A method for autonomous inspection path planning of fixed-wing UAV for power transmission lines

Abstract

A method for autonomous inspection path planning of fixed-wing UAVs of power transmission lines, firstly constructs a two-dimensional grid map based on the environmental information of the power transmission lines to be inspected, and marks the target points to be inspected and the obstacles in the grid map; based on the two-dimensional grid map, a fixed-wing UAV multi-objective path planning model is used for global path planning, and the Hippo optimization algorithm is used to solve the model to obtain the global optimal path, which is composed of multiple track segments, and the end point of the previous track segment is the starting point of the next track segment; the artificial potential field method is used to perform local path planning on all track segments, and the optimal path planning scheme is output. The present invention comprehensively considers the total length of the flight path, the flight energy consumption and the flight time to model the model objective function, and sets safety condition constraints, which can reasonably plan the inspection fixed-wing UAV path, and realize the local obstacle avoidance function of the fixed-wing UAV while improving the inspection efficiency.

Description

Technical Field

[0001] The present invention belongs to the technical field of autonomous inspection by unmanned aerial vehicles (UAVs), and in particular relates to a method for planning a path for autonomous inspection by a fixed-wing UAV of a power transmission line. Background Art

[0002] As a key channel for power supply, transmission lines ensure the transmission of electricity from power plants to end users and are an indispensable part of the power system. my country's transmission lines are widely distributed, and most of them are located in areas with harsh natural environments. Transmission wires, insulators and other hardware exposed to harsh environments for a long time are prone to wear, corrosion, material aging and other material damage. Therefore, operation and maintenance personnel need to patrol and inspect transmission lines regularly. The traditional manual inspection method is limited by natural conditions such as lines crossing lakes and mountains, and can no longer meet the current inspection needs. However, drones are increasingly used in line inspections due to their special inspection methods. In order to ensure that drones conduct efficient and refined inspections, it is essential to conduct in-depth research on the autonomous inspection path planning method of fixed-wing drones for transmission lines.

[0003] After searching the existing technical literature, it was found that the document "UAV Path Planning Based on Improved Genetic Algorithm" proposed a UAV path planning method based on an improved genetic algorithm to address the problems of slow convergence speed of traditional genetic algorithms, easy to fall into local optimality, insufficient smoothness of planned paths, and high cost. The algorithm improves the selection operator, crossover operator, and mutation operator of the genetic algorithm to plan a smooth and flyable path. The method has good environmental adaptability. The document "UAV Path Planning Based on Improved Tasmanian Devil Optimization Algorithm" combines the adaptive weight method to reduce the situation of falling into local optimality based on the Tasmanian Devil Optimization Algorithm (TDO), and also introduces the Limit threshold idea, which can better balance global search and local convergence. The invention patent with application number CN202210885343.5 discloses a transmission line inspection path planning method and system, which takes the UAV's endurance time as a constraint, and establishes the objective function of path planning with the shortest overall inspection path and the shortest inspection time as the goal. In the group internal movement stage of the artificial jellyfish search algorithm, the dialogue operator, debate operator and innovation operator in the social network search algorithm are introduced to obtain an improved artificial jellyfish search algorithm. The objective function is optimized by the improved artificial jellyfish search algorithm to obtain the optimal inspection path of each UAV. However, none of the above prior arts considers the local obstacle avoidance problem of UAVs during the transmission line inspection process.

[0004] The invention patent with application number CN202310552501.X discloses a path planning method for UAV inspection of power transmission lines. The method first mathematically models the towers and surrounding environment in the transmission lines to determine the obstacles and detection points in the transmission lines; according to the obstacles and detection points, the patrol line of the UAV is set, and the UAV inspects the transmission lines along the patrol line. Although this method takes into account the obstacle avoidance problem of UAVs, it does not take into account the characteristics of complex and wide distribution of transmission lines and limited endurance of UAVs. Therefore, how to reasonably plan the path of the inspection UAV and realize local obstacle avoidance of the UAV while improving the inspection efficiency is a problem that needs to be solved urgently. Summary of the invention

[0005] The purpose of the present invention is to address the above-mentioned problems existing in the prior art and to provide a method for autonomous inspection path planning of fixed-wing UAVs for power transmission lines, which can reasonably plan the inspection path of fixed-wing UAVs and realize local obstacle avoidance of UAVs while improving the inspection efficiency.

[0006] To achieve the above objectives, the technical solution of the present invention is as follows:

[0007] In a first aspect, the present invention provides a method for autonomous inspection path planning of a fixed-wing UAV for a power transmission line, comprising:

[0008] Based on the environmental information of the power transmission line to be inspected, a two-dimensional grid map of the power transmission line to be inspected is constructed, and the target points to be inspected and the obstacle conditions in each grid are marked in the two-dimensional grid map;

[0009] Based on the grid map of the inspection transmission line, a pre-built fixed-wing UAV multi-objective path planning model is used to perform global path planning, and the fixed-wing UAV multi-objective path planning model is solved to obtain a global optimal path, wherein the global optimal path includes multiple track segments, and the end point of the previous track segment is the starting point of the next track segment;

[0010] The multi-objective path planning model of the fixed-wing UAV includes an objective function and safety constraints. The objective function is constructed by minimizing the total cost of the fixed-wing UAV flight path. The total cost of the fixed-wing UAV flight path includes the flight length cost, the flight energy consumption cost, and the flight time cost.

[0011] Perform local path planning for each track segment in the global optimal path to obtain the local optimal path;

[0012] Output the optimal path planning solution.

[0013] The objective function of the fixed-wing UAV multi-objective path planning model is:

[0014] ;

[0015] ;

[0016] ;

[0017] ;

[0018] ;

[0019] ;

[0020] In the above formula, represents the total cost of the fixed-wing UAV flight path; , , All are constant coefficients; , , are all weight constant coefficients, and ; Indicates The length of each track segment; , , They represent flight length cost, flight energy consumption cost, and flight time cost respectively; Indicates The starting coordinates of each track segment, Indicates The end point coordinates of each track segment; is the total number of target points to be inspected; , They represent the load weight and body weight of the fixed-wing UAV respectively; Indicates the energy consumption per unit flight time; Indicates the total flight time of the fixed-wing UAV over the entire flight path; Indicates the energy consumed by the unit hovering time; Set the average flight speed for fixed-wing drones in no wind; represents the wind speed factor; Indicates the total hovering time of the fixed-wing UAV; Indicates the set detection time of the fixed-wing UAV at each target point to be inspected.

[0021] The safety constraints of the fixed-wing UAV multi-objective path planning model include maximum flight range constraint, minimum track segment constraint, flight altitude constraint, and maximum turning angle constraint; the maximum flight range constraint is:

[0022] ;

[0023] In the above formula, Indicates The flight distance of each track segment; Indicates the preset margin margin; Indicates the maximum flight distance allowed for fixed-wing drones;

[0024] The minimum track segment constraint is:

[0025] ;

[0026] In the above formula, Indicates the maximum range allowed for fixed-wing drones;

[0027] The flight altitude constraint is:

[0028] ;

[0029] In the above formula, , Indicates the minimum and maximum altitudes that fixed-wing drones are allowed to fly; Indicates the current flight altitude of the fixed-wing drone;

[0030] The maximum turning angle constraint is:

[0031] ;

[0032] In the above formula, It represents the angle formed by two adjacent track segments; Indicates the maximum turning angle allowed for fixed-wing drones.

