A distribution network multi-UAV patrol path planning method and system

Abstract

The present invention provides a distribution network multi-UAV patrol line path planning method and system, the method comprising: obtaining distribution network parameter information, constructing an Euler graph according to the distribution network parameter information; calculating the Euler loop length of the Euler graph, and determining the number of UAVs according to the Euler loop length; constructing a multidimensional vector according to the number of UAVs and the initial number of particles in the particle swarm algorithm; taking the total length of the multi-UAV patrol line and the variance of the multi-UAV patrol line length as optimization targets, solving the objective function value corresponding to each particle by a decoding method, and obtaining the multi-UAV patrol line path by using the particle swarm algorithm. By implementing the present invention, the multi-UAV resources are fully utilized, the speed of obtaining the post-disaster fault information of the distribution network is effectively improved, and precious time and important data are gained for the post-disaster repair of the distribution network.

Description

Technical Field

[0001] The present invention relates to the technical field of distribution network inspection, and in particular to a distribution network multi-unmanned aerial vehicle inspection path planning method and system. Background Art

[0002] During the use of power equipment, regular inspections are required to promptly identify potential safety hazards and eliminate them to ensure the stability of power users. The existing power equipment line inspection tasks are mainly completed manually, and managers inspect all power facilities within their respective jurisdictions.

[0003] With the development of drone technology, drones are increasingly being used in power line inspections. When using drones to inspect all power facilities within a jurisdiction, managers only need to control the relevant drones to fly along the required inspection path without actually entering each location within the jurisdiction, which greatly reduces the workload of managers. In addition, drones can inspect power facilities from an overhead perspective compared to managers, so they are safer and have better observation effects.

[0004] However, under existing technical conditions, the path planning of drones is unreasonable when performing power line inspection tasks. Considering that the drones have limited power and cruising distance, they often need to return frequently to replace batteries during the flight, which is very troublesome and unable to locate line faults in the shortest time to provide data and time for post-disaster repairs of the distribution network. Summary of the invention

[0005] Therefore, the technical problem to be solved by the present invention is to overcome the defects of unreasonable power line inspection path planning in the prior art, thereby providing a distribution network multi-UAV inspection path planning method and system.

[0006] In order to achieve the above object, the present invention provides the following technical solutions:

[0007] In a first aspect, an embodiment of the present invention provides a distribution network multi-UAV line patrol path planning method, including: obtaining distribution network parameter information, and constructing an Euler graph according to the distribution network parameter information; calculating the Euler circuit length of the Euler graph, and determining the number of UAVs according to the Euler circuit length; constructing a multidimensional vector according to the number of UAVs and the initial number of particles in a particle swarm algorithm; taking the total length of the multi-UAV line patrol and the variance of the multi-UAV line patrol length as optimization targets, solving the objective function value corresponding to each particle through a decoding method, and obtaining the multi-UAV line patrol path using a particle swarm algorithm.

[0008] Optionally, constructing an Euler graph according to the distribution network parameter information includes: generating a network topology graph according to the distribution network parameter information; obtaining odd points in the network topology graph; calculating the shortest path length between any two of the odd points; and determining an edge-adding route according to the shortest path length based on a minimum weight bisection matching method to form an Euler graph.

[0009] Optionally, constructing a multidimensional vector according to the number of drones and the initial number of particles in the particle swarm algorithm includes: randomly selecting a plurality of line patrol endpoints in the Euler graph according to the number of drones; judging whether the initial number of particles in the particle swarm algorithm reaches a preset number; when the initial number of particles in the particle swarm algorithm does not reach the preset number, repeating the step of randomly selecting a plurality of line patrol endpoints in the Euler graph according to the number of drones; when the initial number of particles in the particle swarm algorithm reaches the preset number, constructing a multidimensional vector according to the number of line patrol endpoints and the initial number of particles.

