Regional electromagnetic patrol method and system based on vehicle-mounted electromagnetic detection equipment

Abstract

The present invention provides a regional electromagnetic patrol method and system based on vehicle-mounted electromagnetic detection equipment. The method includes the following steps: identifying target monitoring nodes based on historical data and electromagnetic propagation models, and constructing an electromagnetic environment map network. The network is divided into subgraphs through multi-scale clustering, and vehicle-mounted electromagnetic patrol vehicles and edge servers are deployed in each subgraph area, and a central server is deployed in the central area. The vehicle-mounted equipment performs electromagnetic detection and collects data according to the optimized path. The edge server uses edge computing and federated learning technology to update the subgraph and perform local anomaly analysis. The central server aggregates all subgraph update information to complete global update and anomaly analysis. Finally, the local and global analysis results are integrated to form a comprehensive electromagnetic anomaly analysis result, which is visualized on the regional map. The present invention realizes real-time and accurate large-scale electromagnetic environment monitoring and analysis, effectively improving electromagnetic management capabilities.

Description

Technical Field

[0001] The present invention belongs to the technical field of electromagnetic inspection, and in particular relates to a regional electromagnetic inspection method and system based on vehicle-mounted electromagnetic detection equipment. Background Art

[0002] With the rapid development of the information society, electromagnetic environment management faces unprecedented challenges and opportunities. On the one hand, the widespread use of wireless communication technologies, such as mobile communications, wireless networks, and the Internet of Things, has made the electromagnetic environment increasingly complex. The proliferation of various electronic and wireless devices has led to a surge in the number and diversification of electromagnetic interference sources, placing tremendous pressure on electromagnetic environment monitoring and management. On the other hand, the development of emerging technologies such as 5G, smart cities, and autonomous driving has placed higher demands on the quality of the electromagnetic environment. The proper operation of these technologies requires a stable and reliable electromagnetic environment, and any interference can have serious consequences. At the same time, public concern about the health effects of electromagnetic radiation continues to grow, raising expectations for the transparency and effectiveness of electromagnetic environment management.

[0003] In modern urban environments, electromagnetic interference sources are numerous and widely distributed, including various communications equipment, power facilities, and industrial equipment. The location, intensity, and characteristics of these interference sources can fluctuate at any time, creating an extremely complex electromagnetic landscape. Therefore, traditional fixed monitoring point layouts struggle to capture these dynamic changes, resulting in monitoring data that fails to truly reflect the current electromagnetic environment. Furthermore, changes in the electromagnetic environment often exhibit temporal and spatial correlations, making single-point or localized monitoring difficult to reveal overall electromagnetic environment trends and potential issues. Traditional methods lack the ability to conduct systematic and comprehensive analysis across large areas, making it difficult to accurately identify and locate the source of abnormal electromagnetic events. These issues severely restrict the efficiency and accuracy of electromagnetic environment management, failing to meet the high demands of modern society for electromagnetic safety and quality. New technical solutions are urgently needed to address this challenge. Summary of the Invention

[0004] The present invention provides a regional electromagnetic patrol method and system based on a vehicle-mounted electromagnetic detection device to solve the technical problems mentioned in the above background technology.

[0005] In a first aspect, the present invention provides a method for regional electromagnetic inspection based on a vehicle-mounted electromagnetic detection device, the method comprising the following steps:

[0006] Obtain regional maps and historical electromagnetic survey data for the target area;

[0007] Based on the historical electromagnetic detection data and according to the electromagnetic propagation model, identifying historical electromagnetic radiation points as target monitoring nodes on the regional map;

[0008] Using the road network in the regional map as the node edges, and combining all the target monitoring nodes to construct an electromagnetic environment map network of the target area;

[0009] Performing multi-scale clustering on the target monitoring nodes in the electromagnetic environment map network using a hierarchical clustering algorithm, and dividing the electromagnetic environment map network into a plurality of regional sub-graphs using a spectral clustering algorithm based on preliminary clustering results of the multi-scale clustering;

[0010] Deploy an on-board electromagnetic inspection vehicle equipped with an edge server in the area where each of the regional submaps is located, and deploy a central server in the central area of the target area, import the regional submaps into the corresponding edge servers, import the electromagnetic environment map network into the central server, and all the edge servers are communicatively connected to the central server;

[0011] For any of the regional subgraphs, intelligently plan the optimal electromagnetic inspection path of the vehicle-mounted electromagnetic inspection vehicle in the area to which it belongs based on the regional subgraph, and control the vehicle-mounted electromagnetic inspection vehicle to perform electromagnetic inspection along the optimal electromagnetic inspection path, and collect electromagnetic inspection data of the area to which the regional subgraph belongs;

[0012] Using edge computing and federated learning technology and based on the electromagnetic inspection data, the regional sub-map is updated in the edge server, and local electromagnetic anomaly analysis is performed on the updated regional sub-map by the edge server to obtain a local anomaly analysis result;

[0013] After all the regional sub-maps have been updated, the central server aggregates the updated information of all the regional sub-maps and completes a global update of the electromagnetic environment map network in the central server, and the central server performs a global electromagnetic anomaly analysis on the updated electromagnetic environment map network to obtain a global anomaly analysis result;

[0014] The local anomaly analysis result and the global anomaly analysis result are merged into a comprehensive electromagnetic anomaly analysis result of the target area, and the comprehensive electromagnetic anomaly analysis result is imported into the regional map for visual display.

[0015] Optionally, the identifying historical electromagnetic radiation points as target monitoring nodes on the regional map based on the historical electromagnetic detection data and according to an electromagnetic propagation model comprises the following steps:

[0016] Using a free space propagation model as the electromagnetic propagation model of the target area;

[0017] Based on the electromagnetic propagation model, the radiation points of the target area are reversely calculated according to the historical electromagnetic detection data and the least square method;

[0018] In the reverse calculation process, the objective function of the least square method is constructed by combining the historical electromagnetic detection data and the output value of the electromagnetic propagation model;

[0019] Solving the objective function through an optimization algorithm to complete the reverse calculation, and marking all potential historical electromagnetic radiation points on the regional map;

[0020] Clustering all the potential historical electromagnetic radiation points using a density clustering algorithm, and obtaining all the historical electromagnetic radiation points in the regional map after clustering is completed;

[0021] Extracting radiation point features of each of the historical electromagnetic radiation points from the historical electromagnetic detection data, the radiation point features including the historical electromagnetic field intensity, historical abnormal frequency, and spatial impact range of the historical electromagnetic radiation point;

[0022] The historical electromagnetic radiation point is used as a target monitoring node, and the node weight of the target monitoring node is calculated according to the corresponding radiation point characteristics.

[0023] Optionally, the step of performing multi-scale clustering on the target monitoring nodes in the electromagnetic environment map network using a hierarchical clustering algorithm, and dividing the electromagnetic environment map network into a plurality of regional sub-maps using a spectral clustering algorithm based on preliminary clustering results of the multi-scale clustering, comprises the following steps:

[0024] Constructing a multidimensional feature vector of the target monitoring node according to the radiation point features;

[0025] Using principal component analysis to reduce the multidimensional feature vector into a low-dimensional feature vector;

[0026] Clustering the low-dimensional feature vectors using a hierarchical clustering algorithm based on a minimum spanning tree to obtain a feature clustering tree;

[0027] Calculating a plurality of different cutoff thresholds based on the average node distance between the root node and the leaf nodes in the feature clustering tree;

[0028] Truncating the feature clustering tree based on each of the truncation thresholds to obtain feature clustering results of multiple different scales;

[0029] Constructing an affinity matrix based on the feature clustering results at multiple different scales;

[0030] The affinity matrix is used as a constraint condition of a spectral clustering algorithm, and based on the constraint condition and using the spectral clustering algorithm, the electromagnetic environment map network is divided into a plurality of regional sub-maps.

[0031] Optionally, using the affinity matrix as a constraint condition of a spectral clustering algorithm, and dividing the electromagnetic environment map network into a plurality of regional sub-maps based on the constraint condition and using the spectral clustering algorithm comprises the following steps:

[0032] Calculating a degree matrix of the electromagnetic environment map network, and calculating a normalized Laplace matrix of the electromagnetic environment map network based on the degree matrix;

[0033] Calculating and obtaining the matrix eigenvalues and matrix eigenvectors of the normalized Laplace matrix;

[0034] Select the matrix eigenvectors corresponding to the k smallest non-zero matrix eigenvalues to form a spectral clustering matrix;

[0035] Construct the target optimization function of the spectral clustering algorithm, which is:

[0036] min tr(Y T LY)+λ[tr(Y T (DA)Y)]

[0037] Wherein: tr represents the trace of the matrix, Y represents the spectral clustering matrix, L represents the normalized Laplace matrix, λ represents the balance parameter, T represents the transposed matrix, D represents the degree matrix, and A represents the affinity matrix;

[0038] Solving the target optimization function by generalized eigenvalues, and forming a subgraph matrix with the K target matrix eigenvectors obtained by the solution;

[0039] The row vectors of the subgraph matrix are clustered using a K-means algorithm, and the electromagnetic environment map network is divided into a plurality of regional subgraphs according to the clustering results.

[0040] Optionally, the intelligent planning of the optimal electromagnetic inspection path of the vehicle-mounted electromagnetic inspection vehicle in the area based on the area sub-map includes the following steps:

[0041] Obtaining historical traffic flow data of a road network in an area to which the regional subgraph belongs, and assigning node edge weights to node edges of the regional subgraph according to the historical traffic flow data;

[0042] Taking the target monitoring node with the highest node weight as the starting node;

[0043] An optimal path selection step is performed based on the starting node, and the optimal path selection step is as follows:

[0044] Calculate the node distances between the starting node and all adjacent nodes;

[0045] Constructing a multi-objective reward function by combining the node distance, the node weights of the adjacent nodes, and the node edge weights of the node edges between the starting node and the adjacent nodes;

[0046] Selecting an optimal adjacent node as an optimal path node from all adjacent nodes based on the multi-objective reward function and using a Monte Carlo tree search method;

[0047] The optimal path node is used as the starting node to repeatedly perform the optimal path selection step until the farthest node distance between the optimal path node and the starting node exceeds a preset distance threshold, thereby obtaining the optimal electromagnetic inspection path of the vehicle-mounted inspection vehicle.

