Path planning method and system for routing inspection of front and back sides of blade in fan shutdown state

Abstract

The invention provides a path planning method and system for routing inspection of the front and back sides of a blade in a fan shutdown state. The method comprises the steps that a camera holder obtains images of a fan hub and a blade root part in a visual field based on the pitch angle and the rotation angle of the camera holder; identifying the blade root contour and the hub position through image segmentation, further obtaining the hub center point and the blade root center point, and then calculating the direction vector of the blade in the image; the direction vector of the blade root in the space is calculated, and the attitude of the wind driven generator is obtained; calculating the orientation of the wind driven generator; calculating space coordinates of a path center point and three blade tip points based on the attitude of the wind driven generator; preliminarily generating a path point sequence along the length of the blade according to the calculated coordinates of the center point of the path and the space coordinates of the tip point of the blade; and the unmanned aerial vehicle flies along the generated path point sequence along the length of the blade, and dynamically corrects the flight path by tracking the blade in real time to ensure that the blade is always located in the visual field of the camera.

Description

Technical Field

[0001] The present invention belongs to the technical field of inspection of wind turbine blades based on unmanned aerial vehicles (UAVs), and particularly relates to a path planning method and system for inspecting the front and back sides of blades in the shutdown state of a wind turbine. Background Art

[0002] The statements in this part merely provide background technical information related to the present invention and do not necessarily constitute prior art.

[0003] During long-term operation, wind turbine blades are vulnerable to environmental erosion and mechanical fatigue, resulting in surface damage (such as cracks, corrosion, etc.). Traditional inspections rely on manual climbing or fixed cameras, which have defects such as low efficiency, high risk, and incomplete coverage.

[0004] In recent years, UAV inspection technology has been gradually applied. For example, in the prior art, a UAV flies to the top of a wind turbine and determines the orientation of the wind turbine by taking a top view, or the UAV flies around the wind turbine and determines the orientation of the wind turbine by the blade length under different perspectives.

[0005] The above methods all require the UAV to perform additional actions, thereby reducing the endurance of the UAV. At the same time, these methods all need to detect the tip position of the blade, and the tip position is difficult to detect in the picture, and the detection accuracy cannot be guaranteed. In short, the existing solutions have the following problems:

[0006] The UAV usually takes a long time to determine the attitude of the wind turbine, reducing the endurance of the UAV and making the attitude recognition step cumbersome.

[0007] The UAV depends on a preset path, resulting in the UAV flying mostly along a fixed path and being unable to adapt to the slight rotation or bending of the blade in the shutdown state.

[0008] Existing methods mostly target one side (front or back) of the blade, and the one-sided coverage is limited, making it difficult to achieve comprehensive detection.

[0009] The displacement of the blade caused by wind force or structural deformation leads to the deviation of the inspection path, and dynamic correction cannot be achieved, and manual intervention is still required. Summary of the Invention

[0010] To overcome the deficiencies of the above prior art, the present invention provides a path planning method for inspecting the front and back sides of blades in the shutdown state of a wind turbine, which can autonomously plan a path, dynamically correct deviations, and cover the front and back sides of the blades for UAV inspection.

[0011] To achieve the above object, one or more embodiments of the present invention provide the following technical solutions:

[0012] In the first aspect, a path planning method for inspecting the front and back sides of blades in the shutdown state of a wind turbine is disclosed, including:

[0013] The camera gimbal acquires images of the fan hub and blade root parts within the field of view based on the pitch angle and rotation angle it is in;

[0014] Through image segmentation, the blade root contour and hub position are recognized, and further the hub center point and blade root center point are obtained, and then the direction vector of the blade in the picture is calculated;

[0015] The direction vector of the blade root in space is calculated to obtain the attitude of the wind turbine; the orientation of the wind turbine is calculated;

[0016] Based on the attitude of the wind turbine, the spatial coordinates of the path center point and the three blade tip points are calculated;

[0017] According to the calculated path center point coordinates and the spatial coordinates of the blade tip points, a path point sequence along the blade length is initially generated;

[0018] The drone flies along the generated path point sequence along the blade length, and dynamically corrects the flight path by tracking the blade in real time to ensure that the blade is always within the camera's field of view.