[0010] Optionally, the method randomly selects multiple patrol endpoints in the Euler graph according to the number of drones, including: solving the patrol path of the drone on the Euler graph according to a preset algorithm, and setting serial numbers in ascending order for the nodes passed by the patrol path, wherein the maximum serial number is the total number of nodes passed by the patrol path in the Euler graph; randomly generating multiple different random integers, and sorting them from small to large, merging the sorted random integers with the maximum serial number to form multiple patrol endpoints, and the multiple different random integers are all smaller than the maximum serial number.

[0011] Optionally, the objective function value is calculated by the following formula:

[0012]

[0013] Where F represents the objective function value; α and β represent weight coefficients; f1 represents the total path length of the UAV patrol line; f2 represents the variance of the path lengths of multiple UAV patrol lines; M represents the number of nodes, i,j∈V, V represents the set of nodes to be patrolled, d ij is the Euclidean distance between nodes i and j, x ij is a binary variable, x ij =1 means that edge (i, j) is on the patrol path, x ij =0 means that edge (i, j) is not on the patrol path; h means the drone number, H means the number of drones, L h represents the patrol path length of UAV h, and L0 represents the mean patrol path length of multiple UAVs.

[0014] Optionally, the constraints for the objective function optimization are:

[0015]

[0016] Among them, Lmax Indicates the maximum flight distance of the drone.

[0017] Optionally, the particle position and velocity update formula in the particle swarm algorithm is:

[0018]

[0019] Among them, u ij represents the j-th velocity component of individual i, x ij represents the jth coordinate component of individual i, P best represents the coordinates of the best individual in the current iteration, G best represents the coordinates of the best individual in the first t iterations, c1 and c2 represent positive learning factors, r1 and r2 are random numbers, and ω is the inertia weight coefficient.

[0020] In a second aspect, an embodiment of the present invention provides a distribution network multi-UAV line patrol path planning system, including: an acquisition module, used to obtain distribution network parameter information, and construct an Euler diagram according to the distribution network parameter information; a calculation module, used to calculate the Euler circuit length of the Euler diagram, and determine the number of UAVs according to the Euler circuit length; a construction module, used to construct a multi-dimensional vector according to the number of UAVs and the initial number of particles in the particle swarm algorithm; a solution module, used to take the total length of multi-UAV line patrol and the variance of the multi-UAV line patrol length as optimization targets, solve the objective function value corresponding to each particle through a decoding method, and obtain the multi-UAV line patrol path using the particle swarm algorithm.

[0021] In a third aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the distribution network multi-UAV patrol path planning method described in the first aspect of the embodiment of the present invention.

[0022] In a fourth aspect, an embodiment of the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the distribution network multi-UAV patrol path planning method described in the first aspect of the embodiment of the present invention by executing the computer instructions.

[0023] The technical solution of the present invention has the following advantages:

[0024] The distribution network multi-UAV patrol line path planning method provided by the present invention includes: obtaining distribution network parameter information, constructing an Euler graph according to the distribution network parameter information; calculating the Euler loop length of the Euler graph, and determining the number of UAVs according to the Euler loop length; constructing a multidimensional vector according to the number of UAVs and the number of initial particles in the particle swarm algorithm; taking the total length of the multi-UAV patrol line and the variance of the multi-UAV patrol line length as optimization targets, solving the objective function value corresponding to each particle by a decoding method, and obtaining the multi-UAV patrol line path by using the particle swarm algorithm. The optimal segmentation point of the multi-UAV patrol line path is searched by the particle swarm algorithm, and the shortest patrol path of each UAV is solved by the Fleury algorithm based on the minimum weight bisection matching method, so as to achieve the goal of reducing the patrol line mileage of the UAV and reducing the patrol line time of the UAV, thereby shortening the distribution network post-disaster data acquisition time, and meeting the requirement of obtaining the distribution network fault information in a short time after the disaster. In addition, the multi-UAV resources are fully utilized, and the speed of obtaining the post-disaster fault information of the distribution network is effectively improved, so as to gain precious time and provide important data for the post-disaster repair of the distribution network. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0026] Figure 1 This is a flowchart of a specific example of a method for planning a multi-UAV patrol path in a distribution network according to an embodiment of the present invention;

[0027] Figure 2 A network topology diagram in an embodiment of the present invention;

[0028] Figure 3 This is a diagram of the path normalization results of multiple UAVs in an embodiment of the present invention;

[0029] Figure 4 It is a principle block diagram of a specific example of a distribution network multi-UAV patrol path planning system in an embodiment of the present invention;

[0030] Figure 5 A composition diagram of a specific example of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0031] The technical solution of the present invention will be described clearly and completely below in conjunction with the accompanying drawings. 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 are within the scope of protection of the present invention.

