Substation inspection method based on unmanned aerial vehicle cluster, electronic equipment and storage medium

Abstract

The invention discloses a substation inspection method based on an unmanned aerial vehicle cluster, electronic equipment and a storage medium. The method comprises the following steps: acquiring an inspection task of a transformer substation, geographical environment information and endurance information of each unmanned aerial vehicle in an unmanned aerial vehicle cluster; the inspection task, the geographical environment information and the endurance information are input to a task planning model, a target inspection area and a target inspection path of each unmanned aerial vehicle are obtained, and the task planning model is determined based on a graph diffusion network and a graph convolution network; and controlling the unmanned aerial vehicle cluster to inspect the transformer substation according to the target inspection area and the target inspection path to obtain an inspection result which is used for determining whether the unmanned aerial vehicle cluster completes an inspection task or not. The technical problems of high complexity and low efficiency of unmanned aerial vehicle power grid inspection operation in related technologies are solved.

Description

Technical Field

[0001] The present invention relates to the field of substation inspection, and in particular to a substation inspection method, electronic equipment and storage medium based on a drone cluster. Background Art

[0002] With the rapid development of drone technology, the application of drones in power grid inspection has gradually attracted attention. The existing drone power grid inspection technology has the following problems:

[0003] 1) The coverage of a single drone inspection is limited and inefficient: The endurance and operating range of a single drone are relatively limited, especially when facing large-scale power lines and complex geographical environments. A single drone cannot quickly complete the inspection task of the entire area, resulting in low inspection efficiency. In addition, in order to achieve a large-scale inspection, multiple take-offs and landings and charging are required, which increases the time cost of the inspection.

[0004] 2) The complexity of drone swarm scheduling is high: Although drone swarms can improve efficiency through collaborative operations, when the number of drones is large, the complexity of problems such as task allocation, flight path planning, and obstacle avoidance increases exponentially, affecting the speed and reliability of inspections.

[0005] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0006] The embodiments of the present invention provide a substation inspection method, electronic device and storage medium based on a drone cluster, so as to at least solve the technical problems of high complexity and low efficiency of drone power grid inspection operations in related technologies.

[0007] According to an aspect of one of the embodiments of the present invention, a substation inspection method based on a drone cluster is provided, including: obtaining the inspection task of the substation, geographical environment information and the endurance information of each drone in the drone cluster; inputting the inspection task, geographical environment information and endurance information into a task planning model to obtain a target inspection area and a target inspection path for each drone, wherein the task planning model is determined based on a graph diffusion network and a graph convolution network; controlling the drone cluster to inspect the substation according to the target inspection area and the target inspection path to obtain an inspection result, wherein the inspection result is used to determine whether the drone cluster has completed the inspection task.

[0008] Optionally, the inspection task, geographic environment information and endurance information are input into the task planning model to obtain the target inspection area and target inspection path of each UAV, including: determining the initial inspection area and initial inspection path of each UAV based on the inspection task, geographic environment information and endurance information; determining the diffusion capability expression matrix and role importance expression matrix of the UAV cluster based on the initial inspection area and initial inspection path; determining the comprehensive score of each UAV based on the diffusion capability expression matrix and the role importance expression matrix; and adjusting the initial inspection area and initial inspection path according to the comprehensive score to obtain the target inspection area and target inspection path.

[0009] Optionally, determining the initial inspection area and initial inspection path of each UAV based on the inspection task, geographic environment information and endurance information includes: dividing the area to be inspected of the substation based on the inspection task and geographic environment information to obtain a division result; assigning tasks to the UAV cluster according to the division result to obtain an initial inspection area; and using a path planning algorithm to analyze the initial inspection area, geographic environment information and endurance information to determine the initial inspection path.

[0010] Optionally, determining the diffusion capability expression matrix of the drone cluster based on the initial inspection area and the initial inspection path includes: establishing a communication network of the drone cluster according to the initial inspection area and the initial inspection path, wherein the nodes of the communication network represent each drone in the drone cluster; and using a graph diffusion network to simulate the information flow transmission process of the communication network to obtain a diffusion capability expression matrix.

[0011] Optionally, determining the role importance expression matrix of the drone cluster based on the initial inspection area and the initial inspection path includes: dividing the roles of each drone according to the initial inspection area and the initial inspection path to obtain role information of each drone; using the role information and the initial inspection area to construct a role map of the drone cluster, wherein the role map is used to determine the location information and importance level of each drone; and inputting the role map, the initial inspection area, and the initial inspection path into a graph convolutional network to obtain a role importance expression matrix.

[0012] Optionally, the task planning model includes at least a multi-layer perceptron network, and determining the comprehensive score of each UAV based on the diffusion capability expression matrix and the role importance expression matrix includes: obtaining the diffusion score of each UAV based on the diffusion capability expression matrix; obtaining the role score of each UAV based on the role importance expression matrix; and using the multi-layer perceptron network to perform data fusion processing on the diffusion score and the role score to obtain a comprehensive score.

[0013] Optionally, the initial inspection area and the initial inspection path are adjusted according to the comprehensive score to obtain the target inspection area and the target inspection path, including: obtaining the level information of each sub-inspection area in the division result; establishing a task allocation mapping relationship based on the level information and the comprehensive score; adjusting the initial inspection area based on the task allocation mapping relationship to obtain the target inspection area; adjusting the initial inspection path based on the target inspection area to obtain the target inspection path.

[0014] According to one embodiment of the present invention, a substation inspection device based on a drone cluster is also provided, including: an acquisition module, used to obtain the inspection task of the substation, geographical environment information and the endurance information of each drone in the drone cluster; a determination module, used to input the inspection task, geographical environment information and endurance information into the task planning model, and obtain the target inspection area and target inspection path of each drone, wherein the task planning model is determined based on a graph diffusion network and a graph convolution network; a control module, used to control the drone cluster to inspect the substation according to the target inspection area and the target inspection path, and obtain the inspection result, wherein the inspection result is used to determine whether the drone cluster has completed the inspection task.

