Power line collaborative inspection system based on unmanned aerial vehicle cluster

Abstract

The invention discloses a power line collaborative inspection system based on an unmanned aerial vehicle cluster, and relates to the technical field of power correlation, and the system comprises a hypergraph topology modeling module which is used for constructing a power line hypergraph model, and extracting a hypergraph topology feature matrix; the fractal region division module is used for dividing the region to be inspected into a plurality of sub-regions by minimizing space coverage balance and boundary complexity under the condition that constraint conditions are met; the dynamic task allocation module is used for constructing an adaptation degree matrix, realizing optimal matching of the unmanned aerial vehicle based on the adaptation degree matrix, and carrying out power line collaborative inspection according to an optimal matching result; and the autonomous fault-tolerant recovery module is used for performing task redistribution when a fault occurs during cooperative inspection of the power line. Through hypergraph modeling, a region division algorithm and adaptive task matching, accurate modeling of a power system structure and risk factors, efficient division of an inspection region and intelligent scheduling of unmanned aerial vehicle resources are realized, and the efficiency of power line inspection and the resource utilization rate are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power-related technologies, and in particular to a power line collaborative inspection system based on a drone cluster. Background Art

[0002] Traditional power inspection methods mainly rely on manual or single drone execution, which has many problems such as low operating efficiency, limited coverage, high safety risks, and poor real-time performance. In recent years, with the development of drone technology, its application in power inspection has gradually increased, but most systems still have shortcomings: the inspection scheduling method is static and has much manual intervention. In the existing technology, most drone inspection systems rely on manually specified routes and targets, lack intelligent task division and allocation mechanisms, and are difficult to cope with large-scale, dynamically changing power environments; the regional division method is rough and the resource utilization rate is low. Traditional methods mostly use fixed grid division or simple geometric partitioning methods, which fail to fully consider the topological structure and spatial complexity of the power network, resulting in uneven regional division, which in turn affects the inspection efficiency and task execution quality; drone cluster scheduling fails to adaptively match tasks according to capability differences. Drones of different models or states have differences in endurance, load capacity, and perception accuracy. The current scheduling mechanism often fails to combine these factors for adaptive task allocation; the fault tolerance and task recovery mechanism lacks intelligence and real-time performance. When some drones fail or run out of energy, the existing system responds laggingly in task recovery and redistribution, and cannot guarantee the continuity and integrity of the inspection tasks. Summary of the invention

[0003] Based on the above-mentioned shortcomings of the prior art, the purpose of the present invention is to provide a power line collaborative inspection system based on drone clusters to solve the above-mentioned technical problems.

[0004] To achieve the above objectives, the present invention provides the following technical solutions: a power line collaborative inspection system based on drone clusters, comprising:

[0005] Hypergraph topology modeling module: constructs a power line hypergraph model based on power system data and extracts the hypergraph topology feature matrix;

[0006] Fractal area division module: Based on the topological feature matrix and the preset fractal algorithm, the area to be inspected is divided into multiple sub-areas while minimizing the spatial coverage balance and boundary complexity under the constraints.

[0007] Dynamic task allocation module: Construct a fitness matrix based on the drone's endurance, drone accuracy and regional volume, achieve optimal matching of drones based on the fitness matrix, and conduct collaborative inspection of power lines according to the optimal matching results;

[0008] Autonomous fault-tolerant recovery module: When conducting collaborative inspections of power lines, the status data of drones is obtained in real time, and tasks are redistributed when a fault occurs.

[0009] The present invention is further configured such that the power system data includes: power equipment nodes, connection relationships, power equipment types, connection lengths of power equipment, betweenness centrality of nodes, and historical fault counts.

[0010] The present invention is further configured to set the power equipment node as a node of the power line hypergraph model , set the connection relationship to the hyperedge of the power line hypergraph model ;

[0011] The topological connection strength coefficient is calculated according to the type of power equipment, the connection length of the hyperedge corresponding to the power equipment and the betweenness centrality of the node;

[0012] Calculate equipment reliability enhancement factor based on historical failure times;

[0013] The product of the topological connection strength coefficient and the device reliability enhancement coefficient is set as the hyperedge weight.