[0019] As a further technical solution, the method for obtaining the pitch angle and rotation angle of the camera gimbal is as follows:

[0020] The camera lens of the camera gimbal carried on the drone is directed towards the direction of the wind turbine nacelle;

[0021] According to the flight altitude of the drone, the hub altitude of the wind turbine, the drone's GPS coordinates and the wind turbine's GPS coordinates, the pitch angle α of the camera gimbal is calculated, and the pitch angle of the camera gimbal is adjusted to α;

[0022] According to the drone's GPS coordinates and the wind turbine's GPS coordinates, the rotation angle β of the camera gimbal is calculated, and the rotation angle of the camera gimbal is adjusted to β.

[0023] As a further technical solution, the calculation process of the pitch angle of the camera gimbal is as follows:

[0024]

[0025] Among them, the flight altitude h of the drone 无人机 , the hub altitude h of the wind turbine 风电 , the drone's GPS coordinates (φ 无人机 , λ 无人机 ) and the wind turbine's GPS coordinates φ is the latitude, λ is the longitude, and d is the straight-line distance between the drone and the wind turbine, which can be directly calculated from the GPS coordinates of the drone and the wind turbine.

[0026] As a further technical solution, the rotation angle of the camera pan-tilt is β, and the calculation process is as follows:

[0027]

[0028] Among them, the GPS coordinates of the UAV (φ 无人机 , λ 无人机 ) and the GPS coordinates of the wind turbine (φ 风电 , λ 风电 ), where φ is the latitude, λ is the longitude, and d is the straight-line distance between the UAV and the wind turbine, which can be directly calculated from the GPS coordinates of the UAV and the wind turbine.

[0029] As a further technical solution, it also includes the step of calculating the direction vector of the camera optical axis according to the lens direction:

[0030] Establish a fixed coordinate system OXYZ, with the positive direction of the Z-axis vertically upward, the positive direction of the X-axis due east, and the positive direction of the Y-axis due south;

[0031] The direction vector of the camera optical axis is obtained after the above rotation of the due-north direction vector, and the direction vector of the camera optical axis can be obtained;

[0032] The calculated direction vector of the camera optical axis is the normal vector of the lens plane.

[0033] As a further technical solution, when calculating the attitude of the wind turbine, let the direction vector of the wind turbine blade root in the fixed coordinate system be Based on the calculated direction vector of the camera optical axis being Obtain the direction vector of the wind turbine blade root in the fixed coordinate system, solve to obtain the direction vector of the blade root in space, and thus obtain the pose of the wind turbine.

[0034] In the second aspect, a path planning system for inspecting the front and back sides of the blades in the shutdown state of the wind turbine is disclosed, including:

[0035] An image acquisition module, configured to: The camera pan-tilt acquires images of the wind turbine hub and blade root parts within the field of view based on the pitch angle and rotation angle;

[0036] An image segmentation module, configured to: Identify the blade root contour and hub position through image segmentation, further obtain the hub center point and blade root center point, and then calculate the direction vector of the blade in the picture;

[0037] A wind turbine attitude acquisition module, configured to: Calculate the direction vector of the blade root in space, obtain the wind turbine attitude; Calculate the orientation of the wind turbine;

[0038] A path point sequence generation module along the blade length, configured to: calculate the spatial coordinates of the path center point and three blade tip points based on the attitude of the wind turbine;

[0039] Based on the calculated path center point coordinates and the spatial coordinates of the blade tip points, preliminarily generate a path point sequence along the blade length;

[0040] An inspection module, configured to: the unmanned aerial vehicle flies along the generated path point sequence along the blade length, and dynamically corrects the flight path by real-time tracking of the blade to ensure that the blade is always within the camera's field of view.

[0041] The above one or more technical solutions have the following beneficial effects:

[0042] The technical solution of the present invention depends on simple conditions: only simple photos of the wind turbine and the viewing angle when the unmanned aerial vehicle takes photos are required, and the photos contain partial areas of the wind turbine hub and three blades.

[0043] The technical solution of the present invention is a multi-modal positioning technology: it integrates GPS coordinates, machine vision and mathematical calculations to accurately locate the wind turbine orientation and blade position.

[0044] The technical solution of the present invention is dynamic path correction: by combining real-time tracking of the blade position, it adapts to the dynamic changes of the blade.

