Power transmission line unmanned aerial vehicle inspection path planning method and system based on swarm intelligence
By using a swarm intelligence-based approach, 3D point cloud data and particle swarm optimization algorithm to optimize UAV inspection paths, the problem of high-voltage electric field influence in UAV inspections is solved, and the safety and efficiency of path planning are improved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- SHANGQIU POWER SUPPLY CO OF STATE GRID HANAN ELECTRIC POWER CO
- Filing Date
- 2026-02-03
- Publication Date
- 2026-05-05
AI Technical Summary
Existing technologies do not consider the influence of high-voltage electric fields on power transmission lines in drone inspection path planning, resulting in insufficient safety of the path planning results.
By collecting three-dimensional point cloud data along the transmission line, identifying the point clouds of the towers and the line, calculating the electric field influence factor and density characteristic value, establishing the inspection objective function, and using the particle swarm optimization algorithm to optimize the path planning, the safe flight of the UAV in the high-voltage electric field environment is ensured.
It improves the safety of drone inspection path planning, reduces the risk of collisions between drones and power transmission lines and towers, and optimizes the smoothness and efficiency of flight trajectories.
Smart Images
Figure CN121979247A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of particle swarm optimization technology, specifically to a method and system for unmanned aerial vehicle (UAV) inspection path planning for power transmission lines based on swarm intelligence. Background Technology
[0002] Using drones with fixed routes for power transmission line inspections cannot dynamically respond to equipment health conditions, potentially leading to missed inspections of critical components. Scientific path planning for drone inspections of power transmission lines can ensure safety, improve inspection efficiency, and reduce costs. During the process of planning drone inspection paths for power transmission lines, various constraints are set to ensure sufficient safety distances between the inspection line and obstacles in the inspection environment, that all inspection targets are included in the planned path, and that the total inspection distance is short.
[0003] However, power transmission lines generate high-voltage electric fields with varying degrees of influence at different locations in the surrounding space. This influence is not considered in the process of planning the path for unmanned aerial vehicle (UAV) inspections of power transmission lines, which can easily lead to insufficient safety of the path planning results. Summary of the Invention
[0004] This invention provides a method and system for unmanned aerial vehicle (UAV) inspection path planning for power transmission lines based on swarm intelligence. This addresses the problem that the influence of the high-voltage electric field generated by the power transmission line is not considered during the UAV inspection path planning process, thus affecting the safety of the path planning results. The specific technical solution adopted is as follows: In a first aspect, one embodiment of the present invention provides a method for unmanned aerial vehicle (UAV) inspection path planning for power transmission lines based on swarm intelligence, the method comprising the following steps: Collect three-dimensional point cloud data along the transmission line, and identify the tower point cloud and line point cloud from the three-dimensional point cloud data; Based on the distances between the adjacent track points that make up the inspection section and the midpoints of the tower point cloud and the line point cloud, the first electric field influence factor of the inspection section is calculated. The three-dimensional point cloud data is voxelized, and the density characteristic value of the voxel grid is calculated. Based on the angle between the direction of the vector determined by the adjacent track points that make up the inspection section and the preset different selected paths, the reference path of the inspection section is determined. Based on the positional relationship between the reference path of the inspection section and the adjacent track points corresponding to the inspection section, the second electric field influence factor of the inspection section is calculated. Based on the first electric field influence factor, the second electric field influence factor of the inspection section, and the density characteristic values of all voxel grids passed by the inspection section, the electric field influence degree of the inspection section is obtained. Based on the positional relationship between adjacent track points, the distance between track points and the midpoints of the tower point cloud and line point cloud, and the electric field influence of all inspection sections, an inspection objective function is established, and the path planning results of UAV inspection of transmission lines are obtained based on the inspection objective function.
[0005] Furthermore, the specific method for obtaining the first electric field influence factor of the inspected section is as follows: The minimum Euclidean distance between the track point and the midpoint of all line tower point clouds is denoted as the line tower collision distance of the track point, and the minimum Euclidean distance between the track point and the midpoint of all line point clouds is denoted as the line collision distance of the track point. The difference between the line collision distance at the end and the beginning of the inspection section is used as the numerator, and the difference between the line tower collision distance at the end and the beginning of the inspection section is used as the denominator. The value of the fraction is recorded as the first electric field influence factor of the inspection section.