[0032] In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicating the orientation or positional relationship, are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first", "second", and "third" are used for descriptive purposes only, and cannot be understood as indicating or implying relative importance.

[0033] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, it can also be the internal connection of two components, it can be a wireless connection, or it can be a wired connection. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0034] In addition, the technical features involved in the different embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0035] The embodiment of the present invention provides a method for planning a multi-UAV patrol path in a distribution network. Figure 1 As shown, the following steps are included:

[0036] Step S1: Obtain distribution network parameter information, and construct an Euler diagram based on the distribution network parameter information.

[0037] In a specific embodiment, the distribution network parameter information includes the locations of pole towers in the distribution network and the distances between the pole towers.

[0038] In an embodiment of the present invention, constructing an Euler diagram according to distribution network parameter information specifically includes the following steps:

[0039] Step S10: Generate a network topology diagram according to the distribution network parameter information.

[0040] Step S11: Obtain singularity points in the network topology graph.

[0041] Step S12: Calculate the shortest path lengths between any two odd-degree points.

[0042] Step S13: Based on the minimum weight bisection matching method, the edge adding route is determined according to the shortest path length to form an Euler graph.

[0043] Specifically, the detailed steps to construct the Euler diagram are:

[0044] Step 1.1: Calculate the degree of each node in the network topology graph and find the number of edges associated with all nodes;

[0045] Step 1.2: Find all nodes with odd degrees, i.e. odd degree points;

[0046] Step 1.3: Calculate the shortest path length from each odd degree point to other odd degree points. To simplify the calculation, this embodiment does not consider the obstacle avoidance situation, so the shortest path length is simplified to the straight line distance between two points;

[0047] Step 1.4: Use the minimum weight bisection matching method to determine the edge addition plan that makes the Euler circuit the shortest, so that the original graph becomes an Euler graph.

[0048] Step S2: Calculate the length of the Euler circuit of the Euler graph, and determine the number of drones based on the length of the Euler circuit.

[0049] In a specific embodiment, the length L of the Euler circuit of the Euler graph in step S1 is calculated. E , estimate the number of drones H, if (H-1)·L max ≤L E ≤H·L max , where L max represents the maximum flight distance of the drone, and the estimated number of drones is H. If H is equal to 1, the drone patrol path is directly solved according to the Fleury algorithm, otherwise go to step S3.

[0050] In an embodiment of the present invention, when planning the line patrol path, various situations are fully considered to avoid wasting resources when planning the path, such as considering the line patrol situation of a single drone when inspecting a small area.

[0051] Step S3: Construct a multidimensional vector according to the number of drones and the initial number of particles in the particle swarm algorithm.

[0052] In a specific embodiment, step S3 specifically includes the following steps:

[0053] Step S31: According to the number of drones, a plurality of patrol endpoints are randomly selected in the Euler graph.

[0054] Step S32: Determine whether the number of initial particles in the particle swarm algorithm reaches a preset number.

[0055] Step S33: When the number of initial particles in the particle swarm algorithm does not reach the preset number, repeat the step of randomly selecting multiple patrol endpoints in the Euler graph according to the number of drones.

[0056] Step S34: when the number of initial particles in the particle swarm algorithm reaches a preset number, a multidimensional vector is constructed according to the number of patrol line endpoints and the number of initial particles.

[0057] In the embodiment of the present invention, according to the number of drones H, H patrol endpoints are randomly selected in the Euler graph to form an H-dimensional vector. If the number of initial particles in the particle swarm algorithm reaches the number N, step S4 is entered, otherwise step S3 is repeated.