[0015] Optionally, the determination module is also used to: determine the initial inspection area and initial inspection path of each UAV based on the inspection task, geographic environment information and endurance information; determine the diffusion capability expression matrix and role importance expression matrix of the UAV cluster based on the initial inspection area and initial inspection path; determine the comprehensive score of each UAV based on the diffusion capability expression matrix and role importance expression matrix; adjust the initial inspection area and initial inspection path according to the comprehensive score to obtain the target inspection area and target inspection path.

[0016] Optionally, the determination module is also used to: divide the substation's area to be inspected based on inspection tasks and geographic environment information to obtain a division result; assign tasks to the drone cluster based on the division result to obtain an initial inspection area; use a path planning algorithm to analyze the initial inspection area, geographic environment information and endurance information to determine the initial inspection path.

[0017] Optionally, the substation inspection device based on drone cluster also includes an establishment module, which is used to establish a communication network of the drone cluster according to the initial inspection area and the initial inspection path, wherein the nodes of the communication network represent each drone in the drone cluster; the substation inspection device based on drone cluster also includes a simulation module, which is used to simulate the information flow transmission process of the communication network using a graph diffusion network to obtain a diffusion capability expression matrix.

[0018] Optionally, the determination module is also used to divide the roles of each drone according to the initial inspection area and the initial inspection path to obtain the role information of each drone; the establishment module is also used to construct a role map of the drone cluster using the role information and the initial inspection area, wherein the role map is used to determine the location information and importance level of each drone; the determination module is also used to input the role map, the initial inspection area and the initial inspection path into the graph convolutional network to obtain a role importance expression matrix.

[0019] Optionally, the acquisition module is also used to: obtain the diffusion score of each drone based on the diffusion capability expression matrix; obtain the role score of each drone based on the role importance expression matrix; the determination module is also used to use a multi-layer perceptron network to perform data fusion processing on the diffusion score and the role score to obtain a comprehensive score.

[0020] Optionally, the acquisition module is also used to obtain the level information of each sub-inspection area in the division result; the establishment module is also used to establish a task allocation mapping relationship based on the level information and the comprehensive score; the determination module is also used to: adjust the initial inspection area based on the task allocation mapping relationship to obtain the target inspection area; adjust the initial inspection path based on the target inspection area to obtain the target inspection path.

[0021] According to one embodiment of the present invention, there is also provided an electronic device, comprising: a memory storing an executable program; and a processor for running the program, wherein the above-mentioned substation inspection method based on drone cluster is executed when the program is running.

[0022] According to one embodiment of the present invention, a computer-readable storage medium is also provided, including: the computer-readable storage medium includes a stored executable program, wherein when the executable program is running, the device where the storage medium is located is controlled to execute the above-mentioned substation inspection method based on drone clusters.

[0023] According to one embodiment of the present invention, a computer program product is also provided, including: a computer program, which implements the above-mentioned substation inspection method based on drone cluster when executed by a processor.

[0024] In an embodiment of the present invention, the inspection tasks, geographical environment information and endurance information of each drone in the drone cluster of the substation are obtained, and the inspection tasks, geographical environment information and endurance information are input into the task planning model to obtain the target inspection area and target inspection path of each drone. By optimizing the scheduling and collaborative operation of the drone cluster, the task allocation and inspection path planning of each drone in the drone cluster are dynamically adjusted, thereby achieving the purpose of automatically allocating inspection tasks and planning inspection paths according to the complexity of the power lines, the geographical environment and the real-time operation conditions, thereby achieving the technical effect of reducing the complexity of drone power grid inspection operations and improving the efficiency of drone power grid inspection operations, and thus solving the technical problems of high complexity and low efficiency of drone power grid inspection operations in related technologies. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0026] Figure 1 It is a hardware structure block diagram of a substation inspection method based on drone cluster according to one embodiment of the present invention;

[0027] Figure 2 is a flow chart of a substation inspection method based on drone clusters according to one embodiment of the present invention;

[0028] Figure 3 is a flow chart of another substation inspection method based on drone clusters according to one embodiment of the present invention;

[0029] Figure 4 It is a structural block diagram of a substation inspection device based on a drone cluster according to one embodiment of the present invention. DETAILED DESCRIPTION

[0030] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0031] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0032] The substation inspection method embodiment based on drone cluster provided in the embodiment of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Figure 1 FIG. 1 is a hardware structure diagram of a substation inspection method based on a drone cluster according to one embodiment of the present invention. Figure 1 As shown, the computer terminal 10 (or electronic device 10) may include one or more (102a, 102b, ..., 102n are used to illustrate) processors (the processor may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 104 for storing data, and a transmission module 106 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the I / O interface), a network interface, a power supply and / or a camera. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0033] It should be noted that the one or more processors and / or other data processing circuits described above may generally be referred to herein as "data processing circuits". The data processing circuits may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuit may be a single independent processing module, or may be incorporated in whole or in part into any of the other components in the computer terminal 10 (or electronic device). As described in the embodiments of the present application, the data processing circuit acts as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0034] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the substation inspection method based on drone clusters in the embodiment of the present application. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, realizing the above-mentioned substation inspection method based on drone clusters. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include a memory remotely arranged relative to the processor, and these remote memories may be connected to the computer terminal 10 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0035] The transmission module 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the computer terminal 10. In one example, the transmission module 106 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission module 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0036] The display may be, for example, a touch screen type liquid crystal display (LCD), which may enable a user to interact with a user interface of the computer terminal 10 (or electronic device).

[0037] It should be noted that, in some optional embodiments, the above Figure 1 The computer device (or electronic device) shown may include hardware elements (including circuits), software elements (including computer code stored on a computer-readable medium), or a combination of hardware elements and software elements. It should be noted that Figure 1 This is merely one example of a particular embodiment and is intended to illustrate the types of components that may be present in the above-described computer device (or electronic device).

[0038] According to an embodiment of the present invention, a method embodiment of a substation inspection method based on a drone cluster is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in an order different from that shown here.

