A method and system for dynamic flight path planning of unmanned aerial vehicles (UAVs) in substations

Abstract

This invention relates to the field of unmanned aerial vehicle (UAV) inspection technology, specifically to a dynamic flight path planning method and system for UAVs in substations. The method converts inspection requirements into a detailed set of point data. Using coordinate transformation, safety radius calculation, and shooting parameter settings, a unified set of safe inspection points is generated. Based on an improved ant colony algorithm, safety constraints are introduced through a path selection probability formula. Combined with multi-ant colony parallel search and an adaptive pheromone update mechanism, an optimized shortest flight path is generated. Subsequently, the optimized path point set is marked for review and verification. Path smoothing is then performed on the path point set. The starting point, ending point, and intermediate inspection points are fitted using a third-order Bézier curve to smoothly connect the flight path, satisfying safety turning angle, path smoothness, and safety radius constraints. This ensures a stable and smooth UAV flight path and ultimately outputs a temporary optimal flight path. This invention meets the safety, efficiency, and accuracy requirements of substation inspection tasks.

Description

Technical Field

[0001] This invention relates to the field of unmanned aerial vehicle (UAV) inspection technology, specifically to a method and system for dynamic flight path planning of UAVs in substations. Background Technology

[0002] With the development of intelligent and automated power systems, substations, as key nodes in power transmission, are crucial for the safe operation of the power grid. Traditional manual inspection methods suffer from low efficiency, high risk, and incomplete data collection, making it difficult to meet the needs of efficient and stable operation of modern power grids. Due to its advantages such as high flexibility, wide coverage, and accurate data collection, drone technology has gradually become an important means of substation inspection.

[0003] Chinese invention application CN116594426A discloses a method and system for planning unmanned aerial vehicle (UAV) inspection routes for substations. The method includes: acquiring three-dimensional point cloud data of the substation within the inspection area, and dividing the substation into several sub-regions in the three-dimensional point cloud data according to equipment intervals; extracting inspection points in each sub-region from the three-dimensional point cloud data, and generating corresponding waypoints based on the inspection points; planning intra-regional routes and intra-regional safety passages for each sub-region based on the waypoints, and planning cross-regional safety passages between sub-regions based on the intra-regional safety passages of all sub-regions; generating inspection route model data based on the cross-regional safety passages, the intra-regional safety passages in each sub-region, and the intra-regional routes; and generating dynamic inspection routes based on the inspection route model data and the substation inspection plan. This invention provides a flexible and efficient inspection method.

[0004] However, in actual production and daily life, when drones fly in substations, they can generally only fly along preset routes. However, the route planning is relatively rigid and fails to flexibly adjust the observation targets and save the maximum possible flight time. In addition, drones must also meet multiple constraints such as safety radius, path smoothness, and flight altitude stability during complex mission execution to avoid flight deviation or collision accidents caused by unreasonable paths. Therefore, an efficient and dynamic drone route planning method is proposed to meet the safety and efficiency requirements of substation equipment inspection, which has important research value and practical application significance. Summary of the Invention

[0005] The purpose of this invention is to address the problems existing in the background technology by proposing a dynamic flight path planning method and system for unmanned aerial vehicles (UAVs) in substations.

[0006] The technical solution of this invention: a dynamic flight path planning method for unmanned aerial vehicles (UAVs) in substations, comprising the following specific implementation steps:

[0007] S1. Convert the inspection requirements into a detailed set of point data, and generate an output set of safe inspection points that meets the inspection requirements through coordinate transformation, safety radius calculation, and shooting parameter setting steps.

[0008] S2. Combining heuristic information and dynamic constraints, the path of the patrol point is optimized and simplified through path selection probability, dynamic safety constraints and multi-ant colony parallel search mechanism. The optimized path point set is output and an inspection mark is generated for the optimized path point set.

[0009] S3. Based on the identifier to be reviewed, the overall integrity of the received path point set is reviewed. Based on the optimized path point set, a third-order Bézier curve is used to perform path smoothing fitting to ensure a smooth transition between the start point, end point, and intermediate points. Flight constraints are considered during the path smoothing process, including the maximum turning angle, path smoothness, and safety radius. Safe connection points and intermediate points are inserted to ensure that the interval between every two path points meets the safety radius requirement. The turning angle is adjusted to meet the maximum safe turning angle constraint, and the final inspection path points are generated.

[0010] S4. Use density-based clustering algorithm to spatially cluster the waypoints and divide them into multiple clusters. For each cluster, use an improved TSP algorithm to optimize the path order to minimize the total path length. The path selection is dynamically adjusted based on pheromone concentration, heuristic factor, path length and safety constraint factor. Through clustering and path optimization, the global temporary optimal route is obtained.

[0011] S5. Upload the global temporary optimal flight path to the UAV control system. The UAV flies sequentially along the flight path, visits all patrol target points, and performs image acquisition and task execution at each target point.

[0012] S6. Utilize the collected images and data to perform image processing and anomaly detection, generate analysis reports, output recognition results, and visualize the planned flight routes, collected images, and recognition results.

[0013] The preferred and optimized process for generating the path point set is as follows:

[0014] S21. Input data: Set of safety inspection points: P = {(x′ i ,y′ i ,z i ,δ i ,θ i ,d i ,R i |i=1,2,...,n};

[0015] Define the initial safe point S = (x′0, y′0, z0);

[0016] Define the termination safety point E = (x′) n y′ n , z n );

[0017] Where n represents the number of safety inspection points;

[0018] S22. Objective: Plan the shortest route R that passes through all inspection points, minimize the route length while ensuring route safety, and output the streamlined and optimized route point sequence and total route length.

[0019] S23. Dynamic path constraint optimization introduces a safety radius constraint during path selection to prevent the drone from approaching obstacles or entering dangerous areas. The path selection probability P... ij The formula is:

[0020]

[0021] In the formula, τ ij Indicates the pheromone concentration along path i→j; η ij Represents the path heuristic factor; d ij Indicates path length; ψ ij Let ψ represent the safety constraint factor. If path i→j does not satisfy the safety radius constraint, then ψ ij <1, otherwise 1; α and β represent parameters that control the weights of pheromones and heuristic factors; U represents the set of remaining points that the ant can currently access;

[0022] S24. Multi-ant colony parallel search mechanism: Multiple ant colonies are introduced to perform the search task in parallel, which increases the global search capability of the algorithm and effectively avoids the problem of local optima. Each ant colony searches the path independently and finally selects the global optimal path for output.

[0023] S25. Adaptive pheromone update mechanism: dynamically adjusts the pheromone update amount based on path quality, strengthening better paths and weakening inferior paths.