[0058] Further, step S31 includes the following steps:

[0059] Step S311: Solve the patrol path of the drone on the Euler graph according to the Fleury algorithm, and set serial numbers for the nodes passed by the patrol path in ascending order, where the maximum serial number is the total number M of nodes passed by the patrol path in the Euler graph.

[0060] Step S312: randomly generate (H-1) different random integers less than M, and sort them from small to large. The sorted random integers are the serial numbers of the (H-1) patrol line endpoints. The sorted random integers are combined with the largest serial number M to form H patrol line endpoints.

[0061] Step S4: The total length of multi-UAV patrol line and the variance of multi-UAV patrol line length are taken as optimization targets, the objective function value corresponding to each particle is solved by decoding method, and the multi-UAV patrol line path is obtained by using particle swarm algorithm.

[0062] In a specific embodiment, the N vectors in S3 are used as the initial particles in the particle swarm algorithm, the total length of the multi-UAV line patrol and the variance of the multi-UAV line patrol length are used as optimization targets, the objective function value F corresponding to each particle is solved by the decoding method, and the multi-UAV line patrol path is obtained using the particle swarm algorithm.

[0063] In an embodiment of the present invention, the decoding method is:

[0064] Step 4.1: Let v0 represent the take-off and landing points of all drones, v h Indicates the patrol endpoint of drone h, h = 1;

[0065] Step 4.2: Construct the current shortest Euler circuit graph on the current subgraph;

[0066] Step 4.3: If v h If it does not exist in the current subgraph, then set F = ∞, otherwise use the Fleury algorithm to calculate the hth drone from v0 to vh The patrol path and calculate the path length L h , if L h >L max , then the objective function value Go to step 4.4, otherwise except v0 and v h In addition, the inspected edges and nodes are deleted from the current subgraph to obtain a new subgraph. If h = H, the objective function value F is calculated according to the multi-UAV patrol path. Otherwise, h = h + 1 is set and the process returns to step 4.2.

[0067] Step 4.4: Output the objective function value F and the decoding is completed.

[0068] The objective function value is calculated by the following formula:

[0069]

[0070] Among them, α and β represent weight coefficients, f1 represents the total path length of the UAV patrol line, and f2 represents the variance of the path length of multiple UAV patrol lines; M represents the number of nodes, i,j∈V, V represents the set of nodes to be patrolled, and d ij is the Euclidean distance between nodes i and j, x ij is a binary variable, x ij =1 means that edge (i, j) is on the patrol path, x ij =0 means that edge (i, j) is not on the patrol path; h means the drone number, H means the number of drones, L h represents the patrol path length of UAV h, and L0 represents the mean patrol path length of multiple UAVs.

[0071] The constraints for objective function optimization are:

[0072]

[0073] Among them, L max Indicates the maximum flight distance of the drone.

[0074] The constraints ensure that the in-degree of each node on the patrol path in the network topology is equal to the out-degree, all edges must be patrolled, and duplicate edges cannot be added.

[0075] The particle position and velocity update formula in the particle swarm algorithm is:

[0076]

[0077] Among them, u ij represents the j-th velocity component of individual i, x ij represents the jth coordinate component of individual i, P best represents the coordinates of the best individual in the current iteration, Gbest represents the coordinates of the best individual in the first t iterations, c1 and c2 represent positive learning factors, r1 and r2 are random numbers, and ω is the inertia weight coefficient, whose value directly determines the balance between the local and global search capabilities of the particle to a large extent. The larger ω is, the stronger the global search capability is, and the weaker the local search capability is. Therefore, when using the particle swarm algorithm, the size of ω must be reasonably set or continuously adjusted so that the particles can obtain the global optimal solution without falling into the local optimal solution.

[0078] Furthermore, the present invention adopts an improved particle swarm algorithm and defines the inertia weight coefficient as:

[0079]

[0080] In the formula, ω max ,ω min represent the maximum and minimum values ​​of ω respectively.

