Remote inspection path generation method and system for wind driven generator blade group

Abstract

The invention relates to a remote inspection path generation method and system for a wind driven generator blade group. The method comprises the following steps: acquiring three-dimensional point cloud data, blade surface texture images, obstacle parameters and surrounding environment data of a target blade group; planning an initial inspection path covering the main area of the target blade group through an A star algorithm; and optimizing the initial inspection path according to the key part of the blade and the obstacle parameters to obtain a final inspection path. According to the remote inspection path generation method, the inspection point density is increased at the key part of the blade, and a reasonable path plan is constructed, so that the comprehensiveness of inspection of the blade set is ensured, and the problems of the blade set can be found in time; the inspection path is optimized through the A star algorithm, the time waste caused by repeated inspection is avoided, the inspection efficiency of the wind driven generator blade group is improved, manual inspection at the site is not needed, the investment of manpower and material resources is reduced, the inspection cost is reduced, and the inspection safety is improved.

Description

Technical Field

[0001] This invention belongs to the field of remote inspection technology, specifically relating to a method and system for generating remote inspection paths for wind turbine blade assemblies. Background Technology

[0002] Current methods for inspecting wind turbine blades include traditional manual inspection and some remote inspections. Traditional manual inspections are greatly affected by inclement weather, making it difficult to carry out the work smoothly. In addition, manual inspections require personnel to go to the site, which not only consumes a lot of manpower and resources and is costly, but also poses safety hazards during the inspection process. The existing remote inspection paths are not generated in a reasonable way, which seriously restricts the inspection effect. There is a phenomenon of repeated inspections, which causes inspection equipment such as drones to waste too much time and energy on invalid paths, resulting in low inspection efficiency and waste of resources. Furthermore, the generated paths have blind spots, which can easily miss critical parts such as blade roots and blade tips. These areas prone to failure cannot be fully inspected, making it difficult to fully grasp the blade condition. Consequently, the failure to detect hidden dangers in time may affect the normal operation of the wind turbine. Summary of the Invention

[0003] Based on the aforementioned problems in the existing technology, the purpose of this invention is to provide a method and system for generating remote inspection paths for wind turbine blades. By rationally planning and optimizing the inspection path, the time wasted due to repeated inspections and unreasonable paths is avoided, thereby improving the inspection efficiency of wind turbine blades, realizing remote inspection, reducing the input of manpower and material resources, and lowering the inspection cost.

[0004] To achieve the above objectives, the present invention adopts the following technical solution: A method for generating remote inspection paths for wind turbine blade assemblies, comprising: Step S1: Perform a full-range scan and photograph of the target blade group to obtain the three-dimensional point cloud data, blade surface texture image, obstacle parameters, and surrounding environment data of the target blade group; the obstacles include static obstacles and dynamic obstacles, and the obstacle parameters include obstacle position, obstacle movement speed, and obstacle volume; Step S2: Based on the three-dimensional point cloud data, the static obstacle information and the surrounding environment data, the A* algorithm is used to plan an initial inspection path covering the main area of ​​the target blade group, starting from the UAV takeoff point and taking the inspection points of the key parts of the target blade group as the waypoints. Step S3: Optimize the initial inspection path based on the key parts of the blade and the obstacle parameters to obtain the final inspection path.

[0005] A further improvement of the present invention is that the step S1 of acquiring the three-dimensional point cloud data, blade surface detail features, obstacle parameters, and surrounding environment data of the target blade group includes: The three-dimensional point cloud data and the static obstacle parameters are obtained by performing a full-view scan of the target blade group using a lidar sensor. Millimeter-wave radar is used to monitor dynamic obstacle parameters; The target blade group is photographed using a high-definition camera to obtain an image of the blade surface texture; The surrounding environmental data is collected using environmental monitoring equipment.

[0006] A further improvement of this invention is that the heuristic function of the A* algorithm in step S2 is: ; in, The actual flight distance from the starting point to the current node. This is the estimated Euclidean distance from the current node to the destination. is the priority coefficient for the key parts of the blade, and wind_factor is the wind field influence coefficient based on real-time wind speed.

[0007] A further improvement of the present invention is that, using the heuristic function of the A* algorithm, a circular path is generated covering all blade surfaces of the target blade group, including the leading edge, windward side, trailing edge, and leeward side, starting from the take-off and landing point of the UAV, ending at the center of the target blade group, and taking the inspection points of the key parts of the blade as the waypoints, to ensure that all surfaces of each blade are inspected in an adjacent order.