[0006] Furthermore, the method for determining the density eigenvalues of the voxel mesh is as follows: The ratio of the number of points in the tower point cloud and line point cloud contained in the voxel grid to the number of points in the 3D point cloud data contained in the voxel grid is denoted as the density characteristic value of the voxel grid.
[0007] Furthermore, the specific method for obtaining the reference path of the inspection section is as follows: Based on the inspection direction of adjacent track points, a directed vector of the adjacent track points is established, and a directed unit vector of each preset selection path is established. The selection path corresponding to the directed unit vector with the smallest angle between it and the directed vector of the adjacent track points is used as the reference path for the inspection segment determined by the adjacent track points.
[0008] Furthermore, the preset selection path includes: The options for flying from one crossarm to another, flying from a distance to a crossarm and then away from it, vertical downward inspection, vertical upward inspection, diagonal downward inspection, and diagonal upward inspection.
[0009] Furthermore, the specific calculation method for the second electric field influence factor of the inspected section is as follows: Establish a first fitted curve of electric field intensity with respect to the distance between each position on the reference path and the starting point of the adjacent track points of the determined inspection section. Based on the inflection point of the fitted curve, divide the inspection section into inspection sub-segments. Calculate the comprehensive relative influence of the inspection section based on the increase or decrease of the curve segments corresponding to all the inspection sub-segments divided by the inspection section on the fitted curve. The slope of the first fitted curve at the point on the reference path with the smallest Euclidean distance to the track point is denoted as the reference slope of the track point. The average of the reference slopes of adjacent track points is recorded as the first average of the inspection route formed by adjacent track points; the positive correlation between the comprehensive relative influence of the inspection route and the first average is recorded as the second electric field influence factor of the inspection route.
[0010] Furthermore, the specific method for obtaining the comprehensive relative influence of the inspected road section is as follows: When the curve segment corresponding to the inspected sub-section on the fitted curve is monotonically increasing, the normalized value of the length of the inspected sub-section is recorded as the relative influence of the inspected sub-section. When the curve segment corresponding to the inspected sub-section on the fitted curve is monotonically decreasing, the normalized value of the negative number of the length of the inspected sub-section is recorded as the relative influence of the inspected sub-section. The sum of the relative impacts of all the sub-segments of the inspection section is recorded as the comprehensive relative impact of the inspection section.
[0011] Furthermore, the specific method for obtaining the electric field influence degree of the inspected section is as follows: The sum of the normalized value of the first electric field influence factor of the inspection section and the density characteristic values of all voxel grids traversed by the inspection section is denoted as the first cumulative sum of the inspection section; the product of the first cumulative sum of the inspection section and the second electric field influence factor is denoted as the electric field influence degree of the inspection section.
[0012] Furthermore, the inspection objective function is: The weighted sum of distance cost, collision cost, electric field effect cost, and penalty function; The distance cost is the sum of the lengths of the inspection route segments formed by all adjacent track points; The cost of electric field influence is the sum of the electric field influence of all inspected road sections; The collision cost is determined based on the minimum Euclidean distance between the track point and all points in the tower point cloud and the line point cloud. The penalty function is determined based on the turning angle of the waypoint position.
[0013] Secondly, embodiments of the present invention also provide a path planning system for unmanned aerial vehicle (UAV) inspection of power transmission lines based on swarm intelligence, including a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor executes the computer program to implement the steps of any of the methods described above.
