Power transmission line unmanned aerial vehicle inspection task intelligent allocation collaborative planning method based on genetic algorithm

Abstract

The invention relates to the technical field of unmanned aerial vehicle inspection, and discloses a power transmission line unmanned aerial vehicle inspection task intelligent allocation collaborative planning method based on a genetic algorithm. The method comprises the following steps: firstly, collecting and analyzing basic information of a power transmission line, an unmanned aerial vehicle, a surrounding environment and weather, and establishing a space model of unmanned aerial vehicle inspection by using a grid method; based on the collected information, establishing a mathematical model to allocate inspection tasks of the unmanned aerial vehicle; a genetic algorithm is used for coding and optimizing a routing inspection path, meanwhile, a fitness function is designed to comprehensively consider multiple factors of a search effect, and quantization, weight distribution and optimization selection are carried out; and an optimal solution is found through iterative optimization, and intelligent distribution and collaborative planning of unmanned aerial vehicle inspection tasks are realized, so that the requirements of regional inspection are met. According to the technical scheme, the flight threat degree under different meteorological conditions can be quantitatively evaluated by considering the wind speed, rainfall and visibility, and the flight plan is adjusted according to the flight threat degree.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned aerial vehicle inspection, and in particular to a method for intelligent allocation and collaborative planning of transmission line unmanned aerial vehicle inspection tasks based on a genetic algorithm. Background Art

[0002] With the rapid development of artificial intelligence and modern technology, drones are increasingly used in multiple fields such as battlefields and rescue operations. They play an important role in reducing risks and economic losses. The collaborative planning technology of drone swarms is crucial. It imitates the unconscious organizational behavior of organisms in nature, produces an overall effect and highly autonomous cooperation through communication between individuals, thereby improving mission efficiency.

[0003] Intelligent allocation and collaborative planning of UAV inspection tasks is committed to optimizing the mission trajectory of UAVs in complex environments, comprehensively considering factors such as flight characteristics, environmental constraints, and mission requirements to achieve more accurate and efficient planning. With the increase in the number of UAVs and the increase in mission complexity, how to intelligently allocate tasks, plan inspection routes, and achieve collaborative work among multiple UAVs has become an important research topic.

[0004] Genetic algorithm is an optimization algorithm that simulates the biological evolution process. It solves optimization problems by simulating biological evolution mechanisms such as natural selection, inheritance, crossover and mutation. In UAV inspection mission planning, genetic algorithm can be used to search for optimal or near-optimal inspection paths to improve the efficiency and effectiveness of path planning.

[0005] Traditional inspection methods are inefficient, costly, have blind spots, a small operation and maintenance scope, and low inspection accuracy. Especially in complex environments such as mountainous areas and waters, manual inspections are difficult, and the inspection efficiency and accuracy are low. In addition, traditional methods may require rigorous calculations, otherwise there will be drone flight safety issues. Genetic algorithms have become an effective tool for intelligent planning of drone inspections due to their advantages in adaptability, global search capabilities, parallelism, flexibility, independence from gradient information, and applicability to complex problems. Summary of the invention

[0006] The present invention provides a collaborative planning method for intelligent allocation of transmission line UAV inspection tasks based on genetic algorithms, which can adapt to variable search areas and target movement probabilities, automatically find and optimize inspection paths by simulating natural selection and genetic mechanisms, and significantly improve inspection efficiency and coverage effects.

[0007] The present invention provides a method for intelligent allocation and collaborative planning of power transmission line UAV inspection tasks based on genetic algorithm, comprising the following steps:

[0008] S1: Obtain basic information about the power transmission line, the UAV, the surrounding environment, and the weather, analyze the basic information, and establish a UAV inspection space model using a grid method;

[0009] S2: Establish a mathematical model for the allocation of UAV inspection tasks based on information analysis;

[0010] S3: Genetic algorithm is used to encode the inspection path of UAV, treating the path points as genes and the search path as chromosomes, optimizing the inspection path of UAV through selection, crossover and mutation operations to adapt to the complex search area and target movement probability, designing the fitness function, comprehensively considering many factors of the search effect, quantifying, assigning weights, synthesizing and selecting the best;

[0011] S4: Find the optimal solution that meets the regional inspection task through iterative optimization, and realize the intelligent allocation and collaborative planning of drone inspection tasks.