[0048] Optionally, controlling the vehicle-mounted electromagnetic inspection vehicle to perform electromagnetic inspection along the optimal electromagnetic inspection path and collecting electromagnetic inspection data of the area to which the area sub-map belongs includes the following steps:

[0049] Before using the optimal path node as the starting node in each round of the optimal path selection step, obtaining real-time traffic flow data of the road network in the area to which the regional subgraph belongs, and updating the edge weights of all the nodes in the regional subgraph according to the real-time traffic flow data;

[0050] After the optimal path node is determined in each round in the optimal path selection step, the on-board electromagnetic inspection vehicle is controlled to travel from the starting node to the optimal path node, and electromagnetic inspection data around the on-board electromagnetic inspection vehicle is continuously collected during the driving process.

[0051] Optionally, the updating of the regional submap in the edge server based on the electromagnetic inspection data by using edge computing and federated learning technology, and performing local electromagnetic anomaly analysis on the updated regional submap by the edge server to obtain the local anomaly analysis result comprises the following steps:

[0052] Deploy the same graph neural network model on all of the edge servers;

[0053] For any of the edge servers, the preprocessed electromagnetic inspection data is input into the graph neural network model, a graph structure learning method is used to update the regional subgraph on the edge server, and the model parameters of the graph neural network model are simultaneously updated;

[0054] Using a federated averaging algorithm to exchange the updated model parameters with all other edge servers;

[0055] Updating the local graph neural network model based on the exchanged model parameters;

[0056] The updated multi-layer graph attention network structure in the graph neural network model is used to calculate the multi-scale anomaly score of the updated regional subgraph, and the local electromagnetic anomaly analysis result of the regional subgraph is calculated using an integrated learning method.

[0057] Optionally, aggregating update information of all the regional submaps through the central server and completing a global update of the electromagnetic environment map network in the central server, and performing a global electromagnetic anomaly analysis on the updated electromagnetic environment map network through the central server to obtain a global anomaly analysis result comprises the following steps:

[0058] Aggregating update information of all the regional subgraphs from all the edge servers through the central server and adopting an incremental update strategy;

[0059] Based on all the update information and using a graph difference algorithm, a global update of the electromagnetic environment map network is completed in the central server;

[0060] Extracting time dimension abnormal features from the updated electromagnetic environment map network using an autoregressive integrated moving average method;

[0061] Extracting spatial dimension abnormal features from the updated electromagnetic environment map network using a spatial autocorrelation analysis method;

[0062] The spatial dimension abnormality features and the temporal dimension abnormality features are combined and an integrated learning method is used to analyze and obtain a global abnormality analysis result.

[0063] Optionally, after fusing the local anomaly analysis result and the global anomaly analysis result into the comprehensive electromagnetic anomaly analysis result of the target area, the method further includes the following steps:

[0064] Build a spatiotemporal graph convolutional network model;

[0065] Inputting the electromagnetic environment map network and the comprehensive electromagnetic anomaly analysis results as input data into the spatiotemporal graph convolutional network model;

[0066] Using the spatiotemporal graph convolutional network model to predict the spatiotemporal evolution trend of electromagnetic anomalies in the target area, and outputting the predicted spatiotemporal evolution results of electromagnetic anomalies;

[0067] The graph network structure of the electromagnetic environment graph network and the node weights of the target monitoring nodes are adjusted according to the spatiotemporal evolution results of the electromagnetic anomaly.

[0068] In a second aspect, the present invention also provides a regional electromagnetic patrol system based on vehicle-mounted electromagnetic detection equipment, comprising a memory, a processor, and a computer program stored on the memory and runnable on the processor. When the processor executes the computer program, it implements the regional electromagnetic patrol method based on vehicle-mounted electromagnetic detection equipment as described in the first aspect.

[0069] The beneficial effects of the present invention are:

[0070] By constructing an electromagnetic environment map network and incorporating a multi-scale clustering algorithm, this invention enables refined segmentation and management of large-scale, complex environments, overcoming the limitations of traditional fixed monitoring point layouts, which are unable to adapt to dynamic electromagnetic environments. The use of mobile, on-board electromagnetic inspection vehicles for flexible monitoring significantly improves monitoring coverage and real-time performance, enabling timely capture of transient changes in the electromagnetic environment. This invention innovatively incorporates edge computing and federated learning technologies to enable real-time data processing and analysis on edge servers, significantly improving the system's response speed and efficiency. Through global analysis on a central server, this invention achieves a systematic understanding of the entire electromagnetic environment, overcoming the fragmented data analysis issues of traditional methods. Furthermore, the invention's multi-level anomaly analysis mechanism, combining local and global analysis results, significantly improves the accuracy of identifying and locating electromagnetic anomalies. This invention also uses visualization technology to intuitively present electromagnetic environmental conditions, facilitating rapid decision-making by managers. Overall, this invention establishes an intelligent, adaptive electromagnetic environment monitoring and management system that not only copes with complex and changing electromagnetic environments but also automatically adjusts monitoring strategies based on environmental changes, significantly improving the efficiency and accuracy of electromagnetic environment management. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] Figure 1 This is a flow chart of a regional electromagnetic patrol method based on vehicle-mounted electromagnetic detection equipment in one embodiment of the present application.

[0072] Figure 2 This is a schematic diagram of the frequency selector system architecture of a vehicle-mounted electromagnetic detection device in one embodiment of the present application.

[0073] Figure 3 This is a schematic diagram of the system architecture of PC data collection software in one embodiment of the present application.

[0074] Figure 4 This is a visual display diagram of a path in one embodiment of the present application that combines the inspection path, inspection results and area map.

[0075] Figure 5 This is a grid-format visualization diagram combining inspection results and area maps in one embodiment of the present application. DETAILED DESCRIPTION

[0076] The following will be combined with the accompanying drawings in the embodiments of the present application to clearly describe the technical solutions in the embodiments of the present application. Obviously, the embodiments described are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field are within the scope of protection of this application.

[0077] The terms "first," "second," and the like in the specification and claims of this application are used to distinguish similar objects, and are not used to describe a specific order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate, so that the embodiments of this application can be implemented in an order other than that illustrated or described herein, and that the objects distinguished by "first," "second," and the like are generally of the same type, and do not limit the number of objects; for example, the first object can be one or more. In addition, the term "and / or" in the specification and claims refers to at least one of the connected objects, and the character " / " generally indicates that the objects connected are in an "or" relationship.

[0078] Figure 1 FIG. 1 is a flow chart of a method for regional electromagnetic inspection based on vehicle-mounted electromagnetic detection equipment in one embodiment. It should be understood that although Figure 1 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. In addition, Figure 1 At least part of the steps in the above process may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but may be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but may be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps. Figure 1 As shown, the regional electromagnetic inspection method based on the vehicle-mounted electromagnetic detection equipment disclosed in the present invention specifically includes the following steps:

[0079] S101. Obtain a regional map and historical electromagnetic detection data of the target area.

[0080] Among them, regional maps are usually obtained in digital format, including two main forms: vector maps and raster maps. Vector maps use geometric elements such as points, lines, and surfaces to represent geographic entities, and are suitable for expressing linear features such as road networks; raster maps divide the area into regular grids, each grid stores corresponding geographic information, and are suitable for expressing continuously changing geographical phenomena. Map data can be obtained from a geographic information system (GIS) database or remote sensing imagery, and usually includes information such as topography, landforms, land use, and building distribution. The resolution and accuracy of map data directly affect the accuracy of subsequent analysis, so it is necessary to select an appropriate spatial resolution, usually between 1 and 10 meters.

[0081] Historical electromagnetic survey data includes electromagnetic field intensity measurements taken within the target area over a period of time. This data typically includes information such as the measurement time, geographic location (latitude and longitude coordinates), frequency range, electric field strength, and magnetic field strength. The data may come from fixed monitoring stations, mobile measurement equipment, or satellite remote sensing. The data format may include CSV, JSON, or proprietary formats and requires standardization. To ensure the representativeness and reliability of the data, data preprocessing is required, including outlier detection, missing value processing, and spatiotemporal consistency checks. The processed data needs to be spatially aligned with the map to ensure that the electromagnetic survey data accurately corresponds to the geographic location. This can be achieved through coordinate transformation and projection alignment. Common projection systems include UTM and Gauss-Krüger projections. Finally, the processed data is stored in a spatial database such as PostGIS or SpatiaLite for rapid subsequent retrieval and analysis.

[0082] S102. Based on historical electromagnetic detection data and in accordance with an electromagnetic propagation model, historical electromagnetic radiation points are identified on a regional map as target monitoring nodes.

[0083] First, it is necessary to select an appropriate electromagnetic propagation model to simulate the propagation characteristics of electromagnetic waves in space. Commonly used models include the free-space propagation model, the Okumura-Hata model, and the COST-231 model. Taking the free-space propagation model as an example, its path loss can be expressed as: L = 32.45 + 20log(f) + 20log(d), where f is the frequency (MHz) and d is the distance (km). For complex terrain, ray tracing or finite-difference time-domain (FDTD) methods can be used for more accurate simulations. When selecting a model, factors such as the regional topographic characteristics, building density, and electromagnetic wave frequency need to be considered. Next, the selected model is used to reverse-calculate historical electromagnetic detection data to determine the possible location of the radiation source. This can be achieved through least squares estimation or maximum likelihood estimation. Solving this minimization problem using an optimization algorithm (such as the Levenberg-Marquardt algorithm) can determine the most likely radiation source location and intensity. For the identified radiation points, cluster analysis is required to remove redundant points. Specifically, the density-based spatial clustering algorithm DBSCAN can be used: for each point p, if there are at least MinPts points within its ε neighborhood, a cluster is formed. The clustered center point serves as the final target monitoring node. Finally, the identified target monitoring nodes are overlaid on the regional map to form a preliminary electromagnetic environment monitoring network.

[0084] S103. Using the road network in the regional map as node edges, and combining all target monitoring nodes, construct an electromagnetic environment map network of the target area.

[0085] First, road network information must be extracted from the regional map. This can be obtained directly from vector map data or extracted from raster maps using image processing techniques. For raster maps, edge detection algorithms (such as the Canny algorithm) and morphological operations can be used to extract road lines. The main steps of the Canny algorithm include Gaussian filtering, gradient calculation, non-maximum suppression, and double threshold detection. The extracted road network needs to be topologically processed to ensure road connectivity and integrity. This can be achieved using topological cleaning algorithms such as the Douglas-Peucker algorithm to simplify road lines and the Snap algorithm to repair broken connections. Next, the road network is converted into a graph structure, with road intersections and endpoints as nodes and road segments as edges. The target monitoring nodes (i.e., identified historical electromagnetic radiation points) are then added to the graph. For monitoring nodes not located on roads, the nearest road point must be found and connected. This can be achieved using a nearest neighbor search algorithm, such as the KD tree: a KD tree containing all road points is constructed, and then a nearest neighbor query is performed for each monitoring node.