[0039] Figure 2is a flow chart of a substation inspection method based on drone clusters according to one embodiment of the present invention, such as Figure 2 As shown, the method comprises the following steps:

[0040] Step S20, obtaining the inspection tasks of the substation, geographical environment information and the endurance information of each drone in the drone cluster;

[0041] In step S20, the inspection tasks are used to characterize the specific objectives and requirements of the substation inspection, for example, which areas of the substation are to be inspected, and which specific equipment or structures need to be paid attention to.

[0042] The above-mentioned geographical environment information is used to characterize the geographical environment data of the substation, including but not limited to: terrain, buildings, vegetation, etc.

[0043] The above-mentioned endurance information of each drone is used to characterize the battery status of the drone, including power level and health status.

[0044] Step S22, inputting the inspection task, geographical environment information and endurance information into the task planning model to obtain the target inspection area and target inspection path of each UAV, wherein the task planning model is determined based on the graph diffusion network and the graph convolution network;

[0045] In step S22, the above-mentioned Graph Diffusion Network (GDN) is a network model built based on graph theory, which is used to simulate the process of information propagation in the network. The graph diffusion network is used to establish a communication network between each drone in the drone cluster, and the diffusion capacity of each drone is determined according to the information sharing between the drones, that is, the ability of each drone to process and deliver tasks throughout the mission. In this communication network, each drone is a node, and the communication or collaboration relationship between them is an edge.

[0046] The above-mentioned Graph Convolutional Network (GCN) understands the position and role of each drone in power grid inspection by learning the local (neighbors of nodes) and global (entire network) network structures in the drone cluster. GCN uses graph convolution operations to aggregate the features of the local neighborhood and combines the features of the global network structure. In this way, GCN can not only capture the relationship between each drone and its direct neighbors, but also understand the impact of the topological structure of the entire network on the drone mission.

[0047] Specifically, the mission planning model can analyze geographic environment information and identify potential risk factors, such as obstacles and climatic conditions, to ensure the safe flight of the drone; match the drone's navigation system with the geographic information system (GIS) or global positioning system (GPS) data to ensure that the drone can be accurately positioned; calculate the expected flight time of the drone based on the drone's load, flight speed and flight status, evaluate the drone's endurance, and combine the complexity and scope of the inspection task, geographic environment information and endurance information to assign the inspection task to each drone in the drone cluster, and plan the target inspection path to ensure that the drone can return to the base safely after completing the task. Among them, the control parameters of the drone during the inspection process are determined according to the target inspection task. For example, flight altitude, speed, shooting frequency, etc.

[0048] Step S24, controlling the drone cluster to inspect the substation according to the target inspection area and the target inspection path, and obtaining the inspection result, wherein the inspection result is used to determine whether the drone cluster has completed the inspection task.

[0049] Specifically, the operator or automatic control system will guide the drone cluster to inspect the target inspection area according to the target inspection path, and use the onboard cameras, sensors and other equipment to collect data. The data collected by the drone during the inspection process will be transmitted back to the control center for analysis and evaluation. By analyzing the collected data, it can be determined whether the drone cluster has completed all inspection tasks. If there are omissions or areas that need further inspection, the drone cluster will be guided to re-inspect.

[0050] Based on the above steps S20 to S24, the inspection tasks, geographical environment information and endurance information of each drone in the drone cluster of the substation are obtained, and the inspection tasks, geographical environment information and endurance information are input into the task planning model to obtain the target inspection area and target inspection path of each drone. By optimizing the scheduling and collaborative operation of the drone cluster, the task allocation and inspection path planning of each drone in the drone cluster are dynamically adjusted, so as to achieve the purpose of automatically allocating inspection tasks and planning inspection paths according to the complexity of the power lines, the geographical environment and the real-time operation conditions, thereby achieving the technical effect of reducing the complexity of drone power grid inspection operations and improving the efficiency of drone power grid inspection operations, and thus solving the technical problems of high complexity and low efficiency of drone power grid inspection operations in related technologies.

[0051] Optionally, in step S22, the inspection task, geographical environment information and endurance information are input into the task planning model to obtain the target inspection area and target inspection path of each drone, including:

[0052] Step S221, determining the initial inspection area and initial inspection path of each UAV based on the inspection task, geographical environment information and endurance information;

[0053] Specifically, a path planning algorithm is used to analyze the initial inspection area, geographical environment information, and endurance information of each drone to obtain an analysis result. For example, the A* algorithm, the Dijkstra algorithm, or a graph-based path planning algorithm. Based on the analysis results, the initial inspection path of each drone is determined to ensure the efficiency of the path and the endurance of the drone.

[0054] Step S222, determining the diffusion capability expression matrix and the role importance expression matrix of the drone cluster based on the initial inspection area and the initial inspection path;

[0055] Specifically, based on the initial inspection area and path of the drone, a communication network is constructed, and GDN is used to simulate the information flow transmission process to obtain the diffusion capability expression matrix of each drone. The diffusion capability expression matrix reflects the ability of the drone in information transmission and task collaboration. The role importance of the drone is analyzed through GCN, a role graph is constructed, and a role importance expression matrix is ​​obtained. The role importance expression matrix represents the role and importance of the drone in the inspection task.

[0056] Step S223, determining the comprehensive score of each UAV based on the diffusion capability expression matrix and the role importance expression matrix;

[0057] Specifically, the diffusion capability expression matrix and the role importance expression matrix are combined, and the multilayer perceptron (MLP) network is used to perform data fusion processing on the diffusion score and role score of each drone to obtain a comprehensive score. This comprehensive score takes into account the performance of the drone in terms of information transmission efficiency and mission importance, and is used to evaluate the overall contribution of each drone.

[0058] Step S224, adjusting the initial inspection area and the initial inspection path according to the comprehensive score to obtain the target inspection area and the target inspection path.

[0059] Specifically, the initial inspection area and initial inspection path are adjusted based on the comprehensive scores of the drones. High-scoring drones are assigned to more important areas, while low-scoring drones are assigned to relatively less important areas. Through this adjustment, the inspection coverage is optimized to ensure that key areas receive more attention, while improving the overall efficiency of the inspection mission.