[0012] Preferably, the basic information obtained in S1 includes the maximum flight speed, initial position, maximum yaw angle and the upper time limit for completing the search mission of the UAV.

[0013] Preferably, the establishing of the mathematical model described in S2 includes establishing an objective function, with the objective of identifying the minimum cost, and defining the objective function;

[0014] In the process of trajectory planning, the entire trajectory is divided into n trajectory segments. At the same time, m UAVs are involved in the execution of this mission. The total trajectory distance cost of m UAVs is f d The formula is as follows:

[0015]

[0016] Among them, d ij represents the track length of the i-th UAV on the j-th track segment, x i0 represents the x-coordinate of the starting position of the i-th UAV, and L represents the length of the track segment;

[0017] The area where the UAV performs its mission is susceptible to environmental influences. Taking the meteorological threat as a factor, the threat area is set as a circular area. The total track threat cost of m UAVs is f t As shown in the formula:

[0018]

[0019]

[0020] Among them, t ijIt represents the distance that the i-th UAV passes through the threat area on the j-th track segment. N represents the penalty coefficient. The penalty coefficient is used to expand the difference between individuals that pass through the threat area and those that do not pass through the threat area on this target, so that the track does not pass through the threat area as much as possible. The value is 1000;

[0021] Considering the recognition cost of drone clusters from the perspective of track distance and threat level, its objective function can be expressed as:

[0022] minf1=min(λ1f L +λ2f T ),

[0023] Among them, f L 、f T Respectively represent the track distance and threat level; λ1+λ2=1

[0024] Preferably, the establishing of the mathematical model in S2 includes establishing constraints, and the constraints are defined as follows:

[0025] The speed of each drone cannot exceed its maximum flight speed.

[0026]

[0027] The total time for each drone to complete its mission cannot exceed the time limit.

[0028]

[0029] The total track length of each drone must cover all track segments,

[0030]

[0031] The change in the direction of the drone’s flight path cannot exceed the maximum yaw angle.

[0032]

[0033] Where n is the number of drones, m is the number of track segments, and x ij is the track length of the i-th UAV on the j-th track segment, P i is the coordinate of the starting position of the i-th UAV, L j is the length of the jth track segment, v max is the maximum flight speed of the UAV, T max is the upper limit of time to complete the search task, θ max is the maximum yaw angle.

[0034] Preferably, the mathematical model includes establishing the threat zone of the drone flight route under different weather conditions, and determining the optimal allocation of drones according to the weather. The specific formula is as follows:

[0035]

[0036] Among them, Q j is the dominance of the jth indicator, and are the difference between the jth index and the ideal upper and lower limits, respectively. λ is the adjustment factor, which can quantitatively evaluate the threat level of UAV flight routes under different meteorological conditions. The calculation result Q j is a value between 0 and 1, indicating the advantage of the current weather relative to the ideal weather. j A high value indicates that the current weather has little impact on the flight of the drone and the flight area is relatively safe. j If the value is low, it means that the current weather has a great impact on the flight and is considered a dangerous area;

[0037] Wind speed, precipitation, and visibility are considered as indicators of the threat degree of different weather conditions to UAV flight routes. The dominance of each indicator is Q1, Q2, and Q3, and the weights are w1, w2, and w3, respectively. The comprehensive dominance is Q t It can be calculated by the following formula:

[0038] Q t =w1·Q1+w2·Q2+w3·Q3

[0039] Among them, w1, w2 and w3 are determined according to the different degrees of influence of the three indicators on the flight of the UAV, w1+w2+w3=1;

[0040] Define Q t ≥0.5 is the safe zone, otherwise it is the dangerous zone.