[0008] A further improvement of the present invention is that the step of optimizing the initial inspection path in step S3 to obtain the final inspection path includes: Increase the density of inspection points on key parts of the blade, adjust the direction and height of the initial inspection path to avoid obstacles, and smooth the initial inspection path. The key parts of the leaf include the leaf root, leaf tip, leading edge of the leaf, and trailing edge of the leaf.

[0009] A further improvement of the present invention is that the step of increasing the inspection point density of the key parts of the blade includes: adopting a dense sampling strategy in the leaf root, the leaf tip, and the leaf tip area, with a lateral spacing of 1 / 3 to 1 / 2 of the conventional area, setting 5 to 8 continuous inspection points in the longitudinal direction, and simultaneously adjusting the flight speed and dwell time of the UAV.

[0010] A further improvement of the present invention is that the step of adjusting the direction and height of the initial inspection path to avoid obstacles includes: employing... The algorithm generates a detour path when the dynamic obstacle enters a preset safe distance threshold, ensuring that the angle between the detour path and the initial inspection path does not exceed a preset angle. The preset safe distance threshold is dynamically set according to the type of obstacle.

[0011] A further improvement of the present invention is that the step of smoothing the initial inspection path adopts the B-spline curve algorithm to transform the polyline path into a continuous smooth curve path, so that the included angle of the tangents of adjacent path segments is controlled within a preset angle, and redundant points are removed from the initial inspection path, and duplicate inspection points with a distance less than a preset distance are deleted.

[0012] A remote inspection path generation system for wind turbine blade assemblies includes: The data acquisition module is used to perform a full-range scan and photograph of the target blade group, and acquire the three-dimensional point cloud data, blade surface texture image, obstacle parameters and surrounding environment data of the target blade group; the obstacles include static obstacles and dynamic obstacles, and the obstacle parameters include obstacle position, obstacle moving speed and obstacle volume; The path planning module is used to plan an initial inspection path covering the main area of ​​the target blade group based on the three-dimensional point cloud data and the surrounding environment data, using the A* algorithm, with the UAV take-off point as the starting point and the various inspection points of the key parts of the target blade group as the waypoints. The path optimization module is used to optimize the initial inspection path based on the key parts of the blade and the obstacle parameters to obtain the final inspection path. The control module is used to connect to the UAV, receive the final inspection path generated by the path optimization module and convert it into control commands, control the UAV to perform inspections according to the final inspection path, receive feedback data from the UAV in real time, and monitor and adjust the inspection process.

[0013] A computer-readable storage medium storing a computer program, which, when executed by a processor, implements the remote inspection path generation method for wind turbine blade assembly.

[0014] Compared with the prior art, the present invention has at least the following beneficial technical effects: This invention provides a method and system for generating remote inspection paths for wind turbine blade assemblies. The method includes comprehensively scanning and photographing the target blade assembly to acquire 3D point cloud data, blade surface texture images, obstacle parameters, and surrounding environmental data. Based on the 3D point cloud data, static obstacle information, and surrounding environmental data, an initial inspection path covering the main areas of the target blade assembly is planned using the A* algorithm. The initial inspection path is then optimized based on key blade components and obstacle parameters to obtain the final inspection path. This invention's remote inspection path generation method ensures comprehensive inspection of the blade assembly by increasing the density of inspection points at key blade components and constructing a reasonable path plan, enabling timely detection of problems. Optimizing the inspection path using the A* algorithm avoids wasted time due to repeated inspections, improves the inspection efficiency of wind turbine blade assemblies, eliminates the need for on-site inspections, reduces manpower and material resources, lowers inspection costs, and improves inspection safety. Attached Figure Description

[0015] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0016] Figure 1 This is a flowchart illustrating the remote inspection path generation method for wind turbine blade assembly according to Embodiment 1 of the present invention. Figure 2 This is a schematic diagram of the remote inspection path generation system for wind turbine blade assembly according to Embodiment 2 of the present invention. Detailed Implementation

[0017] In the following description, only certain exemplary embodiments are briefly described. As those skilled in the art will recognize, the described embodiments can be modified in various ways without departing from the spirit or scope of the invention. Therefore, the drawings and description are considered to be exemplary in nature and not restrictive.