[0033] The Hippo optimization algorithm is used to solve the multi-objective path planning model of fixed-wing UAV. The Hippo algorithm is specifically as follows:

[0034] A1. Initialize the population. A hippopotamus individual in the population represents a candidate solution for the global path planning of a fixed-wing UAV.

[0035] A2. Calculate the fitness of individual hippopotamuses in the population, where the fitness is the total cost of the fixed-wing UAV flight path obtained by substituting the candidate solution corresponding to the hippopotamus individual into the fixed-wing UAV multi-objective path planning model;

[0036] A3. Update the positions of individual hippos in the population according to the three stages of position update in the river or pond, defense against predators, and escape from predators; until the position update of all individual hippos is completed; update the individual hippopotamus with the best fitness;

[0037] A4. Return to A2 for iterative calculation until the iteration termination condition is reached, and output the hippopotamus individual with the best fitness. This hippopotamus individual is the optimal solution.

[0038] The population initialization steps of the Hippo optimization algorithm are improved based on the good point set theory, specifically:

[0039] B1. Generate a good point set according to the following formula:

[0040] ;

[0041] ;

[0042] ;

[0043] In the above formula, represents the generated good point set; Indicates good point vector; Indicates The best point Dimensional elements; is the population size; is the spatial dimension; for The smallest prime number of ;

[0044] B2. Map the good point set to the Hippo optimization algorithm initialization search space according to the following formula:

[0045] ;

[0046] In the above formula, Represents initialization of hippopotamus individuals No. positions; , Respectively represent lower and upper bounds for the decision variables; It is the remainder operation.

[0047] The dynamic adaptive inertia weight is introduced to improve the position update formula of the first stage, specifically:

[0048] ;

[0049] ;

[0050] ;

[0051] In the above formula, Indicates the first phase of position update after the position of female or immature hippos in the population; represents the inertia weight; It means that after the population is initialized the position of the hippopotamus in the population; , Both said Random numbers in ; represents the optimal individual hippo position; represents the average position of random hippopotamus individuals; It means randomly taking 1 or 2; represents the separation distance threshold; , are the maximum and minimum inertia weight values; is the current iteration number; is the maximum number of iterations.

[0052] The position update formula of the third stage is improved based on the surface flight strategy of the Pelican algorithm:

[0053] ;

[0054] In the above formula, The third phase position update Only the location of the hippopotamus; Indicates the position of the hippopotamus after the second phase position update; is the current iteration number; is the maximum number of iterations; express The radius of the domain; is a constant, generally taking the value as 2; , Respectively represent The lower and upper bounds of the decision variables.

[0055] The artificial potential field method is used to perform local path planning for each track segment in the global optimal path. The artificial potential field method is specifically as follows:

[0056] An artificial potential field is constructed, which consists of two parts: one is the gravitational field generated by the end point of the track segment on the fixed-wing UAV, and the other is the repulsive field generated by the obstacle on the fixed-wing UAV. Through the combined force generated by the gravitational field and the repulsive field, the fixed-wing UAV is guided to avoid obstacles while moving from the starting point of the track segment to the end point of the track segment.

[0057] The constructed gravitational field function is:

[0058] ;

[0059] In the above formula, Represents the gravitational field function of the target point; is the gravitational coefficient; is the Euclidean distance between the fixed-wing UAV and the target point; is the threshold distance;

[0060] The calculation formula of the gravitational force generated by the target point on the fixed-wing drone is:

[0061] ;

[0062] In the above formula, Indicates the gravitational force of the target point on the fixed-wing drone;

[0063] The repulsive field function constructed is:

[0064] ;

[0065] ;

[0066] In the above formula, Represents the repulsive field function of the obstacle; is the repulsion coefficient; is the distance adjustment coefficient; is the Euclidean distance between the fixed-wing UAV and the obstacle; is the radius of the obstacle repulsion; is the angle between the moving direction of the fixed-wing UAV and the line connecting the fixed-wing UAV and the obstacle; is a constant, usually set to 0.6;

[0067] The calculation formula of the repulsive force of obstacles on fixed-wing drones is:

[0068] ;

[0069] In the above formula, Represents the repulsive force of obstacles on fixed-wing drones.

[0070] The calculation formula of the resultant force generated by the gravitational field and the repulsive field is:

[0071] ;

[0072] ;

[0073] In the above formula, It represents the resultant force of the gravitational field and the repulsive field; represents the escape force in the direction of gravity; represents the escape force coefficient; Indicates the current position of the fixed-wing drone's movement direction and the fixed-wing drone and obstacles The angle between the connecting lines; Indicates obstacles The repulsive force on the fixed-wing drone at the current position.

[0074] In a second aspect, the present invention provides a transmission line fixed-wing UAV autonomous inspection path planning system, including a two-dimensional grid map forming module, a global path planning module, a local path planning module, and an optimal solution output module;

[0075] The two-dimensional grid map forming module is used to construct a two-dimensional grid map of the power transmission line to be inspected based on the environmental information of the power transmission line to be inspected, wherein the two-dimensional grid map contains the target points to be inspected and the obstacle conditions in each grid;

[0076] The global path planning module is used to perform global path planning based on a two-dimensional grid map of the inspection transmission line and a pre-built fixed-wing UAV multi-objective path planning model, and solve the fixed-wing UAV multi-objective path planning model to obtain a global optimal path, wherein the global optimal path includes multiple track segments, and the end point of the previous track segment is the starting point of the next track segment;

[0077] The multi-objective path planning model of the fixed-wing UAV includes an objective function and safety constraints. The objective function is constructed by minimizing the total cost of the fixed-wing UAV flight path. The total cost of the fixed-wing UAV flight path includes the flight length cost, the flight energy consumption cost, and the flight time cost.

[0078] The local path planning module is used to perform local path planning on each track segment in the global optimal path to obtain a local optimal path;

[0079] The optimal solution output module is used to output an optimal path planning solution based on the global optimal path and the local optimal path.

[0080] The objective function of the fixed-wing UAV multi-objective path planning model is:

[0081] ;

[0082] ;

[0083] ;

[0084] ;

[0085] ;

[0086] ;

[0087] In the above formula, represents the total cost of the fixed-wing UAV flight path; , , All are constant coefficients; , , are all weight constant coefficients, and ; Indicates The length of each track segment; , , They represent flight length cost, flight energy consumption cost, and flight time cost respectively; Indicates The starting coordinates of each track segment, Indicates The end point coordinates of each track segment; is the total number of target points to be inspected; , They represent the load weight and body weight of the fixed-wing UAV respectively; Indicates the energy consumption per unit flight time; Indicates the total flight time of the fixed-wing UAV over the entire flight path; Indicates the energy consumed by the unit hovering time; Set the average flight speed for fixed-wing drones in no wind; represents the wind speed factor; Indicates the total hovering time of the fixed-wing UAV; Indicates the set detection time of the fixed-wing UAV at each target point to be inspected.