[0024] τ ij ←(1-ρ)·τ ij +ρ·Δτ ij ;

[0025]

[0026] In the formula, ρ represents the pheromone evaporation coefficient; Q represents the pheromone intensity; L represents the path length; f adj This represents a dynamic adjustment factor that adaptively adjusts based on the current iteration round and path quality.

[0027] S26. Output the optimized path point set based on the improved ant colony algorithm.

[0028] Preferably, the process of outputting the optimized path point set based on the improved ant colony algorithm is as follows:

[0029] S31. Initialization: Input patrol point data P, initialize ant count m, maximum iteration count T, pheromone concentration τ. ij Heuristic factor η ij and setting a safety radius constraint δ i ;

[0030] S32, Ant Path Search:

[0031] Each ant starts from the starting point S, based on the path selection probability P. ij Visit the inspection points sequentially according to the formula:

[0032] S3201. Calculate the selection probability P for each possible path. ij And based on this probability, select the next patrol point to visit;

[0033] S3202, Selection Strategy: The ant selects its path based on the probability P of its current path. ij When choosing the next point, if there are multiple paths to choose from, the path with the higher pheromone concentration is preferred.

[0034] S3203, Security Constraints: Selected Path d ij Minimum safety radius δ must be met i The requirement is to ensure the flight safety of drones;

[0035] Path execution and recording: Each ant visits multiple checkpoints sequentially until all checkpoints have been visited, finally reaching the destination E. During the visit, the ant records the path it traverses and calculates the path length L. ant And the path length will be used as the basis for path quality assessment;

[0036] S33, Pheromone Update:

[0037] Local update: When ants choose a path, they perform local pheromone updates on the path they traverse to enhance its attractiveness. The formula for local update is:

[0038] τ ij ←(1-ρ)·τ ij +ρ·Δτ ij ;

[0039] Global Update: After each iteration, the algorithm performs a global pheromone update based on the optimal path. Shorter paths release more pheromones, increasing their probability of being selected by subsequent ants. The global update formula is:

[0040] τ ij←(1-ρ)·τ ij +ρ·Δτ ij ;

[0041] S34. Parallel Search and Optimal Path Selection: Under the multi-ant colony parallel search mechanism, multiple ant colonies execute the search process simultaneously.

[0042] S3401, Multi-colony Search: Each ant colony independently performs pathfinding. Each ant starts from the starting point and selects a path based on probability P. ij They choose a path until they reach their destination. Different ant colonies share pheromone updates, but the search paths are independent.

[0043] S3402, Optimal Path Selection: By comparing the path quality of all ant colonies, the route with the shortest path length is selected as the final output optimal path. This optimal path includes the shortest path through all inspection points and meets the safety constraints.

[0044] S35. If the maximum number of iterations T is reached, or the path optimization converges, or the path quality is no longer optimized, then execution stops.

[0045] S36. Output the optimal path point sequence R = {S, p1, p2, ..., p...} m E} represents the optimized inspection path, which includes the starting point, all inspection points, and the ending point.

[0046] Preferably, the process for generating the identifier to be reviewed is as follows:

[0047] S41. Select a random number a∈(0,n), and calculate the verification code CA=g. a mod q;

[0048] Where p = 521 is a prime number; n = 2p-1 is a Mersenne prime; and the corresponding p-th degree irreducible primitive polynomial q = x is taken. 521 +x 32 +1, where x is a polynomial indeterminate variable;

[0049] S42. Select a random number k∈(0,n), and calculate the first-level review factor F1=g k mod q;

[0050] S43. Calculate the secondary review factor F2 = H(List1) × k + a × F1 mod n;

[0051] List1 represents the binary string of the path points in the optimized path point set P′ concatenated in order;

[0052] S44. Generate the identifier to be reviewed, LA = {F1, F2}.

[0053] Preferably, the review process for the overall integrity of the received path point set is as follows:

[0054] S51. Calculate the primary review factor FA1:

[0055] S52. Calculate the secondary review factor FA2:

[0056] S53. If FA1 = FA2, it means that the path point set P′ has been completely received.

[0057] Preferably, the process for generating patrol path points is as follows:

[0058] S61. Based on the received optimized path point set P′={P1,P2,…,P i , ..., P n The core objective of connecting the safety points end to end is:

[0059] Smooth transitions between the start, end, and intermediate inspection points of the path to avoid abrupt turns or large-angle deviations, thus satisfying the smoothness of the UAV's flight path.

[0060] Consider flight constraints: the maximum turning angle, safe radius, and flight altitude stability of the UAV;

[0061] S62. Define problem constraints:

[0062] Safe steering angle: The steering angle between two adjacent path points must satisfy: θ i ≤θ max ;

[0063] Where, θ i Represents path point p i-1 →p i and p i →p i+1 The angle between them; θ max Indicates the maximum safe turning angle allowed for the drone;

[0064] Path smoothness: During route optimization, smooth curves or transition points are introduced to connect routes while ensuring that the increase in path length is minimal.

[0065] Safety radius constraint: Ensures the flight path point p of the UAV i The minimum interval between them is greater than the safety radius R. safe This is to avoid route instability caused by overly dense waypoints;

[0066] S63. Generate a path sequence P after safe end-to-end connection based on the safe point end-to-end connection method. safe :P safe={p1,p′2,...,p′ n}

[0067] The preferred implementation steps of the safety point connection method are as follows:

[0068] S71. For the optimized path point set P′={P1,P2,…,P i , ..., P n The path is smoothly fitted using a third-order Bézier curve, and safe connection points are inserted to ensure a smooth transition between the start, end, and intermediate points. The formula for the third-order Bézier curve is as follows:

[0069] B(t)=(1-t) 3 p0+3t(1-t) 2 p1+3t 2 (1-t)p²+t 3 p3;

[0070] In the formula, B(t) represents any point on the Bézier curve; p0, p1, p2 and p3 represent control points; t represents the curve parameter, t∈[0,1];

[0071] The principles for selecting control points are as follows:

[0072] p0 is the starting point of the path segment; p3 is the ending point of the path segment; p1 and p2 are auxiliary control points, selected according to the following rules:

[0073] p1 represents the offset based on the flight direction from the starting point, with a distance of λ×d. i,i+1 ;

[0074] p2 represents the offset in the opposite direction of the endpoint, with a distance of λ×d. i,i+1 ;

[0075] Where λ∈(0,1) is the smoothing coefficient;

[0076] S72. After generating the smooth path, check whether the interval between path points meets the safety radius constraint R. safe The details are as follows:

[0077] Path point distance calculation: The distance between two path points is:

[0078]

[0079] Verify the safe radius: if d i,j <R safe Then insert an additional intermediate point p. k The path is redefined, and the coordinates of the intermediate points are calculated as follows:

[0080]

[0081] S73, For three consecutive path points p i-1 p i p i+1 Calculate the steering angle θ i :

[0082]

[0083] In the formula, Represents path segment p i-1 →p i ;

[0084] Represents path segment p i →p i+1 ;

[0085] If θ i >θ max If so, the path is adjusted and transition points are inserted to ensure that the path turning angle meets safety requirements.

