Fan blade inspection method and device, electronic equipment, medium and program product

Abstract

The invention discloses a fan blade inspection method and device, electronic equipment, a medium and a program product. The method comprises the steps of determining a target blade corresponding to a first blade based on a comparison result of a first angle of the first blade determined by first point cloud data of the first blade of a current frame and an angle value of each target blade of a fan of a previous frame; acquiring a second angle of a previous frame of a target blade corresponding to the first blade; and if the difference value between the second angle and the first angle is greater than a preset angle threshold value, updating the global route of the previous frame based on the first angle to obtain an updated global route, and synchronously adjusting the central point of the shooting view of the pan-tilt camera carried by the unmanned aerial vehicle to be aligned with the target position of the first blade. And the unmanned aerial vehicle carries out fan blade inspection based on the updated global route. According to the invention, the route of the unmanned aerial vehicle is accurately determined in real time according to the angle change of the fan blade, the pan-tilt camera is accurately adjusted, and the fan blade is accurately inspected.

Description

Technical Field

[0001] This invention relates to the field of wind turbine testing technology, and in particular to a method, device, electronic equipment, medium, and program product for inspecting wind turbine blades. Background Technology

[0002] With the rapid development and deployment of new energy technologies, the installed capacity of wind turbines has grown rapidly. To ensure the long-term stable operation of wind turbines, reduce the failure rate, and avoid production accidents, it is necessary to conduct regular inspections of each wind turbine.

[0003] When a wind turbine is in a stopped but unlocked state, the blades may rotate erratically due to natural wind forces. Existing wind turbine blade inspection solutions typically require locking the turbine after shutdown before conducting inspections along a fixed route to prevent random blade rotation caused by wind from deviating from the drone's tracking of specific targets on the turbine blades. However, locking the turbine requires manual intervention, requiring entry into the tower to perform the operation manually, which significantly impacts the efficiency of automated wind turbine inspections. Therefore, it is crucial to find a way to accurately inspect wind turbine blades when the turbine is stopped but unlocked. Summary of the Invention

[0004] This invention provides a method, apparatus, electronic device, medium, and program product for inspecting wind turbine blades to solve one of the aforementioned technical problems.

[0005] According to one aspect of the present invention, a method for inspecting wind turbine blades is provided, the method comprising:

[0006] The first point cloud data of the wind turbine obtained by the UAV scanning the first blade in the current frame is acquired, and the first angle of the first blade is determined based on the first point cloud data. The first angle is used to describe the angle between the center line of the first blade and a preset horizontal line. The preset horizontal line is a straight line that passes through the center point of the wind turbine hub, is perpendicular to the tower of the wind turbine, and is parallel to the plane where the wind turbine blade is located.

[0007] Based on the comparison between the first angle of the first blade and the angle value of each target blade of the wind turbine in the previous frame, the target blade corresponding to the first blade is determined, and the second angle of the target blade corresponding to the first blade in the previous frame is obtained.

[0008] If the difference between the second angle and the first angle is less than a preset angle threshold, the center point of the field of view of the gimbal camera on the UAV is adjusted to be aligned with the target position of the first blade, so that the UAV can perform wind turbine blade inspection based on the global flight path of the previous frame; the target position is determined based on the first point cloud data.

[0009] If the difference between the second angle and the first angle is greater than a preset angle threshold, the global flight path of the previous frame is updated based on the first angle to obtain the updated global flight path. Simultaneously, the center point of the field of view of the gimbal camera on the UAV is adjusted to align with the target position of the first blade, so that the UAV can perform wind turbine blade inspection based on the updated global flight path.

[0010] According to another aspect of the present invention, a wind turbine blade inspection device is provided, the device comprising:

[0011] The data acquisition module is used to acquire the first point cloud data of the wind turbine obtained by the UAV scanning the first blade in the current frame, and to determine the first angle of the first blade based on the first point cloud data; the first angle is used to describe the angle between the center line of the first blade and a preset horizontal line; the preset horizontal line is a straight line that passes through the center point of the wind turbine hub, is perpendicular to the tower of the wind turbine, and is parallel to the plane where the wind turbine blade is located.

[0012] The blade determination module is used to determine the target blade corresponding to the first blade based on the comparison result between the first angle of the first blade and the angle value of each target blade of the wind turbine in the previous frame, and to obtain the second angle of the target blade corresponding to the first blade in the previous frame.

[0013] The first control module is used to adjust the center point of the field of view of the gimbal camera on the UAV to align with the target position of the first blade if the difference between the second angle and the first angle is less than a preset angle threshold, so that the UAV can perform wind turbine blade inspection based on the global flight path of the previous frame; the target position is determined based on the first point cloud data.

[0014] The second control module is used to update the global flight path of the previous frame based on the first angle if the difference between the second angle and the first angle is greater than a preset angle threshold, and simultaneously adjust the center point of the field of view of the gimbal camera on the UAV to align with the target position of the first blade, so that the UAV can perform wind turbine blade inspection based on the updated global flight path.

[0015] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0016] At least one processor; and

[0017] A memory communicatively connected to the at least one processor; wherein,

[0018] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the wind turbine blade inspection method according to any embodiment of the present invention.

[0019] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the wind turbine blade inspection method according to any embodiment of the present invention.