[0060] Based on the above steps S221 to S224, the initial inspection area and initial inspection path of each UAV are determined based on the inspection task, geographical environment information and endurance information; the diffusion capability expression matrix and role importance expression matrix of the UAV cluster are determined based on the initial inspection area and the initial inspection path; the comprehensive score of each UAV is determined based on the diffusion capability expression matrix and the role importance expression matrix; the initial inspection area and the initial inspection path are adjusted according to the comprehensive score to obtain the target inspection area and the target inspection path, and the task allocation and inspection path planning are dynamically adjusted for each UAV in the UAV cluster by optimizing the scheduling and collaborative operation of the UAV cluster, so as to achieve the purpose of automatically allocating inspection tasks and planning inspection paths according to the complexity of the power lines, the geographical environment and the real-time operation conditions, thereby achieving the technical effect of reducing the complexity of UAV power grid inspection operations and improving the efficiency of UAV power grid inspection operations, thereby solving the technical problems of high complexity and low efficiency of UAV power grid inspection operations in related technologies.

[0061] Optionally, in step S221, determining the initial inspection area and initial inspection path of each drone based on the inspection task, geographical environment information, and endurance information includes:

[0062] Step S2211, dividing the area to be inspected of the substation based on the inspection task and the geographical environment information to obtain a division result;

[0063] Specifically, the inspection area of ​​the substation is logically divided according to the inspection task and geographical environment information. The division can be based on geographical division (such as division by longitude and latitude), functional division (such as transformer area, transmission line area) or risk level division (high risk area and low risk area). For example, the substation is divided into four areas according to the inspection task and geographical environment information: Area A (high voltage transmission line), Area B (transformer area), Area C (low voltage distribution area), and Area D (control center and auxiliary facilities area). Each area is given different priorities according to the importance of the equipment and the complexity of the inspection.

[0064] Step S2212, assigning tasks to the drone cluster according to the division result to obtain an initial inspection area;

[0065] Specifically, according to the regional division results, the inspection needs and characteristics of each area are determined. Then the performance of each drone in the drone cluster is evaluated, including endurance, payload, sensor type, etc. Based on the regional division results and drone capability evaluation, the drone cluster is tasked so that each drone is responsible for a specific inspection area. For example, according to the performance of the drone and the regional division, drone 1 is assigned to area A (high-voltage transmission line) because it has a longer endurance and a high-performance camera suitable for long-distance flight; drone 2 is assigned to area B (transformer area) because it is equipped with an infrared camera suitable for detecting heat anomalies; drone 3 and drone 4 are responsible for areas C and D respectively.

[0066] Step S2213, using a path planning algorithm to analyze the initial inspection area, geographic environment information and endurance information to determine the initial inspection path.

[0067] Specifically, a path planning algorithm is selected. For example, the A* algorithm, the Dijkstra algorithm, or a graph-based path planning algorithm. The path planning algorithm is used to analyze the initial inspection area, geographical environment information, and endurance information of each drone to obtain an analysis result. Based on the analysis results, the initial inspection path of each drone is determined to ensure the efficiency of the path and the endurance of the drone. For example, in the path planning of human-machine 1 in area A, the path planning algorithm plans an optimal path starting from the substation and covering all high-voltage transmission lines, taking into account the geographical environment (such as avoiding mountains and buildings), endurance (such as planning charging points on the way back), and inspection tasks (such as giving priority to inspecting key transmission towers). Drone 1 will fly along this path, perform inspection tasks, and return to the base station for charging if the power allows.

[0068] Based on the above steps S2211 to S2213, the area to be inspected of the substation is divided based on the inspection tasks and geographical environment information to obtain the division results; the tasks of the drone cluster are assigned according to the division results to obtain the initial inspection area; the path planning algorithm is used to analyze the initial inspection area, geographical environment information and endurance information to determine the initial inspection path, which can determine a reasonable initial inspection area and initial inspection path for the drone cluster, thereby improving the efficiency and coverage of the inspection while ensuring the endurance and safety of the drone.

[0069] Optionally, in step S222, determining the diffusion capability expression matrix of the drone cluster based on the initial inspection area and the initial inspection path includes:

[0070] Step S2221, establishing a communication network of the drone cluster according to the initial inspection area and the initial inspection path, wherein the nodes of the communication network represent the individual drones in the drone cluster;

[0071] Specifically, a communication network is constructed based on the initial inspection area and path of the drone. Each drone is represented as a node in the communication network. The lines between nodes represent the communication paths between drones. Each drone is equipped with a communication module that allows them to establish direct or indirect communication links with other drones. These communication links can be wireless, such as Wi-Fi, Bluetooth, or a dedicated drone communication protocol. Each node not only processes its own mission information, but also transmits this information to surrounding nodes. The information shared between drones includes mission status, location data, sensor readings, etc. This information sharing can help drones collaborate to complete tasks. For example, if a drone finds an anomaly, it can quickly pass this information to other drones so that they can adjust their paths or behaviors. In this process, the communication range and communication capabilities of the drones need to be considered to determine whether they can communicate directly or need to pass information through a relay drone. For example, drone 1, drone 2, and drone 3 are responsible for different areas, and their flight paths partially overlap, which means that they may communicate with each other during flight. The flight paths of drone 1 and drone 2 are adjacent, so they can communicate directly; while drone 3 needs to relay information through drone 1 or drone 2 due to the long distance.

[0072] Step S2222, using the graph diffusion network to simulate the information flow transmission process of the communication network to obtain a diffusion capability expression matrix.