[0045] The technical solution of the present invention realizes seamless connection between the front and back sides: through back side coordinate calculation and pan-tilt angle adjustment, it realizes single-flight coverage of double-sided inspection of the blade, simplifies the process and improves the accuracy.

[0046] The technical solution of the present invention is a closed-loop inspection logic: it automatically switches the blade and the front and back sides, reduces manual intervention and improves efficiency.

[0047] Advantages of additional aspects of the present invention will be partly given in the following description, partly will become obvious from the following description, or will be learned through the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] The specification drawings forming a part of the present invention are used to provide a further understanding of the present invention. The schematic embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation to the present invention.

[0049] Figure 1 It is a schematic flow diagram of a method for generating an unmanned aerial vehicle inspection path for a wind turbine in this application;

[0050] Figure 2 It is a schematic structural diagram of a wind turbine in this application;

[0051] Figure 3 It is a schematic position diagram of an unmanned aerial vehicle photographing a wind turbine in this application;

[0052] Figure 4 This is a schematic diagram of the photo taken when the UAV of the present application performs pose recognition.

[0053] Figure 5 This is a schematic diagram of the center point of the wind turbine blade root and the center point of the hub in the photo taken by the UAV of the present application.

[0054] Figure 6 This is a schematic diagram of the path planning of the UAV of the present application. Detailed implementation manners

[0055] It should be noted that the following detailed description is exemplary and is intended to provide further illustration of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which the present invention belongs.

[0056] It should be noted that the terms used herein are only for describing specific implementation manners and are not intended to limit the exemplary embodiments according to the present invention.

[0057] In the case of no conflict, the embodiments in the present invention and the features in the embodiments can be combined with each other.

[0058] Embodiment 1

[0059] Referring to Figure 1-6 As shown, to achieve fully automated intelligent inspection of wind turbines, this embodiment discloses a path planning method for inspecting the front and back sides of blades in the shutdown state of the wind turbine, including:

[0060] Using the UAV to take pictures to calculate the orientation of the wind turbine and the position of the fan blades, and further planning the inspection path of the UAV to achieve the operation of "autonomous flight and automatic planning".

[0061] The UAV model selected in this embodiment is DJI MAVIC 3T. This UAV is equipped with a gimbal and a camera, and is equipped with an RTK high-precision positioning device. This UAV has an obstacle avoidance function.

[0062] The selected UAV takes off and flies to a certain height. According to the coordinates of the UAV and the coordinates of the wind turbine, the gimbal angle is adjusted so that the hub and blade root parts of the wind turbine are within the camera's field of view, and the hub and blade root parts can be clearly photographed.

[0063] There are two methods for image processing. One can directly rely on the calculation module of the UAV for recognition, and the other can transmit the taken pictures to the ground station for processing on the ground station. Both methods are acceptable, depending on the function of the calculation module of the selected UAV.

[0064] Identify the hub and blade root in the photo through image segmentation technology, such as yolov8. And calculate the center points of the hub and blade root and the direction vector of the blade root in the photo through key point recognition technology.

[0065] Calculate the direction vector of the blade in the space coordinate system based on the camera optical axis direction vector when the drone takes the photo and the direction vector of the blade root in the photo.

[0066] Identify the front and back sides of the wind turbine in the photo through a neural network, and combine with the direction vector of the blade to obtain the pose of the wind turbine.

[0067] Generate the drone inspection path points based on the calculated pose and the wind turbine coordinates.

[0068] The drone flies along the path points and tracks the blade in real time, dynamically correcting the flight path to ensure that the blade is always within the camera's field of view.

[0069] When the above method is specifically implemented, it includes:

[0070] Step 1: Determine the attitude of the wind turbine

[0071] Step S1-1: The drone flies to a certain height. Initialize the pitch angle and rotation angle of the camera gimbal. The initial values are that both the pitch angle and rotation angle of the camera gimbal are 0°, that is, the camera lens is facing due north, and the camera lens focal length is the default value l0.

[0072] Step S1-2: According to the flight height h of the drone 无人机 , the hub height h of the wind turbine 风电 , the drone GPS coordinates (φ 无人机 , λ 无人机 ) and the wind turbine GPS coordinates (φ 风电 , λ 风电 ) (note that φ is the latitude and λ is the longitude), calculate the pitch angle α of the camera gimbal. Adjust the pitch angle of the camera to α.