[0014] The present invention is further configured such that the calculation logic of the topological connection strength coefficient is: , For super edge The topological connection strength coefficient, For super edge The number of nodes on is the power equipment type coefficient of the node, For super edge Corresponding to the connection length of the power equipment, is the normalized length reference value, is the regulating factor, For Node Betweenness centrality of ;

[0015] The calculation logic of equipment reliability enhancement factor is: , For super edge Equipment reliability enhancement factor, For Node The cumulative health index, is the control factor.

[0016] The present invention is further configured such that the extraction logic of the hypergraph topology feature matrix is: , is the hypergraph topological feature matrix, is the vertex degree diagonal matrix, , For Node The degree of For super edge Contains nodes , For super edge The hyperedge weight of is the vertex-hyperedge incidence matrix, , is the hyperedge weight matrix, is a hyper-degree diagonal matrix, , For super edge The degree of For super edge The number of vertices contained.

[0017] The present invention is further configured that the fractal region division module comprises:

[0018] Construct an initial cube containing the entire power line, use a recursive partitioning method to generate sub-cubes by continuously reducing the side length of the cube, and calculate the fractal dimension of the power line area based on the number and side length of the sub-cubes;

[0019] Generate inspection areas based on fractal dimensions, minimize spatial coverage balance and boundary complexity under constraints, and divide the area to be inspected into multiple sub-areas;

[0020] The multiple sub-regions are subdivided according to the fractal dimension, and the regional similarity of the sub-regions is calculated. The maximum spanning tree algorithm is used to merge the regions with the highest regional similarity until the number of regions equal to the number of drones is obtained.

[0021] The present invention is further configured such that the calculation logic of the fractal dimension is: , is the fractal dimension, is the side length of the subcube, is the number of sub-cubes;

[0022] The spatial coverage balance and boundary complexity are: , is the number of sub-regions, For the sub-regions, For the The volume of the subregion, For the The boundary complexity of the sub-regions, is the equilibrium parameter; the constraints are: ; ; is the initial cube;

[0023] The number of subdivisions is: , is the number of subdivisions, is the number of nodes, To round up;

[0024] The calculation logic of regional similarity is: , The area after re-division and The regional similarity of and For Region and The hypergraph topological feature matrix of For Region and The distance between is the scale parameter.

[0025] The present invention is further configured such that the fitness matrix Elements in The calculation logic is: , For Region The volume of To extend the flight time of the drone, For drone accuracy, and is the weight coefficient.

[0026] The present invention is further configured to construct an objective function according to the fitness matrix: , Assign matrices to drones, is the number of drones, Assign elements to the drones, satisfying the constraints: ;

[0027] The objective function is solved to obtain the optimal UAV allocation matrix, and the coordinated inspection of power lines is carried out according to the optimal UAV allocation matrix.

[0028] The present invention is further configured that the autonomous fault-tolerant recovery module comprises:

[0029] When conducting collaborative inspections of power lines, each drone periodically sends a heartbeat signal to indicate normal operation. The heartbeat signal contains the progress information of the current task and the remaining endurance.

[0030] Receive and verify the heartbeat signals of all drones. If any drone fails to respond to the heartbeat signal on time, it is judged that the corresponding drone has a fault.

[0031] When any UAV completes the coordinated inspection of the power lines and the remaining endurance is greater than the distance endurance and the required endurance of the remaining tasks in the corresponding area of ​​the faulty UAV, the tasks in that area will be reallocated to the corresponding UAV.

[0032] The present invention provides a power line collaborative inspection system based on a drone cluster, comprising a hypergraph topology modeling module: constructing a power line hypergraph model based on power system data, and extracting a hypergraph topology feature matrix; a fractal region division module: according to the topology feature matrix and a preset fractal algorithm, under the condition of satisfying constraints, the spatial coverage balance and boundary complexity are minimized, and the area to be inspected is divided into multiple sub-areas; a dynamic task allocation module: constructing a fitness matrix according to the drone endurance, the drone accuracy and the regional volume, realizing the optimal matching of the drone based on the fitness matrix, and performing collaborative inspection of the power line according to the optimal matching result; an autonomous fault-tolerant recovery module: when performing collaborative inspection of the power line, the status data of the drone is obtained in real time, and when a fault occurs, the task is redistributed, and the beneficial effects produced include:

[0033] 1. Hypergraph modeling for topological features: The power line structure is abstracted into a hypergraph model, and through topological connection strength and health coefficient modeling, a deep integration expression of power system structure characteristics and risk factors is achieved, which improves the scientificity and pertinence of task division;

[0034] 2. Fractal dimension driven area division algorithm: fractal modeling and regional complexity analysis are used to make the inspection area division more refined and balanced, which can minimize the uneven spatial coverage and boundary processing complexity, and improve the overall operation efficiency;

[0035] 3. Adaptive UAV task matching mechanism: Construct an adaptation matrix based on UAV performance parameters and regional complexity. By optimizing the matching strategy, it can achieve efficient binding of UAVs with differentiated capabilities and task areas, thereby improving resource utilization.

[0036] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0038] Figure 1 The present invention is a flowchart of a power line collaborative inspection system based on drone clusters, showing an exemplary embodiment of the present invention. DETAILED DESCRIPTION

[0039] The following will describe the embodiments of the present invention with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be understood that the preferred embodiments are only for illustrating the present invention, not for limiting the scope of protection of the present invention.

[0040] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present invention, and thus the drawings only show components related to the present invention rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed arbitrarily, and the component layout may also be more complicated.

[0041] In the following description, numerous details are discussed to provide a more thorough explanation of the embodiments of the present invention. However, it is obvious to those skilled in the art that the embodiments of the present invention can be implemented without these specific details. In other embodiments, well-known structures and devices are shown in the form of block diagrams rather than in detail to avoid making the embodiments of the present invention difficult to understand.

[0042] A collaborative inspection system for power lines based on drone swarms, such as Figure 1 As shown, including:

[0043] Hypergraph topology modeling module: constructs a power line hypergraph model based on power system data and extracts the hypergraph topology feature matrix;

[0044] Fractal area division module: Based on the topological feature matrix and the preset fractal algorithm, the area to be inspected is divided into multiple sub-areas while minimizing the spatial coverage balance and boundary complexity under the constraints.

[0045] Dynamic task allocation module: Construct a fitness matrix based on the drone's endurance, drone accuracy and regional volume, achieve optimal matching of drones based on the fitness matrix, and conduct collaborative inspection of power lines according to the optimal matching results;

[0046] Autonomous fault-tolerant recovery module: When conducting collaborative inspections of power lines, the status data of drones is obtained in real time, and tasks are redistributed when a fault occurs.

[0047] The present invention is further configured that the power system data includes: power equipment nodes, connection relationships, power equipment types, connection lengths of power equipment, betweenness centrality of nodes, and the number of historical faults. Specifically, power equipment nodes refer to various equipment or facilities in the power system, including towers, substations, insulators, and connection points on power lines. They are the basic components of the power system, and each node can perform specific functions, such as current distribution, signal transmission, etc.; connection relationships represent physical or logical connections between different power equipment, including power lines, transmission lines, cable connections between supporting structures or equipment. Connection relationships help determine the signal flow, data flow, and flow path of electric energy in the power system; power equipment types refer to the classification of various equipment in the power system, including substations, circuit breakers, wires, insulators, and switches, and each type of equipment has different functions in the power system; the connection length of power equipment refers to the physical connection length between power equipment, which refers to the length of power lines or cables, and is an important factor affecting power transmission efficiency and power loss; the betweenness centrality of a node is an indicator that measures the role of a node as a "bridge" in a network, and refers to the number of times the node participates in the shortest path in the network. Nodes with high betweenness centrality usually play an important intermediary role in the network, connecting multiple other nodes; the number of historical failures indicates the number of failures of a certain power equipment or node in the past period of time. This parameter is crucial for evaluating the reliability of equipment, predicting potential failures, and reallocating tasks.