[0086] Furthermore, to address the time-varying nature of the electromagnetic environment, a time dimension can be introduced, expanding the graph into a space-time graph: G(V, E, T), where T represents the time series. Each time point has a corresponding graph snapshot, and the attributes of nodes and edges change over time. To improve the graph's expressiveness, a multi-layer graph structure can be introduced, with different layers representing different frequency bands or different types of electromagnetic sources. The relationships between layers can be represented by cross-edges. Considering the continuity of the electromagnetic environment, interpolation methods can be used to fill in the electromagnetic attributes of unknown regions in the graph. Commonly used methods include the inverse distance weighted method (IDW) and kriging. This electromagnetic environment graph network, constructed based on the road network and monitoring nodes, can not only effectively express the spatial distribution of the electromagnetic environment but also reflect the impact of the road network on electromagnetic propagation.

[0087] S104. A hierarchical clustering algorithm is used to perform multi-scale clustering on the target monitoring nodes in the electromagnetic environment map network. Based on the preliminary clustering results of the multi-scale clustering, the electromagnetic environment map network is divided into multiple regional sub-maps through a spectral clustering algorithm.

[0088] The main steps of hierarchical clustering include: 1) treating each node as a cluster; 2) calculating the distance between all pairs of clusters; 3) merging the two closest clusters; 4) repeating steps 2 and 3 until a preset number of clusters or distance threshold is reached. Distance calculation can be simply based on the spatial location and electromagnetic properties of the nodes, for example:

[0089] d=sqrt((x1-x2) 2 +(y1-y2) 2 )+λ*|E1-E2|

[0090] Where (x, y) are spatial coordinates, E is the electromagnetic intensity, and λ is the equilibrium parameter. To achieve multi-scale clustering, the cluster tree can be truncated at different distance thresholds to obtain clustering results of different granularities. This can be achieved using dynamic tree cutting algorithms, such as the dynamic hybrid tree cutting method: the cutting position is dynamically determined based on the ratio of the intra-cluster variance to the inter-cluster distance. Next, based on the multi-scale clustering results, an affinity matrix A is constructed, where Aij represents the frequency with which nodes i and j belong to the same cluster at different scales. The entire graph network is then partitioned using a spectral clustering algorithm. The main steps of spectral clustering include: 1) calculating the Laplacian matrix L = DA, where D is the degree matrix; 2) calculating the eigenvalues and eigenvectors of L; 3) selecting the eigenvectors corresponding to the k smallest non-zero eigenvalues to form a matrix U; 4) treating the rows of U as points in k-dimensional space and clustering using the K-means algorithm. During the partitioning process, the continuity of the electromagnetic environment and the integrity of the road network need to be considered. Constraints need to be introduced based on the affinity matrix. This electromagnetic environment map network partitioning method based on multi-scale clustering and spectral clustering can not only effectively capture the spatial structural characteristics of the electromagnetic environment, but also adapt to monitoring needs at different scales.

[0091] S105. Deploy an on-board electromagnetic inspection vehicle equipped with an edge server in the area where each regional sub-map is located, and deploy a central server in the central area of the target area. Import the regional sub-map into the corresponding edge server, import the electromagnetic environment map network into the central server, and all edge servers are connected to the central server in communication.

[0092] Among them, the on-board electromagnetic inspection vehicle includes an intelligent unmanned inspection vehicle, an on-board frequency selector, an on-board measuring probe and a satellite positioning device. The on-board frequency selector and the on-board measuring probe are installed on the roof of the inspection vehicle. No vehicle modification is required. They are easy to install and use, and the connection reliability is guaranteed. The on-board measuring probe is not less than 0.2m away from the roof and is equipped with a non-vehicle-modified on-board bracket for easy installation and disassembly. In order to meet the minimum speed limit of 60km / h on expressways, the equipment sampling time interval is no more than 300 milliseconds to meet the requirement that the distance between survey points should not exceed 5m. By optional mobile power supply, 24-hour fixed-point long-term continuous monitoring is supported. Reference Figure 2 The vehicle-mounted frequency selector includes a multi-layer architecture including the application layer, communication layer, hardware layer, and storage layer. The vehicle-mounted measurement probe can be a medium- and short-wave frequency selector probe, a radio frequency electromagnetic field probe, or a low-frequency electromagnetic field probe. Different probes can be replaced according to the actual environment. The following are the relevant parameters of each probe:

[0093] 1. The parameters of medium and short wave frequency selective probe are as follows:

[0094] 1) Frequency range: 100kHz~30MHz;

[0095] 2) Detection limit: electric field 0.05V / m-500V / m, magnetic field 0.001A / m-10A / m;

[0096] 3) Frequency response: ≤±1.5dB;

[0097] 4) Isotropy: ≤1dB;

[0098] 5) Dynamic range: ≥80dB;

[0099] 6) Frequency error: <±0.1%;

[0100] 7) Linearity: ≤±1dB;

[0101] 8) Meet the technical requirements of the "Method for Monitoring the Environmental Electromagnetic Radiation of Medium Wave Broadcasting Transmitters" (HJ1136-2020) and "Method for Monitoring the Environmental Electromagnetic Radiation of Short Wave Broadcasting Transmitters" (HJ1199-2021).

[0102] 9) Frequency resolution: optional, supports 5kHz, 10kHz, 30kHz, 50kHz, 100kHz, etc.

[0103] 10) Data acquisition sampling rate: supports 1 time / second.

[0104] 11) Measurement results: electric field spectrum and selected frequency field strength value, magnetic field spectrum and selected frequency field strength value, real-time value and 6-minute average value.

[0105] 2. The parameters of the radio frequency electromagnetic field probe are as follows:

[0106] 1) Frequency range: 20MHz~6GHz;

[0107] 2) Detection limit: lower detection limit ≤7×10-6W / m2 (0.05V / m),

[0108] Upper detection limit ≥663W / m2 (500V / m);

[0109] 3) Frequency response: ≤±1.5dB (900MHz~3GHz); ≤±3dB (<900MHz or >3GHz);

[0110] 4) Isotropy: <1dB (30MHz~3GHz), ≤2dB (3GHz~6GHz);

[0111] 5) Dynamic range: ≥80dB;

[0112] 6) Frequency error: <±0.1%;

[0113] 7) Linearity: ≤±1.5dB.

[0114] 3. The parameters of the low-frequency electromagnetic field probe are as follows:

[0115] 1) Frequency range: 1Hz~100kHz; supports 50Hz frequency monitoring;

[0116] 2) Detection limit: Detection limit under electric field ≤0.05V / m, detection limit under magnetic field ≤10nT;

[0117] 3) Isotropy: electric field ≤ 1dB, magnetic field ≤ 1dB;

[0118] 4) Dynamic range: ≥60dB;

[0119] 5) Linearity: ≤±1dB.

[0120] In this implementation, both edge and central servers can be configured with industrial-grade computers, requiring high-performance computing capabilities. When importing regional submaps into the edge server, data compression and format conversion are required. Graph compression algorithms, such as k-core decomposition or edge sampling, can be used to reduce data size. The data format should be a lightweight format suitable for edge computing, such as Protocol Buffers or MessagePack. When importing the electromagnetic environment network map into the central server, in addition to the complete graph structure, metadata, such as creation time, update frequency, and coordinate system information, must also be imported. Distributed storage systems, such as Apache Cassandra, can be used to improve data read and write performance. Fault-tolerance mechanisms should be designed into the import process, such as using a checksum to verify data integrity and an automatic retry mechanism to handle transmission failures. To ensure data security, strong encryption measures, such as the AES-256 encryption algorithm, should be implemented, along with strict access control policies. The communication connection between the edge server and the central server must consider security, reliability, and efficiency. VPN technologies, such as the IPSec protocol, can be used to establish a secure channel. This distributed electromagnetic environment monitoring system based on vehicle-mounted edge servers and central servers can not only achieve large-scale, high-precision electromagnetic environment monitoring, but also improve data processing efficiency and response speed through edge computing.

[0121] In another embodiment, in order to save costs, the edge server configuration can be cancelled, and only the data collection terminal is installed on the inspection vehicle, and the PC data collection software is deployed in the data collection terminal. Figure 3 , PC data collection software can configure UI layer, interface layer, service layer and storage layer, so as to realize simple inspection data storage, data processing and data display process.

[0122] S106. For any regional sub-map, intelligently plan the optimal electromagnetic inspection path for the on-board electromagnetic inspection vehicle in the area based on the regional sub-map, and control the on-board electromagnetic inspection vehicle to perform electromagnetic inspection along the optimal electromagnetic inspection path to collect electromagnetic inspection data for the area belonging to the regional sub-map.

[0123] In one implementation, a path planning model can be constructed based on a regional subgraph. Specifically, the problem is modeled as a vehicle routing problem with a time window (VRPTW): V = {v1,v2,...,vn} represents the set of nodes to be visited, E = {(vi,vj)|vi,vj∈V,i≠j} represents the set of feasible paths, c(vi,vj) represents the cost (e.g., distance or time) of path (vi,vj), and [ai,bi] represents the time window of node vi. The goal is to minimize the total cost: minΣc(vi,vj)x(vi,vj), where x(vi,vj) is a 0-1 variable indicating whether path (vi,vj) is selected. Constraints include: each node can only be visited once, the vehicle must arrive within the time window, and the vehicle capacity limit must not be exceeded. To account for the dynamic nature of the electromagnetic environment, dynamic weights can be introduced: w(vi,t) = f(Hi(t),Si(t)), where Hi(t) is the historical anomaly frequency of node vi at time t and Si(t) is the current electromagnetic signal strength. The path planning algorithm can use an improved ant colony algorithm (ACO). To improve algorithm efficiency, local search optimization, such as the 2-opt algorithm, can be used. Taking into account real-time traffic conditions, real-time traffic data can be integrated to dynamically adjust the path cost. For example, using the Dijkstra algorithm to calculate the shortest path in real time, the cost function can be defined as: c(vi,vj,t) = d(vi,vj) / v(t) + w(vj,t), where d is the distance, v(t) is the current average speed, and w is the node weight. To handle emergencies, a dynamic replanning mechanism can be designed: define trigger conditions, and re-execute the path planning algorithm when triggered.

[0124] Electromagnetic monitoring during inspections requires consideration of multiple factors. The monitoring frequency can be dynamically adjusted based on vehicle speed and environmental change rate: f = max(f_min, v / d + k*ΔE / Δt), where f_min is the minimum monitoring frequency, v is vehicle speed, d is spatial resolution, ΔE / Δt is the rate of change of the electromagnetic environment, and k is the adjustment factor. Monitoring parameters (such as frequency band and bandwidth) should be dynamically optimized based on historical data and real-time conditions. Real-time quality control is required during data collection, specifically using a Kalman filter to remove noise: x(k) = Ax(k-1) + Bu(k) + w(k), z(k) = Hx(k) + v(k), where x is the state vector, u is the control vector, z is the observation vector, and w and v represent process noise and observation noise. Considering the energy constraints of on-board equipment, an adaptive sampling strategy can be designed: reducing the sampling frequency in areas of stable electromagnetic environments and increasing it in areas of rapid change. By continuously optimizing algorithms and parameters, the system can adapt to different electromagnetic environments and monitoring requirements, providing efficient and flexible data collection capabilities for electromagnetic environment monitoring systems.

