a three-dimensional finite element mesh optimization method for scatterers based on neural networks. The scheme uses neural networks to establish a mapping relationship from A-dimensional mesh characteristic variables to the root mean square error of the far-field radar scattering cross section, and then solves the optimal value of the A-dimensional mesh characteristic variables with the goal of reducing the root mean square error of the far-field radar scattering cross section, and optimizes the three-dimensional finite element mesh of the scatterer by node insertion or node movement. However, since GIS electromagnetic field simulation focuses more on the accurate simulation of the interaction between the equipment model and the electromagnetic field distribution, GIS electromagnetic field simulation needs to consider the influence of the specific structure and material properties of the power equipment on the electromagnetic field, as well as how the electromagnetic field is distributed and changed inside these devices. The three-dimensional finite element mesh optimization method for scatterers based on neural networks proposed in the document is to obtain the mapping relationship function by training the acquired sample set and test set, which is not generally adaptable to GIS simulation under different voltage levels of different equipment. In addition, neural networks usually require a large amount of data for training to obtain accurate models. For complex three-dimensional finite element mesh optimization problems, the amount of data required may be very large, including the original mesh data and the corresponding optimization result data, which will increase the cost and time of data collection and processing. Similarly, training and adjusting neural network models also requires a lot of computing resources.

[0005] A multi-physics simulation method based on a residual dense network is proposed in the patent application document with publication number CN116432538A. The scheme obtains a neural network model that can fit physical laws from low-grid density physical fields and output physical fields with high grid density by training the acquired low-grid density physical field data set and high-grid density physical field data set. However, the residual dense network used in the scheme is a deep learning model with high complexity and requires a lot of computing resources and time for training and reasoning. In particular, for the simulation of ultra-high voltage GIS, there are many physical fields involved, which require a large-scale model to process, increasing the computational complexity and resource requirements, and there is an overfitting problem, that is, it performs well on the training set, but performs poorly on the test set or new data. At the same time, the residual dense network is a data-driven method that relies on a large amount of data for training without necessarily considering physical laws. However, in ultra-high voltage GIS simulation, physical laws are crucial to simulating the behavior of the real world, and deep learning models may not be able to fully capture these physical laws. Summary of the invention

[0006] The technical problem to be solved by the present invention is how to enhance the grid node data of GIS finite element method simulation.

[0007] The present invention solves the above technical problems by the following technical means:

[0008] The present invention proposes a GIS simulation data enhancement method based on the GraphSAGE algorithm, the method comprising:

[0009] The simulation model of the GIS equipment is discretized into a plurality of tetrahedral units by using the finite element method, and the coarse mesh data of the GIS equipment is obtained by simulation, wherein each of the tetrahedral units includes a plurality of nodes, and the coarse mesh data includes simulation characteristic data of each node;

[0010] 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;

[0011] The simulated feature data of the node is used as the initial benchmark feature, and the GraphSAGE algorithm is used to aggregate the neighbor nodes of each node in each slice unit to generate the initial benchmark feature of the newly added node;

[0012] 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.

[0013] Furthermore, the simulation characteristic data of each of the nodes includes the three-dimensional spatial coordinates of the node and the electric field strength of the node.

[0014] Furthermore, the simulation feature data of the node is used as the initial benchmark feature, and the neighbor nodes of each node in each slice unit are aggregated using the GraphSAGE algorithm to generate the benchmark feature of the newly added node, including:

[0015] The simulation feature data of each node is used as the initial reference feature of each node;

[0016] 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 ;

[0017] 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 ;

[0018] 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.

[0019] 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:

[0020] The node features after a traversal As a new benchmark feature for the corresponding node;

[0021] 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 ;

[0022] 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.

[0023] Furthermore, a new node is generated corresponding to the overlapping faces of any two adjacent free tetrahedrons.

[0024] Furthermore, when the GraphSAGE algorithm is used to process the node information, the sampling of the node is made to be fixed length through repeated sampling with replacement or negative sampling method.

[0025] Furthermore, the complexity of the GraphSAGE algorithm is:

[0026]

[0027] In the formula, represents the number of aggregators, Indicates The number of sampled neighbors of the layer network is fixed, and the sampling of each layer network is of fixed length.