[0081] The distribution network multi-UAV patrol line path planning method provided by the present invention includes: obtaining distribution network parameter information, constructing an Euler graph according to the distribution network parameter information; calculating the Euler loop length of the Euler graph, and determining the number of UAVs according to the Euler loop length; constructing a multidimensional vector according to the number of UAVs and the number of initial particles in the particle swarm algorithm; taking the total length of the multi-UAV patrol line and the variance of the multi-UAV patrol line length as optimization targets, solving the objective function value corresponding to each particle by a decoding method, and obtaining the multi-UAV patrol line path by using the particle swarm algorithm. The optimal segmentation point of the multi-UAV patrol line path is searched by the particle swarm algorithm, and the shortest patrol path of each UAV is solved by the Fleury algorithm based on the minimum weight bisection matching method, so as to achieve the goal of reducing the patrol line mileage of the UAV and reducing the patrol line time of the UAV, thereby shortening the distribution network post-disaster data acquisition time, and meeting the requirement of obtaining the distribution network fault information in a short time after the disaster. In addition, the multi-UAV resources are fully utilized, and the speed of obtaining the post-disaster fault information of the distribution network is effectively improved, so as to gain precious time and provide important data for the post-disaster repair of the distribution network.

[0082] In one embodiment, a simulation verification process is taken as an example for description. Figure 2 This is the network topology used in the present invention. The network has a total of 79 nodes and a total line length of 22.35 km. In the simulation verification, the setting coefficients in the optimization objective function F are α = 0.2 and β = 0.8. The population size of the particle swarm is N = 50, the maximum number of iterations is T = 50, and the maximum speed u max =5, inertia weight ω max =0.9,ω min =0.4, and the learning factors c1 and c2 are both 0.5.

[0083] The specific steps are as follows:

[0084] Step 1: Read the distribution network parameter information, including the location of the tower to be inspected and the distance between the towers, generate the network topology graph G based on the distribution network parameter information, and construct the Euler graph E based on the graph G.

[0085] Among them, in step 1, the detailed steps of constructing the Euler graph E are:

[0086] Step 1.1: Calculate the degree of each node and find the number of edges associated with all nodes;

[0087] Step 1.2: Find all nodes with odd degrees, i.e. odd degree points;

[0088] Step 1.3: Calculate the shortest path length from each odd degree point to other odd degree points. To simplify the calculation, this embodiment does not consider the obstacle avoidance situation, so the shortest path length is simplified to the straight line distance between two points;

[0089] Step 1.4: Use the minimum weight bisection matching method to determine the edge addition plan that makes the Euler circuit the shortest, so that the original graph becomes the Euler graph E.

[0090] Step 2: Calculate the length L of the Euler circuit of the Euler graph E in step 1 E is 26.183 km, and the estimated number of drones is H. In this embodiment, if L max ≤L E ≤2L max , where the maximum flight distance of the drone is L max If the distance is 20km, the estimated number of drones is 2, so go to step 3.

[0091] Step 3: According to the number of drones 2, randomly select 2 patrol endpoints in Figure E to form a 2D vector. If the number of vectors N reaches 50, go to step 4, otherwise repeat step 3.

[0092] The specific method for randomly selecting two patrol endpoints in step 3 is:

[0093] Step 3.1: Solve the patrol path of the drone on Figure E according to the Fleury algorithm, and set serial numbers for the nodes passed by the patrol path in ascending order. The maximum serial number is the total number M of the nodes passed by the patrol path in Figure E, which is 87;

[0094] Step 3.2: Generate a random integer less than 87. This random integer is the serial number of the first drone's patrol endpoint, and merge it with serial number M=87 to form two patrol endpoints.

[0095] Step 4: Use the N = 50 vectors in step 3 as the initial particles in the particle swarm algorithm, take the total length of multi-UAV patrol line and the variance of multi-UAV patrol line length as optimization targets, solve the objective function value F corresponding to each particle through the decoding method, and use the particle swarm algorithm to obtain the multi-UAV patrol line path.