[0088] The safety constraints of the fixed-wing UAV multi-objective path planning model include maximum flight range constraint, minimum track segment constraint, flight altitude constraint, and maximum turning angle constraint; the maximum flight range constraint is:

[0089] ;

[0090] In the above formula, Indicates The flight distance of each track segment; Indicates the preset margin margin; Indicates the maximum flight distance allowed for fixed-wing drones;

[0091] The minimum track segment constraint is:

[0092] ;

[0093] In the above formula, Indicates the maximum range allowed for fixed-wing drones;

[0094] The flight altitude constraint is:

[0095] ;

[0096] In the above formula, , Indicates the minimum and maximum altitudes that fixed-wing drones are allowed to fly; Indicates the current flight altitude of the fixed-wing drone;

[0097] The maximum turning angle constraint is:

[0098] ;

[0099] In the above formula, It represents the angle formed by two adjacent track segments; Indicates the maximum turning angle allowed for fixed-wing drones.

[0100] The global path planning module uses the Hippo algorithm to solve the multi-objective path planning model of the fixed-wing UAV. The Hippo algorithm is specifically:

[0101] A1. Initialize the population. A hippopotamus individual in the population represents a candidate solution for the global path planning of a fixed-wing UAV.

[0102] A2. Calculate the fitness of individual hippopotamuses in the population, where the fitness is the total cost of the fixed-wing UAV flight path obtained by substituting the candidate solution corresponding to the hippopotamus individual into the fixed-wing UAV multi-objective path planning model;

[0103] A3. Update the positions of individual hippos in the population according to the three stages of position update in the river or pond, defense against predators, and escape from predators; until the position update of all individual hippos is completed; update the individual hippopotamus with the best fitness;

[0104] A4. Return to A2 for iterative calculation until the iteration termination condition is reached, and output the hippopotamus individual with the best fitness. This hippopotamus individual is the optimal solution.

[0105] The population initialization steps of the Hippo optimization algorithm are improved based on the good point set theory, specifically:

[0106] B1. Generate a good point set according to the following formula:

[0107] ;

[0108] ;

[0109] ;

[0110] In the above formula, represents the generated good point set; Indicates good point vector; Indicates The best point Dimensional elements; is the population size; is the spatial dimension; for The smallest prime number of ;

[0111] B2. Map the good point set to the Hippo optimization algorithm initialization search space according to the following formula:

[0112] ;

[0113] In the above formula, Represents initialization of hippopotamus individuals No. positions; , Respectively represent lower and upper bounds for the decision variables; It is the remainder operation.

[0114] The dynamic adaptive inertia weight is introduced to improve the position update formula of the first stage, specifically:

[0115] ;

[0116] ;

[0117] ;

[0118] In the above formula, Indicates the first phase of position update after the position of female or immature hippos in the population; represents the inertia weight; It means that after the population is initialized the position of the hippopotamus in the population; , Both said Random numbers in ; represents the optimal individual hippo position; represents the average position of random hippopotamus individuals; It means randomly taking 1 or 2; represents the separation distance threshold; , are the maximum and minimum inertia weight values; is the current iteration number; is the maximum number of iterations.

[0119] The position update formula of the third stage is improved based on the surface flight strategy of the Pelican algorithm:

[0120] ;

[0121] In the above formula, The third phase position update Only the location of the hippopotamus; Indicates the position of the hippopotamus after the second phase position update; is the current iteration number; is the maximum number of iterations; Indicates the territory radius of each hippopotamus; is a constant, generally taking the value as 2; , Respectively represent The lower and upper bounds of the decision variables.

[0122] The local path planning module uses an artificial potential field method to perform local path planning on each track segment in the global optimal path. The artificial potential field method is specifically:

[0123] An artificial potential field is constructed, which consists of two parts: one is the gravitational field generated by the end point of the track segment on the fixed-wing UAV, and the other is the repulsive field generated by the obstacle on the unmanned boat. Through the combined force generated by the gravitational field and the repulsive field, the fixed-wing UAV is guided to avoid obstacles while moving from the starting point of the track segment to the end point of the track segment.

[0124] The constructed gravitational field function is:

[0125] ;

[0126] In the above formula, Represents the gravitational field function of the target point; is the gravitational coefficient; is the Euclidean distance between the fixed-wing UAV and the target point; is the threshold distance;

[0127] The calculation formula of the gravitational force generated by the target point on the fixed-wing drone is:

[0128] ;

[0129] In the above formula, Indicates the gravitational force of the target point on the fixed-wing drone;

[0130] The repulsive field function constructed is:

[0131] ;

[0132] ;

[0133] In the above formula, Represents the repulsive field function of the obstacle; is the repulsion coefficient; is the distance adjustment coefficient; is the Euclidean distance between the fixed-wing UAV and the obstacle; is the radius of the obstacle repulsion; is the angle between the moving direction of the fixed-wing UAV and the line connecting the fixed-wing UAV and the obstacle; is a constant, usually set to 0.6;

[0134] The calculation formula of the repulsive force of obstacles on fixed-wing drones is:

[0135] ;

[0136] In the above formula, Represents the repulsive force of obstacles on fixed-wing drones.

[0137] The calculation formula of the resultant force generated by the gravitational field and the repulsive field is:

[0138] ;

[0139] ;

[0140] In the above formula, It represents the resultant force of the gravitational field and the repulsive field; represents the escape force in the direction of gravity; represents the escape force coefficient; Indicates the current position of the fixed-wing drone's movement direction and the fixed-wing drone and obstacles The angle between the connecting lines; Indicates obstacles The repulsive force on the fixed-wing drone at the current position.

[0141] Compared with the prior art, the present invention has the following beneficial effects:

[0142] 1. The method for autonomous inspection path planning of a fixed-wing UAV for power transmission lines of the present invention first constructs a two-dimensional grid map of the power transmission line to be inspected based on the environmental information of the power transmission line to be inspected, and marks the target points to be inspected and the obstacles in each grid in the two-dimensional grid map; based on the grid map of the inspection power transmission line, a pre-constructed multi-objective path planning model of a fixed-wing UAV is used to perform global path planning, and the Hippo optimization algorithm is used to solve the multi-objective path planning model of the fixed-wing UAV to obtain a global optimal path, which is composed of multiple track segments, and the end point of the previous track segment is the starting point of the next track segment; a human The artificial potential field method performs local path planning for each track segment in the global optimal path and outputs the optimal path planning scheme; on the one hand, the design comprehensively considers the total length of the flight path, the flight energy consumption and the flight time to model the objective function of the multi-objective path planning model of the fixed-wing UAV, and sets safety condition constraints, which can improve the work efficiency of the autonomous inspection of the power transmission line of the fixed-wing UAV while meeting the safety inspection requirements of the fixed-wing UAV; on the other hand, the artificial potential field method is used to perform local path planning for each track segment in the global optimal path to enhance the autonomous obstacle avoidance capability of the fixed-wing UAV and further ensure safety. Therefore, the present invention can reasonably plan the inspection fixed-wing UAV path, and realize the local obstacle avoidance of the fixed-wing UAV while improving the inspection efficiency.