[0020] The technical solution of this invention involves acquiring the first point cloud data of the wind turbine obtained by the UAV scanning the first blade in the current frame, and determining the first angle of the first blade based on the first point cloud data. The first angle describes the angle between the centerline of the first blade and a preset horizontal line. The preset horizontal line is a straight line perpendicular to the wind turbine hub center point and the wind turbine tower, and parallel to the plane where the wind turbine blade is located, thus achieving accurate determination of the angle of the first blade. Then, based on the comparison between the first angle of the first blade and the angle value of each target blade of the wind turbine in the previous frame, the target blade corresponding to the first blade is determined, achieving accurate matching between the first blade and each pre-marked target blade, thereby facilitating subsequent updates to the global flight path. Simultaneously, the second angle of the target blade corresponding to the first blade in the previous frame is acquired, and the difference between the second angle and the first angle is compared with a preset angle threshold to determine whether an update to the global flight path is needed. Specifically, if the difference between the second angle and the first angle is less than the preset angle threshold, the center point of the field of view of the gimbal camera mounted on the UAV is adjusted to align with the first blade. The target position is determined based on the first point cloud data. If the difference between the second angle and the first angle is greater than a preset angle threshold, the global flight path of the previous frame is updated based on the first angle to obtain the updated global flight path. Simultaneously, the center point of the field of view of the gimbal camera on the UAV is adjusted to align with the target position of the first blade, so that the UAV can perform wind turbine blade inspection based on the updated global flight path. This enables the UAV to accurately determine the flight path in real time based on the angle change of the wind turbine blade, and to precisely adjust the gimbal camera to achieve accurate inspection of the wind turbine blade.

[0021] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1This is a flowchart of a wind turbine blade inspection method according to an embodiment of the present invention;

[0024] Figure 2 This is a schematic diagram of a hardware device mounted on a drone to which an embodiment of the present invention applies;

[0025] Figure 3 This is a schematic diagram of the wind turbine blades and the target coordinate system applicable to the embodiments of the present invention;

[0026] Figure 4 This is a flowchart of a wind turbine blade inspection method according to an embodiment of the present invention;

[0027] Figure 5 This is a schematic diagram of the structure of a wind turbine blade inspection device according to an embodiment of the present invention;

[0028] Figure 6 This is a schematic diagram of the structure of an electronic device for implementing the wind turbine blade inspection method according to an embodiment of the present invention. Detailed Implementation

[0029] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0030] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0031] Example 1

[0032] Figure 1This is a flowchart of a wind turbine blade inspection method provided by an embodiment of the present invention. This embodiment is applicable to the inspection of wind turbine blades that are not locked when the machine is stopped. The method can be executed by a wind turbine blade inspection device, which can be implemented in hardware and / or software. The wind turbine blade inspection device can be configured in any electronic device with network communication function.

[0033] This invention uses drones to inspect wind turbine blades in a stopped but unlocked state, such as... Figure 2 As shown, the drone is equipped with hardware devices such as an onboard computer, a multi-line LiDAR, a gimbal camera, and onboard auxiliary positioning and attitude detection sensors. All hardware devices are installed on the same drone. The multi-line LiDAR is installed at a first preset position on the upper part of the drone's fuselage. For example, the first preset position could be... Figure 2 There are 3 markings in the middle, and there are no obstacles in front to obstruct the detection field of view. It is powered by an aviation plug and communicates with the onboard computer through local area network. The frame-by-frame point cloud data is transmitted to the onboard computer for further processing. The multi-line lidar has a 360-degree all-round scanning detection capability in the horizontal direction and a certain wide-angle scanning detection range in the vertical direction.

[0034] The gimbal camera is fixed at a preset position on the bottom of the drone body, for example... Figure 1 The camera features a 3-DOF (degrees of freedom) gimbal, allowing control of roll, pitch, and yaw angles. The gimbal camera can transmit video streams or images to an onboard computer for further processing via a video or image transmission interface.

[0035] The sensor equipment is built into the drone and can transmit data with the onboard computer via serial port and network. The sensor equipment may include drone attitude sensor, positioning sensor and IMU inertial navigation sensor. The positioning sensor can be GPS or RTK high-precision positioning sensor. The drone sends the position and attitude information after the fusion of multiple sensors to the onboard computer, thereby controlling the drone to perform inspection.

[0036] The onboard computer is fixed at a second preset position on the upper part of the drone's fuselage. For example, the second preset position could be... Figure 2 As indicated by the two markings, the onboard computer can update the rotation angles of each axis of the gimbal camera in real time via program commands. The gimbal also features self-stabilization to counteract the camera's field of view shake caused by drone attitude disturbances. The onboard computer is powered by the drone's own power supply and includes core components such as a CPU, GPU, network interface, Type-C expansion port, memory, and hard drive, providing basic computing power and meeting certain graphics processing requirements.

[0037] like Figure 1As shown, the wind turbine blade inspection method of the present invention includes the following process:

[0038] S110. Obtain the first point cloud data of the wind turbine obtained by the UAV scanning the first blade in the current frame, and determine the first angle of the first blade based on the first point cloud data; the first angle is used to describe the angle between the center line of the first blade and the preset horizontal line; the preset horizontal line is a straight line that passes through the center point of the wind turbine hub, is perpendicular to the tower of the wind turbine, and is parallel to the plane where the wind turbine blade is located.

[0039] The first blade can be the blade that the UAV is inspecting in the current frame during its global flight path inspection mission. The first point cloud data is the 3D point cloud data obtained by the UAV's multi-line lidar scanning of the first blade in the current frame.

[0040] Specifically, after acquiring the first point cloud data of the wind turbine obtained by the UAV scanning the first blade in the current frame, the first point cloud data is converted to point cloud data in the target coordinate system to obtain updated first point cloud data. Then, the updated first point cloud data is fitted to obtain the center line of the first blade, and the angle between the center line of the first blade and the preset horizontal line is taken as the first angle of the first blade.

[0041] Optionally, the target coordinate system is a wind turbine coordinate system, with a preset horizontal line as the first coordinate axis. The target coordinate system is a three-dimensional coordinate system, with its origin at the center point of the wind turbine hub. The target coordinate system includes a first coordinate axis, a second coordinate axis, and a third coordinate axis. The first coordinate axis is perpendicular to the wind turbine tower and parallel to the plane containing the wind turbine blades. The second coordinate axis is perpendicular to the wind turbine tower and perpendicular to the plane containing the wind turbine blades. The third coordinate axis is parallel to the wind turbine tower and parallel to the plane containing the wind turbine blades. The first coordinate axis (y-axis), the second coordinate axis (x-axis), and the third coordinate axis (z-axis) are mutually perpendicular. For example, as shown... Figure 3 As shown.