[0073]

[0074] where d is the straight-line distance between the drone and the wind turbine. For small-sized wind turbines, the influence of the earth's surface curvature can be ignored. x = Rcosφcosλ, y = Rcosφsinλ, z = Rsinφ, where R is the average radius of the earth.

[0075] Step S1-3: Calculate the rotation angle β of the camera gimbal according to the drone GPS coordinates and the wind turbine GPS coordinates. Adjust the rotation angle of the camera gimbal to β:

[0076]

[0077] Step S1-4: After steps S1-1 to S1-3, the camera is now facing the nacelle of the wind turbine. Identify the nacelle through a neural network and adjust the camera focal length according to the ratio of the length / height of the nacelle frame in the picture to the image, so that it can clearly capture the nacelle, hub, and blade root. The adjusted focal length l1 = min(k × l0 × min(width 图像 / width 机舱 ,height 图像 / width 机舱 ),l max ), where k is the focal length adjustment coefficient, set according to the actual situation, and l max is the maximum focal length of the camera. If the wind turbine blade is blocked by the tower, the UAV needs to adjust its position and repeat the previous process until the nacelle, hub, and blade root can be clearly captured.

[0078] Step S1-5: Calculate the camera optical axis direction vector according to the lens direction:

[0079] Establish a fixed coordinate system OXYZ, with the positive direction of the Z-axis being vertically upward, the positive direction of the X-axis being due east, and the positive direction of the Y-axis being due south.

[0080] The camera optical axis direction vector is the due north direction vector Obtained after rotation in steps S1-2 and S1-3. Thus, the camera optical axis direction vector can be obtained as

[0081]

[0082] The calculated camera optical axis direction vector is the normal vector of the lens plane.

[0083] Step S1-6: Identify the blade root contour and hub position through image segmentation technology (such as yolov8), and further obtain the hub center point and blade root center point through key point recognition technology. Calculate the direction vector of the blade in the picture for subsequent step calculations. Assume that the pixel coordinates of the center point of a certain blade root in the picture are p 叶根i = (x 叶根i ,y 叶根i ), and the pixel coordinates of the hub center point in the picture are p 轮毂 = (x 轮毂 ,y 轮毂 ), and its direction vector is where i = 1, 2, 3.

[0084] Step S1-7: Judge the front and back of the wind turbine in the image through a neural network (such as ResNet18 network), that is, judge which quadrant in the XOY plane the orientation of the wind turbine points to.

[0085] The input is a photo of the wind turbine taken by the camera at this time;

[0086] The feature extraction layer can adopt a residual network module (such as the convolutional layer group of ResNet18) or a combination of traditional convolutional modules. After each convolutional layer, a batch normalization layer and a ReLU activation function are connected;

[0087] The classifier consists of a global average pooling layer, a fully connected layer, and a Softmax output layer. The output dimension corresponds to 4 direction categories: the first quadrant (the wind turbine faces the upper left in the photo), the second quadrant (the wind turbine faces the upper right in the photo), the third quadrant (the wind turbine faces the lower right in the photo), and the fourth quadrant (the wind turbine faces the lower left in the photo).

[0088] In this embodiment, the neural network used is the trained ResNet18 network. During training, images of multiple wind turbines when they are shut down are collected. The images should include partial areas of the wind turbine hub and three blades. The collected images are preprocessed to delete duplicate and non-compliant images, and then labeled. When labeling, according to the orientation of the wind turbine in the recognized image, it is labeled as facing the first quadrant (the wind turbine faces the upper left in the photo), facing the second quadrant (the wind turbine faces the upper right in the photo), the third quadrant (the wind turbine faces the lower right in the photo), and the fourth quadrant (the wind turbine faces the lower left in the photo). Specifically, when the wind turbine faces the first quadrant, the label of the image is (1 0 0 0); when the wind turbine faces the second quadrant, the label of the image is (0 1 0 0); when the wind turbine faces the third quadrant, the label of the image is (0 0 1 0); when the wind turbine faces the fourth quadrant, the label of the image is (0 0 0 1).