[0096] Among them, in step 4, the decoding method is:

[0097] Step 4.1: Let v0 = 1 to represent the take-off and landing points of all drones, v h Indicates the patrol endpoint of drone h, h = 1;

[0098] Step 4.2: Construct the current shortest Euler circuit graph on the current subgraph;

[0099] Step 4.3: If v h If it does not exist in the current subgraph, then set F = ∞, otherwise use the Fleury algorithm to calculate the hth drone from v0 to v h The patrol path and calculate the path length L h , if L h >L max , then the objective function value F = ∞, go to step 4.4, otherwise except v0 and v h In addition, the inspected edges and nodes are deleted from the current subgraph to obtain a new subgraph. If h = 2, the objective function value F is calculated according to the multi-UAV patrol path. Otherwise, h = h + 1 is set and the process returns to step 4.2.

[0100] Step 4.4: Output the objective function value F and the decoding is completed.

[0101] Specifically, in step 4, the calculation formula of the objective function value F is as follows:

[0102]

[0103] Among them, f1 represents the total path length of the UAV patrol line, f2 represents the variance of the path length of multiple UAV patrol lines; n represents the number of nodes, i,j∈V, d ij is the Euclidean distance between nodes i and j, x ij is a binary variable, x ij =1 means that edge (i, j) is on the patrol path, x ij =0 means that edge (i, j) is not on the patrol path; h means the drone number, L h represents the patrol path length of UAV h, and L0 represents the mean patrol path length of multiple UAVs.

[0104] The constraints for objective function optimization are:

[0105]

[0106] Step 5: Output the UAV path planning results.

[0107] In one embodiment, Figure 3 This is the result diagram of multi-UAV path regularization. Nodes 1-38 are the route flown by the first UAV, with a path length of 13.744km. Nodes 39-79 are the route flown by the second UAV, with a path length of 15.192km. Node 1 is the UAV control center, which is the departure and return location of all UAVs. The total flight distance of the two UAVs is 28.936km, slightly higher than the 26.183km under the unlimited flight distance of a single UAV. However, since the two UAVs patrol the line at the same time and the patrol path length is similar, the patrol time can be shortened by nearly half compared to the unlimited flight distance of a single UAV, and a single UAV must be constrained by the flight distance. Therefore, the present invention can effectively solve the problem of multi-UAV patrol path regularization after a distribution network disaster, improve the utilization efficiency of UAVs, and shorten the patrol time of the distribution network.

[0108] The embodiment of the present invention also provides a distribution network multi-UAV patrol path planning system, such as Figure 4 As shown, including:

[0109] The acquisition module 1 is used to acquire the distribution network parameter information and construct the Euler diagram according to the distribution network parameter information. For details, please refer to the relevant description of step S1 in the above embodiment, which will not be repeated here.

[0110] The calculation module 2 is used to calculate the length of the Euler circuit of the Euler graph and determine the number of drones according to the length of the Euler circuit. For details, please refer to the relevant description of step S2 in the above embodiment, which will not be repeated here.

[0111] The construction module 3 is used to construct a multidimensional vector according to the number of drones and the number of initial particles in the particle swarm algorithm. For details, please refer to the relevant description of step S3 in the above embodiment, which will not be repeated here.

[0112] The solution module 4 is used to use the total length of the multi-UAV patrol line and the variance of the multi-UAV patrol line length as optimization targets, solve the objective function value corresponding to each particle through the decoding method, and use the particle swarm algorithm to obtain the multi-UAV patrol line path. For details, please refer to the relevant description of step S4 in the above embodiment, which will not be repeated here.

[0113] The embodiment of the present invention also provides a computer device, such as Figure 5 As shown, the device may include a processor 61 and a memory 62, wherein the processor 61 and the memory 62 may be connected via a bus or other means. Figure 5 Take the example of connecting via a bus.

[0114] The processor 61 may be a central processing unit (CPU). The processor 61 may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or a combination of the above chips.

[0115] The memory 62 is a non-transient computer-readable storage medium that can be used to store non-transient software programs, non-transient computer executable programs and modules, such as the corresponding program instructions / modules in the embodiment of the present invention. The processor 61 executes various functional applications and data processing of the processor by running the non-transient software programs, instructions and modules stored in the memory 62, that is, the distribution network multi-UAV patrol line path planning method in the above method embodiment is implemented.