[0048] The present invention is further configured to set the power equipment node as a node of the power line hypergraph model , set the connection relationship to the hyperedge of the power line hypergraph model ;

[0049] The topological connection strength coefficient is calculated according to the type of power equipment, the connection length of the hyperedge corresponding to the power equipment and the betweenness centrality of the node; the calculation logic of the topological connection strength coefficient is: , For super edge The topological connection strength coefficient, For super edge The number of nodes on is the power equipment type coefficient of the node, For super edge Corresponding to the connection length of the power equipment, is the normalized length reference value, is the regulating factor, For Node Specifically, the topological connection strength coefficient is used to measure the betweenness centrality of the hyperedge The structural importance and connectivity of the network are not only related to the physical connection of the power equipment, but also closely related to the equipment type and the centrality of the node. By comprehensively considering the above factors, the role and importance of each power facility or area in the power system can be effectively evaluated. The specific calculation logic includes: For each node On the super edge The power equipment type coefficient on the node indicates the importance of the node in the topology and is set to a discrete value. Each equipment type has a fixed value corresponding to it. The value depends on the type of equipment and is set by a classification system or standard. Normalized length reference value Take the maximum connection length of all hyperedges to eliminate the impact of scale differences between different devices and adjust the factor Controls the influence of connection length on topological connection strength, adjusts the influence of longer power lines, and prevents excessive dominance of weight by excessive connection length. The value range is (0,2]; node Betweenness centrality Indicates the degree to which the node acts as a "bridge" in the network. Nodes with high betweenness centrality usually play an important intermediary role in the power system, responsible for transmitting power flow and information flow; Used to calculate the "importance" of a region, where betweenness centrality The accumulation of reflects the impact of the key nodes in the entire hyperedge on the power flow. By summing the betweenness centrality and performing a logarithmic transformation, we can obtain a strong weighted effect of the nodes that have a greater impact on the system; the connection strength coefficient can effectively help accurately evaluate the importance of the connection between power equipment and lines, optimize task allocation and inspection area division; by considering factors such as the connection length of power equipment and the betweenness centrality of nodes, we can ensure the balance of system load and avoid excessive neglect of certain important areas;

[0050] The equipment reliability enhancement factor is calculated based on the number of historical failures. The calculation logic of the equipment reliability enhancement factor is: , For super edge Equipment reliability enhancement factor, For Node The cumulative health index, is the control factor. Specifically, the equipment reliability enhancement factor Used to measure the health of power equipment The influence of is the adjustment factor of equipment health on the topological connection strength, which indicates the influence of the health status of power equipment on the hyperedge connection strength. It is used to adjust the impact of device health status on the hyperedge connection strength. The value range is [0,2]. Cumulative health index Indicates the health status of the node device, including the relationship between its historical failure count and the allowed failure count. , For device nodes The number of failures of the node in the past. For device nodes The maximum number of failures allowed is set according to the equipment specifications and design requirements. To adjust the factor, prevent the cumulative health index from being too small when the number of faults is zero or very low; the equipment reliability enhancement factor provides a tool for dynamically evaluating the health status of equipment in the power system, which helps to dynamically adjust the system task allocation and resource scheduling according to the health status of the equipment; through the cumulative health index and the equipment reliability enhancement factor, the system can automatically identify high-fault risk areas when equipment fails, and adjust the inspection tasks or fault repair priorities to improve the system's fault tolerance;

[0051] The product of the topological connection strength coefficient and the equipment reliability enhancement coefficient is set as the hyperedge weight; specifically, the hyperedge is used to represent the connection relationship between power equipment, and the topological connection strength coefficient and the equipment reliability enhancement coefficient respectively quantify the impact of the connectivity and health status of power facilities on the power system. Setting the product of these two coefficients as the hyperedge weight can comprehensively evaluate the physical connectivity and health status of power facilities, provide the system with a more comprehensive hyperedge weight, and help identify key equipment and areas in the system.

[0052] The present invention is further configured such that the extraction logic of the hypergraph topology feature matrix is: , is the hypergraph topological feature matrix, is the vertex degree diagonal matrix, , For Node The degree of For super edge Contains nodes , For super edge The hyperedge weight of is the vertex-hyperedge incidence matrix, , is the hyperedge weight matrix, is a hyper-degree diagonal matrix, , For super edge The degree of For super edge The number of vertices contained. Specifically, the vertex degree diagonal matrix The diagonal elements of represent the total weight of each node and its associated hyperedges. , whose degree is the total weight of the hyperedges connected to the node; the hyperedge degree diagonal matrix The diagonal elements of represent the number of nodes connected by each hyperedge. , whose degree is the number of nodes contained in the hyperedge; the vertex-hyperedge association matrix Represents the relationship between nodes and hyperedges. The elements of the matrix are 0 or 1, indicating whether a node belongs to a hyperedge. Included in the hyperedge middle, , otherwise 0. Hyperedge weight matrix is a diagonal matrix whose diagonal elements represent the weight of each hyperedge. The calculation logic of the hyperedge weight has been explained in detail in the above content and will not be repeated here. , accurately describes the connection relationship between power equipment and its importance, providing strong support for task allocation and resource scheduling.