[0041] Preferably, before the UAV flies, the current weather wind speed, precipitation, and visibility data are collected. During the flight, the changes in weather conditions are monitored in real time, and the comprehensive advantage degree Q is updated according to the new weather data. t , dynamically adjust the flight area of ​​the drone to ensure flight safety.

[0042] Preferably, the genetic algorithm described in S3 comprises the following steps:

[0043] S31: Initialize the population and generate an initial population. The population consists of multiple individuals. Each individual represents a possible solution for the drone inspection path. Each individual consists of a series of genes, and the gene represents a specific point on the path. The size of the entire population and the encoding method of the gene are determined according to the scale and complexity of the problem.

[0044] S32: Roulette selection method is used to determine the probability of being selected according to the fitness value of the individual. First, the sum of the fitness values ​​of all individuals is calculated, and then a probability is assigned to each individual, which is proportional to its fitness value. Individuals are selected according to these probabilities through random sampling to form candidate individuals for the next generation of population. The higher the fitness value of an individual, the greater the probability of being selected.

[0045] S33: Using the single-point crossover method, two individuals are randomly selected from the candidate individuals for crossover, a crossover point is randomly selected in the gene sequences of the two individuals, and then the gene sequences after the crossover point are exchanged to generate two new individuals;

[0046] S34: Use the random mutation method to perform mutation operations on newly generated individuals. Randomly select one or more gene points in the gene sequence of the individual, and then randomly change the values ​​of these gene points. The purpose of the mutation operation is to maintain the diversity of the population and prevent the algorithm from converging to the local optimal solution too early.

[0047] Preferably, the genetic algorithm further comprises the following steps: performing fitness evaluation on each individual according to the mathematical model established in step S2, and calculating its fitness value.

[0048] Preferably, the model building described in S1 comprises the following steps:

[0049] S11: Determine the grid size and resolution based on the UAV’s flight altitude, speed, and mission accuracy requirements;

[0050] S12: Collect terrain data, including elevation and slope, and obstacle data, including buildings, trees, and high-voltage lines;

[0051] S13: Use GIS software to convert the collected data into a raster format, assign a unique coordinate identifier to each raster cell, represented by (x, y), and encode it according to its height and the presence or absence of obstacles;

[0052] S14: Define the path space model.

[0053] It can be seen from the above technical scheme that the present invention has the following advantages: 1. The present invention uses genetic algorithms to intelligently encode and optimize the inspection path of the UAV, which can adapt to the variable search area and target movement probability. By simulating natural selection and genetic mechanisms, it automatically finds and optimizes the inspection path, significantly improving the inspection efficiency and coverage effect. This method not only reduces human intervention, but also comprehensively considers multiple factors such as track length and threat level through the fitness function, thereby realizing the optimal selection of the path;

[0054] 2. The invention can dynamically adjust the flight area of ​​the drone according to real-time meteorological data to ensure flight safety. By considering meteorological factors such as wind speed, precipitation, and visibility, it can quantitatively evaluate the degree of flight threat under different meteorological conditions and adjust the flight plan accordingly. This real-time dynamic adjustment capability enables drone inspection operations to adapt to rapidly changing environmental conditions, improving the flexibility and safety of operations;

[0055] 3. The present invention takes minimizing the inspection cost as the objective function, effectively reduces the total track distance cost and threat cost of the UAV inspection, thereby reducing the operating cost. By optimizing the track planning of the UAV, unnecessary flight distance is reduced, while avoiding high-threat areas, reducing potential risks and costs, and achieving the optimization of cost and benefit;