[0028] Furthermore, the aggregation function adopted by the aggregator is an average aggregation function.

[0029] In addition, the present invention provides a GIS simulation data enhancement system based on the GraphSAGE algorithm, the system comprising:

[0030] A coarse grid data acquisition module is used to discretize the simulation model of the GIS equipment into a plurality of tetrahedral units by using the finite element method, and obtain the coarse grid data of the GIS equipment by simulation, wherein each of the tetrahedral units includes a plurality of nodes, and the coarse grid data includes the simulation characteristic data of each node;

[0031] Network topology building module, used to 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;

[0032] The primary aggregation module is used to use the simulation feature data of the node as the initial benchmark feature, and use the GraphSAGE algorithm to perform a primary aggregation process on the neighbor nodes of each node in each slice unit to generate the initial benchmark feature of the newly added node;

[0033] The secondary aggregation module is used to perform secondary aggregation processing on the neighbor nodes of the newly added nodes using the GraphSAGE algorithm to generate a feature vector representation of the newly added nodes.

[0034] 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 GIS simulation data enhancement method based on the GraphSAGE algorithm as described above is implemented.

[0035] The advantages of the present invention are:

[0036] (1) The present invention enhances the coarse mesh data of GIS equipment obtained by finite element method simulation by using the GraphSAGE algorithm. After the GraphSAGE algorithm is used, new node data generated by updating and iterating the neighboring nodes 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, thereby completing the enhancement and refinement of the mesh node data generated by the simulation calculation.

[0037] The present invention can retain the topological structure information of grid data through an algorithm based on a graph structure. For grid data in GIS simulation, which has obvious topological structure characteristics, the present solution can effectively capture the relationship between grids and retain these key network structure information. In GIS simulation, the local connection and global association between grid nodes have an important impact on the simulation results. The present solution updates the representation of the target node by sampling the characteristics of neighboring nodes, which enables the algorithm to simultaneously consider the local characteristics and global characteristics of the target node and effectively utilize these characteristics.

[0038] (2) The present invention performs a graph structure-based algorithm enhancement on the coarse grid data obtained by simulation, which can adapt to grid data of different scales, including small-scale and large-scale grids, and is adaptable to GIS simulation data under different voltage levels of different equipment. It can realize GIS simulation data enhancement and improve the quality of grid data.

[0039] 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

[0040] Figure 1 It is a flowchart of a GIS simulation data enhancement method based on the GraphSAGE algorithm proposed in one embodiment of the present invention;

[0041] Figure 2 It is a principle block diagram of GIS simulation data enhancement based on GraphSAGE algorithm in one embodiment of the present invention;

[0042] Figure 3 It is a schematic diagram of the principle of implementing two-layer aggregation using the GraphSAGE algorithm in one embodiment of the present invention;

[0043] Figure 4 It is a structural schematic diagram of a GIS simulation data enhancement system based on the GraphSAGE algorithm proposed in one embodiment of the present invention. DETAILED DESCRIPTION

[0044] 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.

[0045] like Figure 1 to Figure 2 As shown, the first embodiment of the present invention proposes a GIS simulation data enhancement method based on the GraphSAGE algorithm, and the method includes the following steps:

[0046] S10, using the finite element method to discretize the simulation model of the GIS equipment into a plurality of tetrahedral units, and simulating to obtain coarse mesh data of the GIS equipment, wherein each of the tetrahedral units includes a plurality of nodes, and the coarse mesh data includes simulation feature data of each node;

[0047] It should be noted that, in this embodiment, according to the structural parameters of the GIS equipment, a simulation model of three-dimensional data is established using simulation software such as COMSOL Multiphysics, and the three-dimensional data model is discretized into multiple tetrahedral units through the finite element method, and simulation calculation is performed to obtain the coarse mesh simulation data to be processed. The results obtained by the simulation calculation are exported to obtain each node The simulation feature data (X, Y, Z, V) of the node is used as the feature vector of the node, that is, the input feature , , where X, Y, Z represent the three-dimensional spatial coordinates of the node, and V represents the electric field strength of the node.

[0048] S20. 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;

[0049] 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.