[0143] 2. In the transmission line fixed-wing UAV autonomous inspection path planning method described in the present invention, an improved Hippopotamus optimization algorithm is used to solve the fixed-wing UAV multi-objective path planning model to obtain the global optimal solution; in order to make the Hippopotamus individuals as evenly distributed as possible in the optimization range and further improve the global search ability of the algorithm, the present invention improves the population initialization step of the Hippopotamus optimization algorithm based on the good point set theory; in order to balance the global search ability and local search ability of the Hippopotamus optimization algorithm, avoid premature convergence, and improve the algorithm stability and convergence speed, the present invention introduces dynamic adaptive inertia weights to improve the position update formula of the first stage of the Hippopotamus optimization algorithm, that is, the position update stage in the river or pond; in order to strengthen the local search ability of the Hippopotamus optimization algorithm in the third stage, that is, the stage of escaping from the predator, the present invention combines the surface flight strategy of the Pelican algorithm to improve the position update formula of the stage of escaping from the predator. Therefore, the present invention can effectively improve the algorithm's optimization ability.

[0144] 3. In the transmission line fixed-wing UAV autonomous inspection path planning method described in the present invention, an improved artificial potential field method is used to perform local path planning on the track segment to realize the local obstacle avoidance function of the fixed-wing UAV during the inspection process; in order to solve the problem that the gravitational force near the starting point is too large and the repulsive force is ignored, which causes the fixed-wing UAV to easily collide with obstacles, the present invention uses a piecewise function to represent the gravitational potential field function, divides the gravitational force into two parts, and adds a threshold distance as a basis for judging the distance between the fixed-wing UAV and the target point. When the UAV is close to the target point, the gravitational force is proportional to the distance from the UAV to the target point; when the UAV is far from the target point, the gravitational force is a constant, thereby solving the problem of the UAV colliding with obstacles. In order to make the fixed-wing UAV more flexible in adjusting its position and direction of movement when facing obstacles and avoid collision with obstacles, the present invention introduces a distance adjustment coefficient to improve the repulsive field function of the artificial potential field method, and reduces the influence of the repulsive force of the obstacle on the movement of the UAV after the UAV passes over the obstacle; in order to solve the problem that people are prone to fall into the local minimum during obstacle avoidance, the present invention increases the escape force in the gravitational direction of the artificial potential field, and withdraws the escape force when the local extreme value is escaped and the angle between the movement direction of the fixed-wing UAV and the line connecting the fixed-wing UAV and the obstacle is greater than 90°. The UAV will continue to perform local path planning under the action of the original potential field. Therefore, the present invention can enhance the autonomous obstacle avoidance capability of the UAV and avoid falling into the local extreme value. BRIEF DESCRIPTION OF THE DRAWINGS

[0145] Figure 1 The present invention is a flowchart of the method.

[0146] Figure 2 This is the global optimal path obtained by using the present invention.

[0147] Figure 3 This is the local optimal path of the D→F track segment obtained by using the present invention.

[0148] Figure 4 The structure diagram of the system of the present invention is shown in FIG. DETAILED DESCRIPTION

[0149] The present invention is further described in detail below in conjunction with specific implementations and drawings.

[0150] Embodiment 1:

[0151] See also Figure 1 , a transmission line fixed-wing UAV autonomous inspection path planning method, which is carried out in the following steps:

[0152] S1. Obtain environmental information of the power transmission line to be inspected, which mainly includes information on buildings, vegetation, poles and towers, mountains, etc.; construct a two-dimensional grid map of the power transmission line to be inspected through MapGIS, where each grid represents a specific area, and the dark grid represents the obstacle situation in the area. The position of the pole tower to be inspected is marked in the two-dimensional grid map, and one pole tower to be inspected represents one target point;

[0153] S2. Construct a multi-objective path planning model for fixed-wing UAVs. The multi-objective path planning model for fixed-wing UAVs includes an objective function and safety constraints. The objective function is constructed by minimizing the total cost of the flight path of the fixed-wing UAV, specifically:

[0154] ;

[0155] ;

[0156] ;

[0157] ;

[0158] ;

[0159] ;

[0160] In the above formula, represents the total cost of the fixed-wing UAV flight path; , , All are constant coefficients; , , are all weight constant coefficients, and ; Indicates The length of each track segment; , , They represent flight length cost, flight energy consumption cost, and flight time cost respectively; Indicates The starting coordinates of each track segment, Indicates The end point coordinates of each track segment; is the total number of target points to be inspected; , They represent the load weight and body weight of the fixed-wing UAV respectively; Indicates the energy consumption per unit flight time; Indicates the total flight time of the fixed-wing UAV over the entire flight path; Indicates the energy consumed by the unit hovering time; Set the average flight speed for fixed-wing drones in no wind; represents the wind speed factor; Indicates the total hovering time of the fixed-wing UAV; Indicates the set detection time of the fixed-wing drone at each target point to be inspected;

[0161] The safety constraints include a maximum flight range constraint, a minimum track segment constraint, a flight altitude constraint, and a maximum turning angle constraint; the maximum flight range constraint is:

[0162] ;

[0163] In the above formula, Indicates The flight distance of each track segment; Indicates the preset margin margin; Indicates the maximum flight distance allowed for fixed-wing drones;

[0164] The minimum track segment constraint is:

[0165] ;

[0166] In the above formula, Indicates the maximum range allowed for fixed-wing drones;

[0167] The flight altitude constraint is:

[0168] ;

[0169] In the above formula, , Indicates the minimum and maximum altitudes that fixed-wing drones are allowed to fly; Indicates the current flight altitude of the fixed-wing drone;

[0170] The maximum turning angle constraint is:

[0171] ;

[0172] In the above formula, It represents the angle formed by two adjacent track segments; Indicates the maximum turning angle allowed for fixed-wing drones;

[0173] Based on the grid map of the inspection transmission line, the Hippo optimization algorithm is used to solve the multi-objective path planning model of the fixed-wing UAV to obtain the global optimal path. The global optimal path consists of multiple track segments, and the end point of the previous track segment is the starting point of the next track segment.

[0174] The Hippo algorithm is specifically:

[0175] A1. Initialize the population. One hippopotamus individual in the population corresponds to a candidate solution for the global path planning of a fixed-wing UAV.