[0056] 4. The present invention provides a complete systematic solution from basic information acquisition, mathematical model building to path optimization. By collecting detailed information on drones, environment and meteorology, and using GIS technology to process terrain and obstacle data, the solution can achieve data-driven decision-making. This systematic approach not only improves the scientificity and accuracy of decision-making, but also enhances the practicality and reliability of the solution. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0058] Figure 1 It is a flow chart of a method for intelligent allocation and collaborative planning of transmission line UAV inspection tasks based on genetic algorithm of the present invention. DETAILED DESCRIPTION

[0059] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0060] An embodiment of the present invention provides a method for intelligent allocation and collaborative planning of transmission line UAV inspection tasks based on a genetic algorithm, which is described in detail below.

[0061] Example 1: Intelligent allocation of drone inspection tasks

[0062] See also Figure 1 , a collaborative planning method for intelligent allocation of transmission line UAV inspection tasks based on genetic algorithm, including the following steps:

[0063] S1: Cooperate with the local meteorological department to obtain weather forecast data for the next 24 hours, including wind speed, temperature, humidity and visibility. At the same time, use GIS software to collect geographic information about the environment in which the power transmission line is located, including the precise location, length, surrounding terrain and obstacle distribution of the line, and obtain the maximum flight speed, initial position, maximum deviation angle of the drone, and the upper limit of the time to complete the search mission; divide the environment in which the power transmission line is located into several grids, each grid represents an inspection area, and each grid is encoded according to its geographical characteristics to form a spatial model for drone inspection;

[0064] S2: Based on information analysis, a mathematical model for the allocation of UAV inspection tasks is established. The objective function is defined as minimizing the inspection cost, including the track distance and threat level. The entire track is divided into n track segments. At the same time, m UAVs are involved in the execution of this task. The total track distance cost of m UAVs is f d The formula is as follows:

[0065]

[0066] Among them, d ij represents the track length of the i-th UAV on the j-th track segment, x i0 represents the x-coordinate of the starting position of the i-th UAV, and L represents the length of the track segment;

[0067] Taking the weather threat into consideration, the threat area is set as a circular area, and the total track threat cost of m UAVs is f t As shown in the formula:

[0068]

[0069] Among them, t ij It represents the distance that the i-th UAV passes through the threat area on the j-th track segment. N represents the penalty coefficient. The penalty coefficient is used to expand the difference between individuals that pass through the threat area and those that do not pass through the threat area on this target, so that the track does not pass through the threat area as much as possible. The value is 1000;

[0070] Considering the recognition cost of drone clusters from the perspective of track distance and threat level, its objective function can be expressed as:

[0071] minf1=min(λ1f L +λ2f T ),

[0072] Among them, f L 、f TRespectively represent the track distance and threat level; λ1+λ2=1,

[0073] Define the constraints as follows:

[0074] The speed of each drone cannot exceed its maximum flight speed:

[0075]

[0076] The total time for each drone to complete its mission cannot exceed the time limit:

[0077]

[0078] The total track length of each drone must cover all track segments:

[0079]

[0080] The change in the direction of the drone's flight path cannot exceed the maximum yaw angle:

[0081]

[0082] Where n is the number of drones, m is the number of track segments, and x ij is the track length of the i-th UAV on the j-th track segment, P i is the coordinate of the starting position of the i-th UAV, L j is the length of the jth track segment, v max is the maximum flight speed of the UAV, T max is the upper limit of time to complete the search task, θ max is the maximum yaw angle;

[0083] S3: Use genetic algorithm to optimize the path, treat the path points as genes, and the search path as chromosomes. Each chromosome contains a series of genes, representing the inspection path of the drone; design the fitness function, consider multiple factors such as search efficiency, safety, energy consumption, etc. The fitness function can be expressed as F = w E ·E+w S ·S+w C ·C, where E, S, and C represent efficiency, safety, and energy consumption, respectively. E 、w S 、w C is the corresponding weight; the inspection path of the UAV is optimized through selection, crossover and mutation operations. The selection operation uses the roulette selection method, the crossover operation uses the single point crossover method, and the mutation operation uses the random mutation method;

[0084] S4: Iterate optimization to find the optimal solution. Through the iterative optimization process, the path is continuously improved until the optimal solution is found. After each iteration, the fitness of each individual is evaluated, and the individual with the highest fitness is selected to enter the next generation, thereby realizing the intelligent allocation and collaborative planning of drone inspection tasks, ensuring the efficient completion of tasks, and finally outputting the optimal inspection path and schedule of the drone.