[0053] The present invention is further configured that the fractal region division module comprises:

[0054] An initial cube containing the entire power line is constructed. A recursive partitioning method is used to generate sub-cubes by continuously reducing the side length of the cube. The fractal dimension of the power line area is calculated based on the number and side length of the sub-cubes. The calculation logic of the fractal dimension is: , is the fractal dimension, is the side length of the subcube, is the number of sub-cubes; specifically, the fractal region partitioning module recursively divides the area of ​​the power line and calculates the fractal dimension of the area to determine the complexity of the power line. This process generates sub-cubes by gradually reducing the side length of the initial cube, thereby calculating the fractal dimension of the power line area. The fractal dimension reflects the spatial complexity of the power line area. The higher the fractal dimension, the higher the complexity of the area, the more details, and the finer the granularity of the division; first, build an initial cube , the cube needs to contain the entire power line area. The side length of this cube is , enough to cover the range of the power line, then a recursive partitioning method is used to gradually reduce the side length of the cube. To generate multiple sub-cubes. Each time the cube is recursively split, the side length of the cube is reduced, so that the number of sub-cubes generated each time increases. The side length of each new sub-cube is the original cube. (Each level of recursion generates a new cube) until a certain resolution (i.e., minimum edge length) is reached, at which point no further splitting is possible. With each split, the number of sub-cubes is recorded. and the current subcube side length , the fractal dimension is calculated by recording different The number of sub-cubes under the area is calculated by applying the formula. The logarithmic calculation in the formula helps to evaluate the "complexity" of the area, thus providing a basis for subsequent task allocation and area division. is the number of sub-cubes with the current side length. Gradually decrease (i.e., recursive partitioning process), the number of sub-cubes required to cover the desired area gradually increases. Ultimately, the calculated fractal dimension will represent the complexity of the area;

[0055] The inspection area is generated based on the fractal dimension. Under the constraints, the spatial coverage balance and boundary complexity are minimized, and the inspection area is divided into multiple sub-areas. The spatial coverage balance and boundary complexity are: , is the number of sub-regions, For the sub-regions, For the The volume of the subregion, For the The boundary complexity of the sub-regions, is the equilibrium parameter; the constraints are: ; ; is the initial cube; specifically, the scheme for generating inspection areas based on fractal dimension aims to reasonably divide the inspection areas of power lines by minimizing the spatial coverage balance and boundary complexity. This method takes into account the volume of the area (spatial coverage balance) and the complexity of the boundary, and optimizes the division under constraints. The boundary complexity of the sub-region It reflects the degree of tortuosity or complexity of the sub-area boundary. Areas with higher boundary complexity mean higher inspection task complexity. , Indicates region boundaries The gradient at describes the rate of change of the boundary and reflects the complexity of the boundary. Larger gradient values ​​indicate more complex boundaries. Areas with more complex boundaries mean that more drone resources are needed for inspections. Therefore, try to avoid overly complex boundaries when dividing areas. Constraints ensure that the divided sub-areas can cover the entire power line area and do not overlap. By minimizing the spatial coverage balance and boundary complexity, the inspection area of ​​the power line can be effectively divided to ensure efficient allocation and execution of tasks. Combined with the calculation of fractal dimension, the inspection task allocation can be dynamically optimized according to the complexity of the power line, improving resource utilization efficiency and enhancing the system's fault tolerance and fault detection capabilities.