[0176] A2. Calculate the fitness of the individual hippopotamus in the initialized population; substitute the candidate solution corresponding to the individual hippopotamus into the objective function of the multi-objective path planning model of the fixed-wing UAV to obtain the total cost of the flight path of the fixed-wing UAV, and the total cost of the flight path of the fixed-wing UAV is the fitness of the individual hippopotamus;

[0177] A3. Update the position of the hippopotamus in three stages: position update in the river or pond (exploring new fixed-wing drone flight paths), defense against predators (changing the flight direction of the fixed-wing drone), and escape from predators (searching neighboring areas to improve the best path), until the position update of all hippopotamus is completed; update the hippopotamus with the best fitness;

[0178] A4, return to A2 to iterate until the iteration termination condition is reached, and output the hippopotamus individual with the best fitness, which is the optimal solution;

[0179] The initialization phase of the Hippopotamus optimization algorithm involves the generation of random initial solutions, which may lead to uneven distribution of the population in the solution space and increase the risk of the algorithm falling into local optimality. In order to make the Hippopotamus individuals as evenly distributed as possible in the optimization range and further improve the global search ability of the algorithm, the population initialization of the Hippopotamus algorithm is improved based on the good point set theory; the population initialization steps of the Hippopotamus optimization algorithm improved based on the good point set theory are as follows:

[0180] B1. Generate a good point set according to the following formula:

[0181] ;

[0182] ;

[0183] ;

[0184] In the above formula, represents the generated good point set; Indicates good point vector; Indicates The best point Dimensional elements; is the population size; is the spatial dimension; for The smallest prime number of ;

[0185] B2. Map the good point set to the Hippo optimization algorithm initialization search space according to the following formula:

[0186] ;

[0187] In the above formula, Represents initialization of hippopotamus individuals No. positions; , Respectively represent lower and upper bounds for the decision variables; It is the remainder operation.

[0188] In order to balance the global search ability and local search ability of the Hippo optimization algorithm, avoid premature convergence, and improve the stability and convergence speed of the algorithm, the dynamic adaptive inertia weight is introduced in the first stage of the Hippo optimization algorithm to improve the Hippo position update formula; the position update formula of the first stage after the dynamic adaptive inertia weight is improved is as follows:

[0189] ;

[0190] ;

[0191] ;

[0192] In the above formula, Indicates the first phase of position update after the position of female or immature hippos in the population; represents the inertia weight; It means that after the population is initialized the position of the hippopotamus in the population; , Both said Random numbers in ; represents the optimal individual hippo position; represents the average position of random hippopotamus individuals; It means randomly taking 1 or 2; represents the separation distance threshold; , are the maximum and minimum inertia weight values; is the current iteration number; is the maximum number of iterations;

[0193] After the position update in the first phase, the position update formula of the second phase in the traditional Hippopotamus optimization algorithm is used to continue updating the Hippopotamus position. In order to enhance the local search capability of the Hippopotamus optimization algorithm in the third phase, the Hippopotamus algorithm is improved by combining the surface flight strategy of the Pelican algorithm. The surface flight strategy of the Pelican algorithm can make the algorithm converge to a better position in the hunting area. The position update formula of the third phase after the improvement based on the surface flight strategy of the Pelican algorithm is as follows:

[0194] ;

[0195] In the above formula, The third phase position update Only the location of the hippopotamus; Indicates the position of the hippopotamus after the second phase position update; is the current iteration number; is the maximum number of iterations; express The radius of the domain; is a constant, generally taking the value as 2; , Respectively represent lower and upper bounds for the decision variables;

[0196] S3, using the artificial potential field method to perform local path planning on each track segment in the global optimal path, and outputting the local path;

[0197] The artificial potential field method is specifically as follows: construct an artificial potential field, which consists of two parts: one part is the gravitational field generated by the end point of the track segment on the fixed-wing UAV, and the other part is the repulsive field generated by the obstacle on the fixed-wing UAV. Through the combined force generated by the gravitational field and the repulsive field, the UAV is guided to avoid obstacles while moving from the starting point of the track segment to the end point of the track segment;

[0198] Aiming at the problem that the gravity near the starting point of the traditional gravitational field is too large and the repulsive effect is ignored, which causes the fixed-wing UAV to collide with obstacles, the gravitational field function is expressed in the form of a piecewise function, so that the gravity is divided into two parts, and a threshold distance is added as a basis for judging the distance between the fixed-wing UAV and the target point. When the UAV is close to the target point, the gravity is proportional to the distance from the UAV to the target point; when the UAV is far away from the target point, the gravity is a constant, so as to solve the problem of large gravity when the UAV is far away from the target point; the improved gravitational field function is:

[0199] ;

[0200] In the above formula, Represents the gravitational field function of the target point; is the gravitational coefficient; is the Euclidean distance between the fixed-wing UAV and the target point; is the threshold distance;

[0201] The calculation formula of the gravitational force generated by the target point on the fixed-wing drone is:

[0202] ;

[0203] In the above formula, Indicates the gravitational force of the target point on the fixed-wing drone;

[0204] The traditional repulsive field keeps the distance constant, regardless of the direction of movement of the fixed-wing UAV and the angle between the fixed-wing UAV and the obstacle. No matter how it changes, its repulsive force remains unchanged; by adding the distance adjustment coefficient, when the distance remains unchanged, when the angle When the angle changes, the repulsive force will also change, making the repulsive field more flexible and able to better cope with different obstacle avoidance scenarios and achieve rapid response. When the angle As the angle increases, the repulsive force gradually decreases; Greater than When no one crosses the obstacle, the influence of the obstacle repulsion on the movement of the fixed-wing UAV is reduced, so that the UAV can more flexibly adjust its position and movement direction when facing obstacles to avoid collision with obstacles. The improved repulsion field function is:

[0205] ;

[0206] ;

[0207] In the above formula, Represents the repulsive field function of the obstacle; is the repulsion coefficient; is the distance adjustment coefficient; is the Euclidean distance between the fixed-wing UAV and the obstacle; is the radius of the obstacle repulsion; is the angle between the moving direction of the fixed-wing UAV and the line connecting the fixed-wing UAV and the obstacle; is a constant, usually set to 0.6;

[0208] The calculation formula of the repulsive force of obstacles on fixed-wing drones is:

[0209] ;

[0210] In the above formula, Represents the repulsive force of obstacles on fixed-wing drones;

[0211] In order to solve the problem that artificial potential fields are prone to fall into local optimality during obstacle avoidance, an escape force is added on the basis of traditional artificial potential fields. First, determine whether the fixed-wing UAV is trapped in the local optimality. The judgment method can be: assume that the forward direction of the fixed-wing UAV is the positive direction. If the moving distance of the UAV within five steps is less than the preset value, and the distance between the UAV and the target point remains unchanged, the UAV is considered to be trapped in the local optimality; when it is determined that the fixed-wing UAV has fallen into the local optimality, an escape force is added in the gravitational direction of the artificial potential field to help the UAV escape the local optimality; when the fixed-wing UAV escapes the local optimality and After that, the escape force is withdrawn, and the UAV will continue to plan its path under the action of the original potential field. The calculation formula for the resultant force generated by the improved gravitational field and repulsive field is:

[0212] ;

[0213] ;

[0214] In the above formula, It represents the resultant force of the gravitational field and the repulsive field; represents the escape force in the direction of gravity; represents the escape force coefficient; Indicates the current position of the fixed-wing drone's movement direction and the fixed-wing drone and obstacles The angle between the connecting lines; Indicates obstacles The repulsive force on the fixed-wing drone at the current position;

[0215] S4. Generate the optimal path planning scheme for the power transmission line to be inspected based on the global optimal path planning and the local optimal path, and finally realize the autonomous inspection task of the fixed-wing UAV for the entire power transmission line.