[0125] S107. Utilize edge computing and federated learning technologies and update the regional submap in the edge server based on the electromagnetic inspection data, and perform local electromagnetic anomaly analysis on the updated regional submap through the edge server to obtain local anomaly analysis results.

[0126] S108. After all regional submaps have been updated, the updated information of all regional submaps is aggregated through the central server and the global update of the electromagnetic environment map network is completed in the central server. The central server then performs a global electromagnetic anomaly analysis on the updated electromagnetic environment map network to obtain a global anomaly analysis result.

[0127] Among them, first the central server needs to collect update information from each edge server. In order to reduce communication overhead, an incremental update strategy can be adopted to transmit only the changed parts. When aggregating update information, possible conflicts need to be resolved. Version-based concurrency control (MVCC) can be used: assign a version number to each update, and when a conflict occurs, retain the latest version or use a predefined merge strategy. For updating the graph structure, a graph differential algorithm can be used: calculate the difference between the original graph and the updated graph, and only apply the difference. For example, the A* algorithm is used to find the minimum edit distance path between two graph versions: f(n) = g(n) + h(n), where g(n) is the actual cost from the starting state to the current state, and h(n) is the estimated cost from the current state to the target state.

[0128] After completing the global update, the central server needs to perform global anomaly analysis on the entire electromagnetic environment map network. Due to the large data size, a distributed computing framework such as Apache Spark can be used. GraphX is used for graph computation: valgraph = GraphLoader.edgeListFile(sc,"edges.txt") , followed by iterative computation using the Pregel API: valresult = graph.pregel(initialMsg)(vprog,sendMsg,mergeMsg) Global anomaly analysis can be performed from multiple dimensions. First, spatial anomaly detection can be performed using spatial autocorrelation analysis. Temporal anomaly detection can be performed using time series analysis, for example, using the ARIMA (Autoregressive Integrated Moving Average) model. Finally, to combine the results of multiple anomaly detection methods, ensemble learning techniques can be used. For example, stacking can be used to train multiple base models and then a meta-learner can be used to combine their outputs. This centralized server-based global electromagnetic anomaly analysis approach not only integrates large-scale distributed data but also discovers global patterns and trends that may be overlooked by local analysis.

[0129] S109. The local anomaly analysis results and the global anomaly analysis results are integrated into the comprehensive electromagnetic anomaly analysis results of the target area, and the comprehensive electromagnetic anomaly analysis results are imported into the regional map for visual display.

[0130] In order to fully integrate local and global information, a multi-task learning framework can be adopted. For example, a multi-task neural network with hard parameter sharing: the bottom layer shares parameters, and the top layer sets a specific output layer for each task (local anomaly detection and global anomaly detection). The model can be expressed as:

[0131] y l =softmax(W l *h+b l ), y g =softmax(W g *h+b g )

[0132] Where h is the output of the shared hidden layer. The loss function can be defined as: L = α*L + β*L g +λ*R(W), where L l and L g are the losses for local and global tasks respectively, R(W) is the regularization term, and α, β, and λ are balancing parameters.

[0133] Considering the diversity of electromagnetic anomalies, multi-label learning methods can be used. For example, the label-correlation-aware multi-label learning algorithm ML-kNN is used: for each instance x, its k nearest neighbors are found, and then multiple labels for x are predicted based on the label distribution of these neighbors. The predicted probability can be expressed as: P(Hj|Cx) = (s+cj) / (s*m+c), where Hj represents the jth event with label 1, Cx represents the number of instances with label j among x's k nearest neighbors, s is a smoothing parameter, and m is the number of labels. Based on this method, the results of local and global anomaly analysis can be fused into a comprehensive electromagnetic anomaly analysis result for the target area.

[0134] Finally, the regional map is digitized using Geographic Information System (GIS) software, and the comprehensive electromagnetic anomaly analysis results are converted into a geographic coordinate system and imported into the regional map, usually using latitude and longitude or UTM coordinates. Figure 4 Each abnormal point can be represented by a marker of different color or size. The color can reflect the degree of abnormality, and the size can indicate the scope of impact. The inspection path can be represented by continuous line segments. Different colored segments can represent different inspection time periods, forming a visual display of the path.

[0135] The regional map can also be divided into uniform grids, and the grid size can be determined according to the monitoring accuracy and regional characteristics. Each grid cell corresponds to a specific geographical location and area. Next, the comprehensive electromagnetic anomaly analysis results are mapped to these grid cells. Interpolation algorithms such as Kriging or Inverse Distance Weighted (IDW) can be used to expand the discrete measurement point data to the entire area. The degree of anomaly of each grid cell can be represented by different colors to form a heat map effect, such as Figure 5 The specific color value can be obtained through normalization: Color_value = (Anomaly_value - Min_value) / (Max_value - Min_value). The legend should clearly explain the corresponding relationship between color and anomaly level. This grid-like visualization can comprehensively reflect the electromagnetic environment of the entire area, helping to identify anomaly hotspots, assess the scope of impact, and provide a basis for formulating regional control measures.

[0136] In one embodiment, identifying historical electromagnetic radiation points as target monitoring nodes on a regional map based on historical electromagnetic detection data and an electromagnetic propagation model includes the following steps:

[0137] The free space propagation model is used as the electromagnetic propagation model of the target area;

[0138] Based on the electromagnetic propagation model, the radiation points in the target area are reversely calculated using the least squares method according to historical electromagnetic detection data;

[0139] In the reverse calculation process, the objective function of the least squares method is constructed by combining the historical electromagnetic detection data and the output values of the electromagnetic propagation model;

[0140] The objective function is solved by the optimization algorithm to complete the reverse calculation and mark all potential historical electromagnetic radiation points on the regional map;

[0141] All potential historical electromagnetic radiation points are clustered using a density clustering algorithm. After clustering, all historical electromagnetic radiation points in the regional map are obtained.

[0142] Extracting radiation point features of each historical electromagnetic radiation point from historical electromagnetic detection data, the radiation point features include the historical electromagnetic field intensity, historical abnormal frequency and spatial impact range of the historical electromagnetic radiation point;

[0143] The historical electromagnetic radiation points are used as target monitoring nodes, and the node weights of the target monitoring nodes are calculated according to the corresponding radiation point characteristics.

[0144] In this embodiment, the basic formula of the free space propagation model is: Pr = Pt*(λ / (4πd)) 2*Gt*Gr, where Pr is the received power, Pt is the transmitted power, λ is the wavelength, d is the propagation distance, Gt and Gr are the transmit and receive antenna gains, respectively. In practical applications, the model can be adjusted by introducing additional parameters, such as the path loss exponent n: Pr = Pt*(λ / (4πd)) n *Gt*Gr. This adjustment can better adapt to different environmental conditions. For example, in open areas n is close to 2, while in urban environments n may reach 4 or higher. The advantage of using the free space propagation model is its simplicity and universality, which can quickly provide a preliminary estimate of the electromagnetic field strength for a large area. Next, based on the free space propagation model, the least squares method is used to reversely infer the radiation points in the target area. The large amount of historical electromagnetic detection data obtained includes field strength measurements at different locations. Establish an optimization problem whose goal is to find the most likely radiation source location and power so that the difference between the predicted value and the actual measured value is minimized. Specifically, the error function can be defined: E = ∑(Pi m -Pi p ) 2 , where Pi_m is the actual field strength at the i-th measurement point, and Pi_p is the predicted field strength calculated based on the assumed radiation source location and power. By minimizing this error function, the optimal radiation source parameters can be obtained. In practice, iterative algorithms such as gradient descent can be used to solve this optimization problem. Furthermore, considering the possibility of multiple radiation sources, a step-by-step approximation approach can be employed: first locating the primary radiation source, then gradually considering the contributions of secondary sources. This reverse calculation method effectively utilizes historical data and provides important radiation source information for electromagnetic environment monitoring and management.

[0145] In the reverse calculation process, the construction of the least squares objective function is a key step. This function needs to comprehensively consider the historical electromagnetic detection data and the output values of the electromagnetic propagation model. The objective function is usually defined as the sum of the squares of the differences between the actual measured values and the model predicted values: F = ∑wi*(Mi-Pi(θ)) 2 , where Mi is the actual field strength at the i-th measurement point, Pi(θ) is the predicted field strength calculated based on the current parameters θ (including the radiation source position and power), and wi is the weighting factor. The weighting factor can be set based on the reliability or importance of the measurement point. For example, recent data or measurements with a high signal-to-noise ratio can be given a higher weight. The reverse calculation is then completed by solving the objective function through an optimization algorithm. Commonly used optimization algorithms include gradient descent, Newton's method, and Levenberg-Marquardt algorithm. Taking the gradient descent method as an example, its iterative formula is: Where η is the learning rate, is the gradient of the objective function under the current parameters. In order to accelerate convergence and avoid falling into local optimality, momentum method or adaptive learning rate method such as Adam algorithm can be used. During the solution process, it is necessary to set appropriate initial values and stopping conditions. For example, the grid search method can be used to find a better initial value, and decide when to stop based on the change in the objective function value or the number of iterations. After the solution is completed, the optimal parameter θ* contains the inferred radiation source location and power information. Next, these potential historical electromagnetic radiation points need to be marked on the regional map. Geographic Information System (GIS) tools can be used to convert longitude and latitude coordinates into specific locations on the map.

[0146] Next, a density clustering algorithm is used to cluster all potential historical electromagnetic radiation points, thereby identifying the true radiation source locations and eliminating the influence of noise points. Common density clustering algorithms include DBSCAN (Density-Based Spatial Clustering with Applied Noise) and OPTICS (Ordering Points to Identify Cluster Structure). Taking DBSCAN as an example, its core concept is to consider an area containing at least MinPts points within a given radius ε as a dense area. The main steps of the algorithm include: 1) For each unvisited point p, calculate the number of points in its ε-neighborhood; 2) If the number of points is greater than or equal to MinPts, create a new cluster and mark point p as a core point; 3) Recursively add all points in p's ε-neighborhood to the cluster; 4) Repeat the above steps until all points have been visited. A key advantage of DBSCAN is its ability to automatically identify noise points, eliminating the need to predefine the number of clusters. In practical applications, the ε and MinPts parameters need to be appropriately set based on the characteristics of the electromagnetic environment. For example, these parameters can be determined based on the expected density and distribution range of radiation sources. After clustering is completed, the center of each cluster can be considered a historical electromagnetic radiation point. For each cluster, its centroid can be calculated as the final radiation point location: (x, y) = (∑xi / n, ∑yi / n), where (xi, yi) are the coordinates of the i-th point in the cluster, and n is the total number of points in the cluster. This method effectively merges densely distributed potential radiation points while filtering out isolated points that may be caused by measurement errors or environmental interference, resulting in a more reliable historical electromagnetic radiation point distribution.