[0056] Re-segment multiple sub-regions according to the fractal dimension, calculate the regional similarity of the re-segmented regions, and use the maximum spanning tree algorithm to merge the regions with the highest regional similarity until the number of regions equal to the number of drones is obtained. The number of re-segmentations is: , is the number of subdivisions, is the number of nodes, The calculation logic of regional similarity is: , The area after re-division and The regional similarity of and For Region and The hypergraph topological feature matrix of For Region and The distance between is the scale parameter; specifically, multiple sub-regions are re-divided according to the fractal dimension and the regional similarity is calculated, and then the maximum spanning tree (MST) algorithm is used to merge the regions with the highest regional similarity, and finally the number of regions equal to the number of drones is obtained; the fractal dimension in the formula The larger the fractal dimension, the higher the complexity of the region, so more sub-regions are needed to divide the power line region more finely, and the number of nodes A large number of nodes means that the area may contain more power facilities, resulting in more sub-areas when dividing; the number calculated by the above formula is It determines the number of regions that need to be subdivided in the end, which in turn affects the subsequent calculation and merging process of regional similarity. Regional similarity measures the similarity between two sub-regions in terms of spatial distribution and connection characteristics of power equipment. Specifically, the following two factors are considered when calculating similarity: topological similarity, which measures the similarity of the topological structures of two regions through the connection relationship of nodes, hyperedge weights, etc.; spatial similarity, which calculates the similarity of the geometric shape and distribution of two regions. Fractal dimension Indicators such as and boundary complexity will affect the similarity of region shapes. The maximum spanning tree (MST) algorithm is used to find the most similar region pairs between a set of regions and merge them until the number of regions equals the number of drones is obtained. The steps of the MST algorithm are as follows: (1) Construct a region similarity graph: use regions as nodes and similarity as edge weights to construct a weighted undirected graph; (2) Apply the MST algorithm: Use the Kruskal algorithm and Prim algorithm to find the maximum spanning tree. Among these algorithms, the edges with the highest similarity are preferentially selected for merging until all regions are merged. regions, among which, Kruskal algorithm: sort edges from high to low according to similarity, and gradually select edges with the greatest similarity to merge until the desired Prim's algorithm: Starting from an initial region, gradually select the regions that are most similar to the regions in the current spanning tree and merge them until the desired region is obtained. regions; (3) Ensure that the number of regions after merging is : The algorithm will continue to merge areas with high similarity until the final number of areas equals the number of drones , ensuring that tasks can be evenly distributed to drones. Generating inspection areas based on fractal dimensions and using the maximum spanning tree (MST) algorithm to merge areas with high similarity can effectively optimize task allocation and resource usage. During the segmentation and merging process, the system dynamically adjusts the area division and merging strategies to ensure task load balance, improve the efficiency of inspection tasks, and ultimately achieve the best task allocation effect.

[0057] The present invention is further configured such that the fitness matrix Elements in The calculation logic is: , For Region The volume of To extend the flight time of the drone, For drone accuracy, and is the weight coefficient; specifically, the fitness matrix The calculation of is to solve the task adaptation problem between the UAV and the inspection area, and ensure the effectiveness and fairness of task allocation. The elements in the matrix Indicates area With drones Its calculation logic combines the endurance, accuracy and volume of the mission area of ​​the drone. It refers to the maximum time or maximum flight range that a drone can perform a mission without the need for recharging. Drones with high endurance can cover larger areas and are suitable for missions in areas with a wide range. It refers to the measurement accuracy of the drone's sensors when it performs inspection tasks. High-precision drones are suitable for fine inspection tasks, such as small power equipment inspections; through the calculation of the fitness matrix, the drone can be accurately matched with the mission area based on the drone's endurance, accuracy, and the volume of the inspection area. By adjusting the weight coefficient, the system can flexibly balance the impact between endurance and accuracy, thereby improving the efficiency and accuracy of task allocation, optimizing the use of resources, and ensuring efficient execution of tasks.

[0058] The present invention is further configured to construct an objective function according to the adaptation matrix: , is the UAV allocation matrix, is the number of UAVs, is the UAV allocation element, satisfying the constraint conditions: ; Specifically, the core of the objective function is to maximize the adaptation matrix, that is, to try to assign the UAVs to the inspection areas they are most suitable for, so as to improve the efficiency and accuracy of task completion. The constraint condition means that each UAV can only be assigned to one area, means that each area must be assigned a UAV, represents the binary restriction of the allocation matrix, and this constraint condition ensures that each element is a binary value, either 1 (indicating that the UAV is assigned to this area) or 0 (indicating that the UAV is not assigned to this area). This ensures that the allocation is completely discrete without intermediate states; through the design of the adaptation matrix and the optimization objective function, the present invention can ensure that each UAV is assigned to the most suitable inspection area, while meeting the constraint conditions, ensuring the rationality and fairness of task allocation. This method improves the efficiency and accuracy of task execution by maximizing the weighted sum of the adaptation matrix, and is an effective task allocation and optimization scheme.