[0042] Furthermore, the method for transforming the first point cloud data into point cloud data in the target coordinate system can include: transforming the first point cloud data from the lidar coordinate system to the UAV body coordinate system, then from the UAV body coordinate system to the world coordinate system, and finally from the world coordinate system to the wind turbine coordinate system; wherein, the origin of the world coordinate system is the UAV takeoff point; the specific process is as follows:

[0043] a. Transformation from LiDAR coordinate system to UAV body coordinate system: The LiDAR is mounted on the UAV body, and there is a fixed rigid transformation relationship between the two:

[0044] P B =T B←L ·P L ;

[0045] in: Point coordinates in the lidar coordinate system; Point coordinates in the UAV body coordinate system; T B←L ∈SE(3): The transformation matrix from the laser radar to the UAV body, obtained from the extrinsic parameter calibration, includes a rotation matrix R. BL ∈SO(3) and a translation vector Its structure is as follows:

[0046]

[0047] b. Transformation from UAV body coordinate system to world coordinate system

[0048] During flight, the drone's attitude T W←B (t)∈SE(3) can be obtained through IMU+GPS / NMEA fusion (such as from flight controller (NMEA) or odometry (IMU+GPS)), and the specific formula is as follows:

[0049] P W =T W←B (t)·P B ;

[0050] in: Point coordinates in the world coordinate system; T W←B (t): Represents the transformation matrix from the UAV body coordinate system to the wind turbine coordinate system, which is updated over time.

[0051] c. Transformation from world coordinate system to wind turbine coordinate system (based on wind turbine GPS + altitude + wind turbine yaw angle)

[0052] Given the GPS (WGS84) coordinates and altitude at the wind turbine hub, the orientation and attitude of the wind turbine tower, and the GPS origin at the takeoff point, use the WGS84→ECEF→ENU conversion to obtain the wind turbine's position in the world coordinate system. WGS84 is a geodetic datum and land reference system with the Earth's center fixed. ECEF (Earth-Centered, Earth-Fixed) is a three-dimensional rectangular coordinate system widely used in global positioning, geographic information systems (GIS), and navigation. Its core feature is that the origin is fixed at the Earth's center of mass, and the coordinate axes are synchronized with the Earth's rotation, thus stably describing the position of objects on the Earth's surface and near the Earth. ENU (East-North-Up) is a right-handed rectangular coordinate system widely used for local spatial positioning, often used to describe the relative position or motion of an object with respect to a reference point. The specific formula is as follows:

[0053]

[0054] Where: P WT : represents the coordinates of the fan in ENU; R WT : is the rotation matrix from the world coordinate system to the wind turbine coordinate system; p W p represents the coordinates of the point cloud in the world coordinate system. T The coordinates of the point cloud in the wind turbine coordinate system.

[0055] d. Transformation from lidar coordinate system to wind turbine coordinate system

[0056] From steps a, b, and c above, the transformation formula from the radar coordinate system to the wind turbine coordinate system can be obtained as follows:

[0057] P T =T T←W (t)T W←B (t)·T B←C ·P C ;

[0058] First, the coordinates of point P in the lidar coordinate system are... L Coordinate point P transformed to the UAV body coordinate system B Then, combined with the coordinates P of the body attitude transformation to the world coordinate system W Finally, in the wind turbine's body coordinate system P T This method is used to project radar point cloud data onto the wind turbine coordinate system in real time, facilitating mapping, fusion, or perception-based decision-making.

[0059] S120. Based on the comparison result between the first angle of the first blade and the angle value of each target blade of the wind turbine in the previous frame, determine the target blade corresponding to the first blade, and obtain the second angle of the target blade corresponding to the first blade in the previous frame.

[0060] The target blade can be a blade that has been marked in advance in the wind turbine, so as to ensure that the determination of the blade angle in each frame can match the corresponding target blade, and to ensure that the angle sequence of each target blade can be obtained and the real-time angle change curve of each target blade can be output.

[0061] Specifically, the first angle of the first blade is compared with the angle value of each target blade of the wind turbine in the previous frame, and the target blade of the wind turbine in the previous frame with the smallest difference from the first angle of the first blade is taken as the target blade corresponding to the first blade.

[0062] In an embodiment of the present invention, optionally, the process of determining the angle value of each target blade of the wind turbine in the previous frame may include steps A1-A2:

[0063] Step A1: If the previous frame is the first frame, then obtain the second point cloud data of the wind turbine obtained by the UAV scanning the second blade, and determine the angle value of each target blade of the wind turbine in the previous frame based on the second point cloud data and the target coordinate system.

[0064] The second blade can be the blade that the UAV initially inspects when performing an inspection mission according to the global flight path. The second point cloud data is the three-dimensional point cloud data obtained by the UAV's multi-line lidar scanning of the second blade in the first frame. The first frame is the initial frame.

[0065] Specifically, after acquiring the second point cloud data, it is transformed into point cloud data in the target coordinate system to obtain updated second point cloud data. Then, the updated second point cloud data is fitted to obtain the centerline of the second blade. The angle between the centerline of the second blade and a preset horizontal line is taken as the angle value of the second blade. Based on the preset angle rules and the angle value of the second blade, the angle values ​​between the other blades and the preset horizontal line are determined. The preset angle rule is that the three blades are spaced 120° apart from each other. All angle values ​​of the wind turbine blades are sorted in ascending order to obtain the first angle value, the second angle value, and the third angle value. The first angle value is less than the second angle value, and the second angle value is less than the third angle value. The blade corresponding to the first angle value is taken as the first target blade, the blade corresponding to the second angle value is taken as the second target blade, and the blade corresponding to the third angle value is taken as the third target blade, thus accurately obtaining the angle value of each target blade. Each target blade is then marked, for example... Figure 3 As shown, the first target blade is marked A, the second target blade is marked B, and the third target blade is marked C. The angle value of the first target blade A is θ, the angle value of the second target blade B is θ+120°, and the angle value of the third target blade C is θ+240°.