[0085] Example 2: UAV inspection considering weather conditions

[0086] Before the drone takes off, collect current weather data, including wind speed, precipitation, visibility, etc., and predict future trends;

[0087] According to the meteorological conditions, the threat level of drone flight routes is evaluated, the threat areas of drone flight routes under different weather conditions are determined, and the optimal allocation of drones is determined based on the weather. The specific formula is as follows:

[0088]

[0089] Among them, Q j is the dominance of the jth indicator, and are the difference between the jth index and the ideal upper and lower limits, respectively. λ is the adjustment factor, which can quantitatively evaluate the threat level of UAV flight routes under different meteorological conditions. The calculation result Q j is a value between 0 and 1, indicating the advantage of the current weather relative to the ideal weather. j A high value indicates that the current weather has little impact on the flight of the drone and the flight area is relatively safe. j If the value is low, it means that the current weather has a great impact on the flight and is considered a dangerous area;

[0090] Wind speed, precipitation, and visibility are considered as indicators of the threat degree of different weather conditions to UAV flight routes. The dominance of each indicator is calculated, which are Q1, Q2, and Q3. The weights w1, w2, and w3 are determined respectively, and the comprehensive dominance Q is calculated. t :

[0091] Q t =w1·Q1+w2·Q2+w3·Q3

[0092] Among them, w1, w2 and w3 are determined according to the different degrees of influence of the three indicators on the flight of the UAV, w1+w2+w3=1;

[0093] Define Q t ≥0.5 is the safe zone, otherwise it is the dangerous zone;

[0094] Before flying, follow Q tPlan the route, monitor the changes in weather conditions in real time during the flight, and update the comprehensive advantage degree Q according to the new weather data t , dynamically adjust the flight area of ​​the drone to avoid dangerous areas and ensure flight safety. If the comprehensive advantage is lower than the threshold, the drone will automatically adjust the flight path to avoid high-risk areas.

[0095] Example 3: Specific operation steps of genetic algorithm

[0096] S31: Initialize the population. Randomly generate an initial population. Each individual represents a possible solution to the drone inspection path. The population size is determined according to the scale and complexity of the problem. 100 individuals can be selected. Each individual consists of a series of genes. The gene represents a specific point on the path. Each gene can be a coordinate pair (x, y).

[0097] S32: Roulette selection method, calculates the fitness values ​​of all individuals. The fitness values ​​are based on the path length, safety and energy consumption of the individuals, and assigns a probability to each individual, which is proportional to its fitness value. The higher the fitness value of the individual, the greater the probability of being selected;

[0098] S33: Single-point crossover method, randomly select two individuals from the candidate individuals for crossover, randomly select a crossover point in the gene sequences of the two individuals, and then exchange the gene sequences after the crossover point to generate two new individuals;

[0099] S34: Random mutation method, which performs mutation operations on newly generated individuals to maintain the diversity of the population, such as randomly changing the value of a gene to prevent the algorithm from converging to the local optimal solution too early and maintain the diversity of the population.

[0100] The above embodiments describe in detail the specific application steps of the intelligent allocation and collaborative planning method for transmission line drone inspection tasks based on genetic algorithm. Each embodiment targets different application scenarios and demonstrates the flexibility and effectiveness of the method in practical applications.

[0101] A person skilled in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium, which can include: read-only memory, random access memory, disk or CD, etc.