[0018] In the description of this invention, it should be understood that, when used in this specification and the appended claims, the terms "comprising" and "including" indicate the presence of the described features, integrals, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0019] It should also be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0020] It should also be further understood that the term "and / or" as used in this specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0021] The accompanying drawings illustrate various structural schematic diagrams according to embodiments disclosed in this invention. These drawings are not to scale, and some details have been enlarged for clarity, and some details may have been omitted. The shapes of the various regions and layers shown in the drawings, as well as their relative sizes and positional relationships, are merely exemplary and may deviate from reality due to manufacturing tolerances or technical limitations. Furthermore, those skilled in the art can design regions / layers with different shapes, sizes, and relative positions as needed.

[0022] The embodiments of the present invention will now be described in detail with reference to the accompanying drawings.

[0023] Example 1 like Figure 1 As shown, this embodiment provides a method for generating remote inspection paths for wind turbine blade assemblies. The method includes: Step S1: Perform a full-range scan and photograph of the target blade group to obtain the three-dimensional point cloud data, blade surface texture image, obstacle parameters, and surrounding environment data of the target blade group; obstacles include static obstacles and dynamic obstacles, and obstacle parameters include obstacle position, obstacle movement speed, and obstacle volume.

[0024] In this embodiment, step S1, acquiring the 3D point cloud data, detailed features of the blade surface, obstacle parameters, and surrounding environment data of the target blade group, includes: obtaining 3D point cloud data by performing a full-range scan of the target blade group using a lidar sensor, clarifying the blade's geometric dimensions (length, chord length, twist angle), spatial attitude, and overall structure, providing a digital target for path planning; and static obstacle parameters, using the obstacle penetration detection mechanism of the AlphaGo algorithm to ensure that the initial path avoids fixed obstacles from the design stage, avoiding the risk of drone collisions; adjusting the starting point and waypoint order of the initial path through the spatial layout of the static environment data to make the global path more consistent with the site layout; and using millimeter-wave radar to monitor dynamic obstacle parameters, monitoring surrounding birds, drones, and other dynamic obstacles, updating the safety distance threshold to trigger the dynamic avoidance mechanism in path optimization, and when an obstacle enters the safety distance threshold, the system will automatically avoid it. The algorithm generates real-time detour paths to ensure the drone maintains a safe distance from dynamic obstacles and avoids collisions. High-definition cameras capture images of the target blade assembly to obtain blade surface texture images, which are used to mark stress concentration areas such as blade root bolt connections, vulnerable areas such as the leading edge sandstorm impact zone, and high-wear areas such as the high-speed operating area at the blade tip. This provides a basis for path optimization, ensuring that the inspection point density, dwell time, and shooting angle in these high-risk areas are suitable for defect detection requirements. Environmental monitoring equipment collects surrounding environmental data to dynamically adjust flight parameters.

[0025] Step S2: Based on 3D point cloud data, static obstacle information and surrounding environment data, the A* algorithm is used to plan an initial inspection path covering the main area of ​​the target blade group, starting from the UAV takeoff point and taking the inspection points of the key parts of the target blade group as the waypoints.

[0026] In this embodiment, based on three-dimensional point cloud data, an edge detection algorithm is used to extract the boundary coordinates of 12 key parts, such as the leaf root, leaf tip, leading edge of the blade, and trailing edge of the blade, and these are marked as stress concentration areas. The three-dimensional point cloud data collected by the lidar sensor is converted into a 1m×1m×1m three-dimensional grid map, and no-fly zones (such as within a 5m radius of the tower) are marked. The data volume is compressed using an octree algorithm to improve computational efficiency.

[0027] In this embodiment, using the heuristic function of the A* algorithm, a circular path is generated covering all blade surfaces of the target blade assembly, including the leading edge, windward side, trailing edge, and leeward side, starting from the UAV's take-off and landing point, ending at the center of the target blade assembly, and using various inspection points on key parts of the blade as waypoints. This ensures that all surfaces of each blade are inspected in adjacent order. By marking no-fly zones for static obstacles such as towers and supports on a 3D grid map, insurmountable global constraints are set for subsequent path optimization, such as always maintaining a distance of more than 5 meters from the tower, to avoid drastic route deviations during the optimization process.

[0028] As an optional implementation, the heuristic function of the A* algorithm is: ; in, The actual flight distance from the starting point to the current node. This is the estimated Euclidean distance from the current node to the destination. Here, `wind_factor` is the priority coefficient for key parts of the blade, and `wind_factor` is the wind field influence coefficient based on real-time wind speed. In areas such as the blade root and tip, the heuristic function is multiplied by 1.2 times the priority coefficient to guide the initial inspection path to prioritize covering high-risk areas.