[0147] Next, the characteristics of each historical electromagnetic radiation point are extracted from the historical electromagnetic detection data. Radiation point characteristics typically include historical electromagnetic field strength, historical anomaly frequency, and spatial impact range. For historical electromagnetic field strength, the average, maximum, minimum, and standard deviation over a period of time can be calculated. The historical anomaly frequency can be defined as the frequency at which field strength exceeds a certain threshold, which can be set as the average value plus a multiple of the standard deviation. The spatial impact range can be determined by analyzing the attenuation of field strength with distance. Interpolation methods (such as kriging) can be used to generate a field strength distribution map. The impact range is then determined as the distance at which the field strength drops to a certain threshold (e.g., 10% of the maximum value). After feature extraction, historical electromagnetic radiation points are designated as target monitoring nodes, and node weights are calculated based on the corresponding radiation point characteristics. The calculation of node weights requires comprehensive consideration of multiple factors, and a weighted summation method can be used: W = w1*F1+w2*F2+w3*F3, where F1, F2, and F3 represent the normalized historical electromagnetic field strength, historical anomaly frequency, and spatial impact range, respectively, and w1, w2, and w3 are the corresponding weighting coefficients. Normalization can be performed using the min-max method. The choice of weight coefficient can be tailored to the needs of the specific application scenario. For example, if anomalies are of particular concern, the weight of the historical anomaly frequency can be increased. To make the weight more dynamic, a time decay factor can be introduced: W(t) = W*exp(-λ*Δt), where λ is the decay coefficient and Δt is the time interval. This allows the most recent observation to have a greater influence on the weight. Weight information can be used to construct an electromagnetic environment graph network, where the edge weight between nodes can be defined as a function of the weights of the two nodes. This weight calculation method based on historical data and feature analysis can effectively capture the important characteristics of the electromagnetic environment, providing an important basis for subsequent monitoring strategy formulation and anomaly detection.

[0148] In one embodiment, a hierarchical clustering algorithm is used to perform multi-scale clustering on target monitoring nodes in an electromagnetic environment map network. Based on the preliminary clustering results of the multi-scale clustering, the electromagnetic environment map network is divided into multiple regional sub-maps using a spectral clustering algorithm, including the following steps:

[0149] Construct a multi-dimensional feature vector of the target monitoring node based on the radiation point characteristics;

[0150] The principal component analysis method is used to reduce the multi-dimensional feature vector into a low-dimensional feature vector;

[0151] The low-dimensional feature vectors are clustered using a hierarchical clustering algorithm based on the minimum spanning tree to obtain a feature clustering tree;

[0152] Multiple different cutoff thresholds are calculated based on the average node distance between the root node and the leaf nodes in the feature clustering tree;

[0153] The feature clustering tree is truncated based on each truncation threshold to obtain feature clustering results of multiple different scales;

[0154] Construct an affinity matrix based on the feature clustering results at multiple different scales;

[0155] The affinity matrix is used as the constraint condition of the spectral clustering algorithm. Based on the constraint condition and the spectral clustering algorithm, the electromagnetic environment map network is divided into multiple regional sub-graphs.

[0156] In this embodiment, the radiation point characteristics include historical electromagnetic field strength, frequency distribution, spatial influence range, etc. For each monitoring node, a feature vector V = [E_avg, E_max, E_std, f_main, BW, R] is constructed. In order to process features of different dimensions, standardization processing is usually required, such as Z-score standardization. The feature vector processed in this way can better reflect the electromagnetic environment characteristics of each monitoring node, and provide a comparable data basis for subsequent analysis and clustering. The principal component analysis (PCA) is then used to reduce the multi-dimensional feature vector to a low-dimensional feature vector. The core idea of PCA is to find the main direction of change of the data, that is, the principal component. The specific steps include: 1) calculating the covariance matrix; 2) solving the eigenvalues and eigenvectors of the covariance matrix; 3) selecting the eigenvectors corresponding to the largest k eigenvalues as the principal components; 4) projecting the original data onto these k principal components. The eigenvector after dimensionality reduction can be expressed as: V new =P T *V, where P is the matrix consisting of k principal components and V is the original eigenvector. Typically, the number of principal components is chosen to explain 80% to 90% of the variance. PCA not only reduces data dimensionality but also removes noise, highlighting key features, and providing a more streamlined and efficient data representation for subsequent cluster analysis.

[0157] Next, we use a hierarchical clustering algorithm based on the minimum spanning tree to cluster the low-dimensional feature vectors and obtain a feature clustering tree. First, we construct a complete graph, and the distance between nodes can be calculated using the Euclidean distance: The Kruskal algorithm is then used to construct a minimum spanning tree: 1) sort all edges by weight; 2) select the edge with the smallest weight in sequence, adding it to the tree if it does not form a cycle; 3) repeat until n-1 edges have been selected. Finally, hierarchical clustering is performed based on the minimum spanning tree: starting with the longest edge, edges are progressively deleted, forming a new cluster with each deletion. This method effectively captures the hierarchical structure of the data and is suitable for processing data with non-spherical distributions. Truncation thresholds are calculated based on the characteristic clustering tree, and the tree is truncated at each threshold to obtain multi-scale clustering results. An affinity matrix is then constructed. Specifically, multiple percentile thresholds can be selected as thresholds, such as 25%, 50%, and 75% of the node distance. The elements aij of the affinity matrix A represent the number of times nodes i and j are clustered together at different scales. Finally, the affinity matrix is used as a constraint for spectral clustering. Based on these constraints, the spectral clustering algorithm is used to partition the electromagnetic environment network into multiple regional subgraphs. This multi-scale constrained spectral clustering method better captures the spatial structure of the electromagnetic environment and produces more reasonable regional divisions.

[0158] In one embodiment, the affinity matrix is used as a constraint condition of the spectral clustering algorithm. Based on the constraint condition and using the spectral clustering algorithm, the electromagnetic environment map network is divided into multiple regional sub-graphs, including the following steps:

[0159] The degree matrix of the electromagnetic environment map network is calculated, and the normalized Laplace matrix of the electromagnetic environment map network is calculated based on the degree matrix;

[0160] Calculate the matrix eigenvalues and matrix eigenvectors of the normalized Laplace matrix;

[0161] Select the matrix eigenvectors corresponding to the k smallest non-zero matrix eigenvalues to form a spectral clustering matrix;

[0162] Construct the objective optimization function of the spectral clustering algorithm;

[0163] The target optimization function is solved by generalized eigenvalues, and the K eigenvectors of the target matrix obtained are combined into a subgraph matrix;

[0164] The K-means algorithm is used to cluster the row vectors of the subgraph matrix, and the electromagnetic environment map network is divided into multiple regional subgraphs according to the clustering results.

[0165] In this embodiment, the adjacency matrix W of the electromagnetic environment graph network is first constructed, where Wij represents the similarity or connection strength between nodes i and j. The degree matrix D is a diagonal matrix whose diagonal elements Dii are equal to the degree of node i. The normalized Laplace matrix L is defined as: L = ID (-1 / 2) WD (-1 / 2), where I is the identity matrix. This normalization can reduce the influence of node degree, making the clustering results more balanced. Next, we need to calculate the matrix eigenvalues and matrix eigenvectors of the normalized Laplacian matrix. This step utilizes the eigendecomposition theory in linear algebra. For an n×n symmetric matrix L, solve the characteristic equation Lv=λv, where λ is the eigenvalue and v is the corresponding eigenvector. The numerical calculation is usually performed using the QR algorithm or the Lanczos algorithm. The result is n eigenvalues λ1≤λ2≤...≤λn and their corresponding eigenvectors v1, v2,..., vn. The eigenvalues reflect important structural information of the graph, and the eigenvectors corresponding to smaller eigenvalues contain key information about the graph partitioning. The matrix eigenvectors corresponding to the k smallest non-zero matrix eigenvalues are then selected to form the spectral clustering matrix. Here, k is usually equal to the desired number of clusters. The smallest non-zero eigenvalues are chosen because they contain the most important information about the graph structure. These k eigenvectors are arranged in columns to form the n×k spectral clustering matrix Y. This matrix Y actually maps the original n-dimensional data points into a k-dimensional space. In this new space, the distribution of data points is easier to cluster. This step not only achieves dimensionality reduction but also preserves key information about the graph structure, laying the foundation for subsequent clustering.

[0166] Next, we construct the objective optimization function of the spectral clustering algorithm in order to formalize the problem into a mathematical optimization problem. The objective function of the standard spectral clustering is usually defined as: min tr(Y T LY), stY T Y = I, this optimization problem is equivalent to minimizing the normalized cut. However, in practical applications, it is necessary to introduce additional constraints based on the affinity matrix to improve the clustering effect. The final target optimization function is:

[0167] min tr(Y T LY)+λ[tr(Y T (DA)Y)]

[0168] Where tr represents the trace of the matrix, Y represents the spectral clustering matrix, L represents the normalized Laplace matrix, λ represents the balance parameter, T represents the transposed matrix, D represents the degree matrix, and A represents the affinity matrix.

[0169] Next, the objective optimization function is solved through the generalized eigenvalue problem. Taking into account the aforementioned constraints, this optimization problem can be transformed into solving the generalized eigenvalue equation: (L+αC)y=λDy, where D is the degree matrix. Numerical methods such as the Lanczos algorithm or Arnoldi iteration can be used to solve this equation. Specifically, it is necessary to find the eigenvectors corresponding to the K smallest generalized eigenvalues. These eigenvectors form an n×K subgraph matrix, where each column represents an eigenvector and each row corresponds to the representation of a node in the new K-dimensional space. This step is actually looking for an optimal low-dimensional representation so that in the new space, similar nodes are closer and dissimilar nodes are farther apart. The subgraph matrix contains the essential information of the graph structure and provides an ideal data representation for the final clustering.