[0086] The preferred process for generating the global provisional optimal route is as follows:

[0087] S81. The inspection path points P are clustered using a density-based clustering algorithm. safe The routes are divided into several clusters, and the waypoints are merged into C1, C2, ..., C6. k cluster;

[0088] The formula for density-based clustering algorithm is: for any path point p i If the following conditions are met, then p i Belongs to a certain cluster:

[0089] N(p i )={p j |d i,j ≤ε};

[0090] In the formula, N(p) i ) represents path point p i d's neighborhood; i,j Represents path point p i and p j The Euclidean distance between them; ε represents the neighborhood radius, i.e., the distance threshold between path points;

[0091] S82, For each cluster C i The improved Traveling Salesman Problem algorithm optimizes the path execution order to form the shortest path. The specific operation process is as follows:

[0092] S8201. The goal is to find an optimal path sequence that minimizes the total path length from the starting point, through all path points, and back to the starting point.

[0093]

[0094] In the formula, D TSP Indicates the total length of the TSP path; d i,i+1 Represents path point p i to p i+1 The distance; n represents the number of path points within the cluster;

[0095] S8202, Path selection probability, that is, the probability that an ant moves from path point i to path point j is:

[0096]

[0097] In the formula, τ ij Indicates the pheromone concentration along path i→j; η ij Represents the path heuristic factor; d ij Indicates path length; ψ ij Let ψ represent the safety constraint factor. If path i→j does not satisfy the safety radius constraint, then ψ ij <1, otherwise 1; α and β represent parameters controlling the weights of pheromones and heuristic factors; N i This represents the set of remaining points that the ant can currently visit;

[0098] Pheromone updates, which refer to the changes in pheromone concentration over time, include pheromone evaporation and ant path contributions:

[0099] τ ij ←(1-ρ)·τ ij +ρ·Δτ ij ;

[0100]

[0101] In the formula, ρ represents the pheromone evaporation coefficient; Q represents the total amount of pheromone released; L k The 'm' represents the total length of the path traveled by ant k; the 'm' represents the number of ants.

[0102] S83. By clustering routes and optimizing dynamic paths, the globally optimal temporary route P is obtained. best ={q1, q2, ..., q m}

[0103] The technical solution of this invention: A dynamic flight path planning system for substation unmanned aerial vehicles (UAVs), used to execute the aforementioned dynamic flight path planning method for substation UAVs, comprising:

[0104] The task input module is used to receive input information for patrol tasks and generate a set of target points as the basic data input for route planning.

[0105] The route planning module is used to divide the target point into several sub-routes based on the input patrol point data, using route simplification and dynamic combination algorithms. It performs minimum path optimization on each sub-routes to generate a local optimal path. Then, it introduces all sub-routes into the safety point connection mechanism and uses dynamic programming algorithm to merge multiple sub-routes to form a complete optimal temporary route.

[0106] The safety management module provides a safety point connection function during the flight of the UAV. Based on the mission requirements and safety radius threshold, it automatically introduces safety points at the start and end points of each flight path and calculates the shortest connection path between safety points during flight path optimization.

[0107] The UAV execution module transmits the dynamic temporary flight path data generated by the flight path planning module to the UAV control system, controls the UAV to perform patrol tasks according to the planned optimal path in real time, achieves accurate arrival at the target point and data collection, and dynamically adjusts the flight path according to changes in the task.

[0108] The AI ​​recognition module is responsible for processing the image and video data collected by the drone's execution module, uploading the data to the AI ​​analysis engine, using target recognition algorithms to intelligently identify and analyze the status of the patrol targets, automatically detect equipment anomalies, defects or safety hazards, and generate recognition result reports.

[0109] The user terminal module provides a visual operation interface for the entire mission process, allowing users to view dynamic flight paths, equipment anomaly reports, and the real-time status of the UAV. It also enables users to quickly adjust the next patrol mission plan based on the recognition results, thus realizing the human-computer interaction function of the system.

[0110] Compared with the prior art, the above-mentioned technical solution of the present invention has the following beneficial technical effects:

[0111] This invention presents a dynamic flight path planning method and system for substation UAVs. By combining precise processing of task data, flight path optimization, and dynamic safety constraints, it ensures the efficiency, stability, and safety of flight path planning, effectively solving the flight path planning problem in substation UAV inspections.

[0112] (1) Accurate and efficient task input: By converting the inspection requirements into a detailed set of point data, and combining coordinate transformation, safety radius calculation and shooting parameter setting steps, high-quality data that meets the inspection requirements is generated, and unified processing of multiple data sources is achieved, ensuring the accuracy and reliability of coordinate data, and providing a solid foundation for subsequent route planning.

[0113] (2) Precise optimization of flight path planning: By using the flight path optimization method based on the improved ant colony algorithm (IACO), the problems of path simplification and safety constraints in UAV flight path planning are solved. Dynamic safety radius constraints, heuristic information guidance and multi-ant colony parallel search mechanism are introduced to effectively improve the global optimal capability of flight path planning and avoid local optimal solutions. At the same time, the adaptive pheromone update mechanism strengthens the high-quality path, and the optimization results meet the dual requirements of shortest path and safe flight.

[0114] (3) High path safety and stability: During the route planning process, a safety radius constraint is dynamically introduced to effectively prevent the UAV from approaching obstacles or entering dangerous areas. In addition, through path smoothing, the UAV is ensured to make a smooth transition between the starting point, the ending point and the intermediate inspection point, which improves the feasibility and flight stability of the route. The minimum combination calculation of the current route is performed based on the target of each route, that is, the route is simplified and a safe point is formed at both the beginning and the end. Then, after multiple routes are simplified, the safe points are connected and merged to form a new temporary route. Finally, all the observed targets are reached, which also meets the dual requirements of shortest path and safe flight.

[0115] (4) Multi-level review mechanism to ensure data integrity: Design a method for generating review identifiers based on random numbers, hash functions and path point sequences, and verify the integrity of path point data through first-level and second-level review factors, effectively ensuring the accuracy and security of optimized path data during transmission and reception, and ensuring the reliability of route planning.