[0014] The beneficial effects of this invention are: This application first evaluates the significance of the trend of gradually increasing distance between the UAV and the transmission line and gradually decreasing distance between the UAV and the transmission line tower based on the distances between adjacent track points and the midpoints of the corresponding tower and line point clouds of the inspection route, thus obtaining the first electric field influence factor of the inspection route. Then, based on the density of the tower and line point clouds adjacent to each other when the inspection route passes through the voxel grid, the possibility of collision with the transmission line tower during the UAV's inspection of the route is evaluated, and the density characteristic value of the voxel grid is obtained. Next, considering that the electric field of the high-voltage transmission line causes the potential to gradually decrease along the path from the transmission line to the tower, reaching zero potential at the tower, and considering the local electric field distortion concentrated at the end of the crossarm, the degree of influence of the high-voltage electric field on the inspection route is evaluated, thus obtaining the second electric field influence factor of the inspection route. The method involves obtaining the electric field influence degree of the inspection section based on the first and second electric field influence factors of the inspection section, as well as the density characteristic values of all voxel grids traversed by the inspection section. Finally, based on the degree of influence of the high-voltage electric field of the transmission line on the path planning result composed of all inspection sections, the smoothness and stability of the flight trajectory of the UAV when flying according to the path planning result composed of all inspection sections, the length of the UAV inspection path, and the probability of collision when the UAV inspects according to the inspection path, an inspection objective function is established. The path planning result of UAV inspection of the transmission line is obtained based on the inspection objective function, which solves the problem that the influence of the high-voltage electric field generated by the transmission line is not considered in the UAV inspection path planning process, thus affecting the safety of the path planning result and improving the safety of the path planning result. Attached Figure Description
[0015] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0016] Figure 1 This is a flowchart illustrating a method for unmanned aerial vehicle (UAV) inspection path planning for power transmission lines based on swarm intelligence, provided in one embodiment of the present invention. Detailed Implementation
[0017] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0018] Please see Figure 1 The diagram illustrates a flowchart of a method for unmanned aerial vehicle (UAV) inspection path planning for power transmission lines based on swarm intelligence, according to an embodiment of the present invention. The method includes the following steps: Step S001: Collect three-dimensional point cloud data along the transmission line and identify the tower point cloud and line point cloud from the three-dimensional point cloud data.
[0019] A drone equipped with a LiDAR (Light Detection and Ranging) was used to collect 3D point cloud data along the power transmission line. The APSS algebraic point set surface algorithm was used to denoise the 3D point cloud data, removing noise points caused by dust, bird flocks, and flight vibrations. A cloth simulation filtering algorithm was used to identify ground and non-ground points in the 3D point cloud data. All non-ground points were clustered using the AP clustering algorithm to obtain clusters. The PointNet point cloud target recognition model was used to perform semantic segmentation on all clusters, identifying the point clouds corresponding to the power transmission towers and lines. The point clouds corresponding to the power transmission towers were designated as tower point clouds, and the point clouds corresponding to the power transmission lines were designated as line point clouds.
[0020] Among them, the APSS algebraic point set surface algorithm, cloth simulation filtering algorithm, AP clustering algorithm and PointNet point cloud target recognition model are all well-known technologies and will not be described in detail.
[0021] At this point, the point cloud of the tower and the point cloud of the line have been obtained.
[0022] Step S002: Calculate the first electric field influence factor of the inspection section based on the distances between the adjacent track points forming the inspection section and the midpoints of the tower point cloud and the line point cloud. Perform voxelization on the 3D point cloud data and calculate the density characteristic value of the voxel grid. Determine the reference path of the inspection section based on the angle between the direction of the vector determined by the adjacent track points forming the inspection section and the preset different selected paths. Calculate the second electric field influence factor of the inspection section based on the positional relationship between the reference path of the inspection section and the adjacent track points corresponding to the inspection section. Obtain the electric field influence degree of the inspection section based on the first electric field influence factor, the second electric field influence factor, and the density characteristic values of all voxel grids traversed by the inspection section.
[0023] The minimum Euclidean distance between the track point and the midpoint of all tower point clouds is denoted as the tower collision distance of the track point, and the minimum Euclidean distance between the track point and the midpoint of all line point clouds is denoted as the line collision distance of the track point. The difference between the line collision distances at the end and the beginning of the inspection section is used as the numerator, and the difference between the tower collision distances at the end and the beginning of the inspection section is used as the denominator. The value of the fraction is denoted as the first electric field influence factor of the inspection section.