[0102] The above is a detailed introduction to the intelligent allocation and collaborative planning method for transmission line drone inspection tasks based on genetic algorithm provided by an embodiment of the present invention. This article uses specific examples to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for general technical personnel in this field, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A method for intelligent allocation and collaborative planning of transmission line UAV inspection tasks based on genetic algorithm, characterized in that: The following steps are involved: S1: Obtain basic information about the power transmission line, the UAV, the surrounding environment, and the weather, analyze the basic information, and establish a UAV inspection space model using a grid method; S2: Establish a mathematical model for the allocation of UAV inspection tasks based on information analysis; S3: Genetic algorithm is used to encode the inspection path of UAV, treating the path points as genes and the search path as chromosomes, optimizing the inspection path of UAV through selection, crossover and mutation operations to adapt to the complex search area and target movement probability, designing the fitness function, comprehensively considering many factors of the search effect, quantifying, assigning weights, synthesizing and selecting the best; S4: Find the optimal solution that meets the regional inspection task through iterative optimization, and realize the intelligent allocation and collaborative planning of drone inspection tasks.

2. According to the genetic algorithm-based intelligent allocation and collaborative planning method for power transmission line UAV inspection tasks according to claim 1, it is characterized by: The basic information obtained in S1 includes the maximum flight speed, initial position, maximum yaw angle of the drone, and the upper limit of the time to complete the search mission.

3. According to claim 1, a method for intelligent allocation and collaborative planning of power transmission line UAV inspection tasks based on genetic algorithm, characterized in that: The establishment of the mathematical model described in S2 includes establishing an objective function, with the goal of identifying the minimum cost, and defining the objective function; In the process of trajectory planning, the entire trajectory is divided into n trajectory segments. At the same time, m UAVs are involved in the execution of this mission. The total trajectory distance cost of m UAVs is f d The formula is as follows: Among them, d ij represents the track length of the i-th UAV on the j-th track segment, x i0 represents the x-coordinate of the starting position of the i-th UAV, and L represents the length of the track segment; The area where the UAV performs its mission is susceptible to environmental influences. Taking the meteorological threat as a factor, the threat area is set as a circular area. The total track threat cost of m UAVs is f t As shown in the formula: Among them, t ij It represents the distance that the i-th UAV passes through the threat area on the j-th track segment. N represents the penalty coefficient. The penalty coefficient is used to expand the difference between individuals that pass through the threat area and those that do not pass through the threat area on this target, so that the track does not pass through the threat area as much as possible. The value is 1000; Considering the recognition cost of drone clusters from the perspective of track distance and threat level, its objective function can be expressed as: minf1=min(λ1f L +λ2f T ), Among them, f L 、f T Respectively represent track distance and threat level; λ1+λ2=1.

4. According to the genetic algorithm-based intelligent allocation and collaborative planning method for power transmission line UAV inspection tasks in claim 1, it is characterized by: The establishment of the mathematical model described in S2 includes establishing constraints, and the constraints are defined as follows: The speed of each drone cannot exceed its maximum flight speed. The total time for each drone to complete its mission cannot exceed the time limit. The total track length of each drone must cover all track segments, The change in the direction of the drone’s flight path cannot exceed the maximum yaw angle. Where n is the number of drones, m is the number of track segments, and x ij is the track length of the i-th UAV on the j-th track segment, P i is the coordinate of the starting position of the i-th UAV, L j is the length of the jth track segment, v max is the maximum flight speed of the UAV, T max is the upper limit of time to complete the search task, θ max is the maximum yaw angle.