[0029] As an optional implementation, the step of setting insurmountable global constraints for subsequent path optimization specifically includes: dividing the blade group space into a 0.5m × 0.5m × 0.5m cubic grid, where each node contains attributes such as coordinates, obstacle status, and wind influence coefficient. The system allows the UAV to move in eight directions (±x, ±y, ±z, ±45° diagonal) with a step size of 0.5m, avoiding path redundancy in traditional four-neighbor search. When expanding nodes, a ray casting algorithm is used to verify whether a new node is located inside an obstacle; if it penetrates, the node is skipped.

[0030] Step S3: Optimize the initial inspection path based on the parameters of key blade components and obstacles to obtain the final inspection path. In this embodiment, the initial inspection path is generated based on static data during planning, such as preset wind fields and fixed obstacle positions. This cannot cope with real-time changes, such as sudden gusts and dynamic obstacles like birds, and has limitations. Further optimization of the inspection path is needed. This embodiment uses real-time data from millimeter-wave radar and weather stations to dynamically adjust the direction in local sections of the initial inspection path, such as the upwind flight section, to avoid birds that suddenly intrude, or the speed, such as slowing down to 6 m / s in upwind conditions, to adapt the path to the dynamic environment. Specifically, the steps in step S3 to optimize the initial inspection path to obtain the final inspection path include: increasing the inspection point density of key blade components, adjusting the direction and height of the initial inspection path to avoid obstacles, and smoothing the initial inspection path; wherein, the key blade components include the blade root, blade tip, blade leading edge, and blade trailing edge.

[0031] As an optional embodiment, increasing the density of inspection points on key parts of the blade involves employing a dense sampling strategy in the blade root and tip areas. The lateral spacing is 1 / 3 to 1 / 2 of that in conventional areas, and 5 to 8 consecutive inspection points are set vertically. Simultaneously, the drone's flight speed and dwell time are adjusted. Specifically, in the blade width direction, the spacing between inspection points on key parts such as the blade root and tip is reduced from the conventional 1m to 0.3m, and continuous inspection sections are set vertically, for example, 5 consecutive points in the blade root area, to ensure that the lidar point cloud density reaches 20 points / cm². In high-speed wear areas such as the blade tip, the drone's flight speed is reduced to 60%-80% of the conventional speed, and the dwell time at a single point is extended to 2 seconds to ensure that the high-definition camera captures surface cracks down to 0.2mm. Simultaneously, for the blade leading edge, which is susceptible to wind and sand impact, the drone can be set to take pictures from four directions: ±30° and ±60°, to avoid missing inspections from a single perspective. The leaf was vertically divided into three layers: upper, middle, and lower. The upper layer was photographed at a 45° upward angle, the middle layer at a horizontal angle, and the lower layer at a 30° downward angle to ensure that there were no blind spots in the trailing edge area of ​​the leaf.

[0032] As an optional embodiment, the step of adjusting the direction and height of the initial inspection path to avoid obstacles is achieved by adopting... The algorithm generates a detour path when a dynamic obstacle enters a preset safe distance threshold, ensuring that the angle between the detour path and the initial inspection path does not exceed a preset angle. The preset safe distance threshold is dynamically set according to the obstacle type. The preset angle can be set to 30°; the safe distance threshold can be set to 5m for static obstacles and 10m for dynamic obstacles. In this embodiment, in addition to avoiding dynamic obstacles, the initial inspection path is also modified for wind field adaptability by combining real-time wind speed and direction data collected from the weather station. This includes dividing the initial inspection path into headwind (wind speed > 8m / s), crosswind (wind speed 5-8m / s), and tailwind (wind speed < 5m / s) sections, and specifically adjusting the drone's flight speed for headwind deceleration and tailwind acceleration, as well as its attitude such as controlling the tilt angle, to avoid inspection path deviation or inspection time delays caused by wind field interference, ensuring that the overall inspection task time deviation is controlled within 5%.

[0033] As an optional embodiment, the step of smoothing the initial inspection path adopts the B-spline curve algorithm to transform the polygonal path into a continuous smooth curve path, so that the tangent angle between adjacent path segments is controlled within a preset angle, and redundant points are removed from the initial inspection path, and duplicate inspection points with a distance less than a preset distance are deleted; specifically, the tangent angle between adjacent path segments is controlled within 15°, and redundant points are removed from the path, and duplicate inspection points with a distance less than 0.5 meters are deleted to reduce the number of turns and turning angle of the UAV.