[0024] When the first electric field influence factor of the inspection section is larger, the distance between the drone and the power transmission line gradually increases and the distance between the drone and the power transmission tower gradually decreases during the inspection of the drone along the inspection section, and the trend of the drone being affected by the high voltage electric field along the inspection section decreases more obvious.
[0025] The number and height of power poles vary in different locations. Generally, taller poles carry higher voltages, while shorter poles carry lower voltages. Therefore, the degree to which the locations around the power tower point cloud and the power line point cloud at different heights are affected by the high-voltage electric field generated by the transmission line is different.
[0026] The 3D point cloud data is voxelized to define a voxel grid. In this embodiment, the side length of the voxel grid is set to 5 cm. The ratio of the number of points in the tower point cloud and line point cloud contained in the voxel grid to the number of points in the 3D point cloud data contained in the voxel grid is denoted as the density characteristic value of the voxel grid.
[0027] Each pair of adjacent track points can form an inspection segment. The larger the density characteristic value of the voxel grid, the more likely the UAV is to collide with the power transmission tower when it passes through the voxel grid.
[0028] For the electric field effect of high-voltage transmission lines, the potential gradually decreases along the path from the transmission line to the tower, reaching zero potential at the tower. The hollow structure of the tower causes local electric field distortion, which is mainly concentrated at the ends of the crossarms. The center of the tower is shielded by the tower and is relatively less affected by the electric field. However, the electric field at the edge of the crossarm is significantly distorted by the high-voltage transmission conductor, and this distortion is more pronounced at both ends of the crossarm. Therefore, the more points in the tower point cloud and line point cloud contained in the voxel mesh, and the closer the voxel mesh is to the edge of the transmission tower crossarm, the greater the influence of the high-voltage electric field on the voxel mesh.
[0029] When drones conduct power transmission line inspections, the inspection path is not unique. They can fly diagonally downwards from the tower crossarm, fly vertically downwards, or fly upwards from the base of the tower to inspect the vicinity of the power transmission line. Therefore, by pre-setting different path options and determining the angle between the selected path and the inspection segment formed by two adjacent trackpoints, the most reasonable path is determined, i.e., the direction of the most reasonable inspection path is determined. Furthermore, the degree to which the inspection segment formed by the two adjacent trackpoints is affected by the high-voltage electric field of the power transmission line is further determined.
[0030] Specifically, this embodiment pre-sets 6 different selection paths, of which: the first selection path is to fly from one crossarm to another; the second selection path is to fly from a distance to the crossarm and then fly away from the crossarm; the third selection path is to inspect vertically downwards; the fourth selection path is to inspect vertically upwards; the fifth selection path is to inspect diagonally downwards; and the sixth selection path is to inspect diagonally upwards.
[0031] Understandably, the electric field strength of the first selected path first decreases and then increases, with the increase in electric field strength due to the faster rate of potential decrease at the end of the crossarm of the transmission tower; the electric field strength of the second selected path first increases and then decreases, with the decrease in electric field strength due to the increased potential further away from the end of the crossarm; the electric field strength of the third and fifth selected paths both show the greatest electric field strength near the high-voltage transmission line, followed by a rapid decrease, exhibiting an overall exponential decay characteristic; the fourth and sixth selected paths show the opposite trend to the third and fifth selected paths, exhibiting an overall exponential growth characteristic.