[0066] Furthermore, the process of determining the initial global flight path when the UAV begins its inspection is as follows: A surface scanning flight path for each blade in each orientation is generated using a 3D model of the wind turbine. These segmented flight paths are then stitched together to form the initial global flight path. After determining the angle values ​​of each target blade in the first frame, the initial global flight path can be updated based on these angle values, ensuring that the first frame inspection and subsequent inspections use the updated initial global flight path.

[0067] Optionally, determining the angle value of each target blade of the wind turbine in the previous frame based on the second point cloud data and the target coordinate system may include steps B1-B3:

[0068] Step B1: Determine the angle value of the second blade based on the second point cloud data. According to the preset angle rule and the angle value of the second blade, determine the angle values ​​between the other blades and the preset horizontal line. The preset angle rule is that the interval between each pair of the three blades is 120°.

[0069] Specifically, the second point cloud data is transformed into point cloud data in the target coordinate system to obtain updated second point cloud data. Then, the updated second point cloud data is fitted using a random sampling consensus algorithm to obtain the centerline of the second blade, and the fourth vector of the centerline of the second blade is determined. The fourth vector is the direction vector of the centerline of the second blade, and the starting point of the second vector is the origin of the target coordinate system. At the same time, the second vector of the first coordinate axis is determined. The second vector is the direction vector in the positive direction of the first coordinate axis, and the starting point of the second vector is the origin of the target coordinate system. Further, the angle between the fourth vector and the second vector is determined as the fourth angle, and the cross product of the fourth vector and the second vector is taken as the fifth vector. The second dot product result between the fifth vector and the direction vector in the positive direction of the second coordinate axis is determined. If the second dot product result is less than zero, the angle value of the second blade is the difference between 360° and the fourth angle; if the second dot product result is greater than zero, the angle value of the second blade is the fourth angle. Further, according to the preset angle rules and the angle value of the second blade, the angle values ​​between the other blades and the preset horizontal line are determined.

[0070] Step B2: Sort all angle values ​​of the wind turbine blades in ascending order to obtain the first angle value, the second angle value, and the third angle value; the first angle value is less than the second angle value, and the second angle value is less than the third angle value.

[0071] Step B3: Take the blade corresponding to the first angle value as the first target blade, the blade corresponding to the second angle value as the second target blade, and the blade corresponding to the third angle value as the third target blade.

[0072] For example, the angle value of the second blade in the first frame is θ1; based on the preset angle rules, the angle values ​​of the other two blades are derived as θ2 = fmod(θ1 + 120, 360) and θ3 = fmod(θ1 + 240, 360); then the initial angle values ​​of the three target blades are as follows: the angle value of the first target blade θ a =min(θ1,θ2,θ3), the angle value θ of the third target blade c =max(θ1,θ2,θ3), the angle value θ of the second target blade. b = mid(θ1,θ2,θ3);

[0073] The technical solution of this embodiment determines the angle value of the second blade based on the second point cloud data. According to the preset angle rule and the angle value of the second blade, the angle values ​​between other blades and the preset horizontal line are determined. The preset angle rule is that the interval between each pair of three blades is 120°, which realizes the accurate determination of the angle value of each blade in the first frame. Furthermore, all the angle values ​​of the wind turbine blades are sorted in ascending order to obtain the first angle value, the second angle value, and the third angle value. The first angle value is less than the second angle value, and the second angle value is less than the third angle value. The blade corresponding to the first angle value is taken as the first target blade, the blade corresponding to the second angle value is taken as the second target blade, and the blade corresponding to the third angle value is taken as the third target blade. This realizes the accurate marking of the target blades so that the angle sequence of each target blade can be obtained in subsequent frames.

[0074] Step A2: If the previous frame is not the first frame, determine the angle value of the third blade of the fan in the previous frame. Based on the comparison result between the angle value of the third blade of the fan and the angle value of each target blade of the fan in the frame before the previous frame, determine the target blade corresponding to the third blade, as well as the target blades corresponding to the other blades besides the third blade.

[0075] The third blade can be the blade that the UAV was inspecting in the previous frame during its global flight path inspection mission. The previous frame is the frame closest to the current frame, and the frame from which the blade's angle value can be calculated using the acquired point cloud data. The frame before that can be understood as the frame closest to the previous frame, and the frame from which the blade's angle value can be calculated using the acquired point cloud data.

[0076] The specific process for determining the angle value of the third blade of the wind turbine in the previous frame can be as follows: acquire the third point cloud data, which is the three-dimensional point cloud data obtained by the multi-line lidar scanning of the third blade of the UAV in the previous frame; convert the third point cloud data to point cloud data in the target coordinate system to obtain updated third point cloud data; then fit the updated third point cloud data to obtain the center line of the third blade; and then take the angle between the center line of the third blade and the preset horizontal line as the angle value of the third blade.

[0077] Furthermore, the difference between the angle value of the third blade and the angle value of each target blade of the wind turbine in the previous frame is determined; the target blade with the smallest angle difference in the difference results is taken as the target blade corresponding to the third blade, and the target blades corresponding to the other blades besides the third blade are determined according to the preset angle rules.

[0078] The technical solution of this embodiment determines whether the previous frame of the wind turbine blades is the first frame of the wind turbine blades, and then uses different methods to accurately obtain the angle value of each target blade of the wind turbine in the previous frame, so as to accurately determine the target blade corresponding to the first blade of the current frame by using the angle value of each target blade of the wind turbine in the previous frame.