[0034] This embodiment provides a method for generating remote inspection paths for wind turbine blade assemblies. This method increases the density of inspection points at key parts of the blades and constructs a reasonable path plan, ensuring comprehensive inspection of the blade assembly and enabling timely detection of problems. By optimizing the inspection path using the A* algorithm, time wasted due to repeated inspections is avoided, improving the inspection efficiency of wind turbine blade assemblies. This eliminates the need for on-site inspections, reducing manpower and material costs, lowering inspection costs, and enhancing inspection safety.

[0035] Example 2 like Figure 2 As shown, this embodiment provides a remote inspection path generation system 10 for wind turbine blade assembly. The remote inspection path generation system includes: a data acquisition module 11, a path planning module 12, a path optimization module 13, and a control module 14.

[0036] The data acquisition module 11 is used to perform a full-range scan and photograph of the target blade group to obtain the three-dimensional point cloud data of the target blade group, the blade surface texture image, obstacle parameters and surrounding environment data; the obstacles include static obstacles and dynamic obstacles, and the obstacle parameters include obstacle position, obstacle moving speed and obstacle volume.

[0037] The path planning module 12 is used to plan an initial inspection path covering the main area of ​​the target blade group based on 3D point cloud data and surrounding environment data, using the A* algorithm, with the UAV take-off point as the starting point and various inspection points of the key parts of the target blade group as the waypoints.

[0038] The path optimization module 13 is used to optimize the initial inspection path based on the parameters of key parts of the blade and obstacles to obtain the final inspection path.

[0039] The control module 14 is used to connect with the UAV, receive the final inspection path generated by the path optimization module and convert it into control commands, control the UAV to perform inspections according to the final inspection path, and receive feedback data from the UAV in real time to monitor and adjust the inspection process.

[0040] This embodiment provides a remote inspection path generation system for wind turbine blade assemblies. This system is based on the remote inspection path generation method for wind turbine blade assemblies provided in Embodiment 1 above; specific details are not repeated here. This system increases the density of inspection points at key blade locations and constructs a reasonable path plan, ensuring comprehensive inspection of the blade assembly and enabling timely detection of problems. By optimizing the inspection path using the A* algorithm, it avoids wasting time due to repeated inspections, improving the inspection efficiency of wind turbine blade assemblies. It eliminates the need for on-site inspections, reducing manpower and material resources, lowering inspection costs, and enhancing inspection safety.

[0041] Example 3 This embodiment relates to a computer-readable storage medium storing a computer program. When executed by a processor, the computer program implements the remote inspection path generation method for wind turbine blade assembly described in Embodiment 1 above.

[0042] That is, those skilled in the art will understand that all or part of the steps in the methods of the above embodiments can be implemented by a program instructing related hardware. This program is stored in a storage medium and includes several instructions to cause a device (which may be a microcontroller, chip, etc.) or processor to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0043] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above, and that the invention can be implemented in other specific forms without departing from its spirit or essential characteristics. Therefore, the embodiments should be considered illustrative and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be included within the scope of the invention. No reference numerals in the claims should be construed as limiting the scope of the claims.

[0044] Furthermore, it should be understood that although this specification describes embodiments, not every embodiment contains only one independent technical solution. This narrative style is merely for clarity. Those skilled in the art should consider the specification as a whole, and the technical solutions in each embodiment can be appropriately combined to form other embodiments that can be understood by those skilled in the art. The above content is only for illustrating the technical concept of the present invention and should not be construed as limiting the scope of protection of the present invention. Any modifications made based on the technical concept proposed in this invention shall fall within the scope of protection of the claims of this invention.

Claims

1. A method for generating remote inspection paths for wind turbine blade assemblies, characterized in that, include: Step S1: Perform a full-range scan and photograph of the target blade group to obtain the three-dimensional point cloud data, blade surface texture image, obstacle parameters, and surrounding environment data of the target blade group; the obstacles include static obstacles and dynamic obstacles, and the obstacle parameters include obstacle position, obstacle movement speed, and obstacle volume; Step S2: Based on the three-dimensional point cloud data, the static obstacle information and the surrounding environment data, the A* algorithm is used to plan an initial inspection path covering the main area of ​​the target blade group, starting from the UAV takeoff point and taking the inspection points of the key parts of the target blade group as the waypoints. Step S3: Optimize the initial inspection path based on the key parts of the blade and the obstacle parameters to obtain the final inspection path.