[0050] S30, 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, and generating the initial benchmark feature of the newly added node;

[0051] It should be noted that when the GraphSAGE algorithm is used in this embodiment for one aggregation, the information of the adjacent nodes of all nodes in each slice unit is aggregated, so that the overlapping faces of any two adjacent tetrahedrons will generate a new node.

[0052] S40, 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.

[0053] 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.

[0054] 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 neighbor nodes 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, using the spatial coordinates and electric field strength of the node as node features is more in line with the data connection of GIS simulation. In addition, this embodiment can adjust 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, thereby improving the algorithm's ability to express data in order to obtain better performance.

[0055] As a further preferred technical solution, Figure 3 As shown, the step S30: 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:

[0056] S31, using the simulation feature data of each node as the initial reference feature of each node;

[0057] S32, 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 ;

[0058] 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 .

[0059] 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:

[0060]

[0061] In the formula, Represents an aggregate function.

[0062] S33, 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 ;

[0063] 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:

[0064]

[0065] In the formula, is the concatenation function, is the first weight matrix, yes function.

[0066] Furthermore, in this embodiment, the aggregation function uses the average aggregation function MEAN ,Right now .

[0067] S34. 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.

[0068] 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:

[0069]

[0070] In the formula, is the initial datum feature of the common node of two adjacent free tetrahedrons.

[0071] Furthermore, the aggregation function in this embodiment adopts the average aggregation function, so .

[0072] As a further preferred technical solution, the step S40: 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:

[0073] S41, the node features after one traversal As a new benchmark feature for the corresponding node;

[0074] S42, 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 ;

[0075] 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, ( ), and obtain the secondary aggregated neighbor features , the formula is:

[0076]

[0077] In the formula, is an aggregate function, is the new reference feature for each node in the sheet element.

[0078] S43, 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.

[0079] Specifically, the feature vector of the newly added node obtained in this embodiment is expressed as:

[0080]

[0081] In the formula, is the concatenation function, is the second weight matrix, yes function.

[0082] 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.

[0083] As a further preferred technical solution, the complexity of the GraphSAGE algorithm used in this embodiment is:

[0084]

[0085] 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.

[0086] 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 .

[0087] In addition, if Figure 4 As shown, the second embodiment of the present invention proposes a GIS simulation data enhancement system based on the GraphSAGE algorithm, and the system includes:

[0088] The coarse grid data acquisition module 10 is used to discretize the simulation model of the GIS equipment into a plurality of tetrahedral units by using the finite element method, and obtain the coarse grid data of the GIS equipment by simulation, wherein each of the tetrahedral units includes a plurality of nodes, and the coarse grid data includes the simulation characteristic data of each node;

[0089] The network topology building module 20 is used to abstract the simulation model of the 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;

[0090] A primary aggregation module 30 is used to use the simulation feature data of the node as the initial reference feature, and use the GraphSAGE algorithm to perform a primary aggregation process on the neighbor nodes of each node in each slice unit to generate the initial reference feature of the newly added node;

[0091] The secondary aggregation module 40 is used to perform secondary aggregation processing on the neighbor nodes of the newly added node using the GraphSAGE algorithm to generate a feature vector representation of the newly added node.

[0092] As a further preferred technical solution, the primary aggregation module 30 includes:

[0093] A traversal unit is used to use the simulation feature data of each node as the initial reference feature of each node; traversing 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 ;

[0094] A node feature calculation unit, used to connect 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 ;

[0095] The primary aggregation unit is used to aggregate the initial reference features of the common nodes of two free tetrahedrons in each piece unit using an aggregation function to obtain the initial reference features of the newly added nodes.

[0096] As a further preferred technical solution, the secondary aggregation module 40 includes:

[0097] The secondary traversal unit is used to convert the node features after the first traversal into As a new reference feature of 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 ;

[0098] The feature calculation unit is used to connect the initial baseline feature of the newly added node with the secondary aggregated neighbor feature to obtain a second joint feature, perform a matrix multiplication operation on the second weight matrix and the second joint feature, and obtain a feature vector representation of the newly added node through a nonlinear transformation.

[0099] It should be noted that other embodiments or implementation methods of the GIS simulation data enhancement system based on the GraphSAGE algorithm described in the present invention can refer to the above-mentioned method embodiments and will not be described in detail here.