[0170] Finally, the K-means algorithm is used to cluster the row vectors of the subgraph matrix. This process is also the key to converting continuous spectral embedding into discrete clustering results. The basic idea of the K-means algorithm is to divide n data points into K clusters so that each data point belongs to the cluster center closest to it. The specific steps are as follows: 1) Randomly select K initial cluster centers; 2) Assign each data point to the nearest cluster center; 3) Recalculate the center of each cluster; 4) Repeat steps 2 and 3 until convergence or the maximum number of iterations is reached. Here, the data points are the row vectors of the subgraph matrix Y, and each row vector represents the coordinates of a node in the K-dimensional space. After clustering is completed, each node is assigned to a cluster, which results in the regional subgraph division of the electromagnetic environment map network.

[0171] In one embodiment, intelligent planning of an optimal electromagnetic inspection path for an on-board electromagnetic inspection vehicle within a region based on a region subgraph includes the following steps:

[0172] Obtain the historical traffic flow data of the road network in the area to which the regional subgraph belongs, and assign node edge weights to the node edges of the regional subgraph based on the historical traffic flow data;

[0173] The target monitoring node with the highest node weight is used as the starting node;

[0174] The optimal path selection steps are performed based on the starting node. The optimal path selection steps are as follows:

[0175] Calculate the node distance between the starting node and all adjacent nodes;

[0176] A multi-objective reward function is constructed by combining node distance, node weights of adjacent nodes, and node edge weights of the node edges between the starting node and adjacent nodes;

[0177] Based on the multi-objective reward function and the Monte Carlo tree search method, the best adjacent node is selected from all adjacent nodes as the optimal path node;

[0178] The optimal path node is used as the starting node and the optimal path selection step is repeatedly performed until the farthest node distance between the optimal path node and the starting node exceeds a preset distance threshold, thereby obtaining the optimal electromagnetic inspection path of the vehicle-mounted inspection vehicle.

[0179] In this embodiment, historical traffic flow data can be obtained from traffic management departments or intelligent transportation systems. These data usually include information such as traffic flow and average vehicle speed at different time periods. Then, these data are mapped to the road network of the regional subgraph. For example, the weighted average method can be used to calculate the traffic flow weight of each road: W = ∑(w i *f i ) / ∑w i , where f_i is the traffic volume in the i-th time period, and w_i is the weight of the time period (which can be adjusted according to the inspection time). This method not only takes into account the importance of the road, but also reflects the traffic characteristics of different time periods, providing an important reference for subsequent path planning. Then traverse all target monitoring nodes and compare their weight values. A simple linear search or a more efficient data structure such as a max heap can be used to find the maximum weight node. For example, if there are nodes A (weight 10), B (weight 15), and C (weight 8), then node B is selected as the starting node. There are several advantages to choosing a high-weight node as the starting point: 1) the most important or most complex areas can be monitored first; 2) it is conducive to covering the maximum monitoring value within a limited time; 3) it may be easier to detect potential electromagnetic anomalies.

[0180] Next, the optimal path selection step is performed based on the starting node. The optimal path selection step involves the following sub-steps:

[0181] 1) Calculate the node distances between the starting node and all adjacent nodes. This distance can be physical distance, travel time, or a weighted distance that takes into account multiple factors. For example, the straight-line distance between two nodes can be calculated using Euclidean distance, or the actual road length can be used. This step provides essential spatial information for subsequent path selection, helping to determine the possible range and direction of movement.

[0182] 2) Construct a multi-objective reward function by combining node distance, node weights of adjacent nodes, and node edge weights. This reward function needs to balance multiple objectives, including minimizing travel distance, maximizing monitoring value, and optimizing traffic flow. The reward function can be in the form of: R = α*(1 / d) + β*W n +γ*W e, where d is the node distance, W_n is the neighboring node weight, W_e is the edge weight, and α, β, and γ are balancing parameters. This function encourages the selection of paths with moderate distances, high node importance, and good road conditions. The parameters can be adjusted based on specific needs. For example, if monitoring coverage is more important, the value of β can be increased.

[0183] 3) Based on a multi-objective reward function, the Monte Carlo Tree Search (MCTS) method is used to select the optimal adjacent nodes. MCTS evaluates the long-term value of each choice by simulating a large number of possible paths. Its basic steps include selection, expansion, simulation, and backtracking. During the selection phase, the UCT (Upper Confidence Bound for Trees) formula is used to balance exploration and exploitation. The advantage of MCTS lies in its ability to find near-optimal solutions in complex decision spaces, making it particularly well-suited for dynamically changing environments. Through numerous simulations, MCTS can predict the long-term impact of different choices, enabling more informed decisions.

[0184] Next, the optimal path node is used as the new starting node, and the optimal path selection steps are repeated until the preset distance threshold is reached. This process gradually constructs the entire inspection path. A new optimal node is selected for inclusion in each iteration, and the list of visited nodes is updated in each iteration to avoid duplicate visits. Furthermore, the parameters of the reward function can be dynamically adjusted; for example, as the path extends, the weight of returning to the starting point can be gradually increased. This process can end in a variety of situations: reaching the distance threshold, visiting all important nodes, or reaching the inspection time limit. The resulting path not only takes into account spatial coverage but also balances monitoring value and traffic conditions, providing an optimized electromagnetic monitoring path solution for vehicle-based inspections.

[0185] In one embodiment, controlling the on-board electromagnetic inspection vehicle to perform electromagnetic inspection along the optimal electromagnetic inspection route and collecting electromagnetic inspection data of the area belonging to the regional sub-map includes the following steps:

[0186] Before using the optimal path node as the starting node in each round of the optimal path selection step, obtain the real-time traffic flow data of the road network in the area to which the regional subgraph belongs, and update the edge weights of all nodes in the regional subgraph according to the real-time traffic flow data;

[0187] After the optimal path node is determined in each round of the optimal path selection step, the on-board electromagnetic inspection vehicle is controlled to travel from the starting node to the optimal path node, and electromagnetic inspection data around the on-board electromagnetic inspection vehicle is continuously collected during the driving process.

[0188] In this embodiment, during each round of the optimal path selection step, real-time traffic flow data for the road network in the region to which the regional subgraph belongs is updated, and node and edge weights are updated accordingly. This step first requires real-time traffic flow data from an intelligent transportation system or road condition monitoring device. This data includes vehicle density, average speed, and congestion index. Traffic flow density D = N / L (where N is the number of vehicles and L is the road length) can be used to represent road congestion. This real-time data is then combined with historical data to update the weights of each edge. An exponential moving average method can be used to smooth the update. This method considers both current road conditions and historical trend information. The updated weights directly influence the next step of path selection, allowing inspection vehicles to avoid unexpectedly congested sections and select more unobstructed routes. This dynamic update mechanism makes inspection route planning more flexible, adapts to real-time traffic changes, and improves inspection efficiency and coverage. After the optimal path node is determined in the optimal path selection step, the on-board electromagnetic inspection vehicle is controlled to travel from the starting node to the optimal path node, continuously collecting surrounding electromagnetic inspection data during travel.

[0189] In one embodiment, edge computing and federated learning technologies are used to update a regional submap in an edge server based on electromagnetic inspection data, and local electromagnetic anomaly analysis is performed on the updated regional submap by the edge server to obtain a local anomaly analysis result, including the following steps:

[0190] Deploy the same graph neural network model on all edge servers;

[0191] For any edge server, the preprocessed electromagnetic inspection data is input into the graph neural network model, and the graph structure learning method is used to update the regional subgraph on the edge server, and the model parameters of the graph neural network model are simultaneously updated;

[0192] Use the federated averaging algorithm to exchange updated model parameters with all other edge servers;

[0193] Update the local graph neural network model based on the exchanged model parameters;

[0194] The multi-scale anomaly score of the updated regional subgraph is calculated through the multi-layer graph attention network structure in the updated graph neural network model, and the local electromagnetic anomaly analysis result of the regional subgraph is calculated using the ensemble learning method.

[0195] In this implementation, we first need to design a graph neural network model suitable for electromagnetic environment analysis, which typically includes multiple layers of graph convolution or graph attention layers. For example, we can use the Graph Attention Network (GAT) as the basic structure: Where h_i is the feature of node i, α_ij is the attention coefficient, and W is the weight matrix. The model's input layer receives node features (such as location and historical anomaly frequency) and edge features (such as signal strength changes). The middle layer performs feature extraction and information transfer, and the output layer is used for anomaly detection or classification. After the model structure is determined, it needs to be initialized and deployed to each edge server. Ensure that all servers use the same initial model. The deployment process also includes configuring the operating environment and setting up data interfaces.

[0196] For any edge server, the preprocessed electromagnetic inspection data is input into the graph neural network model, and the graph structure learning method is used to update the regional subgraph and model parameters. Specifically, preprocessing can include data standardization, outlier processing and feature extraction. The graph structure learning method can dynamically adjust the topological structure of the graph, such as using the attention mechanism to calculate the weight of the edge. The model parameter update usually uses the backpropagation algorithm. This process not only updates the model parameters, but also adjusts the structure of the regional subgraph according to the new data, so that the model can better capture the dynamic characteristics of the local electromagnetic environment. The updated model parameters are then exchanged with all other edge servers using the federated averaging algorithm to achieve distributed learning. The federated averaging algorithm allows the learning results of all edge servers to be utilized while protecting data privacy. The specific process is as follows: First, each edge server i trains the model on local data to obtain the updated parameters θ_i. Then, all servers share the parameters in a point-to-point network. Each edge server calculates the average parameter: θ avg =(1 / N)*∑ i θ i , where N is the number of edge servers. To protect privacy, secure aggregation protocols such as homomorphic encryption can be used. Finally, the exchanged model parameters are used to update the local graph neural network model, completing the federated learning of the model in the edge server.

[0197] Next, the updated graph neural network model uses a multi-layer graph attention network structure to calculate the multi-scale anomaly score of the updated regional subgraph, and an ensemble learning method is used to calculate the local electromagnetic anomaly analysis results of the regional subgraph. The multi-layer graph attention network can capture features at different scales. The attention mechanism of each layer can be expressed as:

[0198]

[0199] Multi-scale anomaly scores can be calculated by aggregating the outputs of different layers: score_i = f(h_i^1, h_i^2, ..., h_i^L), where f can be a simple average or a weighted sum. Ensemble learning methods can combine the outputs of multiple models, such as using random forests or gradient boosting trees. The final anomaly analysis result is a probability distribution or a binary classification (normal / abnormal).