[0216] Performance Testing:

[0217] In order to verify the effectiveness of the method described in the present invention, an autonomous inspection path planning of a fixed-wing UAV was carried out in a certain place.

[0218] A two-dimensional grid map based on the surrounding environment of a place, such as Figure 2 As shown in the figure, the locations of all the poles and towers to be inspected in the area are marked on the established two-dimensional grid map, where the coordinate origin represents the starting point of the fixed-wing UAV inspection, and the marked points AJ are all transmission line poles and towers to be inspected. The global optimal path obtained through global path planning is: B→D→F→I→J→H→G→E→C→A, that is, when considering the total length of the flight path, the energy consumption of the flight track and the flight time as cost indicators, the total flight cost of the fixed-wing UAV transmission line autonomous inspection corresponding to this path is the smallest.

[0219] Based on the global optimal path obtained, the transmission line tower D→F track segment is taken for local path planning. Figure 3 As shown, the range of a single grid is 2.5×2.5m. When there are obstacles in the grid area that affect the flight of the fixed-wing UAV, the entire grid is marked as the obstacle position, that is, the black part in the figure, where D is the starting point, F is the target point, the dotted line is the local autonomous obstacle avoidance path of the fixed-wing UAV obtained by the traditional artificial potential field method (APF), and the solid line is the local autonomous obstacle avoidance path of the fixed-wing UAV obtained by the improved artificial potential field method (IAPF) in the present invention. It can be seen that the fixed-wing UAV using the traditional artificial potential field method falls into the local minimum and cannot move forward, so it does not reach the target point F, and the inspection mission fails; while the fixed-wing UAV using the improved artificial potential field method accurately avoids the obstacles in the area that restrict flight, successfully arrives at the target point, and realizes the local autonomous obstacle avoidance function of the fixed-wing UAV.

[0220] Embodiment 2:

[0221] See also Figure 4 , a transmission line fixed-wing UAV autonomous inspection path planning system, including a two-dimensional grid map forming module, a global path planning module, a local path planning module, and an optimal solution output module; the two-dimensional grid map forming module is used to obtain environmental information of the transmission line to be inspected, and the environmental information mainly includes information such as buildings, vegetation, poles and towers, and mountains; a two-dimensional grid map of the transmission line to be inspected is constructed by MapGIS, each grid represents a specific area, and the obstacles in the area are represented by dark grids. The positions of the poles and towers to be inspected are marked in the two-dimensional grid map, and one pole and tower to be inspected represents a target point; the global path planning module is used to construct a multi-target path planning model for a fixed-wing UAV, and based on the grid map of the inspection transmission line, the Hippo optimization algorithm is used to solve the multi-target path planning model for the fixed-wing UAV to obtain a global optimal path, and the global optimal path is composed of multiple track segments, and the end point of the previous track segment is the starting point of the next track segment;

[0222] Specifically, the fixed-wing UAV multi-objective path planning model includes an objective function and safety constraints. The objective function is constructed by minimizing the total cost of the fixed-wing UAV flight path, specifically:

[0223] ;

[0224] ;

[0225] ;

[0226] ;

[0227] ;

[0228] ;

[0229] In the above formula, represents the total cost of the fixed-wing UAV flight path; , , All are constant coefficients; , , are all weight constant coefficients, and ; Indicates The length of each track segment; , , They represent flight length cost, flight energy consumption cost, and flight time cost respectively; Indicates The starting coordinates of each track segment, Indicates The end point coordinates of each track segment; is the total number of target points to be inspected; , They represent the load weight and body weight of the fixed-wing UAV respectively; Indicates the energy consumption per unit flight time; Indicates the total flight time of the fixed-wing UAV over the entire flight path; Indicates the energy consumed by the unit hovering time; Set the average flight speed for fixed-wing drones in no wind; represents the wind speed factor; Indicates the total hovering time of the fixed-wing UAV; Indicates the set detection time of the fixed-wing drone at each target point to be inspected;

[0230] The safety constraints include a maximum flight range constraint, a minimum track segment constraint, a flight altitude constraint, and a maximum turning angle constraint; the maximum flight range constraint is:

[0231] ;

[0232] In the above formula, Indicates The flight distance of each track segment; Indicates the preset margin margin; Indicates the maximum flight distance allowed for fixed-wing drones;

[0233] The minimum track segment constraint is:

[0234] ;

[0235] In the above formula, Indicates the maximum range allowed for fixed-wing drones;

[0236] The flight altitude constraint is:

[0237] ;

[0238] In the above formula, , Indicates the minimum and maximum altitudes that fixed-wing drones are allowed to fly; Indicates the current flight altitude of the fixed-wing drone;

[0239] The maximum turning angle constraint is:

[0240] ;

[0241] In the above formula, It represents the angle formed by two adjacent track segments; Indicates the maximum turning angle allowed for fixed-wing drones;

[0242] Specifically, the Hippo algorithm is as follows:

[0243] A1. Initialize the population. One hippopotamus individual in the population corresponds to a candidate solution for the global path planning of a fixed-wing UAV.

[0244] A2. Calculate the fitness of the individual hippopotamus in the initialized population; substitute the candidate solution corresponding to the individual hippopotamus into the objective function of the multi-objective path planning model of the fixed-wing UAV to obtain the total cost of the flight path of the fixed-wing UAV, and the total cost of the flight path of the fixed-wing UAV is the fitness of the individual hippopotamus;

[0245] A3. Update the position of the hippopotamus in three stages: position update in the river or pond (exploring new fixed-wing drone flight paths), defense against predators (changing the flight direction of the fixed-wing drone), and escape from predators (searching neighboring areas to improve the best path), until the position update of all hippopotamus is completed; update the hippopotamus with the best fitness;

[0246] A4, return to A2 to iterate until the iteration termination condition is reached, and output the hippopotamus individual with the best fitness, which is the optimal solution;

[0247] The initialization phase of the Hippopotamus optimization algorithm involves the generation of random initial solutions, which may lead to uneven distribution of the population in the solution space and increase the risk of the algorithm falling into local optimality. In order to make the Hippopotamus individuals as evenly distributed as possible in the optimization range and further improve the global search ability of the algorithm, the population initialization of the Hippopotamus algorithm is improved based on the good point set theory; the population initialization steps of the Hippopotamus optimization algorithm improved based on the good point set theory are as follows:

[0248] B1. Generate a good point set according to the following formula:

[0249] ;

[0250] ;

[0251] ;

[0252] In the above formula, represents the generated good point set; Indicates good point vector; Indicates The best point Dimensional elements; is the population size; is the spatial dimension; for The smallest prime number of ;

[0253] B2. Map the good point set to the Hippo optimization algorithm initialization search space according to the following formula:

[0254] ;

[0255] In the above formula, Represents initialization of hippopotamus individuals No. positions; , Respectively represent lower and upper bounds for the decision variables; It is the remainder operation.