[0059] Solve the objective function to obtain the optimal UAV allocation matrix, and perform collaborative inspection of power lines according to the optimal UAV allocation matrix.

[0060] The present invention is further configured to that the autonomous fault tolerance and recovery module includes:

[0061] When performing collaborative inspection of power lines, each UAV regularly sends a heartbeat signal to indicate the normal operation status, and the heartbeat signal includes the progress information of the current task and the remaining battery life;

[0062] Receive and verify the heartbeat signals of all UAVs. When any UAV fails to respond to the heartbeat signal on time, it is judged that the corresponding UAV has a fault;

[0063] When any UAV completes the collaborative inspection of power lines and the remaining battery life is greater than the required battery life for the journey and the remaining tasks in the area corresponding to the faulty UAV, the tasks in this area are re-assigned to the corresponding UAV. Specifically, the autonomous fault tolerance and recovery module is designed to improve the reliability and robustness of the power line collaborative inspection system. The module detects faults by monitoring the heartbeat signals of UAVs, ensuring the continuity of the system and the timely completion of tasks. When a UAV fault is detected, the system can automatically re-allocate tasks to ensure that the inspection tasks are not affected.

[0064] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wired (such as infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or a data center that contains one or more collections of available media. The available media can be magnetic media (such as floppy disks, hard disks, magnetic tapes), optical media (such as DVDs), or semiconductor media. The semiconductor media can be a solid-state drive.

[0065] It should be understood that the term "and / or" in this document is merely a description of the association relationship between associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. Here, A and B can be singular or plural. Additionally, the character " / " in this document generally represents an "or" relationship between the associated objects before and after, but it may also represent an "and / or" relationship, which can be specifically understood by referring to the context before and after.

[0066] In the present application, "at least one" means one or more, and "a plurality" means two or more. "At least one of the following" or its similar expressions refer to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can represent: a, b, c, a - b, a - c, b - c, or a - b - c, where a, b, and c can be single or multiple.

[0067] It should be understood that in various embodiments of the present application, the magnitudes of the sequence numbers of the above processes do not mean the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0068] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. A professional technician can use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of this application.

[0069] Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein.

[0070] In several embodiments provided in this application, it should be understood that the disclosed system can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. 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 displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of devices or units can be electrical, mechanical, or other forms.

[0071] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place, or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0072] In addition, the functional units in each embodiment of this application can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit.

[0073] When the above-mentioned functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art or a part of this technical solution can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of this application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs that can store program codes.

[0074] As described above, the above are only specific implementation manners of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art within the technical scope disclosed by this application can easily think of changes or substitutions, which should all be covered within the protection scope of this application. Therefore, the protection scope of this application shall be subject to the protection scope of the claims.

Claims

1. A collaborative inspection system for power lines based on a drone swarm, characterized in that, Including: Hypergraph topology modeling module: constructing a power line hypergraph model based on power system data and extracting a hypergraph topology feature matrix; Fractal region division module: dividing the area to be inspected into multiple sub-regions by minimizing the spatial coverage balance and boundary complexity under the satisfaction of constraint conditions according to the topology feature matrix and a preset fractal algorithm; Dynamic task allocation module: constructing a fitness matrix based on the UAV endurance, UAV accuracy, and regional volume, achieving the optimal matching of UAVs based on the fitness matrix, and performing collaborative inspection of power lines according to the optimal matching result; Autonomous fault tolerance and recovery module: obtaining the status data of UAVs in real time during the collaborative inspection of power lines, and reallocating tasks when a fault occurs.

2. The collaborative power line inspection system based on an unmanned aerial vehicle cluster according to claim 1, wherein, Power system data includes: power equipment nodes, connection relationships, power equipment types, connection lengths of power equipment, betweenness centrality of nodes, and historical fault times.