[0032] Adjacent track points are used as start and end points according to the order of inspection direction. Directed vectors are established for adjacent track points, and directed unit vectors are established for each selected path. The selected path corresponding to the directed unit vector with the smallest angle to the directed vectors of adjacent track points is used as the reference path for the inspection segment determined by the adjacent track points. The distance between each position on the reference path and the starting point of the adjacent track points in the determined inspection segment is used as the independent variable, and the electric field strength is used as the dependent variable. A first fitted curve of distance versus electric field strength is obtained through curve fitting. The inflection point of the fitted curve is used as the dividing point. The dividing point is located on the inspection segment formed by connecting adjacent track points with straight lines. The points are used as the dividing points of the inspection route segment, dividing the inspection route segment into inspection sub-segments. When the curve segment corresponding to the inspection sub-segment on the fitted curve is monotonically increasing, the normalized value of the length of the inspection sub-segment is recorded as the relative influence of the inspection sub-segment. When the curve segment corresponding to the inspection sub-segment on the fitted curve is monotonically decreasing, the normalized value of the negative value of the length of the inspection sub-segment is recorded as the relative influence of the inspection sub-segment. The sum of the relative influences of all the inspection sub-segments divided by the inspection route segment is recorded as the comprehensive relative influence of the inspection route segment. The slope of the point with the smallest Euclidean distance between the reference path and the track point on the first fitted curve is recorded as the reference slope of the track point.
[0033] In this embodiment, the least squares method is used to achieve curve fitting.
[0034] The electric field intensity varies with distance on adjacent inspection sub-segments based on the inflection point of the fitted curve. Therefore, when calculating the comprehensive relative influence of the inspection sub-segment, the relative influence of each inspection sub-segment is evaluated separately and then accumulated.
[0035] The average of the reference slopes of adjacent track points is recorded as the first average of the inspection route formed by adjacent track points; the positive correlation between the comprehensive relative influence of the inspection route and the first average is recorded as the second electric field influence factor of the inspection route.
[0036] It is understood that a positive correlation is applied to the comprehensive relative influence degree of the inspected road segment and the first mean, ensuring that the comprehensive relative influence degree and the first mean of the inspected road segment are positively correlated with the second electric field influence factor of the inspected road segment. It is understood that the positive correlation in this application refers to the relationship between the independent and dependent variables, where the independent variables are the comprehensive relative influence degree and the first mean of the inspected road segment, and the dependent variable is the second electric field influence factor of the inspected road segment. The positive correlation means that the dependent variable increases (decreases) as the independent variable increases (decreases), and can be an additive or multiplicative relationship.
[0037] Preferably, as an embodiment of this application, the normalized value of the product of the comprehensive relative influence degree of the inspection section and the first mean is denoted as the second electric field influence factor of the inspection section.
[0038] The sum of the normalized value of the first electric field influence factor of the inspection section and the density characteristic values of all voxel grids traversed by the inspection section is denoted as the first cumulative sum of the inspection section. The product of the first cumulative sum of the inspection section and the second electric field influence factor is denoted as the electric field influence degree of the inspection section.
[0039] At this point, the electric field influence of the inspected section is obtained.
[0040] Step S003: Based on the positional relationship between adjacent track points, the distance between track points and the midpoints of the tower point cloud and the line point cloud, and the electric field influence of all inspection sections, establish the inspection objective function, and obtain the path planning results of UAV inspection of transmission lines based on the inspection objective function.
[0041] This application selects the PSO (Particle Swarm Optimization) algorithm to implement path planning for UAV inspection of power transmission lines.
[0042] To minimize safety risks, shorten inspection paths, and ensure smoother inspection routes during drone inspections, an inspection objective function is established.
[0043] in, Represent the inspection objective function; This represents the distance cost, which is the sum of the lengths of the inspection route formed by all adjacent track points, i.e., the sum of the Euclidean distances between all adjacent track points. Indicates the cost of collision; This represents the total number of different trackpoints included in all inspected routes; This function represents the maximum value and its function is to find the maximum value among all the comma-separated values within the parentheses. This indicates the preset safe distance for drone flight; Indicates the first The minimum Euclidean distance between a track point and all points in the tower point cloud and the line point cloud; This represents the cost of electric field impact, which is the sum of the electric field impact values of all inspected road sections. Represents the penalty function; Show the first Penalty value for each waypoint; Indicates the first The turning angle of a trackpoint position is the angle between the direction from the trackpoint position to the previous adjacent trackpoint position and the direction from the trackpoint position to the next adjacent trackpoint position. This represents the maximum turning angle for all waypoint positions; , , as well as The first preset weight, the second preset weight, the third preset weight, and the fourth preset weight are respectively. The sum of the first preset weight, the second preset weight, the third preset weight, and the fourth preset weight is 1. In this embodiment, the values of the first preset weight, the second preset weight, the third preset weight, and the fourth preset weight are all 0.25.