[0079] S130. If the difference between the second angle and the first angle is less than the preset angle threshold, adjust the center point of the field of view of the gimbal camera on the drone to align with the target position of the first blade, so that the drone can perform wind turbine blade inspection based on the global flight path of the previous frame; the target position is determined based on the first point cloud data.

[0080] Specifically, if the difference between the second angle and the first angle is less than the preset angle threshold, it indicates that the wind turbine blades in this frame are less affected by wind. The current global flight path can be used to continue the inspection between adjacent frames; that is, the drone inspects the wind turbine blades based on the global flight path of the previous frame. Before the inspection, the center point of the gimbal camera's field of view on the drone needs to be aligned with the target position of the first blade.

[0081] S140. If the difference between the second angle and the first angle is greater than the preset angle threshold, the global flight path of the previous frame is updated based on the first angle to obtain the updated global flight path. Simultaneously, the center point of the field of view of the gimbal camera on the UAV is adjusted to align with the target position of the first blade, so that the UAV can perform wind turbine blade inspection based on the updated global flight path.

[0082] The global flight path in the previous frame is the global flight path that has not yet been updated.

[0083] Specifically, if the difference between the second angle and the first angle is greater than the preset angle threshold, it indicates that the wind turbine blades in this frame are greatly affected by the wind force, and the current global flight path needs to be updated. That is, the global flight path of the previous frame needs to be updated based on the first angle to obtain the updated global flight path. At the same time, the center point of the field of view of the gimbal camera on the UAV is adjusted to align with the target position of the first blade, so that the UAV can perform wind turbine blade inspection based on the updated global flight path.

[0084] The technical solution of this invention involves acquiring the first point cloud data of the wind turbine obtained by the UAV scanning the first blade in the current frame, and determining the first angle of the first blade based on the first point cloud data. The first angle describes the angle between the centerline of the first blade and a preset horizontal line. The preset horizontal line is a straight line perpendicular to the wind turbine hub center point and the wind turbine tower, and parallel to the plane where the wind turbine blade is located, thus achieving accurate determination of the angle of the first blade. Then, based on the comparison between the first angle of the first blade and the angle value of each target blade of the wind turbine in the previous frame, the target blade corresponding to the first blade is determined, achieving accurate matching between the first blade and each pre-marked target blade, thereby facilitating subsequent updates to the global flight path. Simultaneously, the second angle of the target blade corresponding to the first blade in the previous frame is acquired, and the difference between the second angle and the first angle is compared with a preset angle threshold to determine whether an update to the global flight path is needed. Specifically, if the difference between the second angle and the first angle is less than the preset angle threshold, the center point of the field of view of the gimbal camera mounted on the UAV is adjusted to align with the first blade. The target position is determined based on the first point cloud data. If the difference between the second angle and the first angle is greater than a preset angle threshold, the global flight path of the previous frame is updated based on the first angle to obtain the updated global flight path. Simultaneously, the center point of the field of view of the gimbal camera on the UAV is adjusted to align with the target position of the first blade, so that the UAV can perform wind turbine blade inspection based on the updated global flight path. This enables the UAV to accurately determine the flight path in real time based on the angle change of the wind turbine blade, and to precisely adjust the gimbal camera to achieve accurate inspection of the wind turbine blade.

[0085] Example 2

[0086] Figure 4 This is a flowchart illustrating a wind turbine blade inspection method according to an embodiment of the present invention. The technical solution of this embodiment further optimizes the wind turbine blade inspection method based on the above embodiments. This embodiment can be combined with various optional solutions in one or more of the above embodiments. Figure 4 As shown, the wind turbine blade inspection method of the present invention includes the following process:

[0087] S210: Obtain the first point cloud data of the wind turbine obtained by the UAV scanning the first blade in the current frame.

[0088] S220. Fit the first point cloud data to obtain the centerline of the first blade, and determine the first vector of the centerline of the first blade; the first vector is the direction vector of the centerline of the first blade, and the starting point of the first vector is the origin of the target coordinate system.

[0089] The target coordinate system is the wind turbine coordinate system, with the preset horizontal line as the first coordinate axis of the target coordinate system. The target coordinate system is a three-dimensional coordinate system, with the origin of the target coordinate system being the center point of the wind turbine hub. The target coordinate system includes a first coordinate axis, a second coordinate axis, and a third coordinate axis. The first coordinate axis is perpendicular to the wind turbine tower and parallel to the plane where the wind turbine blades are located. The second coordinate axis is perpendicular to the wind turbine tower and perpendicular to the plane where the wind turbine blades are located. The third coordinate axis is parallel to the wind turbine tower and parallel to the plane where the wind turbine blades are located. The first coordinate axis (y-axis), the second coordinate axis (x-axis), and the third coordinate axis (z-axis) are mutually perpendicular to each other.

[0090] Specifically, the first point cloud data is transformed into point cloud data in the target coordinate system to obtain updated first point cloud data. The updated first point cloud data is then fitted using a random sampling consensus algorithm to obtain the centerline of the first blade. The vector along the centerline of the first blade is determined as the first vector, with the origin of the target coordinate system as the starting point.

[0091] S230. Determine the second vector of the first coordinate axis, and determine the first angle of the first blade based on the first vector and the second vector; the second vector is the direction vector of the positive direction of the first coordinate axis, and the starting point of the second vector is the origin of the target coordinate system.

[0092] Specifically, the angle between the first vector and the second vector is determined as the first angle of the first blade.