[0089] The labeled and processed images are divided into a training set and a test set. The training set is used to train the ResNet18 network to obtain the trained ResNet18 network, and then the test set is used for testing until the requirements are met to obtain the final trained ResNet18 network.

[0090] Step S1-8: Calculate the attitude of the wind turbine. Assume that the direction vector of the wind turbine blade root in the fixed coordinate system is And the direction vector of the optical axis of the camera calculated in step S1-5 is Therefore, the direction vector of the wind turbine blade root in the fixed coordinate system can be expressed by the following formula. Where a, b, and c are unknowns to be solved.

[0091]

[0092] At the same time, the angles between these three direction vectors are 120° to each other. Therefore, it can be obtained that

[0093]

[0094] That is

[0095]

[0096] By solving these three equations, the values of the unknowns a, b, and c can be obtained. Furthermore, the direction vector of the blade root in space can be obtained, and thus the pose of the wind turbine can be obtained.

[0097] Step S1-9: Calculate the direction vector of the orientation of the wind turbine. The direction vector of the orientation of the wind turbine in the fixed coordinate system can be calculated by the following formula. Since the three blade direction vectors are in the same plane and this plane is perpendicular to the horizontal plane, any two direction vectors can be selected for calculation, and this direction vector must be in the horizontal plane.

[0098]

[0099] Step S1-10: Calculate the orientation of the wind turbine. Calculate the angle γ between the direction vector of the orientation and the due north direction.

[0100]

[0101] Then, combine with Step S1-7 to determine the orientation of the wind turbine. Taking the camera facing north as an example, if the orientation of the wind turbine in the photo points to the first quadrant, the orientation of the wind turbine is east of north by γ; if it points to the second quadrant, the orientation of the wind turbine is east of north by (360° - γ); if it points to the third quadrant, the orientation of the wind turbine is east of north by (180° + γ); if it points to the fourth quadrant, the orientation of the wind turbine is east of north by (180° - γ).

[0102] Step Two: Path Planning and Dynamic Correction

[0103] Step S2-1: Assume the length of the wind turbine blade is l. The spatial coordinates of the path center point and the three blade tip points can be calculated based on the pose of the wind turbine obtained from Steps S1-1 to S1-10. The calculation method is as follows:

[0104] Coordinates of the path center point on the front of the wind turbine: Coordinates of the path center point on the back of the wind turbine: where P 风电 =(x 风电 , y 风电 , h 风电 ), k is a positive parameter that can be set according to the size of the wind turbine. It is necessary to ensure that the UAV is at a certain distance from the wind turbine while being able to clearly capture the damage condition on the blade surface. Generally, k can be taken as twice the length of the nacelle. The judgment of the front and back sides needs to be combined with Step S1-7

[0105] Spatial coordinates of the tip points of the three blades on the front of the fan: Spatial coordinates of the tip points of the three blades on the back of the fan: where i = 1, 2, 3.

[0106] Step S2-2: According to the calculated path center point coordinates and the spatial coordinates of the blade tip points, preliminarily generate a sequence of path points along the blade length, and the number of path points can be adjusted.

[0107] Taking the inspection of the front of one blade by the UAV as an example, the path center point coordinates of the front of the fan calculated according to Step S2-1 are The spatial coordinates of the tip points of the front blade are Then the generated path point coordinates are where m is the number of generated path points and n is the path point serial number.

[0108] Step S2-3: The UAV flies along the generated path points and dynamically corrects the flight path by continuously tracking the blade to ensure that the blade is always within the camera's field of view.

[0109] Detect the position of the blade contour in the image through machine vision. When the blade contour is on the left side of the image, the UAV flies to the left. When the blade contour is on the right side of the image, the UAV flies to the right. The UAV combines the generated path points and image detection to dynamically correct the flight path to ensure that the blade contour is always in the middle position of the image.

[0110] S2-4: During the inspection process, the UAV continuously detects whether there are blade tip features or hub features in the image. When these two features appear, it means that the inspection of this side has been completed, and the UAV finds the nearest path point to conduct the inspection of another blade or the other side of the blade. This process continues until the inspection is completed.

[0111] Step Three: Closed-loop Control and Safety Mechanism

[0112] Step S3-1: Use a counter to mark the inspected blades. If the inspection is interrupted (such as due to strong wind interference), the UAV automatically returns to a safe point and records the progress.