[0044] It should be noted that in this embodiment, the turning angle of the first and last waypoint positions is set to 0°.
[0045] The electric field impact cost is used to evaluate the degree to which the path planning results composed of all inspection segments are affected by the high-voltage electric field of the transmission line; the penalty function is used to evaluate the smoothness and stability of the flight trajectory of the UAV when it flies according to the path planning results composed of all inspection segments.
[0046] The nodes to be inspected are pre-defined by those skilled in the art according to the inspection requirements. The pre-defined nodes are marked in the 3D point cloud data. Each node is treated as a particle. The inspection objective function is used as the objective function of the particle swarm algorithm. The particle swarm algorithm is used to minimize the objective function and obtain the optimal inspection path.
[0047] In this embodiment, the number of particles in the particle swarm optimization algorithm should be greater than or equal to 20 and less than or equal to 50, and the number of iterations should be greater than or equal to 50 and less than or equal to 200. The number of iterations is set to 75 in this embodiment. The values of individual cognitive factor and social cognitive factor are both random numbers greater than or equal to 0 and less than or equal to 1 to enhance the randomness of the search. The value of inertia weight is 0.5, and the value of the upper limit of velocity is 10% of the number of nodes.
[0048] This completes the path planning for the unmanned aerial vehicle (UAV) inspection of power transmission lines.
[0049] Based on the same inventive concept as the above methods, this embodiment of the invention also provides a swarm intelligence-based unmanned aerial vehicle (UAV) inspection path planning system for power transmission lines, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, it implements the steps of any one of the above-described swarm intelligence-based UAV inspection path planning methods for power transmission lines.
[0050] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the principles of the present invention should be included within the protection scope of the present invention.
Claims
1. A method for unmanned aerial vehicle (UAV) inspection path planning for power transmission lines based on swarm intelligence, characterized in that, The method includes the following steps: Collect three-dimensional point cloud data along the transmission line, and identify the tower point cloud and line point cloud from the three-dimensional point cloud data; Based on the distances between the adjacent track points that make up the inspection section and the midpoints of the tower point cloud and the line point cloud, the first electric field influence factor of the inspection section is calculated. The three-dimensional point cloud data is voxelized, and the density characteristic value of the voxel grid is calculated. Based on the angle between the direction of the vector determined by the adjacent track points that make up the inspection section and the preset different selected paths, the reference path of the inspection section is determined. Based on the positional relationship between the reference path of the inspection section and the adjacent track points corresponding to the inspection section, the second electric field influence factor of the inspection section is calculated. Based on the first electric field influence factor, the second electric field influence factor of the inspection section, and the density characteristic values of all voxel grids passed by the inspection section, the electric field influence degree of the inspection section is obtained. Based on the positional relationship between adjacent track points, the distance between track points and the midpoints of the tower point cloud and line point cloud, and the electric field influence of all inspection sections, an inspection objective function is established, and the path planning results of UAV inspection of transmission lines are obtained based on the inspection objective function.
2. The method for unmanned aerial vehicle (UAV) inspection path planning for power transmission lines based on swarm intelligence as described in claim 1, characterized in that, The specific method for obtaining the first electric field influence factor of the inspected section is as follows: The minimum Euclidean distance between the track point and the midpoint of all line tower point clouds is denoted as the line tower collision distance of the track point, and the minimum Euclidean distance between the track point and the midpoint of all line point clouds is denoted as the line collision distance of the track point. The difference between the line collision distance at the end and the beginning of the inspection section is used as the numerator, and the difference between the line tower collision distance at the end and the beginning of the inspection section is used as the denominator. The value of the fraction is recorded as the first electric field influence factor of the inspection section.