3. The collaborative power line inspection system based on a drone swarm according to claim 2, wherein, Set the power equipment nodes as the nodes of the power line hypergraph model , and set the connection relationships as the hyperedges of the power line hypergraph model ; Calculating the topological connection strength coefficient according to the power equipment type, connection length of the power equipment corresponding to the hyperedge, and betweenness centrality of the node; Calculating the equipment reliability enhancement coefficient according to the historical fault times; Setting the product of the topological connection strength coefficient and the equipment reliability enhancement coefficient as the hyperedge weight.

4. A collaborative power line inspection system based on a drone swarm according to claim 1, characterized in that, The calculation logic of the topological connection strength coefficient is as follows: , is the topological connection strength coefficient of the hyperedge , is the number of nodes on the hyperedge , is the power equipment type coefficient of the node, is the connection length of the power equipment corresponding to the hyperedge , is the normalized length reference value, is the adjustment factor, is the node 's betweenness centrality; The calculation logic of the device reliability enhancement factor is as follows: , is the device reliability enhancement factor of the hyperedge , is the cumulative health index of the node , is the control factor.

5. The collaborative power line inspection system based on an unmanned aerial vehicle cluster according to claim 1, wherein The extraction logic of the hypergraph topological feature matrix is as follows: , is the hypergraph topological feature matrix, is the vertex degree diagonal matrix, , is the node degree, is the hyperedge containing the node , is the hyperedge hyperedge weight, is the vertex-hyperedge incidence matrix, , is the hyperedge weight matrix, is the hyperedge degree diagonal matrix, , is the hyperedge degree, is the hyperedge number of vertices contained.

6. The collaborative power line inspection system based on an unmanned aerial vehicle (UAV) cluster according to claim 1, wherein The fractal region division module includes: Constructing an initial cube containing the entire power line, using a recursive segmentation method, generating sub-cubes by continuously reducing the side length of the cube, and calculating the fractal dimension of the power line region according to the number and side length of the sub-cubes; Generating an inspection area based on the fractal dimension, and dividing the area to be inspected into multiple sub-regions by minimizing the spatial coverage balance and boundary complexity under the satisfaction of constraint conditions; Re-segmenting multiple sub-regions according to the fractal dimension, calculating the regional similarity of the re-segmented regions, and using the maximum spanning tree algorithm to merge the regions with the highest regional similarity until the number of regions equal to the number of UAVs is obtained.

7. An electric power line collaborative inspection system based on a drone swarm according to claim 6, characterized in that, The calculation logic of the fractal dimension is as follows: , is the fractal dimension, is the side length of the sub-cube, is the number of sub-cubes; The spatial coverage balance and boundary complexity are as follows: , is the number of sub-regions, is the th sub-region, is the th sub-region's volume, is the th sub-region's boundary complexity, is the balance parameter; the constraint conditions are: ; ; is the initial cube; The number of re-divisions is: , is the number of re-divisions, is the number of nodes, is rounding up; The calculation logic of regional similarity is as follows: , is the region after re-segmentation and is the regional similarity of and is the region and is the hypergraph topological feature matrix of is the region and is the distance between is the scale parameter.

8. A collaborative power line inspection system based on a drone swarm according to claim 1, characterized in that Adaptation matrix The elements in The calculation logic is as follows: , is the volume of area , is the endurance of the UAV, is the accuracy of the UAV, and are weight coefficients.

9. The collaborative power line inspection system based on an unmanned aerial vehicle cluster according to claim 8, characterized in that, Construct the objective function according to the adaptation matrix: , is the UAV allocation matrix, is the number of UAVs, is the UAV allocation element, satisfying the constraint conditions: ; Solving the objective function to obtain the optimal UAV allocation matrix, and performing collaborative inspection of power lines according to the optimal UAV allocation matrix.

10. A collaborative power line inspection system based on a drone swarm according to claim 1, characterized in that, The autonomous fault tolerance and recovery module includes: During the collaborative inspection of power lines, each UAV regularly sends a heartbeat signal to indicate the normal operation status, and the heartbeat signal includes the progress information of the current task and the remaining endurance; Receiving and verifying the heartbeat signals of all UAVs, and determining that the corresponding UAV has a fault when any UAV fails to respond to the heartbeat signal on time; When any UAV completes the collaborative inspection of power lines and the remaining endurance is greater than the required endurance for the journey endurance and the remaining tasks in the area corresponding to the faulty UAV, reallocating the tasks in this area to the corresponding UAV.

Images