[0116] (5) Path smoothing improves flight quality: The path points are smoothly fitted by the third-order Bézier curve, which effectively solves the problem of flight instability caused by dense path points or sharp turns in path planning, and ensures the smoothness of the UAV flight under the safety radius constraint. In addition, the safety and smoothness of the flight route are improved by the steering angle constraint and the path point interval control.

[0117] (6) Dynamic adaptation and high execution efficiency: This invention combines dynamic constraint optimization and multi-ant colony parallel search mechanism in route planning, which improves the globality and efficiency of path search. At the same time, the adaptive pheromone update mechanism enables the algorithm to dynamically adjust according to different task scenarios and route requirements, ensuring the optimality and adaptability of the planning results. Attached Figure Description

[0118] Figure 1 This is a system architecture diagram of a dynamic flight path planning system for substation unmanned aerial vehicles proposed in this invention;

[0119] Figure 2 This is a flowchart of a dynamic flight path planning method for substation drones proposed in this invention. Detailed Implementation

[0120] Example 1, as Figure 1 As shown, the present invention proposes a dynamic flight path planning system for substation drones, which includes a task input module, a flight path planning module, a safety management module, a drone execution module, an AI recognition module, and a user terminal module.

[0121] The task input module receives input information for the patrol task, including but not limited to the latitude and longitude of the target patrol point, aerial photography angle, task priority and safety requirements, and generates a set of target points as the basic data input for route planning.

[0122] Based on the input inspection point data, the route planning module uses route simplification and dynamic combination algorithms to divide the target point into several sub-routes. It performs minimum path optimization on each sub-routes to generate a local optimal path. Then, it introduces all sub-routes into the safety point connection mechanism to ensure flight safety. Under the premise of ensuring flight safety, it uses dynamic programming algorithm to merge multiple sub-routes to form a complete optimal temporary route.

[0123] The safety management module provides a safety point connection function during UAV flight. Based on mission requirements and safety radius thresholds, it automatically introduces safety points at the start and end points of each flight path and calculates the shortest connection path between safety points during flight path optimization to ensure UAV flight safety and mission continuity.

[0124] The UAV execution module transmits the dynamic temporary flight path data generated by the flight path planning module to the UAV control system, and controls the UAV to perform the patrol mission according to the planned optimal path in real time, so as to achieve accurate arrival at the target point and data collection, and dynamically adjust the flight path according to the changes in the mission.

[0125] The AI ​​recognition module is responsible for processing the image and video data collected by the drone's execution module, uploading the data to the AI ​​analysis engine, using target recognition algorithms to intelligently identify and analyze the status of the patrol targets, automatically detecting equipment anomalies, defects or safety hazards, and generating recognition result reports.

[0126] The user terminal module provides a visual operation interface for the entire task process, including but not limited to task input, flight path planning result display, UAV execution path monitoring, and AI recognition result feedback. It supports users in viewing dynamic flight paths, equipment anomaly reports, and real-time UAV status. At the same time, it can quickly adjust the next patrol task plan based on the recognition result feedback, realizing the system's human-computer interaction function.

[0127] Example 2, as Figure 2As shown, the present invention proposes a dynamic flight path planning method for substation UAVs, which is applied to a dynamic flight path planning system for substation UAVs proposed in Embodiment 1. The specific implementation steps are as follows:

[0128] S1. The task input module converts the inspection requirements into a detailed set of point data. Through coordinate transformation, safety radius calculation, and shooting parameter setting, it generates high-quality data that meets the inspection requirements, laying the foundation for subsequent route planning. The specific implementation process is as follows:

[0129] S11. Obtain the geographic coordinates of the location data. The sources of geographic coordinate data include, but are not limited to:

[0130] GIS (Geographic Information System): Provides accurate coordinate data for equipment within the substation;

[0131] Drone flight history data: Records known target locations through historical aerial photography missions;

[0132] Real-time detection feedback: The anomaly detection module outputs the coordinates of the fault point as the new target point;

[0133] Define each inspection point p i The coordinates are represented as: p i ={x i y i , z i};

[0134] Where, x i Represents the longitude coordinates of the i-th inspection point; y i This represents the latitude coordinates of the i-th inspection point; z i This indicates the safe inspection height for the i-th inspection point;

[0135] S12. To ensure coordinate data consistency, data from different sources will be converted to a unified world coordinate system using the coordinate transformation formula: (x′ i y′ i )=T(x i y i );

[0136] Where T represents the coordinate transformation function;

[0137] Based on this, the patrol task is set, and the set of target locations for the patrol is as follows:

[0138] P = {p1, p2, ..., p} i , ..., p n};

[0139] Where n represents the number of target points, p i This represents the i-th inspection point;

[0140] S13. To ensure the safety of drone flight, for each inspection point p i Set a safety radius δ i :

[0141] δ i =f(h i ,r);

[0142] Among them, h i The safe inspection height z represents the height of the i-th inspection point. i ; r represents the positioning accuracy threshold of the UAV equipment; f represents the function that dynamically adjusts the safety radius based on flight altitude and positioning accuracy; δ i =α×h i +β×r; α represents the safety factor weight, i.e., the degree of influence of the inspection height on the safety radius; β represents the positioning accuracy weight, i.e., the degree of influence of the equipment accuracy on the safety radius;

[0143] S14, Set each point p i The shooting parameters for the patrol mission specifically include:

[0144] Shooting angle θ i : Indicates the pitch angle during drone aerial photography;

[0145] Shooting distance d i : Indicates the distance between the camera and the target device;

[0146]

[0147] Shooting resolution R i : Indicates the required resolution for aerial images;

[0148] S15. Output the set of safety inspection points based on this: P = {(x′ i ,y′ i ,z i ,δ i ,θ i ,d i ,R i )|i=1,2,...,n}.

[0149] S2. The route planning module optimizes the route planning of UAVs during substation inspections. It proposes an improved ant colony optimization (IACO) method, combining heuristic information and dynamic constraints. Through path selection probability, dynamic safety constraints, and a multi-ant colony parallel search mechanism, it optimizes and simplifies the routes to inspection points, ultimately generating the optimal route. The specific implementation process is as follows:

[0150] S21. Input data: Set of safety inspection points: P = {(x′ i ,y′ i ,z i ,δ i ,θ i ,d i ,R i |i=1,2,...,n};

[0151] Define the initial safe point S = (x′0, y′0, z0);

[0152] Define the termination safety point E = (x′) n y′ n , z n );

[0153] S22. Objective: Plan the shortest route R that passes through all inspection points, minimize the route length while ensuring route safety, and output the streamlined and optimized route point sequence and total route length.