[0073] Specifically, the graph diffusion network (GDN) model is used to simulate the transmission process of information flow between drones. In GDN, information starts from the source node and gradually diffuses to other nodes through the communication links between drones. This process can simulate the speed and range of information propagation. By simulating the transmission process of information flow, a diffusion capacity expression matrix can be obtained, which describes the diffusion capacity of each drone in the drone cluster, that is, their role and influence in information transmission. For example, drone 1, drone 2, and drone 3 form a small drone cluster. Through GDN model simulation, we can obtain the diffusion capacity expression matrix: In this matrix, the values ​​represent the influence of drones on the information dissemination of other drones. For example, drone 1 has an influence of 0.8 on the information dissemination of drone 2, while drone 2 has an influence of 0.8 on drone 1, showing that the communication between them is bidirectional and has similar influence. Drone 3 has a smaller influence on drone 1 (0.5), which may mean that the communication between them is affected by distance or obstacles.

[0074] Based on the above steps S2221 to S2222, a communication network of the drone cluster is established according to the initial inspection area and the initial inspection path; the graph diffusion network is used to simulate the information flow transmission process of the communication network, and the diffusion capability expression matrix is ​​obtained. The importance and role of each drone in the drone cluster in the information transmission process are evaluated by quantitative methods, which can optimize the inspection task allocation and communication strategy of the drones.

[0075] Optionally, in step S222, determining the role importance expression matrix of the drone cluster based on the initial inspection area and the initial inspection path includes:

[0076] Step S2223, dividing the roles of each drone according to the initial inspection area and the initial inspection path to obtain the role information of each drone;

[0077] Specifically, the role extraction algorithm (ROIX) is used to automatically extract the role of the drone in the inspection task. The ROIX algorithm analyzes the functional role of the drone based on the importance of the inspection area and neighboring equipment where the drone is located. The ROIX algorithm divides the drone into different roles by analyzing the number of power grid equipment covered by the drone, the complexity of the task, the location, the importance of the inspection area where the drone is located, and the neighboring equipment. For example, key area inspectors, secondary area monitors, emergency responders, etc. The obtained role information will include the specific role and responsibilities of each drone, providing basic data for the subsequent role map construction and role importance assessment. For example, drone 1 is responsible for inspecting high-voltage transmission lines, so it is classified as a "key area inspector"; drone 2 is responsible for monitoring the secondary area around the substation and is classified as a "secondary area monitor"; drone 3, as an emergency responder, is ready to support other drones at any time.

[0078] Step S2224, constructing a role map of the drone cluster using the role information and the initial inspection area, wherein the role map is used to determine the location information and importance level of each drone;

[0079] Specifically, based on the role information extracted by the ROIX algorithm, a role graph is constructed to describe the task relationship and importance between drones. The role graph shows the functional roles and importance of different drones in the power grid inspection network, including their positions and importance levels in the inspection tasks. Through the role graph, the mutual relationship and role of drones in the inspection tasks are further analyzed to ensure that key areas and equipment are inspected first. For example, the constructed role graph may show that drone 1 (critical area inspector) has more direct connections with other drones because it is responsible for the inspection of the most critical parts of the power grid; drone 2 (secondary area monitor) has relatively fewer connections because its role is more independent; drone 3 (emergency responder) is in the center of the graph because it needs to be ready to support other drones at any time.

[0080] Step S2225, input the role map, initial inspection area and initial inspection path into the graph convolutional network to obtain the role importance expression matrix.

[0081] Specifically, after the role graph is constructed, the role importance of the nodes is further analyzed through the GCN network. The GCN model calculates the importance of each drone in the power grid inspection by learning the local and global network structures in the drone cluster. GCN is able to generate role importance scores based on the relationship between drones and the complexity of their inspection tasks. For example, through the analysis of the GCN model, drone 1 has the highest role importance score because the key area it is responsible for inspecting is crucial to the stable operation of the power grid; drone 3, as an emergency responder, also has a high role importance score because it needs to be ready to deal with emergencies at any time; drone 2 has a relatively low role importance score because the area it is responsible for is relatively minor.

[0082] Based on the above steps S2223 to S2225, the initial inspection area and the initial inspection path are used to divide the roles of each drone to obtain the role information of each drone; the role information and the initial inspection area are used to construct a role map of the drone cluster, wherein the role map is used to determine the location information and importance level of each drone; the role map, the initial inspection area and the initial inspection path are input into the graph convolutional network to obtain a role importance expression matrix, which can determine the role importance expression matrix of the drone cluster, provide decision support for the optimization of power grid inspection tasks and resource allocation, help improve inspection efficiency, ensure that key areas and equipment are inspected first, and reasonably allocate drone resources to improve the overall inspection effect.

[0083] Optionally, in step S223, the mission planning model includes at least a multi-layer perceptron network, and determining the comprehensive score of each drone based on the diffusion capability expression matrix and the role importance expression matrix includes:

[0084] Step S2231, obtaining the diffusion score of each UAV based on the diffusion capability expression matrix;

[0085] Specifically, a diffusion capability score is generated for each drone based on the diffusion capability expression matrix. The diffusion score reflects the efficiency of the drone in information transfer and task allocation. The diffusion capability score takes into account factors such as the drone's communication range, information transfer speed, and task coverage. Drones with high diffusion scores can collaborate more effectively and cover a wider inspection area. For example, drone 1 has extensive communication links with other drones in the diffusion network and is able to cover multiple key areas, so it obtains a high diffusion capability score.

[0086] Step S2232, obtaining the role score of each drone based on the role importance expression matrix;

[0087] Specifically, based on the role importance analyzed by GCN, a role importance expression matrix is ​​obtained. A role importance score is generated for each drone according to the role importance expression matrix. The role importance score reflects whether the role played by the drone in the inspection task is critical and the priority of its task execution in the inspection network. The role importance score takes into account factors such as the importance of the area the drone is responsible for, the complexity of the task, and the location of the drone. Drones with high scores play a more important role in the inspection network. For example, drone 2 is responsible for inspecting a critical transformer area and therefore obtains a higher role importance score.

[0088] Step S2233, using a multi-layer perceptron network to perform data fusion processing on the diffusion score and the role score to obtain a comprehensive score.