[0200] In one embodiment, a central server aggregates update information of all regional submaps and completes a global update of the electromagnetic environment map network in the central server. The central server performs a global electromagnetic anomaly analysis on the updated electromagnetic environment map network to obtain a global anomaly analysis result, including the following steps:

[0201] Aggregate updated information of all regional subgraphs from all edge servers through the central server using an incremental update strategy;

[0202] Based on all updated information and using graph difference algorithm, the global update of the electromagnetic environment map network is completed in the central server;

[0203] The autoregressive integrated moving average method is used to extract the time dimension anomaly features from the updated electromagnetic environment map network;

[0204] Spatial autocorrelation analysis is used to extract spatial dimension anomaly features from the updated electromagnetic environment map network;

[0205] The global anomaly analysis results are obtained by combining the abnormal features of spatial dimension and temporal dimension and adopting ensemble learning method.

[0206] In this embodiment, the incremental update strategy only transmits the changed parts rather than the entire subgraph, which greatly reduces the amount of data transmission. In specific implementation, each edge server maintains a version number and update log. When the local subgraph changes, the server records the changes (such as new nodes, deleted edges, attribute modifications, etc.) and the corresponding timestamps. The central server requests updates from the edge server regularly or on demand, and the edge server only sends the changes since the last synchronization. After receiving these update information, the central server applies the changes in timestamp order. To handle possible conflicts, version-based concurrency control can be used: if the received update is based on an old version, the central server may need to request the complete subgraph data. This method not only reduces the network load, but also improves the real-time performance of updates, enabling the global graph network to quickly reflect local changes.

[0207] Based on all updated information, a global update of the electromagnetic environment map network is completed in a central server using a graph differencing algorithm. Specifically, the graph differencing algorithm can efficiently handle the dynamic changes of large-scale graphs. Its basic idea is to represent graph changes as a series of basic operations (such as adding / deleting nodes or edges, modifying attributes, etc.). The algorithm first constructs a difference graph ΔG to represent all changes. Then, this difference graph is applied to the original graph G to obtain the updated graph G'. In specific implementation, the graph can be represented using an adjacency list or adjacency matrix, and the difference operation can be expressed as a modification of these data structures.

[0208] After the global update is completed, the autoregressive integrated moving average (ARIMA) method is used to extract time-dimensional anomaly features from the updated electromagnetic environment network. The ARIMA model combines three components: autoregression (AR), differencing (I), and moving average (MA), and can effectively process time series data. For each node or key feature in the electromagnetic environment network, an ARIMA (p, d, q) model can be constructed, where p is the number of autoregressive terms, d is the number of differencing terms, and q is the number of moving average terms. The model can be expressed as: φ(B)(1-V) d X t =θ(B)ε t , where B is the lag operator, and φ and θ are the AR and MA polynomials, respectively. In implementation, the time series is first tested for stationarity (such as the ADF test) and, if nonstationary, differencing is performed. The autocorrelation function (ACF) and partial autocorrelation function (PACF) are then used to determine the values of p and q. After fitting the model, it can be used to forecast future values and calculate prediction intervals. Anomalies can be defined as situations where the actual value falls outside the prediction interval. For example, if the actual value falls outside the 95% prediction interval, this may indicate an anomaly.

[0209] On the other hand, spatial autocorrelation analysis is used to extract spatial dimension anomaly features from the updated electromagnetic environment map network. Spatial autocorrelation analysis is based on the first law of geography: things that are close together are more correlated than things that are far away. In the electromagnetic environment map network, this is manifested as the electromagnetic characteristics of adjacent areas are likely to be more similar. Commonly used spatial autocorrelation indicators include the Global Moran's Index (GMO) and the Local Moran's Index (LGMO). The calculation formula for the Global Moran's Index is:

[0210]

[0211] Where N is the number of nodes, W is the sum of weights, and w_ij is the spatial weight. I values close to 1 indicate positive correlation, close to -1 indicate negative correlation, and close to 0 indicate random distribution. The local Moran index is used to identify local clusters and can find hot and cold areas. When implementing, it is first necessary to define the spatial weight matrix, which can be based on distance or adjacency. Then the global and local indices are calculated and significance tests are performed. Anomalies can be defined as significant high-value clusters (hot spots) or low-value clusters (cold spots), or outliers that are significantly different from the surrounding environment. This method can effectively identify spatial anomaly patterns in the electromagnetic environment, such as the location of interference sources or the propagation range of abnormal signals.

[0212] Finally, the spatial and temporal anomaly features are combined and analyzed using ensemble learning methods to obtain global anomaly analysis results. Ensemble learning improves overall performance and robustness by combining the predictions of multiple models. In this scenario, methods such as random forests, gradient boosting trees (such as XGBoost), or stacked ensembles can be used. First, the temporal anomaly features obtained from the ARIMA model and the spatial anomaly features obtained from spatial autocorrelation analysis are combined into a feature vector. Next, multiple base models are trained, each potentially focusing on a different subset of features or using a different algorithm. For example, a decision tree can be trained to focus on temporal patterns, while a support vector machine can be trained to focus on spatial patterns. Finally, the predictions of these base models are combined using voting, weighted averaging, or a meta-learner. The above steps not only comprehensively consider spatiotemporal features but also improve detection accuracy and generalization by integrating multiple models, providing reliable results for global anomaly analysis of the electromagnetic environment.

[0213] In one embodiment, after the local anomaly analysis results and the global anomaly analysis results are merged into the comprehensive electromagnetic anomaly analysis results of the target area, the following steps are further included:

[0214] Build a spatiotemporal graph convolutional network model;

[0215] The electromagnetic environment map network and the comprehensive electromagnetic anomaly analysis results are fed as input data into the spatiotemporal graph convolutional network model;

[0216] The spatiotemporal graph convolutional network model is used to predict the spatiotemporal evolution trend of electromagnetic anomalies in the target area and output the predicted spatiotemporal evolution results of electromagnetic anomalies;

[0217] The graph network structure of the electromagnetic environment graph network and the node weights of the target monitoring nodes are adjusted according to the spatiotemporal evolution results of electromagnetic anomalies.

[0218] In this embodiment, constructing a spatiotemporal graph convolutional network model is a key step in capturing the spatiotemporal dynamic characteristics of the electromagnetic environment. This model combines the advantages of graph convolutional networks (GCNs) and temporal convolutional networks (TCNs) and can simultaneously process information in both spatial and temporal dimensions. The model structure typically includes multiple spatiotemporal convolutional blocks, each consisting of a graph convolution layer and a temporal convolution layer. The graph convolution layer captures spatial dependencies and can be expressed as: in is the normalized adjacency matrix, H^(l) is the node feature of the lth layer, and W^(l) is the learnable weight matrix. The temporal convolution layer uses causal convolution to process temporal information, which can be expressed as: t =f(∑ i W i *I (t-i) ), where I_t is the input sequence and W_i is the convolution kernel. The model can also include attention mechanisms, such as self-attention layers: To capture long-range dependencies, the prediction result is output through a fully connected layer and an activation function (such as ReLU). This structure allows the model to simultaneously learn the spatial correlation and temporal evolution of the electromagnetic environment, providing a strong foundation for subsequent anomaly prediction.

[0219] Next, the electromagnetic environment map network and the comprehensive electromagnetic anomaly analysis results are input as input data into the spatiotemporal graph convolutional network model, and the spatiotemporal graph convolutional network model is used to predict the spatiotemporal evolution trend of electromagnetic anomalies in the target area, and output the predicted spatiotemporal evolution results of electromagnetic anomalies. During the prediction process, the model performs forward propagation through multiple spatiotemporal convolution blocks, and each block captures spatiotemporal dependencies at different scales. For example, the first block may focus on local short-term patterns, while subsequent blocks may capture larger-scale and longer-term patterns. The predicted output can be the anomaly probability or degree of anomaly for each node in the next H time steps. Specifically, if a softmax output layer is used, the model can output a probability distribution for each node in each future time step: P(y i , t|X,A,T)=softmax(f θ (X, A, T)), where f_θ represents the function of the entire network. To evaluate the prediction performance, metrics such as mean squared error (MSE), mean absolute error (MAE), or area under the ROC curve (AUC) can be used.

[0220] Based on the predicted anomaly evolution trend, the edge weights of the graph network can be adjusted. For example, if the anomaly correlation between two nodes increases, the weight of the edge between them can be increased: w′ ij =w ij *(1+α*corr(y i ,y j )), where Corr(y i ,y j ) is the correlation coefficient of the predicted anomalies of nodes i and j, and α is the adjustment factor. For node weight adjustment, it can be based on the degree of abnormality and uncertainty of the prediction. For example, information entropy is used to quantify the uncertainty of the prediction: H i =-∑ k p ik log(p ik ), where p ik is the predicted probability of node i in category k. The new node weight can be defined as: i =w i *(1+β*H i +γ*y i), where y_i is the predicted anomaly level, and β and γ are balancing parameters. This adjustment strategy enables the network structure to adapt to dynamic changes in the electromagnetic environment, focusing on areas of high risk and high uncertainty. This adaptive approach can improve monitoring efficiency and better allocate limited monitoring resources, thereby enhancing the overall electromagnetic environment anomaly detection capability.

[0221] The present invention also discloses a regional electromagnetic patrol system based on a vehicle-mounted electromagnetic detection device, comprising a memory, a processor, and a computer program stored in the memory and runnable on the processor. When the processor executes the computer program, it implements the regional electromagnetic patrol method based on the vehicle-mounted electromagnetic detection device as described in any one of the above embodiments.

[0222] Among them, the processor can adopt a central processing unit (CPU). Of course, according to actual usage, other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. can also be adopted. The general-purpose processor can adopt a microprocessor or any conventional processor, etc., and this application does not impose any restrictions on this.

[0223] Among them, the memory can be an internal storage unit of a computer device, such as a hard disk or memory of a computer device, or an external storage device of a computer device, such as a plug-in hard disk, smart memory card (SMC), secure digital card (SD) or flash memory card (FC) equipped on the computer device. In addition, the memory can also be a combination of an internal storage unit and an external storage device of a computer device. The memory is used to store computer programs and other programs and data required by the computer device. The memory can also be used to temporarily store data that has been output or is to be output. This application does not impose any restrictions on this.

[0224] Those skilled in the art should understand that the discussion of any of the above embodiments is merely illustrative and is not intended to imply that the scope of protection of the present application is limited to these examples. In line with the present application, the technical features in the above embodiments or different embodiments may be combined, the steps may be implemented in any order, and there are many other variations of different aspects of one or more embodiments of the present application as above, which are not provided in detail for the sake of simplicity.

[0225] The one or more embodiments of this application are intended to encompass all such substitutions, modifications, and variations that fall within the broad scope of this application. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of one or more embodiments of this application should be included in the scope of protection of this application.