[0100] In addition, the third 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 GIS simulation data enhancement method based on the GraphSAGE algorithm as described in the first embodiment above is implemented.

[0101] 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.

[0102] 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.

[0103] 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.

[0104] 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.

[0105] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. A GIS simulation data enhancement method based on GraphSAGE algorithm, characterized in that: The method comprises: The simulation model of the GIS equipment is discretized into a plurality of tetrahedral units by using the finite element method, and the coarse mesh data of the GIS equipment is obtained by simulation, wherein each of the tetrahedral units includes a plurality of nodes, and the coarse mesh data includes simulation characteristic data of each node; 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; The simulated feature data of the node is used as the initial benchmark feature, and the GraphSAGE algorithm is used to aggregate the neighbor nodes of each node in each slice unit to generate the initial benchmark feature 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, including: As a new reference feature of 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 ; Connect the initial baseline feature of the newly added node and the secondary aggregated neighbor feature to obtain a second joint feature, perform a matrix multiplication operation on the second weight matrix and the second joint feature, and obtain a feature vector representation of the newly added node through a nonlinear transformation.

2. The GIS simulation data enhancement method based on the GraphSAGE algorithm according to claim 1, characterized in that: The simulation characteristic data of each of the nodes includes the three-dimensional space coordinates of the node and the electric field strength of the node.

3. The GIS simulation data enhancement method based on the GraphSAGE algorithm according to claim 1, characterized in that: The simulation feature data of the node is used as the initial benchmark feature, and the neighbor nodes of each node in each slice unit are aggregated using the GraphSAGE algorithm to generate the benchmark feature of the newly added node, including: The simulation feature data of each node is used as the initial reference feature 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.

4. The GIS simulation data enhancement method based on the GraphSAGE algorithm according to claim 1, characterized in that: A new node is generated for any two adjacent free tetrahedrons where their faces overlap.

5. The GIS simulation data enhancement method based on the GraphSAGE algorithm as claimed in claim 3, characterized in that: When the GraphSAGE algorithm is used to process node information, the sampling of nodes is made fixed-length through repeated sampling with replacement or negative sampling methods.

6. The GIS simulation data enhancement method based on the GraphSAGE algorithm according to claim 1, characterized in that: The complexity of the GraphSAGE algorithm is: In the formula, represents the number of aggregators, Indicates The number of sampled neighbors of the layer network is fixed, and the sampling of each layer network is of fixed length.

7. The GIS simulation data enhancement method based on the GraphSAGE algorithm as claimed in claim 6, characterized in that: The aggregation function adopted by the aggregator is the average aggregation function.

8. A GIS simulation data enhancement system based on GraphSAGE algorithm, characterized in that: The system comprises: A coarse grid data acquisition module is used to discretize the simulation model of the GIS equipment into a plurality of tetrahedral units by using the finite element method, and obtain the coarse grid data of the GIS equipment by simulation, wherein each of the tetrahedral units includes a plurality of nodes, and the coarse grid data includes the simulation characteristic data of each node; Network topology building module, used to 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; The primary aggregation module is used to use the simulation feature data of the node as the initial benchmark feature, and use the GraphSAGE algorithm to perform a primary aggregation process on the neighbor nodes of each node in each slice unit to generate the initial benchmark feature of the newly added node; The secondary aggregation module is used to perform secondary aggregation processing on the neighbor nodes of the newly added nodes using the GraphSAGE algorithm to generate a feature vector representation of the newly added nodes; The secondary aggregation module comprises: The secondary traversal unit is used to convert the node features after the first traversal into As a new reference feature of 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 feature calculation unit is used to connect the initial baseline feature of the newly added node with the secondary aggregated neighbor feature to obtain a second joint feature, perform a matrix multiplication operation on the second weight matrix and the second joint feature, and obtain a feature vector representation of the newly added node through a nonlinear transformation.

9. The GIS simulation data enhancement system based on the GraphSAGE algorithm as claimed in claim 8, characterized in that: A new node is generated for any two adjacent free tetrahedrons where their faces overlap.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the GIS simulation data enhancement method based on the GraphSAGE algorithm as described in any one of claims 1 to 7 is implemented.

Images