[0154] S23. Dynamic path constraint optimization introduces a safety radius constraint during path selection to prevent the drone from approaching obstacles or entering dangerous areas. The path selection probability P... ij The formula is:

[0155]

[0156] In the formula, τ ij Indicates the pheromone concentration along path i→j; η ij Represents the path heuristic factor; d ij Indicates path length; ψ ij Let ψ represent the safety constraint factor. If path i→j does not satisfy the safety radius constraint, then ψ ij <1, otherwise 1; α and β represent parameters that control the weights of pheromones and heuristic factors; U represents the set of remaining points that the ant can currently access;

[0157] S24. Multi-ant colony parallel search mechanism: Multiple ant colonies are introduced to perform the search task in parallel, which increases the global search capability of the algorithm and effectively avoids the problem of local optima. Each ant colony searches the path independently and finally selects the global optimal path for output.

[0158] S25. Adaptive pheromone update mechanism: dynamically adjusts the pheromone update amount based on path quality, strengthening better paths and weakening inferior paths.

[0159] τ ij ←(1-ρ)·τ ij +ρ·Δτ ij ;

[0160]

[0161] In the formula, ρ represents the pheromone evaporation coefficient; Q represents the pheromone intensity; L represents the path length; f adj This represents a dynamic adjustment factor that adaptively adjusts based on the current iteration round and path quality.

[0162] S26. The execution flow of the method based on the Improved Ant Colony Optimization (IACO) algorithm is as follows:

[0163] S2601. Initialization: Input patrol point data P, initialize ant count m, maximum iteration count T, pheromone concentration τ. ij Heuristic factor η ij and setting a safety radius constraint δ i ;

[0164] S2602, Ant Path Search:

[0165] Each ant starts from the starting point S, based on the path selection probability P. ij Visit the inspection points sequentially according to the formula:

[0166] (1) Calculate the selection probability P for each possible path. ij And based on this probability, select the next patrol point to visit;

[0167] (2) Selection strategy: The ant selects the path based on the probability P of the current path. ij When choosing the next point, if there are multiple paths to choose from, the path with the higher pheromone concentration is preferred.

[0168] (3) Security constraints: the selected path d ij Minimum safety radius δ must be met i The requirement is to ensure the flight safety of drones;

[0169] Path execution and recording: Each ant visits multiple checkpoints sequentially until all checkpoints have been visited, finally reaching the destination E. During the visit, the ant records the path it traverses and calculates the path length L. ant And the path length will be used as the basis for path quality assessment;

[0170] S2603, Pheromone Update:

[0171] (1) Local Update: When ants choose a path, they update the pheromones of the path they pass through locally to enhance the attractiveness of the path. The formula for local update is:

[0172] τ ij ←(1-ρ)·τij +ρ·Δτ ij ;

[0173] (2) Global Update: After each iteration, the algorithm performs a global pheromone update based on the optimal path. Shorter paths release more pheromones, increasing their probability of being selected by subsequent ants. The global update formula is:

[0174] τ ij ←(1-ρ)·τ ij +ρ·Δτ ij ;

[0175] S2604, Parallel Search and Optimal Path Selection:

[0176] Under the multi-ant colony parallel search mechanism, multiple ant colonies execute the search process simultaneously:

[0177] (1) Multi-ant colony search: Each ant colony independently performs path search. Each ant starts from the starting point and selects a path according to the probability P. ij They choose a path until they reach their destination. Different ant colonies share pheromone updates, but the search paths are independent.

[0178] (2) Optimal path selection: By comparing the path quality of all ant colonies, the route with the shortest path length is selected as the final output optimal path. This optimal path includes the shortest path through all inspection points and meets the safety constraints.

[0179] S2605. If the maximum number of iterations T is reached, or the path optimization converges, or the path quality is no longer optimized, then execution stops.

[0180] S2606. Output the optimal path point sequence R = {S, p1, p2, ..., p...} m E} is the optimized inspection path, which includes the starting point, all inspection points, and the ending point;

[0181] The total path D, i.e., the total length of the optimal path,

[0182] S27. Output the optimized path point set P′={P1,P2,…,P i , ..., P n};

[0183] Where P1 is the starting point, P k It is the endpoint, P i (i = 2, ..., k-1) are the simplified inspection points in the middle;

[0184] S28. Generate review identifiers for the optimized path point set P′. The specific implementation process is as follows:

[0185] S2801. Select a random number a∈(0,n), and calculate the verification code CA=g. a mod q;

[0186] Where p = 521, is a prime number; n = 2 p -1 is a Mersenne prime; take the corresponding p-th degree irreducible primitive polynomial q = x 521 +x 32 +1, where x is a polynomial indeterminate variable;

[0187] S2802. Select a random number k∈(0,n) and calculate the first-level review factor F1=g. k mod q;

[0188] S2803. Calculate the secondary review factor F2 = H(List1) × k + a × F1 mod n;

[0189] Where List1 represents the binary string of the path points in the optimized path point set P′ concatenated in order; H represents the hash function;

[0190] S2804. Generate the identifier to be reviewed, LA = {F1, F2};

[0191] S29. Transfer {LA, P′} to the security management module.

[0192] S3, the safety management module outputs a safe and efficient flight path by accurately calculating path distances, checking safety constraints, adjusting the path to avoid safe areas, and ensuring smooth flight through smoothing processes. The specific implementation process is as follows:

[0193] S31. Based on the identifier LA to be reviewed, the overall integrity of the received path point set is reviewed. The review process is as follows:

[0194] S3101, Calculate the primary review factor FA1:

[0195] S3102, Calculate the secondary review factor FA2:

[0196] S3103. If FA1 = FA2, it means that the path point set P′ has been completely received.

[0197] S32. Based on the received optimized path point set P′={P1,P2,…,P i , ..., P n The core objective of connecting the safety points end to end is:

[0198] Smooth transitions between the start, end, and intermediate inspection points of the path to avoid abrupt turns or large-angle deviations, thus satisfying the smoothness of the UAV's flight path.

[0199] Consider flight constraints: the maximum turning angle, safe radius, and flight altitude stability of the UAV;

[0200] S33. Define problem constraints:

[0201] S3301, Safety Turning Angle: The turning angle between two adjacent path points must satisfy: θ i ≤θ max ;

[0202] Where, θ i Represents path point p i-1 →p i and p i →p i+1 The angle between them; θ max Indicates the maximum safe turning angle allowed for the drone;

[0203] S3302, Path Smoothness: During route optimization, smooth curves or transition points are introduced to connect routes while ensuring that the increase in path length is minimal.