2. The method for generating remote inspection paths for wind turbine blade assemblies according to claim 1, characterized in that, The steps of obtaining the three-dimensional point cloud data, blade surface detail features, obstacle parameters, and surrounding environment data of the target blade group in step S1 include: The three-dimensional point cloud data and the static obstacle parameters are obtained by performing a full-view scan of the target blade group using a lidar sensor. Millimeter-wave radar is used to monitor dynamic obstacle parameters; The target blade group is photographed using a high-definition camera to obtain an image of the blade surface texture; The surrounding environmental data is collected using environmental monitoring equipment.

3. The method for generating remote inspection paths for wind turbine blade assemblies according to claim 1, characterized in that, The heuristic function of the A* algorithm in step S2 is: ; in, The actual flight distance from the starting point to the current node. This is the estimated Euclidean distance from the current node to the destination. is the priority coefficient for the key parts of the blade, and wind_factor is the wind field influence coefficient based on real-time wind speed.

4. The method for generating remote inspection paths for wind turbine blade assemblies according to claim 3, characterized in that, Using the heuristic function of the A* algorithm, a circular path is generated covering all blade surfaces of the target blade group, including the leading edge, windward side, trailing edge, and leeward side, starting from the take-off and landing point of the UAV, ending at the center of the target blade group, and taking each inspection point of the key parts of the blade as a path point, to ensure that all surfaces of each blade are inspected in adjacent order.

5. The method for generating remote inspection paths for wind turbine blade assemblies according to claim 1, characterized in that, The step S3, which optimizes the initial inspection path to obtain the final inspection path, includes: Increase the density of inspection points on key parts of the blade, adjust the direction and height of the initial inspection path to avoid obstacles, and smooth the initial inspection path. The key parts of the leaf include the leaf root, leaf tip, leading edge of the leaf, and trailing edge of the leaf.

6. The method for generating remote inspection paths for wind turbine blade assemblies according to claim 5, characterized in that, The step of increasing the inspection point density of the key parts of the blade includes: adopting a dense sampling strategy in the leaf root, leaf tip and leaf tip areas, with a horizontal spacing of 1 / 3 to 1 / 2 of the conventional area, setting 5 to 8 continuous inspection points in the vertical direction, and simultaneously adjusting the flight speed and dwell time of the UAV.

7. The method for generating remote inspection paths for wind turbine blade assemblies according to claim 5, characterized in that, The step of adjusting the direction and height of the initial inspection path to avoid obstacles includes: using The algorithm generates a detour path when the dynamic obstacle enters a preset safe distance threshold, ensuring that the angle between the detour path and the initial inspection path does not exceed a preset angle. The preset safe distance threshold is dynamically set according to the type of obstacle.

8. The method for generating remote inspection paths for wind turbine blade assemblies according to claim 5, characterized in that, The step of smoothing the initial inspection path uses a B-spline curve algorithm to transform the polyline path into a continuous smooth curve path, so that the included angle of the tangents of adjacent path segments is controlled within a preset angle, and redundant points are removed from the initial inspection path, and duplicate inspection points with a distance less than a preset distance are deleted.

9. A remote inspection path generation system for wind turbine blade assembly, characterized in that, include: The data acquisition module is used to perform a full-range scan and photograph of the target blade group, and acquire the three-dimensional point cloud data, blade surface texture image, obstacle parameters and surrounding environment data of the target blade group; the obstacles include static obstacles and dynamic obstacles, and the obstacle parameters include obstacle position, obstacle moving speed and obstacle volume; The path planning module is used to plan an initial inspection path covering the main area of ​​the target blade group based on the three-dimensional point cloud data and the surrounding environment data, using the A* algorithm, with the UAV take-off point as the starting point and the various inspection points of the key parts of the target blade group as the waypoints. The path optimization module is used to optimize the initial inspection path based on the key parts of the blade and the obstacle parameters to obtain the final inspection path. The control module is used to connect to the UAV, receive the final inspection path generated by the path optimization module and convert it into control commands, control the UAV to perform inspections according to the final inspection path, receive feedback data from the UAV in real time, and monitor and adjust the inspection process.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the remote inspection path generation method for wind turbine blade assembly as described in any one of claims 1 to 8.

Images