[0256] In order to balance the global search ability and local search ability of the Hippo optimization algorithm, avoid premature convergence, and improve the stability and convergence speed of the algorithm, the dynamic adaptive inertia weight is introduced in the first stage of the Hippo optimization algorithm to improve the Hippo position update formula; the position update formula of the first stage after the dynamic adaptive inertia weight is improved is as follows:

[0257] ;

[0258] ;

[0259] ;

[0260] In the above formula, Indicates the first phase of position update after the position of female or immature hippos in the population; represents the inertia weight; It means that after the population is initialized the position of the hippopotamus in the population; , Both said Random numbers in ; represents the optimal individual hippo position; represents the average position of random hippopotamus individuals; It means randomly taking 1 or 2; represents the separation distance threshold; , are the maximum and minimum inertia weight values; is the current iteration number; is the maximum number of iterations;

[0261] After the position update in the first phase, the position update formula of the second phase in the traditional Hippopotamus optimization algorithm is used to continue updating the Hippopotamus position. In order to enhance the local search capability of the Hippopotamus optimization algorithm in the third phase, the Hippopotamus algorithm is improved by combining the surface flight strategy of the Pelican algorithm. The surface flight strategy of the Pelican algorithm can make the algorithm converge to a better position in the hunting area. The position update formula of the third phase after the improvement based on the surface flight strategy of the Pelican algorithm is as follows:

[0262] ;

[0263] In the above formula, The third phase position update Only the location of the hippopotamus; Indicates the position of the hippopotamus after the second phase position update; is the current iteration number; is the maximum number of iterations; express The radius of the domain; is a constant, generally taking the value as 2; , Respectively represent lower and upper bounds for the decision variables;

[0264] The local path planning module adopts an artificial potential field method to perform local path planning on each track segment in the global optimal path, and outputs a local path; the artificial potential field method specifically comprises: constructing an artificial potential field, which is composed of two parts, one part is the gravitational field generated by the end point of the track segment on the fixed-wing UAV, and the other part is the repulsive field generated by the obstacle on the fixed-wing UAV, and the combined force generated by the gravitational field and the repulsive field is used to guide the UAV to avoid obstacles while moving from the starting point of the track segment to the end point of the track segment;

[0265] Aiming at the problem that the gravity near the starting point of the traditional gravitational field is too large and the repulsive effect is ignored, which causes the fixed-wing UAV to collide with obstacles, the gravitational field function is expressed in the form of a piecewise function, so that the gravity is divided into two parts, and a threshold distance is added as a basis for judging the distance between the fixed-wing UAV and the target point. When the UAV is close to the target point, the gravity is proportional to the distance from the UAV to the target point; when the UAV is far away from the target point, the gravity is a constant, so as to solve the problem of large gravity when the UAV is far away from the target point; the improved gravitational field function is:

[0266] ;

[0267] In the above formula, Represents the gravitational field function of the target point; is the gravitational coefficient; is the Euclidean distance between the fixed-wing UAV and the target point; is the threshold distance;

[0268] The calculation formula of the gravitational force generated by the target point on the fixed-wing drone is:

[0269] ;

[0270] In the above formula, Indicates the gravitational force of the target point on the fixed-wing drone;

[0271] The traditional repulsive field keeps the distance constant, regardless of the direction of movement of the fixed-wing UAV and the angle between the fixed-wing UAV and the obstacle. No matter how it changes, its repulsive force remains unchanged; by adding the distance adjustment coefficient, when the distance remains unchanged, when the angle When the angle changes, the repulsive force will also change, making the repulsive field more flexible and able to better cope with different obstacle avoidance scenarios and achieve rapid response. When the angle As the angle increases, the repulsive force gradually decreases; Greater than When no one crosses the obstacle, the influence of the obstacle repulsion on the movement of the fixed-wing UAV is reduced, so that the UAV can more flexibly adjust its position and movement direction when facing obstacles to avoid collision with obstacles. The improved repulsion field function is:

[0272] ;

[0273] ;

[0274] In the above formula, Represents the repulsive field function of the obstacle; is the repulsion coefficient; is the distance adjustment coefficient; is the Euclidean distance between the fixed-wing UAV and the obstacle; is the radius of the obstacle repulsion; is the angle between the moving direction of the fixed-wing UAV and the line connecting the fixed-wing UAV and the obstacle; is a constant, usually set to 0.6;

[0275] The calculation formula of the repulsive force of obstacles on fixed-wing drones is:

[0276] ;

[0277] In the above formula, Represents the repulsive force of obstacles on fixed-wing drones;

[0278] In order to solve the problem that artificial potential fields are prone to fall into local optimality during obstacle avoidance, an escape force is added on the basis of traditional artificial potential fields. First, determine whether the fixed-wing UAV is trapped in the local optimality. The judgment method can be: assume that the forward direction of the fixed-wing UAV is the positive direction. If the moving distance of the UAV within five steps is less than the preset value, and the distance between the UAV and the target point remains unchanged, the UAV is considered to be trapped in the local optimality; when it is determined that the fixed-wing UAV has fallen into the local optimality, an escape force is added in the gravitational direction of the artificial potential field to help the UAV escape the local optimality; when the fixed-wing UAV escapes the local optimality and After that, the escape force is withdrawn, and the UAV will continue to plan its path under the action of the original potential field. The calculation formula for the resultant force generated by the improved gravitational field and repulsive field is:

[0279] ;

[0280] ;

[0281] In the above formula, It represents the resultant force of the gravitational field and the repulsive field; represents the escape force in the direction of gravity; represents the escape force coefficient; Indicates the current position of the fixed-wing drone's movement direction and the fixed-wing drone and obstacles The angle between the connecting lines; Indicates obstacles The repulsive force on the fixed-wing drone at the current position;

[0282] The optimal solution output module is used to generate an optimal path planning solution for the power transmission line to be inspected based on the global optimal path planning and the local optimal path, and finally realize the fixed-wing UAV autonomous inspection task of the entire power transmission line.