[0204] S3303, Safety Radius Constraint: Ensures the UAV's flight path point p i The minimum interval between them is greater than the safety radius R. safe This is to avoid route instability caused by overly dense waypoints;

[0205] S34. Based on this, a method for connecting the beginning and end of a safety point is designed, and its specific implementation process is as follows:

[0206] S3401. For the optimized path point set P′={P1,P2,…,P i , ..., P n The path is smoothly fitted using a third-order Bézier curve, and safe connection points are inserted to ensure a smooth transition between the start, end, and intermediate points. The formula for the third-order Bézier curve is as follows:

[0207] B(t)=(1-t) 3 p0+3t(1-t) 2 p1+3t 2 (1-t)p²+t 3 p3;

[0208] In the formula, B(t) represents any point on the Bézier curve; p0, p1, p2 and p3 represent control points; t represents the curve parameter, t∈[0,1];

[0209] The principles for selecting control points are as follows:

[0210] p0 is the starting point of the path segment; p3 is the ending point of the path segment; p1 and p2 are auxiliary control points, selected according to the following rules:

[0211] p1 represents the offset based on the flight direction from the starting point, with a distance of λ×d. i,i+1 ;

[0212] p2 represents the offset in the opposite direction of the endpoint, with a distance of λ×d. i,i+1 ;

[0213] Where λ∈(0,1) is the smoothing coefficient;

[0214] S3402. After generating the smooth path, check whether the interval between path points meets the safety radius constraint R. safe The details are as follows:

[0215] Path point distance calculation: The distance between two path points is:

[0216]

[0217] Verify the safe radius: if d i,j <R safe Then insert an additional intermediate point p. k The path is redefined, and the coordinates of the intermediate points are calculated as follows:

[0218]

[0219] It should be noted that inserting the intermediate point p k The excessively dense path points are smoothly segmented, gradually increasing the distance between them, and new transition points p are generated through linear interpolation. k This allows the drone to smoothly transition from p during flight. i Transition to p j This reduces the severity of flight turning and inserts the midpoint p. k The path can be redefined to ensure that the interval d between any two adjacent points is... i,k and d k,j All satisfy d i,j ≧R safe This satisfies the safety radius constraint.

[0220] S3403, For three consecutive path points p i-1 p i p i+1 Calculate the steering angle θ i :

[0221]

[0222] In the formula, Represents path segment p i-1 →p i ;

[0223] Represents path segment p i →p i+1 ;

[0224] If θ i >θ max If so, the path is adjusted and transition points are inserted to ensure that the path turning angle meets safety requirements;

[0225] S35. Generate a secure path sequence P after end-to-end alignment. safe :P safe ={p1,p′2,...,p′ n};

[0226] Total path length D safe :

[0227] S36. Connect the path sequence P after secure end-to-end connection. safe Transmitted to the route planning module.

[0228] S4. The route planning module merges route points using the DBSCAN (Density-Based Spatial Clustering of Applications with Noise) clustering algorithm and optimizes the path order using an improved ant colony algorithm, achieving dynamic route merging and optimization. The specific implementation process is as follows:

[0229] S41. Use the DBSCAN algorithm to locate the inspection path point P. safe The routes are divided into several clusters, and the waypoints are merged into C1, C2, ..., C6. k cluster;

[0230] The DBSCAN algorithm formula is: For any path point p i If the following conditions are met, then p i Belongs to a certain cluster:

[0231] N(p i )={p j |d i,j ≤ε};

[0232] In the formula, N(p) i ) represents path point p i d's neighborhood; i,j Represents path point p i and p jThe Euclidean distance between them; ε represents the neighborhood radius, i.e., the distance threshold between path points;

[0233] S42, For each cluster C i The improved Traveling Salesman Problem (TSP) algorithm optimizes the path execution order to form the shortest path. The specific operation process is as follows:

[0234] S4201. The goal is to find an optimal path sequence that minimizes the total path length from the starting point, through all path points, and back to the starting point.

[0235]

[0236] In the formula, D TSP Indicates the total length of the TSP path; d i,i+1 Represents path point p i to p i+1 The distance; n represents the number of path points within the cluster;

[0237] S4202, Path selection probability, that is, the probability that an ant moves from path point i to path point j is:

[0238]

[0239] In the formula, τ ij Indicates the pheromone concentration along path i→j; η ij Represents the path heuristic factor; d ij Indicates path length; ψ ij Let ψ represent the safety constraint factor. If path i→j does not satisfy the safety radius constraint, then ψ ij <1, otherwise 1; α and β represent parameters controlling the weights of pheromones and heuristic factors; N i This represents the set of remaining points that the ant can currently visit;

[0240] Pheromone updates, which refer to the changes in pheromone concentration over time, include pheromone evaporation and ant path contributions:

[0241] τ ij ←(1-ρ)·τ ij +ρ·Δτ ij ;

[0242]

[0243] In the formula, ρ represents the pheromone evaporation coefficient; Q represents the total amount of pheromone released; L k The 'm' represents the total length of the path traveled by ant k; the 'm' represents the number of ants.

[0244] S43. By clustering routes and optimizing dynamic paths, the globally optimal temporary route P is obtained. best ={q1, q2, ..., q m};

[0245] Total path length D best :

[0246] S44, Set the global temporary optimal route P best Transmitted to the UAV execution module.

[0247] S5, the UAV execution module will determine the globally temporary optimal flight path P best The data is uploaded to the drone control system. The drone flies sequentially along the flight path, visiting all target locations and p at each target location. i Perform image acquisition and task execution.

[0248] S6. The drones performing the patrol mission will collect images and data and transmit them to the AI ​​recognition module. The AI ​​recognition module will perform the following tasks: image processing and anomaly detection and generate analysis reports, and output the recognition results. Based on this, the user terminal module will visualize the planned flight path, the collected images and the recognition results.

[0249] The embodiments of the present invention have been described in detail above with reference to the accompanying drawings. However, the present invention is not limited thereto. Various changes can be made within the scope of knowledge possessed by those skilled in the art without departing from the spirit of the present invention.