[0089] Specifically, in order to determine the target inspection area and target inspection path of each drone, the diffusion capability score is fused with the role importance score. The fusion process is completed through the MLP network, and finally the comprehensive task score of each drone is generated. The MLP network learns the nonlinear relationship between the diffusion score and the role score, weights and fuses the two scores, and generates a comprehensive score. Drones with higher comprehensive scores will give priority to key tasks, while drones with lower scores will perform secondary tasks or serve as inspection supplements. For example, the diffusion capability score of drone 1 is 0.9 and the role importance score is 0.7; the diffusion capability score of drone 2 is 0.6 and the role importance score is 0.8. Through the fusion processing of the MLP model, the comprehensive score of drone 1 may be 0.8, while the comprehensive score of drone 2 may be 0.7. According to the comprehensive score, drone 1 will give priority to key tasks, while drone 2 will perform secondary tasks or serve as a supplement.

[0090] Based on the above steps S2231 to S2233, the diffusion score of each UAV is obtained based on the diffusion capability expression matrix; the role score of each UAV is obtained based on the role importance expression matrix; the diffusion score and the role score are fused using a multi-layer perceptron network to obtain a comprehensive score. By evaluating the diffusion capability and role importance of each UAV and combining the scoring and fusion mechanism, the inspection tasks can be dynamically adjusted, which not only improves the coverage and efficiency of the inspection, but also ensures that key areas and equipment are inspected first, thereby improving the safety and reliability of the power grid.

[0091] Optionally, in step S224, the initial inspection area and the initial inspection path are adjusted according to the comprehensive score, and the target inspection area and the target inspection path are obtained, including:

[0092] Step S2241, obtaining the level information of each sub-area to be inspected in the division result;

[0093] Specifically, the inspection area of ​​the substation is divided based on the inspection task and geographical environment information to obtain the division result. Each sub-inspection area in the division result is assigned level information according to its importance, risk level, historical fault record and other factors. This information is collected from the power grid management system, historical inspection data and on-site investigation to provide a basis for determining the level information, wherein the level information can be adjusted in real time according to the importance, risk level and historical fault record of the sub-inspection area. The level information is used to distinguish which areas require more frequent or more detailed inspections and which areas can be inspected less frequently. For example, the substation is divided into four areas, area A is the high-voltage transmission line, the level is high; area B is the transformer area, the level is medium; area C is the low-voltage distribution area, the level is low; area D is the control center and auxiliary facilities area, the level is medium.

[0094] Step S2242, establishing a task allocation mapping relationship based on the level information and the comprehensive score;

[0095] Specifically, a task allocation mapping relationship is established based on the comprehensive score of the drone and the level information of the sub-inspection area. Drones with high scores are assigned to high-level areas to ensure that important areas receive adequate attention and inspection. In this way, the allocation of drone resources is optimized to ensure that the tasks of each drone match its capabilities and importance. For example, drone 1 has the highest comprehensive score and is assigned to the high-level area A; drone 2 and drone 3 have lower scores and are assigned to areas B and D in the level respectively; drone 4 has the lowest score and is assigned to the low-level area C.

[0096] Step S2243, adjusting the initial inspection area based on the task allocation mapping relationship to obtain a target inspection area;

[0097] Specifically, #According to the task allocation mapping relationship, the initial inspection area is adjusted to ensure that the area each drone is responsible for matches its comprehensive score and regional level. Through the adjustment, the efficiency and coverage of the inspection are improved to ensure that key areas receive more attention. The inspection area of ​​each drone is reallocated to make it consistent with the established mapping relationship. For example, the initial inspection area of ​​drone 1 may include part of area A and area B. After adjustment, drone 1 will only be responsible for the inspection of area A to concentrate its capabilities on the most important areas.

[0098] Step S2244: adjust the initial inspection path based on the target inspection area to obtain the target inspection path.

[0099] Specifically, based on the adjusted target inspection area, the initial inspection path of each drone is adjusted. A path planning algorithm is used to calculate the new target inspection path to improve inspection efficiency. For example, the A* algorithm, Dijkstra algorithm, etc. In the process of path adjustment, the endurance of the drone and the geographical environment information need to be considered to ensure the feasibility of the path.

[0100] Based on the above steps S2241 to S2244, the level information of each sub-inspection area in the division result is obtained; a task allocation mapping relationship is established based on the level information and the comprehensive score; the initial inspection area is adjusted based on the task allocation mapping relationship to obtain the target inspection area; the initial inspection path is adjusted based on the target inspection area to obtain the target inspection path, which can intelligently adjust the inspection area and path of the drone, optimize the execution of the inspection task, and ensure the efficiency and accuracy of the power grid inspection, which not only improves the coverage and efficiency of the inspection, but also ensures that key areas and equipment are inspected first, thereby improving the safety and reliability of the power grid.

[0101] Figure 3 is a flow chart of another substation inspection method based on drone clusters according to one embodiment of the present invention, such as Figure 3 As shown, the method comprises the following steps:

[0102] Step S301, obtaining the inspection tasks of the substation, geographical environment information and the endurance information of each drone in the drone cluster;

[0103] Step S302, dividing the area to be inspected of the substation based on the inspection task and the geographical environment information to obtain a division result;

[0104] Step S303, assigning tasks to the drone cluster according to the division results to obtain an initial inspection area;

[0105] Step S304, using a path planning algorithm to analyze the initial inspection area, geographical environment information and endurance information to determine an initial inspection path;

[0106] Step S305, establishing a communication network of the drone cluster according to the initial inspection area and the initial inspection path;

[0107] Step S306, using a graph diffusion network to simulate the information flow transmission process of the communication network to obtain a diffusion capability expression matrix;

[0108] Step S307, obtaining the diffusion score of each UAV based on the diffusion capability expression matrix;

[0109] Step S308, dividing the roles of each drone according to the initial inspection area and the initial inspection path to obtain the role information of each drone;

[0110] Step S309, constructing a role graph of the drone cluster using the role information and the initial inspection area;

[0111] Step S310, inputting the role graph, the initial inspection area, and the initial inspection path into a graph convolutional network to obtain a role importance expression matrix;

[0112] Step S311, obtaining the role score of each drone based on the role importance expression matrix;

[0113] Step S312, using a multi-layer perceptron network to perform data fusion processing on the diffusion score and the role score to obtain a comprehensive score;

[0114] Step S313, obtaining the level information of each sub-area to be inspected in the division result;

[0115] Step S314, establishing a task allocation mapping relationship based on the level information and the comprehensive score;

[0116] Step S315, adjusting the initial inspection area based on the task allocation mapping relationship to obtain a target inspection area;

[0117] Step S316, adjusting the initial inspection path based on the target inspection area to obtain a target inspection path;

[0118] Step S317, controlling the drone cluster to inspect the substation according to the target inspection area and the target inspection path to obtain the inspection result.