[0093] Optionally, determining the first angle of the first blade based on the first vector and the second vector may include: determining the angle between the first vector and the second vector as the third angle, and using the cross product of the first vector and the second vector as the third vector, and determining the first dot product result between the third vector and the direction vector of the positive direction of the second coordinate axis; if the first dot product result is less than zero, then the first angle of the first blade is the difference between 360° and the third angle; if the first dot product result is greater than zero, then the first angle of the first blade is the third angle. Because the angle between the two vectors ranges from 0 to 180 degrees, while the actual angle value of the blade ranges from 0 to 360 degrees, this embodiment determines the quadrant in which the first vector is located by judging the relationship between the first dot product result and zero, thereby accurately determining whether the first angle of the first blade is the supplementary angle of the third angle, and achieving precise determination of the first angle of the first blade.

[0094] S240. Determine the difference between the first angle of the first blade and the angle value of each target blade of the wind turbine in the previous frame. Take the target blade with the smallest angle difference in the difference results as the target blade corresponding to the first blade, and obtain the second angle of the target blade corresponding to the first blade in the previous frame.

[0095] Specifically, since the angle change of the same target blade between two consecutive frames is not particularly large, the target blade with the smallest angle difference in the difference results can be taken as the target blade corresponding to the first blade.

[0096] S250. If the difference between the second angle and the first angle is less than the preset angle threshold, adjust the center point of the field of view of the gimbal camera on the drone to align with the target position of the first blade, so that the drone can perform wind turbine blade inspection based on the global flight path of the previous frame; the target position is determined based on the first point cloud data.

[0097] Specifically, adjusting the center point of the field of view of the gimbal camera on the drone to align with the target position of the first blade may include steps C1-C4:

[0098] Step C1: Fit the first point cloud data to obtain the centerline of the first blade. Draw a perpendicular line from the center point of the gimbal camera to the centerline of the first blade to obtain the first perpendicular line. Determine the intersection of the first perpendicular line and the centerline of the first blade as the target position.

[0099] Step C2: Convert the first coordinate point information of the target location into the second coordinate point information relative to the center point of the field of view of the gimbal camera.

[0100] Specifically, the first coordinate point information of the target location is converted into the coordinate points of the lidar. The lidar coordinate points can be represented as: C lidar (x c ,y c ,z c Then, the coordinates of the LiDAR are converted into second coordinate information relative to the center of the field of view of the gimbal camera. The second coordinate information can be represented as: C cam =R ld ×R dc ×[x c ,y c ,z c ,1] T C cam =(C cam .x, C cam .y,C cam .z).

[0101] Among them, R ld R is the homogeneous coordinate transformation matrix from the center coordinates of the lidar to the center coordinates of the UAV. dc Let R be the homogeneous coordinate transformation matrix from the UAV's center coordinates to the gimbal camera's center coordinates. ld For example, let P be the relative position of the fixed position and azimuth of the lidar at the center of the UAV. l = (x, y, z), attitude quaternion is Q l =(q x,q y ,q z ,q w ), R ld The calculation formula is expressed as follows:

[0102]

[0103] Step C3: Determine and adjust the pitch and yaw angles of the gimbal camera based on the information from the second coordinate point.

[0104] Specifically, the pitch and yaw angles of the gimbal camera can be expressed as:

[0105] pitch = arctan(C cam .z,C cam .x);

[0106] yaw = arctan(C cam .y,C cam .x).

[0107] Step C4: Based on the pitch and yaw angles of the gimbal camera, adjust the center point of the field of view of the gimbal camera on the UAV to align with the target position of the first blade.

[0108] Furthermore, wind turbine blade inspection based on the previous frame's global flight path can include: determining the UAV's control parameters based on the previous frame's global flight path and a nonlinear model; using the nonlinear model to predict the UAV's control parameters based on the flight path; the control parameters include state variables and control variables; and sending the UAV's control parameters to the UAV's control actuator to control the UAV to perform wind turbine blade inspection based on the UAV's control variables.

[0109] The nonlinear model includes an objective function, which can be expressed as follows:

[0110]

[0111] in,

[0112]

[0113] X=[x,y,z,u,v,w,q x q y q z q w ];

[0114]

[0115] U = [p, q, r, T];

[0116] Where X is the UAV's state vector, consisting of the UAV's spatial coordinates (x, y, z), its velocity in the UAV's body coordinate system (u, v, w), and its attitude quaternion (q). x q y q z q w It consists of ) . U is the control variable of the UAV, which is composed of the UAV's Euler angles, angular velocity (p, q, r), and electric thrust T. X ref For the desired trajectory state, U ref Here, k represents the reference control variable corresponding to the desired trajectory state, and N is the prediction time step, where 0 < k ≤ N. In the objective function... These are the state deviation term of the UAV at time step K, the control deviation term of the UAV at time step K, and the state deviation term of the trajectory segment terminal, respectively. x W u This is the weight matrix corresponding to the state variable deviation and the control variable deviation. f is the weight matrix corresponding to the terminal state deviation. d (X k U k Here is the state transition equation for the system:

[0117]

[0118] Among them, R EB Let m be the coordinate transformation matrix of the UAV body to the time coordinate system, m be the total mass of the UAV, and T be the power steering thrust. The UAV's onboard computer calculates the optimal control parameters for the current UAV based on the above nonlinear model and the global flight path of the previous frame, and sends them to the UAV control actuator to continuously adjust the UAV's flight state, thereby achieving follow-flight control of the rotating blades.

[0119] S260. If the difference between the second angle and the first angle is greater than the preset angle threshold, the global flight path of the previous frame is updated based on the first angle to obtain the updated global flight path. Simultaneously, the center point of the field of view of the gimbal camera on the UAV is adjusted to align with the target position of the first blade, so that the UAV can perform wind turbine blade inspection based on the updated global flight path.

[0120] Specifically, the process of aligning the center point of the field of view of the gimbal camera on the UAV with the target position of the first blade is consistent with the steps in S250. Furthermore, the UAV's inspection of the wind turbine blades based on the updated global flight path can include: determining the UAV's control parameters based on the updated global flight path and a nonlinear model; using the nonlinear model to predict the UAV's control parameters based on the flight path; the control parameters include state variables and control variables; sending the UAV's control parameters to the UAV control actuator to continuously adjust the UAV's flight state, controlling the UAV to perform wind turbine blade inspections based on the UAV's control variables, thus achieving follow-fly control of the rotating blades.