Claims

1. A method for autonomous inspection path planning of a fixed-wing UAV for a power transmission line, characterized by: include: Based on the environmental information of the power transmission line to be inspected, a two-dimensional grid map of the power transmission line to be inspected is constructed, and the target points to be inspected and the obstacle conditions in each grid are marked in the two-dimensional grid map; Based on the two-dimensional grid map of the inspection transmission line, a pre-built fixed-wing UAV multi-objective path planning model is used to perform global path planning, and the fixed-wing UAV multi-objective path planning model is solved to obtain a global optimal path, wherein the global optimal path includes multiple track segments, and the end point of the previous track segment is the starting point of the next track segment; The multi-objective path planning model of the fixed-wing UAV includes an objective function and safety constraints. The objective function is constructed by minimizing the total cost of the fixed-wing UAV flight path. The total cost of the fixed-wing UAV flight path includes the flight length cost, the flight energy consumption cost, and the flight time cost. The artificial potential field method is used to perform local path planning on each track segment in the global optimal path to obtain the local optimal path; Based on the global optimal path and the local optimal path, output the optimal path planning solution; The Hippo optimization algorithm is used to solve the multi-objective path planning model of fixed-wing UAV. The Hippo optimization algorithm is specifically as follows: A1. Initialize the population. A hippopotamus individual in the population represents a candidate solution for the global path planning of a fixed-wing UAV. A2. Calculate the fitness of individual hippopotamuses in the population, where the fitness is the total cost of the fixed-wing UAV flight path obtained by substituting the candidate solution corresponding to the hippopotamus individual into the fixed-wing UAV multi-objective path planning model; A3. Update the positions of individual hippos in the population according to the three stages of position update in the river or pond, defense against predators, and escape from predators; until the position update of all individual hippos is completed; update the individual hippopotamus with the best fitness; A4, return to A2 to iterate until the iteration termination condition is reached, and output the hippopotamus individual with the best fitness, which is the optimal solution; The dynamic adaptive inertia weight is introduced to improve the position update formula of the first stage, specifically: In the above formula, r i FB represents the position of the ith female or immature hippopotamus in the population after the first stage of position update; ω represents the inertia weight; represents the position of the i-th hippopotamus in the population after the population is initialized; h1 and h2 are both random numbers in [0, 1]; D represents the optimal hippopotamus individual position; g i represents the average position of random hippopotamus individuals; I2 represents randomly taking 1 or 2; R represents the separation distance threshold; ω max ,ω min are the maximum and minimum inertia weight values; k is the current number of iterations; k max is the maximum number of iterations; The position update formula of the third stage is improved based on the surface flight strategy of the Pelican algorithm: In the above formula, is the position of the i-th hippopotamus after the third stage position update; r i 2 represents the hippopotamus position after the second stage position update; k is the current iteration number; k max is the maximum number of iterations; represents the territory radius of each hippopotamus; B is a constant, generally taking the value as 2; l j 、u j They represent the lower and upper bounds of the j-th decision variable respectively.

2. The method for autonomous inspection path planning of a fixed-wing UAV for a power transmission line according to claim 1 is characterized in that: The objective function of the fixed-wing UAV multi-objective path planning model is: min F=c1w1F L +c2w2F E +c3w3F T ; F T =T f +T s ; T s =nt s ; In the above formula, F represents the total cost of the fixed-wing UAV flight path; c1, c2, c3 are all constant coefficients; w1, w2, w3 are all weight constant coefficients, and w1+w2+w3=1; d i represents the length of the i-th track segment; F L 、F E 、F T Respectively represent the flight length cost, flight energy consumption cost, and flight time cost; (x i ,y i ) represents the starting point coordinates of the ith track segment, (x i+1 ,y i+1 )、(x i+1 ,y i+1 ) represent the starting point and end point coordinates of the i-th track segment; n is the total number of target points to be inspected; g and G represent the load weight and body weight of the fixed-wing UAV, respectively; P f Indicates the energy consumption per unit flight time; T f represents the total flight time of the fixed-wing UAV along the entire flight path; P s Indicates the energy consumed by the unit hovering time; Set the average flight speed for the fixed-wing UAV in the absence of wind; η represents the wind speed factor; T s Indicates the total hovering time of the fixed-wing UAV; t s Indicates the set detection time of the fixed-wing UAV at each target point to be inspected.

3. A method for autonomous inspection path planning of a fixed-wing UAV for a power transmission line according to claim 1 or 2, characterized in that: The safety constraints of the fixed-wing UAV multi-objective path planning model include maximum flight range constraint, minimum track segment constraint, flight altitude constraint, and maximum turning angle constraint; the maximum flight range constraint is: In the above formula, L i represents the flight distance of the i-th track segment; Δ L Indicates the preset margin; L max Indicates the maximum flight distance allowed for fixed-wing drones; The minimum track segment constraint is: L min ≤L i ; In the above formula, L min Indicates the maximum range allowed for fixed-wing drones; The flight altitude constraint is: h min ≤h t ≤h max ; In the above formula, h min 、h max Indicates the minimum and maximum altitudes allowed for fixed-wing drones to fly; h t Indicates the current flight altitude of the fixed-wing drone; The maximum turning angle constraint is: θ≤θ max ; In the above formula, θ represents the angle formed by two adjacent track segments; θ max Indicates the maximum turning angle allowed for fixed-wing drones.

4. The method for autonomous inspection path planning of a fixed-wing UAV for a power transmission line according to claim 1 is characterized in that: The population initialization steps of the Hippo optimization algorithm are improved based on the good point set theory, specifically: B1. Generate a good point set according to the following formula: R＝{r1′，...，r i ′...，r N ′}； r i ′＝{r i1 ′，...，r ij ′，...，r im ′}； In the above formula, R represents the generated good point set; r i ′ represents the i-th best point vector; r ij ′ represents the j-th dimension element of the i-th best point; N is the population size; m is the space dimension; p is the smallest prime number such that (p-3) / 2>m; B2. Map the good point set to the Hippo optimization algorithm initialization search space according to the following formula: r i，j =l j +mod(r ij ′,1)·(u j -l j ); In the above formula, r i，j Indicates the jth position of the initialized hippopotamus individual i; l j 、u j They represent the lower and upper bounds of the j-th decision variable respectively; mod is the remainder operation.

5. A method for autonomous inspection path planning of a fixed-wing UAV for a power transmission line according to claim 1 or 2, characterized in that: The artificial potential field method is used to perform local path planning for each track segment in the global optimal path. The artificial potential field method is specifically as follows: An artificial potential field is constructed, which consists of two parts: one is the gravitational field generated by the end point of the track segment on the fixed-wing UAV, and the other is the repulsive field generated by the obstacle on the unmanned boat. Through the combined force generated by the gravitational field and the repulsive field, the fixed-wing UAV is guided to avoid obstacles while moving from the starting point of the track segment to the end point of the track segment.

6. A method for autonomous inspection path planning of a fixed-wing UAV for a power transmission line according to claim 5, characterized in that: The constructed gravitational field function is: In the above formula, U att Represents the gravitational field function of the target point; k att is the gravitational coefficient; ρ(q,q goal ) is the Euclidean distance between the fixed-wing UAV and the target point; d g is the threshold distance; The calculation formula of the gravitational force generated by the target point on the fixed-wing drone is: In the above formula, F att Indicates the gravitational force of the target point on the fixed-wing drone; The repulsive field function constructed is: In the above formula, U rep represents the repulsive field function of the obstacle; k rep is the repulsion coefficient; k d is the distance adjustment coefficient; ρ(q,q obs ) is the Euclidean distance between the fixed-wing UAV and the obstacle; ρ0 is the radius of the obstacle repulsion; α is the angle between the fixed-wing UAV's moving direction and the line connecting the fixed-wing UAV and the obstacle; m d is a constant, usually set to 0.6; The calculation formula of the repulsive force of obstacles on fixed-wing drones is: In the above formula, F rep Represents the repulsive force of obstacles on fixed-wing drones.

7. The method for autonomous inspection path planning of a fixed-wing UAV for a power transmission line according to claim 6 is characterized by: The calculation formula of the resultant force generated by the gravitational field and the repulsive field is: In the above formula, F APF Represents the resultant force of the gravitational field and the repulsive field; F exc represents the escape force in the direction of gravity; γ represents the escape force coefficient; α v Indicates the angle between the current position of the fixed-wing UAV's moving direction and the line connecting the fixed-wing UAV and the obstacle v; F rep (v) represents the repulsive force of obstacle v on the fixed-wing drone at the current position.

Images