[0116] The memory 62 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and an application required by at least one function; the data storage area may store data created by the processor 61, etc. In addition, the memory 62 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory 62 may optionally include a memory remotely arranged relative to the processor 61, and these remote memories may be connected to the processor 61 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, an intranet, a mobile communication network, and combinations thereof.

[0117] One or more modules are stored in the memory 62, and when executed by the processor 61, the distribution network multi-UAV patrol path planning method provided by the embodiment of the present invention is executed.

[0118] For details of the above computer equipment, please refer to Figure 1-Figure 3 The corresponding related descriptions and effects in the illustrated embodiments can be understood and will not be repeated here.

[0119] Those skilled in the art can understand that the implementation of all or part of the processes in the above-mentioned embodiments can be completed by instructing the relevant hardware through a computer program. The program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the storage medium can be a disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory, a hard disk drive (HDD) or a solid-state drive (SSD), etc.; the storage medium can also include a combination of the above-mentioned types of memory.

[0120] Obviously, the above embodiments are merely examples for the purpose of clear explanation, and are not intended to limit the implementation methods. For those skilled in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to list all the implementation methods here. The obvious changes or modifications derived from these are still within the scope of protection of the invention.

Claims

1. A distribution network multi-UAV patrol path planning method, characterized in that: include: Acquire distribution network parameter information, and construct an Euler diagram according to the distribution network parameter information; Calculating the length of the Euler circuit of the Euler graph, and determining the number of drones according to the length of the Euler circuit; Construct a multidimensional vector based on the number of drones and the number of initial particles in the particle swarm algorithm; The total length of multi-UAV patrol line and the variance of multi-UAV patrol line length are taken as optimization targets, the objective function value corresponding to each particle is solved by decoding method, and the multi-UAV patrol line path is obtained by particle swarm algorithm. The decoding method is: Step 4.1: Let v0 = 1 to represent the take-off and landing points of all drones, v h Indicates the patrol endpoint of drone h, h = 1; Step 4.2: Construct the current shortest Euler circuit graph on the current subgraph; Step 4.3: If v h If it does not exist in the current subgraph, let F = ¥, otherwise use Fleury algorithm to calculate the hth drone from v0 to v h The patrol path and calculate the path length L h , if L h >L max , then the objective function value F = ￥, go to step 4.4, otherwise except v0 and v h In addition, the inspected edges and nodes are deleted from the current subgraph to obtain a new subgraph. If h = 2, the objective function value F is calculated according to the multi-UAV patrol path. Otherwise, h = h + 1 is set and the process returns to step 4.

2. Step 4.4: Output the objective function value F, and the decoding is completed; The objective function value is calculated by the following formula: Where F represents the objective function value; α and β represent weight coefficients; f1 represents the total path length of the UAV patrol line; f2 represents the variance of the path lengths of multiple UAV patrol lines; M represents the number of nodes, i,j∈V, V represents the set of nodes to be patrolled, d ij is the Euclidean distance between nodes i and j, x ij is a binary variable, x ij =1 means that edge (i, j) is on the patrol path, x ij =0 means that edge (i, j) is not on the patrol path; h means the drone number, H means the number of drones, L h represents the patrol path length of UAV h, and L0 represents the mean patrol path length of multiple UAVs.

2. The distribution network multi-UAV patrol path planning method according to claim 1 is characterized in that: The constructing an Euler diagram according to the distribution network parameter information includes: Generate a network topology diagram according to the distribution network parameter information; Obtaining singularity points in the network topology graph; Calculate the shortest path length between any two of the odd degree points; Based on the minimum weight bisection matching method, the edge adding route is determined according to the shortest path length to form an Euler graph.