[0113] The technical solution of the present invention is an automatic path planning method for a UAV to inspect the front and back sides of the blades of a wind turbine in a shutdown state. This method determines the orientation of the wind turbine and the position of the blades through machine vision, and combines dynamic path correction technology to achieve full coverage inspection of the front and back sides of the blades, solving the problems of rigid paths and incomplete coverage in the prior art. The present invention is applicable to the automated operation and maintenance of wind turbines and has the characteristics of high efficiency, safety, and strong adaptability.

[0114] Embodiment Two

[0115] The purpose of this embodiment is to provide a computer device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, the steps of the above method are implemented.

[0116] Embodiment III

[0117] The purpose of this embodiment is to provide a computer-readable storage medium.

[0118] A computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, the steps of the above method are executed.

[0119] Embodiment IV

[0120] The purpose of this embodiment is to provide a path planning system for inspecting the front and back sides of blades in the shutdown state of a wind turbine, including:

[0121] An image acquisition module, configured to: The camera pan-tilt head acquires an image of the wind turbine hub and blade root parts within the field of view based on the pitch angle and rotation angle.

[0122] An image segmentation module, configured to: Identify the blade root contour and hub position through image segmentation, and further obtain the hub center point and blade root center point, and then calculate the direction vector of the blade in the picture.

[0123] A wind turbine attitude acquisition module, configured to: Calculate the direction vector of the blade root in space to obtain the wind turbine attitude; Calculate the orientation of the wind turbine.

[0124] A path point sequence generation module along the blade length, configured to: Calculate the spatial coordinates of the path center point and the three blade tip points based on the wind turbine attitude.

[0125] According to the calculated path center point coordinates and the spatial coordinates of the blade tip points, preliminarily generate a path point sequence along the blade length.

[0126] An inspection module, configured to: The unmanned aerial vehicle flies along the generated path point sequence along the blade length, and dynamically corrects the flight path by tracking the blade in real time to ensure that the blade is always within the camera field of view.

[0127] Embodiment V

[0128] The purpose of this embodiment is to provide a computer program product containing instructions, which, when running on a computer, causes the computer to execute the methods and functions involved in any one of the above embodiments.

[0129] In the devices of the above embodiments, the steps involved correspond to those in the first method embodiment, and for specific implementation details, reference may be made to the relevant description part of the first embodiment. The term "computer-readable storage medium" should be understood to include a single medium or multiple media containing one or more instruction sets; it should also be understood to include any medium that can store, encode, or carry an instruction set for execution by a processor and cause the processor to execute any method in the present invention.

[0130] Those skilled in the art should understand that the above modules or steps of the present invention can be implemented using a general-purpose computer device. Optionally, they can be implemented using program codes executable by a computing device, so that they can be stored in a storage device for execution by the computing device, or they can be separately fabricated into individual integrated circuit modules, or multiple of them can be fabricated into a single integrated circuit module. The present invention is not limited to any specific combination of hardware and software.

[0131] Although the specific implementation of the present invention has been described above in conjunction with the accompanying drawings, it is not a limitation on the protection scope of the present invention. Those skilled in the art should understand that, based on the technical solutions of the present invention, various modifications or deformations that can be made without creative efforts by those skilled in the art are still within the protection scope of the present invention.

Claims

1. Path planning method for inspecting the front and back sides of blades during the shutdown state of a fan, characterized in that, Including: The camera gimbal acquires images of the fan hub and blade root parts within the field of view based on the pitch angle and rotation angle at which it is located; Through image segmentation, the blade root contour and hub position are identified, and further the hub center point and blade root center point are obtained, and then the direction vector of the blade in the picture is calculated; The direction vector of the blade root in space is calculated to obtain the attitude of the wind turbine; Calculate the orientation of the wind turbine; Based on the attitude of the wind turbine, calculate the spatial coordinates of the path center point and the three blade tip points; According to the calculated path center point coordinates and the spatial coordinates of the blade tip points, a path point sequence along the blade length is initially generated; The drone flies along the generated path point sequence along the blade length, and dynamically corrects the flight path by continuously tracking the blade to ensure that the blade is always within the camera's field of view.