[0119] Based on the above steps S301 to S317, the inspection tasks, geographical environment information and endurance information of each drone in the drone cluster of the substation are obtained, and the inspection tasks, geographical environment information and endurance information are input into the task planning model to obtain the target inspection area and target inspection path of each drone. By optimizing the scheduling and collaborative operation of the drone cluster, the task allocation and inspection path planning of each drone in the drone cluster are dynamically adjusted, so as to achieve the purpose of automatically allocating inspection tasks and planning inspection paths according to the complexity of the power lines, the geographical environment and the real-time operation conditions, thereby achieving the technical effect of reducing the complexity of drone power grid inspection operations and improving the efficiency of drone power grid inspection operations, and thus solving the technical problems of high complexity and low efficiency of drone power grid inspection operations in related technologies.

[0120] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods of various embodiments of the present invention.

[0121] In an embodiment of the present invention, a substation inspection device based on a drone cluster is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and will not be repeated hereafter. As used below, the term "module" can implement a combination of software and / or hardware of a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0122] Figure 4 is a structural block diagram of a substation inspection device based on a drone cluster according to one embodiment of the present invention, such as Figure 4 As shown, the device comprises:

[0123] The acquisition module 401 is used to acquire the inspection tasks of the substation, the geographical environment information and the endurance information of each drone in the drone cluster;

[0124] Determination module 402, used to input the inspection task, geographical environment information and endurance information into the task planning model to obtain the target inspection area and target inspection path of each UAV, wherein the task planning model is determined based on the graph diffusion network and the graph convolution network;

[0125] The control module 403 is used to control the drone cluster to inspect the substation according to the target inspection area and the target inspection path to obtain the inspection result, wherein the inspection result is used to determine whether the drone cluster has completed the inspection task.

[0126] Optionally, the determination module 402 is also used to: determine the initial inspection area and initial inspection path of each UAV based on the inspection task, geographic environment information and endurance information; determine the diffusion capability expression matrix and role importance expression matrix of the UAV cluster based on the initial inspection area and the initial inspection path; determine the comprehensive score of each UAV based on the diffusion capability expression matrix and the role importance expression matrix; adjust the initial inspection area and initial inspection path according to the comprehensive score to obtain the target inspection area and target inspection path.

[0127] Optionally, the determination module 402 is also used to: divide the area to be inspected of the substation based on the inspection tasks and geographic environment information to obtain the division results; assign tasks to the drone cluster according to the division results to obtain the initial inspection area; use the path planning algorithm to analyze the initial inspection area, geographic environment information and endurance information to determine the initial inspection path.

[0128] Optionally, the substation inspection device based on drone cluster also includes an establishment module 404, which is used to establish a communication network of the drone cluster according to the initial inspection area and the initial inspection path, wherein the nodes of the communication network represent each drone in the drone cluster; the substation inspection device based on drone cluster also includes a simulation module, which is used to simulate the information flow transmission process of the communication network using a graph diffusion network to obtain a diffusion capability expression matrix.

[0129] Optionally, the determination module 402 is also used to divide the roles of each drone according to the initial inspection area and the initial inspection path to obtain the role information of each drone; the establishment module 404 is also used to construct a role map of the drone cluster using the role information and the initial inspection area, wherein the role map is used to determine the location information and importance level of each drone; the determination module is also used to input the role map, the initial inspection area and the initial inspection path into the graph convolutional network to obtain a role importance expression matrix.

[0130] Optionally, the acquisition module 401 is also used to: obtain the diffusion score of each drone based on the diffusion capability expression matrix; obtain the role score of each drone based on the role importance expression matrix; the determination module 402 is also used to use a multi-layer perceptron network to perform data fusion processing on the diffusion score and the role score to obtain a comprehensive score.

[0131] Optionally, the acquisition module 401 is also used to obtain the level information of each sub-inspection area in the division result; the establishment module is also used to establish a task allocation mapping relationship based on the level information and the comprehensive score; the determination module 402 is also used to: adjust the initial inspection area based on the task allocation mapping relationship to obtain the target inspection area; adjust the initial inspection path based on the target inspection area to obtain the target inspection path.

[0132] It should be noted that the above modules can be implemented by software or hardware. For the latter, it can be implemented in the following ways, but not limited to: the above modules are all located in the same processor; or the above modules are located in different processors in any combination.

[0133] According to one embodiment of the present invention, there is also provided an electronic device, comprising: a memory storing an executable program; and a processor for running the program, wherein the above-mentioned substation inspection method based on drone cluster is executed when the program is running.

[0134] Optionally, in this embodiment, the processor may be configured to perform the following steps through a computer program:

[0135] Step S1, obtaining the inspection tasks of the substation, geographical environment information and the endurance information of each drone in the drone cluster;

[0136] Step S2, inputting the inspection task, geographical environment information and endurance information into the task planning model to obtain the target inspection area and target inspection path of each UAV, wherein the task planning model is determined based on the graph diffusion network and the graph convolution network;

[0137] Step S3, controlling the drone cluster to inspect the substation according to the target inspection area and the target inspection path, and obtaining the inspection result, wherein the inspection result is used to determine whether the drone cluster has completed the inspection task.

[0138] According to one embodiment of the present invention, a computer-readable storage medium is also provided, including: the computer-readable storage medium includes a stored executable program, wherein when the executable program is running, the device where the storage medium is located is controlled to execute the above-mentioned substation inspection method based on drone clusters.