3. The distribution network multi-UAV patrol path planning method according to claim 1 is characterized in that: According to the number of drones and the number of initial particles in the particle swarm algorithm, a multidimensional vector is constructed, including: According to the number of drones, multiple patrol endpoints are randomly selected in the Euler graph; Determine whether the number of initial particles in the particle swarm algorithm reaches the preset number; When the number of initial particles in the particle swarm algorithm does not reach the preset number, the step of randomly selecting multiple patrol endpoints in the Euler graph according to the number of drones is repeated; When the number of initial particles in the particle swarm algorithm reaches a preset number, a multidimensional vector is constructed according to the number of patrol endpoints and the number of initial particles.

4. The distribution network multi-UAV patrol path planning method according to claim 3 is characterized in that: According to the number of drones, multiple patrol endpoints are randomly selected in the Euler graph, including: Solve the patrol path of the drone on the Euler graph according to the preset algorithm, and set serial numbers for the nodes passed by the patrol path in ascending order, where the maximum serial number is the total number of nodes passed by the patrol path in the Euler graph; A plurality of different random integers are randomly generated and sorted from small to large. The sorted random integers are merged with the largest sequence number to form a plurality of patrol endpoints. The plurality of different random integers are all smaller than the largest sequence number.

5. The distribution network multi-UAV patrol path planning method according to claim 1 is characterized in that: The constraints for objective function optimization are: Among them, L max Indicates the maximum flight distance of the drone.

6. The distribution network multi-UAV patrol path planning method according to claim 5 is characterized in that: The particle position and velocity update formula in the particle swarm algorithm is: Among them, u ij represents the j-th velocity component of individual i; x ij represents the jth coordinate component of individual i, P best Represents the coordinates of the best individual in the current iteration; G best represents the coordinates of the best individual in the first t iterations; c1 and c2 represent positive learning factors; r1 and r2 are random numbers; ω is the inertia weight coefficient.

7. A distribution network multi-UAV patrol path planning system, characterized in that: include: An acquisition module is used to acquire distribution network parameter information and construct an Euler diagram according to the distribution network parameter information; A calculation module, used for calculating the length of the Euler circuit of the Euler graph, and determining the number of drones according to the length of the Euler circuit; A construction module is used to construct a multidimensional vector according to the number of drones and the number of initial particles in the particle swarm algorithm; The solution module is used to take the total length of multi-UAV patrol line and the variance of multi-UAV patrol line length as optimization targets, solve the objective function value corresponding to each particle through the decoding method, and use the particle swarm algorithm to obtain the multi-UAV patrol line path; The decoding method is: Step 4.1: Let v0 = 1 to represent the take-off and landing points of all drones, v h Indicates the patrol endpoint of drone h, h = 1; Step 4.2: Construct the current shortest Euler circuit graph on the current subgraph; Step 4.3: If v h If it does not exist in the current subgraph, let F = ¥, otherwise use Fleury algorithm to calculate the hth drone from v0 to v h The patrol path and calculate the path length L h , if L h >L max , then the objective function value F = ￥, go to step 4.4, otherwise except v0 and v h In addition, the inspected edges and nodes are deleted from the current subgraph to obtain a new subgraph. If h = 2, the objective function value F is calculated according to the multi-UAV patrol path. Otherwise, h = h + 1 is set and the process returns to step 4.

2. Step 4.4: Output the objective function value F, and the decoding is completed; The objective function value is calculated by the following formula: Where F represents the objective function value; α and β represent weight coefficients; f1 represents the total path length of the UAV patrol line; f2 represents the variance of the path lengths of multiple UAV patrol lines; M represents the number of nodes, i,j∈V, V represents the set of nodes to be patrolled, d ij is the Euclidean distance between nodes i and j, x ij is a binary variable, x ij =1 means that edge (i, j) is on the patrol path, x ij =0 means that edge (i, j) is not on the patrol path; h means the drone number, H means the number of drones, L h represents the patrol path length of UAV h, and L0 represents the mean patrol path length of multiple UAVs.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the distribution network multi-UAV patrol path planning method as described in any one of claims 1-6.

9. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the distribution network multi-UAV patrol path planning method as described in any one of claims 1-6 by executing the computer instructions.

Images