3. The method for unmanned aerial vehicle (UAV) inspection path planning for power transmission lines based on swarm intelligence as described in claim 1, characterized in that, The method for determining the density eigenvalues of the voxel grid is as follows: The ratio of the number of points in the tower point cloud and line point cloud contained in the voxel grid to the number of points in the 3D point cloud data contained in the voxel grid is denoted as the density characteristic value of the voxel grid.
4. The method for unmanned aerial vehicle (UAV) inspection path planning for power transmission lines based on swarm intelligence as described in claim 1, characterized in that, The specific method for obtaining the reference path of the inspection section is as follows: Based on the inspection direction of adjacent track points, a directed vector of the adjacent track points is established, and a directed unit vector of each preset selection path is established. The selection path corresponding to the directed unit vector with the smallest angle between it and the directed vector of the adjacent track points is used as the reference path for the inspection segment determined by the adjacent track points.
5. The method for unmanned aerial vehicle (UAV) inspection path planning for power transmission lines based on swarm intelligence according to claim 4, characterized in that, The preset selection path includes: The options for flying from one crossarm to another, flying from a distance to a crossarm and then away from it, vertical downward inspection, vertical upward inspection, diagonal downward inspection, and diagonal upward inspection.
6. The method for unmanned aerial vehicle (UAV) inspection path planning for power transmission lines based on swarm intelligence as described in claim 1, characterized in that, The specific calculation method for the second electric field influence factor of the inspected section is as follows: Establish a first fitted curve of electric field intensity with respect to the distance between each position on the reference path and the starting point of the adjacent track points of the determined inspection section. Based on the inflection point of the fitted curve, divide the inspection section into inspection sub-segments. Calculate the comprehensive relative influence of the inspection section based on the increase or decrease of the curve segments corresponding to all the inspection sub-segments divided by the inspection section on the fitted curve. The slope of the first fitted curve at the point on the reference path with the smallest Euclidean distance to the track point is denoted as the reference slope of the track point. The average of the reference slopes of adjacent track points is recorded as the first average of the inspection route formed by adjacent track points; the positive correlation between the comprehensive relative influence of the inspection route and the first average is recorded as the second electric field influence factor of the inspection route.
7. The method for unmanned aerial vehicle (UAV) inspection path planning for power transmission lines based on swarm intelligence as described in claim 6, characterized in that, The specific method for obtaining the comprehensive relative influence of the inspected road section is as follows: When the curve segment corresponding to the inspected sub-section on the fitted curve is monotonically increasing, the normalized value of the length of the inspected sub-section is recorded as the relative influence of the inspected sub-section. When the curve segment corresponding to the inspected sub-section on the fitted curve is monotonically decreasing, the normalized value of the negative number of the length of the inspected sub-section is recorded as the relative influence of the inspected sub-section. The sum of the relative impacts of all the sub-segments of the inspection section is recorded as the comprehensive relative impact of the inspection section.
8. The method for unmanned aerial vehicle (UAV) inspection path planning for power transmission lines based on swarm intelligence according to claim 1, characterized in that, The specific method for obtaining the electric field influence of the inspected section is as follows: The sum of the normalized value of the first electric field influence factor of the inspection section and the density characteristic values of all voxel grids traversed by the inspection section is denoted as the first cumulative sum of the inspection section; the product of the first cumulative sum of the inspection section and the second electric field influence factor is denoted as the electric field influence degree of the inspection section.
9. The method for unmanned aerial vehicle (UAV) inspection path planning for power transmission lines based on swarm intelligence according to claim 1, characterized in that, The inspection objective function is: The weighted sum of distance cost, collision cost, electric field effect cost, and penalty function; The distance cost is the sum of the lengths of the inspection route segments formed by all adjacent track points; The cost of electric field influence is the sum of the electric field influence of all inspected road sections; The collision cost is determined based on the minimum Euclidean distance between the track point and all points in the tower point cloud and the line point cloud. The penalty function is determined based on the turning angle of the waypoint position.
10. A swarm intelligence-based unmanned aerial vehicle (UAV) inspection path planning system for power transmission lines, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as claimed in any one of claims 1-9.