[0139] Optionally, in this embodiment, the storage medium may be configured to store a computer program for performing the following steps:

[0140] Step S1, obtaining the inspection tasks of the substation, geographical environment information and the endurance information of each drone in the drone cluster;

[0141] Step S2, inputting the inspection task, geographical environment information and endurance information into the task planning model to obtain the target inspection area and target inspection path of each UAV, wherein the task planning model is determined based on the graph diffusion network and the graph convolution network;

[0142] Step S3, controlling the drone cluster to inspect the substation according to the target inspection area and the target inspection path, and obtaining the inspection result, wherein the inspection result is used to determine whether the drone cluster has completed the inspection task.

[0143] Optionally, in this embodiment, the above-mentioned storage medium may include but is not limited to: a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and other media that can store computer programs.

[0144] According to one embodiment of the present invention, a computer program product is also provided, including: a computer program, which implements the above-mentioned substation inspection method based on drone cluster when executed by a processor.

[0145] Optionally, in this embodiment, the computer program product may be configured to store computer program instructions for performing the following steps:

[0146] Step S1, obtaining the inspection tasks of the substation, geographical environment information and the endurance information of each drone in the drone cluster;

[0147] Step S2, inputting the inspection task, geographical environment information and endurance information into the task planning model to obtain the target inspection area and target inspection path of each UAV, wherein the task planning model is determined based on the graph diffusion network and the graph convolution network;

[0148] Step S3, controlling the drone cluster to inspect the substation according to the target inspection area and the target inspection path, and obtaining the inspection result, wherein the inspection result is used to determine whether the drone cluster has completed the inspection task.

[0149] Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments and optional implementation modes, and this embodiment will not be described in detail here.

[0150] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0151] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0152] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0153] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0154] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0155] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0156] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A substation inspection method based on drone clusters, characterized in that: include: Obtain inspection tasks, geographic environment information, and flight time information of each drone in the drone cluster at the substation; Inputting the inspection task, the geographic environment information and the endurance information into a task planning model to obtain a target inspection area and a target inspection path for each UAV, wherein the task planning model is determined based on a graph diffusion network and a graph convolution network; The drone cluster is controlled to inspect the substation according to the target inspection area and the target inspection path to obtain an inspection result, wherein the inspection result is used to determine whether the drone cluster has completed the inspection task.

2. The substation inspection method based on drone cluster according to claim 1 is characterized in that: Inputting the inspection task, the geographical environment information and the endurance information into the task planning model, and obtaining the target inspection area and target inspection path of each UAV includes: Determine the initial inspection area and initial inspection path of each drone based on the inspection task, the geographical environment information and the endurance information; Determine a diffusion capability expression matrix and a role importance expression matrix of the drone cluster based on the initial inspection area and the initial inspection path; Determining a comprehensive score of each drone based on the diffusion capability expression matrix and the role importance expression matrix; The initial inspection area and the initial inspection path are adjusted according to the comprehensive score to obtain the target inspection area and the target inspection path.

3. The substation inspection method based on drone cluster according to claim 2 is characterized in that: Determining the initial inspection area and initial inspection path of each drone based on the inspection task, the geographical environment information and the endurance information includes: Dividing the area to be inspected of the substation based on the inspection task and the geographical environment information to obtain a division result; According to the division result, tasks are assigned to the drone cluster to obtain the initial inspection area; The initial inspection area, the geographical environment information and the endurance information are analyzed using a path planning algorithm to determine the initial inspection path.

4. The substation inspection method based on drone cluster according to claim 2 is characterized in that: Determining the diffusion capability expression matrix of the drone cluster based on the initial inspection area and the initial inspection path includes: Establishing a communication network of the drone cluster according to the initial inspection area and the initial inspection path, wherein the nodes of the communication network represent the individual drones in the drone cluster; The graph diffusion network is used to simulate the information flow transmission process of the communication network to obtain the diffusion capability expression matrix.

5. The substation inspection method based on drone cluster according to claim 2 is characterized in that: Determining the role importance expression matrix of the drone cluster based on the initial inspection area and the initial inspection path includes: The initial inspection area and the initial inspection path are used to divide the roles of the drones to obtain role information of the drones; Constructing a role map of the drone cluster using the role information and the initial inspection area, wherein the role map is used to determine the location information and importance level of each drone; The role graph, the initial inspection area, and the initial inspection path are input into the graph convolutional network to obtain a role importance expression matrix.

6. The substation inspection method based on drone cluster according to claim 2 is characterized in that: The mission planning model includes at least a multi-layer perceptron network, and determining the comprehensive score of each drone based on the diffusion capability expression matrix and the role importance expression matrix includes: Obtaining a diffusion score of each drone based on the diffusion capability expression matrix; Obtaining a role score for each drone based on the role importance expression matrix; The multilayer perceptron network is used to perform data fusion processing on the diffusion score and the role score to obtain the comprehensive score.

7. The substation inspection method based on drone cluster according to claim 3 is characterized in that: The initial inspection area and the initial inspection path are adjusted according to the comprehensive score to obtain the target inspection area and the target inspection path, including: Obtaining level information of each sub-area to be inspected in the division result; Establishing a task allocation mapping relationship based on the level information and the comprehensive score; Adjusting the initial inspection area based on the task allocation mapping relationship to obtain the target inspection area; The initial inspection path is adjusted based on the target inspection area to obtain the target inspection path.

8. An electronic device, characterized in that: include: A memory storing an executable program; A processor is used to run the program, wherein when the program is running, the substation inspection method based on drone clusters described in any one of claims 1 to 7 is executed.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored executable program, wherein when the executable program is running, the device where the storage medium is located is controlled to execute the substation inspection method based on drone clusters as described in any one of claims 1 to 7.

10. A computer program product, characterized in that It includes a computer program, which, when executed by a processor, implements the substation inspection method based on drone cluster according to any one of claims 1 to 7.

Images