Claims

1. A dynamic flight path planning method for unmanned aerial vehicles (UAVs) in substations, characterized in that, The specific implementation steps include the following: S1. Convert the inspection requirements into a detailed set of point data, and generate an output set of safe inspection points that meets the inspection requirements through coordinate transformation, safety radius calculation, and shooting parameter setting steps. The optimized path point set generation process is as follows: A1. Input Data: Set of Safety Inspection Points: ; Define the initial safe point S = (x'0, y'0, z0); Define the termination safe point E=(x' n y' n , z n ); Where n represents the number of safety inspection points; δ i This represents each inspection point p. i The set safety radius; θ i Indicates point p i The shooting angle in the shooting parameters of the patrol mission, that is, the pitch angle when the drone is taking aerial photos; d i Indicates point p i The shooting distance in the shooting parameters of the patrol mission is the distance between the camera and the target device; R i Indicates point p i The shooting resolution in the shooting parameters of the patrol mission; A2. Objective: To plan the shortest route R that passes through all inspection points, minimize the route length while ensuring route safety, and output the streamlined and optimized route point sequence and total route length. A3. Dynamic path constraint optimization introduces a safety radius constraint during path selection to prevent the drone from approaching obstacles or entering dangerous areas. The path selection probability P... ij The formula is: ； ； ； In the formula, τ ij Indicates the pheromone concentration along path i→j; η ij Represents the path heuristic factor; d ij Indicates path length; ψ ij Let ψ represent the safety constraint factor. If path i→j does not satisfy the safety radius constraint, then ψ ij <1, otherwise 1; α and β represent parameters that control the weights of pheromones and heuristic factors; U represents the set of remaining points that the ant can currently access; A4. Multi-ant colony parallel search mechanism: Multiple ant colonies are introduced to perform the search task in parallel, which increases the global search capability of the algorithm and effectively avoids the problem of local optima. Each ant colony searches the path independently and finally selects the global optimal path for output. A5. Adaptive pheromone update mechanism: dynamically adjusts the pheromone update amount based on path quality, strengthening better paths and weakening inferior paths. ； ； In the formula, ρ represents the pheromone evaporation coefficient; Q represents the pheromone intensity; L represents the path length; f adj This represents a dynamic adjustment factor that adaptively adjusts based on the current iteration round and path quality. A6. Output the optimized path point set based on the improved ant colony algorithm; S2. Combining heuristic information and dynamic constraints, the path of the patrol point is optimized and simplified through path selection probability, dynamic safety constraints and multi-ant colony parallel search mechanism. The optimized path point set is output and an inspection mark is generated for the optimized path point set. S3. Based on the identifier to be reviewed, the overall integrity of the received path point set is reviewed. Based on the optimized path point set, a third-order Bézier curve is used to perform path smoothing fitting to ensure a smooth transition between the start point, end point, and intermediate points. Flight constraints are considered during the path smoothing process, including the maximum turning angle, path smoothness, and safety radius. Safe connection points and intermediate points are inserted to ensure that the interval between every two path points meets the safety radius requirement. The turning angle is adjusted to meet the maximum safe turning angle constraint, and the final inspection path points are generated. S4. Use density-based clustering algorithm to spatially cluster the waypoints and divide them into multiple clusters. For each cluster, use an improved TSP algorithm to optimize the path order to minimize the total path length. The path selection is dynamically adjusted based on pheromone concentration, heuristic factor, path length and safety constraint factor. Through clustering and path optimization, the global temporary optimal route is obtained. S5. Upload the global temporary optimal flight path to the UAV control system. The UAV flies sequentially along the flight path, visits all patrol target points, and performs image acquisition and task execution at each target point. S6. Utilize the collected images and data to perform image processing and anomaly detection, generate analysis reports, output recognition results, and visualize the planned flight routes, collected images, and recognition results.

2. The method for dynamic flight path planning of unmanned aerial vehicles (UAVs) in substations according to claim 1, characterized in that, The process of outputting the optimized path point set based on the improved ant colony algorithm is as follows: S31. Initialization: Input patrol point data P, initialize ant count m, maximum iteration count T, pheromone concentration τ. ij Heuristic factor η ij and setting a safety radius constraint δ i ; S32, Ant Path Search: Each ant starts from the starting point S, based on the path selection probability P. ij Visit the inspection points sequentially according to the formula: S3201. Calculate the selection probability P for each possible path. ij And based on this probability, select the next patrol point to visit; S3202, Selection Strategy: The ant selects its path based on the probability P of its current path. ij When choosing the next point, if there are multiple paths to choose from, the path with the higher pheromone concentration is preferred. S3203, Security Constraints: Selected Path d ij Minimum safety radius δ must be met i The requirement is to ensure the flight safety of drones; Path execution and recording: Each ant visits multiple checkpoints sequentially until all checkpoints have been visited, finally reaching the destination E. During the visit, the ant records the path it traverses and calculates the path length L. ant And the path length will be used as the basis for path quality assessment; S33, Pheromone Update: Local update: When ants choose a path, they perform local pheromone updates on the path they traverse to enhance its attractiveness. The formula for local update is: ； Global Update: After each iteration, the algorithm performs a global pheromone update based on the optimal path. Shorter paths release more pheromones, increasing their probability of being selected by subsequent ants. The global update formula is: ； S34. Parallel Search and Optimal Path Selection: Under the multi-ant colony parallel search mechanism, multiple ant colonies execute the search process simultaneously. S3401, Multi-colony Search: Each ant colony independently performs pathfinding. Each ant starts from the starting point and selects a path based on probability P. ij They choose a path until they reach their destination. Different ant colonies share pheromone updates, but the search paths are independent. S3402, Optimal Path Selection: By comparing the path quality of all ant colonies, the route with the shortest path length is selected as the final output optimal path. This optimal path includes the shortest path through all inspection points and meets the safety constraints. S35. If the maximum number of iterations T is reached, or the path optimization converges, or the path quality is no longer optimized, then execution stops. S36. Output the optimal path point sequence R={S, p1, p2, ..., p m E} represents the optimized inspection path, which includes the starting point, all inspection points, and the ending point.

3. The method for dynamic flight path planning of unmanned aerial vehicles (UAVs) in substations according to claim 1, characterized in that, The process for generating the identifier to be reviewed is as follows: S41. Select a random number a∈(0,n), and calculate the verification code CA=g. a mod q; Where p = 521, is a prime number; n = 2 p -1 is a Mersenne prime; take the corresponding p-th degree irreducible primitive polynomial q=x 521 +x 32 +1, where x is a polynomial indefinite variable; S42. Select a random number k∈(0,n), and calculate the first-level review factor F1=g. k mod q; S43. Calculate the secondary review factor F2 = H(List1) × k + a × F1 mod n; List1 represents the binary string of the path points in the optimized path point set P' concatenated in order; S44. Generate the identifier to be reviewed, LA={F1, F2}.