[0121] The technical solution of this invention involves acquiring the first point cloud data of the wind turbine obtained by the UAV scanning the first blade in the current frame, fitting the first point cloud data to obtain the centerline of the first blade, and determining the first vector of the centerline of the first blade. The first vector is the direction vector of the centerline of the first blade, and the starting point of the first vector is the origin of the target coordinate system. The second vector of the first coordinate axis is determined. Based on the first and second vectors, the first angle of the first blade can be quantitatively determined, achieving accurate determination of the first angle. Furthermore, the difference between the first angle of the first blade and the angle value of each target blade of the wind turbine in the previous frame is determined. The target blade with the smallest angle difference in the difference results is taken as the target blade corresponding to the first blade, achieving accurate matching between the first blade and each pre-marked target blade, thereby facilitating subsequent updates to the global flight path. At the same time, the second angle of the target blade corresponding to the first blade in the previous frame is obtained. By judging the difference between the second angle and the first angle and comparing it with a preset angle threshold, it is determined whether the global flight path needs to be updated. This enables real-time and accurate determination of the UAV's flight path based on the angle changes of the wind turbine blades. Furthermore, it precisely determines the pitch and yaw angles of the gimbal camera in a quantitative manner. Based on the pitch and yaw angles of the gimbal camera, it adjusts the center point of the field of view of the UAV's gimbal camera to align with the target position of the first blade, achieving precise adjustment of the gimbal camera. At the same time, it determines the control parameters of the UAV based on the global flight path and a nonlinear model. The control parameters of the UAV are sent to the UAV controller actuator, which controls the UAV to perform wind turbine blade inspection based on the control inputs of the UAV, achieving precise inspection of the wind turbine blades.

[0122] Example 3

[0123] Figure 5 This is a schematic diagram of a wind turbine blade inspection device provided in an embodiment of the present invention. This embodiment is applicable to the inspection of wind turbine blades when the turbine is stopped but not locked. The wind turbine blade inspection device can be implemented in hardware and / or software, and can be configured in any electronic device with network communication capabilities. Figure 5As shown, the wind turbine blade inspection device includes:

[0124] The data acquisition module 310 is used to acquire the first point cloud data of the wind turbine obtained by the UAV scanning the first blade in the current frame, and to determine the first angle of the first blade based on the first point cloud data; the first angle is used to describe the angle between the center line of the first blade and a preset horizontal line; the preset horizontal line is a straight line that passes through the center point of the wind turbine hub, is perpendicular to the tower of the wind turbine, and is parallel to the plane where the wind turbine blade is located.

[0125] The blade determination module 320 is used to determine the target blade corresponding to the first blade based on the comparison result between the first angle of the first blade and the angle value of each target blade of the wind turbine in the previous frame, and to obtain the second angle of the target blade corresponding to the first blade in the previous frame.

[0126] The first control module 330 is used to adjust the center point of the field of view of the gimbal camera on the UAV to align with the target position of the first blade if the difference between the second angle and the first angle is less than a preset angle threshold, so that the UAV can perform wind turbine blade inspection based on the global flight path of the previous frame; the target position is determined based on the first point cloud data.

[0127] The second control module 340 is used to update the global flight path of the previous frame based on the first angle if the difference between the second angle and the first angle is greater than a preset angle threshold, and simultaneously adjust the center point of the field of view of the gimbal camera on the UAV to align with the target position of the first blade, so that the UAV can perform wind turbine blade inspection based on the updated global flight path.

[0128] Based on the above embodiments, optionally, the preset horizontal line is the first coordinate axis of the target coordinate system; the target coordinate system is a three-dimensional coordinate system, the origin of the target coordinate system is the center point of the wind turbine hub, and the target coordinate system includes a first coordinate axis, a second coordinate axis, and a third coordinate axis; the first coordinate axis is perpendicular to the wind turbine tower and parallel to the plane where the wind turbine blades are located; the second coordinate axis is perpendicular to the wind turbine tower and perpendicular to the plane where the wind turbine blades are located; the third coordinate axis is parallel to the wind turbine tower and parallel to the plane where the wind turbine blades are located; the first coordinate axis, the second coordinate axis, and the third coordinate axis are mutually perpendicular to each other;

[0129] Accordingly, the data acquisition module includes an angle determination unit, which is used to: fit the first point cloud data to obtain the centerline of the first blade, and determine a first vector of the centerline of the first blade; the first vector is the direction vector of the centerline of the first blade, and the starting point of the first vector is the origin of the target coordinate system; determine a second vector of the first coordinate axis; the second vector is the direction vector of the positive direction of the first coordinate axis, and the starting point of the second vector is the origin of the target coordinate system; and determine a first angle of the first blade based on the first vector and the second vector.

[0130] Based on the above embodiments, optionally, the angle determination unit is further configured to: determine the angle between the first vector and the second vector as a third angle, and take the cross product of the first vector and the second vector as the third vector, and determine the first dot product result between the third vector and the direction vector of the positive direction of the second coordinate axis; if the first dot product result is less than zero, then the first angle of the first blade is the difference between 360° and the third angle; if the first dot product result is greater than zero, then the first angle of the first blade is the third angle.

[0131] Based on the above embodiments, optionally, the blade determination module is used to: determine the difference between the first angle of the first blade and the angle value of each target blade of the wind turbine in the previous frame; and take the target blade with the smallest angle difference in the difference results as the target blade corresponding to the first blade.

[0132] Based on the above embodiments, optionally, the process of determining the angle value of each target blade of the wind turbine in the previous frame includes:

[0133] If the previous frame is the first frame, then the second point cloud data of the wind turbine obtained by the drone scanning the second blade is acquired, and the angle value of each target blade of the wind turbine in the previous frame is determined based on the second point cloud data and the target coordinate system.