5. According to claim 3, a method for intelligent allocation and collaborative planning of power transmission line UAV inspection tasks based on genetic algorithm, characterized in that: The mathematical model includes establishing the threat zone of drone flight routes under different weather conditions, and determining the optimal allocation of drones based on weather conditions. The specific formula is as follows: Among them, Q j is the dominance of the jth indicator, and are the difference between the jth index and the ideal upper and lower limits, respectively. λ is the adjustment factor, which can quantitatively evaluate the threat level of UAV flight routes under different meteorological conditions. The calculation result Q j is a value between 0 and 1, indicating the advantage of the current weather relative to the ideal weather. j A high value indicates that the current weather has little impact on the flight of the drone and the flight area is relatively safe. j If the value is low, it means that the current weather has a great impact on the flight and is considered a dangerous area; Wind speed, precipitation, and visibility are considered as indicators of the threat degree of different weather conditions to UAV flight routes. The dominance of each indicator is Q1, Q2, and Q3, and the weights are w1, w2, and w3, respectively. The comprehensive dominance is Q t It can be calculated by the following formula: <h2 style=";text-align:left;direction:ltr">Q<h2 style=";text-align:left;direction:ltr"> t <h2 style=";text-align:left;direction:ltr"> = w1 Q1 + w2 Q2 + w3 Q3 Among them, w1, w2 and w3 are determined according to the different degrees of influence of the three indicators on the flight of the UAV, w1+w2+w3=1; Define Q t ≥0.5 is the safe zone, otherwise it is the dangerous zone.

6. The method for intelligent allocation and collaborative planning of power transmission line UAV inspection tasks based on genetic algorithm according to claim 5 is characterized by: Before the UAV flies, it collects the current weather data of wind speed, precipitation, and visibility. During the flight, it monitors the changes of weather conditions in real time and updates the comprehensive advantage degree Q according to the new weather data. t , dynamically adjust the flight area of ​​the drone to ensure flight safety.

7. The method for intelligent allocation and collaborative planning of power transmission line UAV inspection tasks based on genetic algorithm according to claim 1 is characterized by: The genetic algorithm described in S3 comprises the following steps: S31: Initialize the population and generate an initial population. The population consists of multiple individuals. Each individual represents a possible solution for the drone inspection path. Each individual consists of a series of genes, and the gene represents a specific point on the path. The size of the entire population and the encoding method of the gene are determined according to the scale and complexity of the problem. S32: Roulette selection method is used to determine the probability of being selected according to the fitness value of the individual. First, the sum of the fitness values ​​of all individuals is calculated, and then a probability is assigned to each individual, which is proportional to its fitness value. Individuals are selected according to these probabilities through random sampling to form candidate individuals for the next generation of population. The higher the fitness value of an individual, the greater the probability of being selected. S33: Using the single-point crossover method, two individuals are randomly selected from the candidate individuals for crossover, a crossover point is randomly selected in the gene sequences of the two individuals, and then the gene sequences after the crossover point are exchanged to generate two new individuals; S34: Use the random mutation method to perform mutation operations on newly generated individuals. Randomly select one or more gene points in the gene sequence of the individual, and then randomly change the values ​​of these gene points. The purpose of the mutation operation is to maintain the diversity of the population and prevent the algorithm from converging to the local optimal solution too early.

8. The method for intelligent allocation and collaborative planning of power transmission line UAV inspection tasks based on genetic algorithm according to claim 7 is characterized by: The genetic algorithm further comprises the following steps: performing fitness evaluation on each individual according to the mathematical model established in step S2, and calculating its fitness value.

9. The method for intelligent allocation and collaborative planning of power transmission line UAV inspection tasks based on genetic algorithm according to claim 1 is characterized by: The model building described in S1 includes the following steps: S11: Determine the grid size and resolution based on the UAV’s flight altitude, speed, and mission accuracy requirements; S12: Collect terrain data, including elevation and slope, and obstacle data, including buildings, trees, and high-voltage lines; S13: Use GIS software to convert the collected data into a raster format, assign a unique coordinate identifier to each raster cell, represented by (x, y), and encode it according to its height and the presence or absence of obstacles; S14: Define the path space model.

Images