4. The method for dynamic flight path planning of unmanned aerial vehicles (UAVs) in substations according to claim 3, characterized in that, The review process for the overall integrity of the received path point set is as follows: S51. Calculate the primary review factor FA1: ; S52. Calculate the secondary review factor FA2: ; S53. If FA1=FA2, it means that the path point set P' has been fully received.

5. The method for dynamic flight path planning of a substation UAV according to claim 1, characterized in that, The process of generating patrol path points is as follows: S61. Based on the received optimized path point set P'={P1, P2, ..., P...} i , ..., P n The core objective of connecting the safety points end to end is: Smooth transitions between the start, end, and intermediate inspection points of the path to avoid abrupt turns or large-angle deviations, thus satisfying the smoothness of the UAV's flight path. Consider flight constraints: the maximum turning angle, safe radius, and flight altitude stability of the UAV; S62. Define problem constraints: Safe steering angle: The steering angle between two adjacent path points must satisfy: θ i ≤θ max ; Where, θ i Represents path point p i-1 →p i and p i →p i+1 The angle between them; θ max Indicates the maximum safe turning angle allowed for the drone; Path smoothness: During route optimization, smooth curves or transition points are introduced to connect routes while ensuring that the increase in path length is minimal. Safety radius constraint: Ensures the flight path point p of the UAV i The minimum interval between them is greater than the safety radius R. safe This is to avoid route instability caused by overly dense waypoints; S63. Generate a path sequence P after safe end-to-end connection based on the safe point end-to-end connection method. safe : .

6. The method for dynamic flight path planning of a substation UAV according to claim 5, characterized in that, The implementation steps of the safety point connection method are as follows: S71. For the optimized path point set P'={P1, P2, ..., P...} i , ..., P n The path is smoothly fitted using a third-order Bézier curve, and safe connection points are inserted to ensure a smooth transition between the start, end, and intermediate points. The formula for the third-order Bézier curve is as follows: ； In the formula, B(t) represents any point on the Bézier curve; p0, p1, p2 and p3 represent control points; t represents the curve parameter, t∈[0,1]; The principles for selecting control points are as follows: p0 is the starting point of the path segment; p3 is the ending point of the path segment; p1 and p2 are auxiliary control points, selected according to the following rules: p1 represents the offset based on the flight direction from the starting point, with a distance of λ×d. i,i+1 ; p2 represents the offset in the opposite direction of the endpoint, with a distance of λ×d. i,i+1 ; Where λ∈(0,1) is the smoothing coefficient; S72. After generating the smooth path, check whether the interval between path points meets the safety radius constraint R. safe , as follows: Path point distance calculation: The distance between two path points is: ； Verify the safe radius: if d i,j <R safe Then insert an additional intermediate point p. k The path is redefined, and the coordinates of the intermediate points are calculated as follows: ； S73, For three consecutive path points p i-1 p i p i+1 Calculate the steering angle θ i : ； In the formula, Represents path segment p i-1 →p i ; Represents path segment p i →p i+1 ; If θ i >θ max If so, the path is adjusted and transition points are inserted to ensure that the path turning angle meets safety requirements.

7. The method for dynamic flight path planning of unmanned aerial vehicles (UAVs) in substations according to claim 1, characterized in that, The process of generating the global provisional optimal route is as follows: S81. The inspection path points P are clustered using a density-based clustering algorithm. safe The data is divided into several clusters, and flight paths are merged, with waypoints divided into C1, C2, ..., C... k cluster; The formula for density-based clustering algorithm is: for any path point p i If the following conditions are met, then p i Belongs to a certain cluster: ； In the formula, N(p) i ) represents path point p i d's neighborhood; i,j Represents path point p i and p j The Euclidean distance between them; ε represents the neighborhood radius, i.e., the distance threshold between path points; S82, For each cluster C i The improved Traveling Salesman Problem algorithm optimizes the path execution order to form the shortest path. The specific operation process is as follows: S8201. The goal is to find an optimal path sequence that minimizes the total path length from the starting point, through all path points, and back to the starting point. ； In the formula, D TSP Indicates the total length of the TSP path; d i,i+1 Represents path point p i to p i+1 The distance; n represents the number of path points within the cluster; S8202, Path selection probability, that is, the probability that an ant moves from path point i to path point j is: ； ； ； In the formula, τ ij This represents the pheromone concentration along the path i→j; η ij Represents the path heuristic factor; d ij Indicates path length; ψ ij Let ψ represent the safety constraint factor. If path i→j does not satisfy the safety radius constraint, then ψ ij <1, otherwise 1; α and β represent parameters controlling the weights of pheromones and heuristic factors; N i This represents the set of remaining points that the ant can currently visit; Pheromone updates, which refer to the changes in pheromone concentration over time, include pheromone evaporation and ant path contributions: ； ； In the formula, ρ represents the pheromone evaporation coefficient; Q represents the total amount of pheromone released; L k The 'm' represents the total length of the path traveled by ant k; the 'm' represents the number of ants. S83. By clustering routes and optimizing dynamic paths, the globally optimal temporary route P is obtained. best ={q1, q2, ..., q m } 8. A dynamic flight path planning system for a substation unmanned aerial vehicle (UAV), used to execute the dynamic flight path planning method for a substation UAV as described in any one of claims 1 to 7, characterized in that, include: The task input module is used to receive input information for patrol tasks and generate a set of target points as the basic data input for route planning. The route planning module is used to divide the target point into several sub-routes based on the input patrol point data, using route simplification and dynamic combination algorithms. It performs minimum path optimization on each sub-routes to generate a local optimal path. Then, it introduces all sub-routes into the safety point connection mechanism and uses dynamic programming algorithm to merge multiple sub-routes to form a complete optimal temporary route. The safety management module provides a safety point connection function during the flight of the UAV. Based on the mission requirements and safety radius threshold, it automatically introduces safety points at the start and end points of each flight path and calculates the shortest connection path between safety points during flight path optimization. The UAV execution module transmits the dynamic temporary flight path data generated by the flight path planning module to the UAV control system, controls the UAV to perform patrol tasks according to the planned optimal path in real time, achieves accurate arrival at the target point and data collection, and dynamically adjusts the flight path according to changes in the task. The AI ​​recognition module is responsible for processing the image and video data collected by the drone's execution module, uploading the data to the AI ​​analysis engine, using target recognition algorithms to intelligently identify and analyze the status of the patrol targets, automatically detect equipment anomalies, defects or safety hazards, and generate recognition result reports. The user terminal module provides a visual operation interface for the entire mission process, allowing users to view dynamic flight paths, equipment anomaly reports, and the real-time status of the UAV. It also enables users to quickly adjust the next patrol mission plan based on the recognition results, thus realizing the human-computer interaction function of the system.

Images