2. The path planning method for inspecting the front and back sides of blades during the shutdown state of the fan according to claim 1, characterized in that, The method for obtaining the pitch angle and rotation angle at which the camera gimbal is located is as follows: The camera lens of the camera gimbal carried on the drone is directly facing the direction of the wind turbine nacelle; According to the flight altitude of the drone, the hub height of the wind turbine, the drone's GPS coordinates and the wind turbine's GPS coordinates, calculate the pitch angle α of the camera gimbal, and adjust the pitch angle of the camera gimbal to α; According to the drone's GPS coordinates and the wind turbine's GPS coordinates, calculate the rotation angle β of the camera gimbal, and adjust the rotation angle of the camera gimbal to β.

3. The path planning method for inspecting the front and back sides of the blade during the shutdown state of the fan according to claim 1, characterized in that, The calculation process of the pitch angle of the camera gimbal is as follows: Among them, the flight altitude h of the unmanned aerial vehicle 无人机 , the hub height h of the wind turbine 风电 , the GPS coordinates (φ 无人机 , λ 无人机 ) of the unmanned aerial vehicle and the GPS coordinates (φ 风电 , λ 风电 ) of the wind turbine, where φ is the latitude, λ is the longitude, and d is the straight-line distance between the unmanned aerial vehicle and the wind turbine, which can be directly calculated from the GPS coordinates of the unmanned aerial vehicle and the wind turbine.

4. The path planning method for inspecting the front and back sides of the blade during the shutdown state of the fan according to claim 1, characterized in that, The calculation process of the rotation angle β of the camera gimbal is as follows: Among them, the UAV GPS coordinates (φ 无人机 , λ 无人机 ) and the wind turbine GPS coordinates (φ 风电 , λ 风电 ), where φ is the latitude, λ is the longitude, and d is the straight-line distance between the UAV and the wind turbine, which can be directly calculated from the GPS coordinates of the UAV and the wind turbine.

5. The path planning method for inspecting the front and back sides of the blade during the shutdown state of the fan according to claim 1, characterized in that, It also includes the step of calculating the camera optical axis direction vector according to the lens direction: Establish a fixed coordinate system OXYZ, with the positive direction of the Z-axis being vertically upward, the positive direction of the X-axis being due east, and the positive direction of the Y-axis being due south; The camera optical axis direction vector is obtained after the north direction vector is rotated as described above, and the camera optical axis direction vector can be obtained; The calculated direction vector of the camera optical axis is the normal vector of the lens plane.

6. The path planning method for inspecting the front and back sides of the blades during the shutdown state of the fan according to claim 1, characterized in that, When calculating the attitude of the wind turbine, let the direction vector of the wind turbine blade root in the fixed coordinate system be Based on the calculation, the direction vector of the optical axis of the camera is Obtain the direction vector of the wind turbine blade root in the fixed coordinate system, solve to obtain the direction vector of the blade root in space, combine with the neural network to judge the general orientation of the wind turbine, and then obtain the accurate pose of the wind turbine.

7. A path planning system for inspecting the front and back sides of blades during the shutdown state of a fan, characterized in that, Including: An image acquisition module, configured to: The camera gimbal acquires images of the fan hub and blade root parts within the field of view based on the pitch angle and rotation angle at which it is located; An image segmentation module, configured to: Through image segmentation, identify the blade root contour and hub position, and further obtain the hub center point and blade root center point, and then calculate the direction vector of the blade in the picture; A wind turbine attitude acquisition module, configured to: Calculate the direction vector of the blade root in space to obtain the attitude of the wind turbine; Calculate the orientation of the wind turbine; A path point sequence generation module along the blade length, configured to: Based on the attitude of the wind turbine, calculate the spatial coordinates of the path center point and the three blade tip points; According to the calculated path center point coordinates and the spatial coordinates of the blade tip points, initially generate a path point sequence along the blade length; An inspection module, configured to: The drone flies along the generated path point sequence along the blade length, and dynamically corrects the flight path by continuously tracking the blade to ensure that the blade is always within the camera's field of view.

8. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method described in any one of claims 1 to 6.

9. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein, When the processor executes the program, it implements the steps of the method described in any one of the above claims 1-6.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by a processor, it performs the steps of the method according to any one of the above-mentioned claims 1-6.

Images