Claims

1. A regional electromagnetic inspection method based on vehicle-mounted electromagnetic detection equipment, characterized in that: The steps include: Obtain regional maps and historical electromagnetic survey data for the target area; Based on the historical electromagnetic detection data and according to the electromagnetic propagation model, identifying historical electromagnetic radiation points as target monitoring nodes on the regional map; Using the road network in the regional map as the node edges, and combining all the target monitoring nodes to construct an electromagnetic environment map network of the target area; Performing multi-scale clustering on the target monitoring nodes in the electromagnetic environment map network using a hierarchical clustering algorithm, and dividing the electromagnetic environment map network into a plurality of regional sub-graphs using a spectral clustering algorithm based on preliminary clustering results of the multi-scale clustering; Deploy an on-board electromagnetic inspection vehicle equipped with an edge server in the area where each of the regional submaps is located, and deploy a central server in the central area of the target area, import the regional submaps into the corresponding edge servers, import the electromagnetic environment map network into the central server, and all the edge servers are communicatively connected to the central server; For any of the regional subgraphs, intelligently plan the optimal electromagnetic inspection path of the vehicle-mounted electromagnetic inspection vehicle in the area to which it belongs based on the regional subgraph, and control the vehicle-mounted electromagnetic inspection vehicle to perform electromagnetic inspection along the optimal electromagnetic inspection path, and collect electromagnetic inspection data of the area to which the regional subgraph belongs; Using edge computing and federated learning technology and based on the electromagnetic inspection data, the regional sub-map is updated in the edge server, and local electromagnetic anomaly analysis is performed on the updated regional sub-map by the edge server to obtain a local anomaly analysis result; After all the regional sub-maps have been updated, the central server aggregates the updated information of all the regional sub-maps and completes a global update of the electromagnetic environment map network in the central server, and the central server performs a global electromagnetic anomaly analysis on the updated electromagnetic environment map network to obtain a global anomaly analysis result; The local anomaly analysis result and the global anomaly analysis result are merged into a comprehensive electromagnetic anomaly analysis result of the target area, and the comprehensive electromagnetic anomaly analysis result is imported into the regional map for visual display.

2. The regional electromagnetic inspection method based on vehicle-mounted electromagnetic detection equipment according to claim 1 is characterized in that: The identifying of historical electromagnetic radiation points as target monitoring nodes on the regional map based on the historical electromagnetic detection data and according to the electromagnetic propagation model comprises the following steps: Using a free space propagation model as the electromagnetic propagation model of the target area; Based on the electromagnetic propagation model, the radiation points of the target area are reversely calculated according to the historical electromagnetic detection data and the least square method; In the reverse calculation process, the objective function of the least square method is constructed by combining the historical electromagnetic detection data and the output value of the electromagnetic propagation model; Solving the objective function through an optimization algorithm to complete the reverse calculation, and marking all potential historical electromagnetic radiation points on the regional map; Clustering all the potential historical electromagnetic radiation points using a density clustering algorithm, and obtaining all the historical electromagnetic radiation points in the regional map after clustering is completed; Extracting radiation point features of each of the historical electromagnetic radiation points from the historical electromagnetic detection data, the radiation point features including the historical electromagnetic field intensity, historical abnormal frequency, and spatial impact range of the historical electromagnetic radiation point; The historical electromagnetic radiation point is used as a target monitoring node, and the node weight of the target monitoring node is calculated according to the corresponding radiation point characteristics.

3. The regional electromagnetic inspection method based on vehicle-mounted electromagnetic detection equipment according to claim 2 is characterized in that: The method of performing multi-scale clustering on the target monitoring nodes in the electromagnetic environment map network by using a hierarchical clustering algorithm and dividing the electromagnetic environment map network into a plurality of regional sub-maps by using a spectral clustering algorithm based on the preliminary clustering results of the multi-scale clustering comprises the following steps: Constructing a multidimensional feature vector of the target monitoring node according to the radiation point features; Using principal component analysis to reduce the multidimensional feature vector into a low-dimensional feature vector; Clustering the low-dimensional feature vectors using a hierarchical clustering algorithm based on a minimum spanning tree to obtain a feature clustering tree; Calculating a plurality of different cutoff thresholds based on the average node distance between the root node and the leaf nodes in the feature clustering tree; Truncating the feature clustering tree based on each of the truncation thresholds to obtain feature clustering results of multiple different scales; Constructing an affinity matrix based on the feature clustering results at multiple different scales; The affinity matrix is used as a constraint condition of a spectral clustering algorithm, and based on the constraint condition and using the spectral clustering algorithm, the electromagnetic environment map network is divided into a plurality of regional sub-maps.

4. The regional electromagnetic inspection method based on vehicle-mounted electromagnetic detection equipment according to claim 3 is characterized in that: The method of using the affinity matrix as a constraint of a spectral clustering algorithm and dividing the electromagnetic environment map network into a plurality of regional sub-maps based on the constraint by using the spectral clustering algorithm comprises the following steps: Calculating a degree matrix of the electromagnetic environment map network, and calculating a normalized Laplace matrix of the electromagnetic environment map network based on the degree matrix; Calculating and obtaining the matrix eigenvalues and matrix eigenvectors of the normalized Laplace matrix; Select the matrix eigenvectors corresponding to the k smallest non-zero matrix eigenvalues to form a spectral clustering matrix; Construct the target optimization function of the spectral clustering algorithm, which is: min tr(Y T LY)+λ[tr(Y T (DA)Y)] Wherein: tr represents the trace of the matrix, Y represents the spectral clustering matrix, L represents the normalized Laplace matrix, λ represents the balance parameter, T represents the transposed matrix, D represents the degree matrix, and A represents the affinity matrix; Solving the target optimization function by generalized eigenvalues, and forming a subgraph matrix with the K target matrix eigenvectors obtained by the solution; The row vectors of the subgraph matrix are clustered using a K-means algorithm, and the electromagnetic environment map network is divided into a plurality of regional subgraphs according to the clustering results.

5. The regional electromagnetic inspection method based on vehicle-mounted electromagnetic detection equipment according to claim 2 is characterized in that: The intelligent planning of the optimal electromagnetic inspection path of the vehicle-mounted electromagnetic inspection vehicle in the area based on the area sub-graph includes the following steps: Obtaining historical traffic flow data of a road network in an area to which the regional subgraph belongs, and assigning node edge weights to node edges of the regional subgraph according to the historical traffic flow data; Taking the target monitoring node with the highest node weight as the starting node; An optimal path selection step is performed based on the starting node, and the optimal path selection step is as follows: Calculate the node distances between the starting node and all adjacent nodes; Constructing a multi-objective reward function by combining the node distance, the node weights of the adjacent nodes, and the node edge weights of the node edges between the starting node and the adjacent nodes; Selecting an optimal adjacent node as an optimal path node from all adjacent nodes based on the multi-objective reward function and using a Monte Carlo tree search method; The optimal path node is used as the starting node to repeatedly perform the optimal path selection step until the farthest node distance between the optimal path node and the starting node exceeds a preset distance threshold, thereby obtaining the optimal electromagnetic inspection path of the vehicle-mounted inspection vehicle.

6. The regional electromagnetic inspection method based on vehicle-mounted electromagnetic detection equipment according to claim 5 is characterized in that: Controlling the vehicle-mounted electromagnetic inspection vehicle to perform electromagnetic inspection according to the optimal electromagnetic inspection path and collecting electromagnetic inspection data of the area to which the area sub-map belongs includes the following steps: Before using the optimal path node as the starting node in each round of the optimal path selection step, obtaining real-time traffic flow data of the road network in the area to which the regional subgraph belongs, and updating the edge weights of all the nodes in the regional subgraph according to the real-time traffic flow data; After the optimal path node is determined in each round in the optimal path selection step, the on-board electromagnetic inspection vehicle is controlled to travel from the starting node to the optimal path node, and electromagnetic inspection data around the on-board electromagnetic inspection vehicle is continuously collected during the driving process.

7. The regional electromagnetic inspection method based on vehicle-mounted electromagnetic detection equipment according to claim 1 is characterized in that: The method of using edge computing and federated learning technology and updating the regional submap in the edge server based on the electromagnetic inspection data, performing local electromagnetic anomaly analysis on the updated regional submap by the edge server, and obtaining the local anomaly analysis result comprises the following steps: Deploy the same graph neural network model on all of the edge servers; For any of the edge servers, the preprocessed electromagnetic inspection data is input into the graph neural network model, a graph structure learning method is used to update the regional subgraph on the edge server, and the model parameters of the graph neural network model are simultaneously updated; Using a federated averaging algorithm to exchange the updated model parameters with all other edge servers; Updating the local graph neural network model based on the exchanged model parameters; The updated multi-layer graph attention network structure in the graph neural network model is used to calculate the multi-scale anomaly score of the updated regional subgraph, and the local electromagnetic anomaly analysis result of the regional subgraph is calculated using an integrated learning method.

8. The regional electromagnetic inspection method based on vehicle-mounted electromagnetic detection equipment according to claim 7 is characterized in that: Aggregating update information of all the regional submaps through the central server and completing a global update of the electromagnetic environment map network in the central server, and performing a global electromagnetic anomaly analysis on the updated electromagnetic environment map network through the central server to obtain a global anomaly analysis result comprises the following steps: Aggregating update information of all the regional subgraphs from all the edge servers through the central server and adopting an incremental update strategy; Based on all the update information and using a graph difference algorithm, a global update of the electromagnetic environment map network is completed in the central server; Extracting time dimension abnormal features from the updated electromagnetic environment map network using an autoregressive integrated moving average method; Extracting spatial dimension abnormal features from the updated electromagnetic environment map network using a spatial autocorrelation analysis method; The spatial dimension abnormality features and the temporal dimension abnormality features are combined and an integrated learning method is used to analyze and obtain a global abnormality analysis result.

9. The regional electromagnetic inspection method based on vehicle-mounted electromagnetic detection equipment according to claim 1 is characterized in that: After fusing the local anomaly analysis result and the global anomaly analysis result into the comprehensive electromagnetic anomaly analysis result of the target area, the method further includes the following steps: Build a spatiotemporal graph convolutional network model; Inputting the electromagnetic environment map network and the comprehensive electromagnetic anomaly analysis results as input data into the spatiotemporal graph convolutional network model; Using the spatiotemporal graph convolutional network model to predict the spatiotemporal evolution trend of electromagnetic anomalies in the target area, and outputting the predicted spatiotemporal evolution results of electromagnetic anomalies; The graph network structure of the electromagnetic environment graph network and the node weights of the target monitoring nodes are adjusted according to the spatiotemporal evolution results of the electromagnetic anomaly.

10. A regional electromagnetic inspection system based on a vehicle-mounted electromagnetic detection device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the regional electromagnetic patrol method based on the vehicle-mounted electromagnetic detection equipment according to any one of claims 1 to 9 is implemented.

Images