[0134] If the previous frame is not the first frame, then the angle value of the third blade of the wind turbine in the previous frame is determined. Based on the comparison result between the angle value of the third blade of the wind turbine and the angle value of each target blade of the wind turbine in the frame before the previous one, the target blade corresponding to the third blade and the target blades corresponding to the other blades besides the third blade are determined.

[0135] Based on the above embodiments, optionally, determining the angle value of each target blade of the wind turbine in the previous frame based on the second point cloud data and the target coordinate system includes:

[0136] Based on the second point cloud data, the angle value of the second blade is determined. According to the preset angle rule and the angle value of the second blade, the angle values ​​between the other blades and the preset horizontal line are determined. The preset angle rule is that the three blades are spaced 120° apart from each other.

[0137] All angle values ​​of the wind turbine blades are sorted in ascending order to obtain a first angle value, a second angle value, and a third angle value; the first angle value is less than the second angle value, and the second angle value is less than the third angle value;

[0138] The blade corresponding to the first angle value is taken as the first target blade, the blade corresponding to the second angle value is taken as the second target blade, and the blade corresponding to the third angle value is taken as the third target blade.

[0139] Based on the above embodiments, optionally, the first control module or the second control module includes a position information determination unit, which is used to: fit the first point cloud data to obtain the centerline of the first blade; draw a perpendicular line from the center point of the gimbal camera to the centerline of the first blade to obtain a first perpendicular line; determine the intersection of the first perpendicular line and the centerline of the first blade as the target position; convert the first coordinate point information of the target position into second coordinate point information relative to the center point of the field of view of the gimbal camera; determine and adjust the pitch angle and yaw angle of the gimbal camera based on the second coordinate point information; and adjust the center point of the field of view of the gimbal camera mounted on the UAV to align with the target position of the first blade based on the pitch angle and yaw angle of the gimbal camera.

[0140] Based on the above embodiments, optionally, the wind turbine blade inspection device includes a control unit, which is used to: determine the control parameters of the UAV based on the updated global flight path and the nonlinear model; the nonlinear model is used to predict the control parameters of the UAV based on the flight path; the control parameters include state variables and control variables; and send the control parameters of the UAV to the UAV control actuator to control the UAV to perform wind turbine blade inspection based on the control variables of the UAV.

[0141] The wind turbine blade inspection device provided in this embodiment of the invention can execute the wind turbine blade inspection method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0142] Example 4

[0143] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0144] Figure 6A schematic diagram of an electronic device that can be used to implement the wind turbine blade inspection method of embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0145] like Figure 6 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0146] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0147] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as wind turbine blade inspection methods.

[0148] In some embodiments, the wind turbine blade inspection method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded into and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the wind turbine blade inspection method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the wind turbine blade inspection method by any other suitable means (e.g., by means of firmware).

[0149] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transferring data and instructions to the storage system, the at least one input device, and the at least one output device.

[0150] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0151] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0152] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0153] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0154] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0155] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and no limitation is imposed herein.

[0156] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for inspecting wind turbine blades, characterized in that, The method includes: The first point cloud data of the wind turbine obtained by the UAV scanning the first blade in the current frame is acquired, and the first angle of the first blade is determined based on the first point cloud data. The first angle is used to describe the angle between the center line of the first blade and a preset horizontal line. The preset horizontal line is a straight line that passes through the center point of the wind turbine hub, is perpendicular to the tower of the wind turbine, and is parallel to the plane where the wind turbine blade is located. Based on the comparison between the first angle of the first blade and the angle value of each target blade of the wind turbine in the previous frame, the target blade corresponding to the first blade is determined, and the second angle of the target blade corresponding to the first blade in the previous frame is obtained. If the difference between the second angle and the first angle is less than a preset angle threshold, the center point of the field of view of the gimbal camera on the UAV is adjusted to be aligned with the target position of the first blade, so that the UAV can perform wind turbine blade inspection based on the global flight path of the previous frame; the target position is determined based on the first point cloud data. If the difference between the second angle and the first angle is greater than a preset angle threshold, the global flight path of the previous frame is updated based on the first angle to obtain the updated global flight path. Simultaneously, the center point of the field of view of the gimbal camera on the UAV is adjusted to align with the target position of the first blade, so that the UAV can perform wind turbine blade inspection based on the updated global flight path.

2. The method according to claim 1, characterized in that, The preset horizontal line is the first coordinate axis of the target coordinate system; the target coordinate system is a three-dimensional coordinate system, the origin of the target coordinate system is the center point of the wind turbine hub, and the target coordinate system includes a first coordinate axis, a second coordinate axis, and a third coordinate axis; the first coordinate axis is perpendicular to the wind turbine tower and parallel to the plane where the wind turbine blades are located; the second coordinate axis is perpendicular to the wind turbine tower and perpendicular to the plane where the wind turbine blades are located; the third coordinate axis is parallel to the wind turbine tower and parallel to the plane where the wind turbine blades are located. The first, second, and third coordinate axes are perpendicular to each other; Accordingly, determining the first angle of the first blade based on the first point cloud data includes: The first point cloud data is fitted to obtain the centerline of the first blade, and a first vector of the centerline of the first blade is determined; the first vector is the direction vector of the centerline of the first blade, and the starting point of the first vector is the origin of the target coordinate system. Determine a second vector for the first coordinate axis; the second vector is the direction vector of the positive direction of the first coordinate axis, and the starting point of the second vector is the origin of the target coordinate system; Based on the first vector and the second vector, the first angle of the first blade is determined.

3. The method according to claim 2, characterized in that, Determining the first angle of the first blade based on the first vector and the second vector includes: The angle between the first vector and the second vector is defined as the third angle, and the cross product of the first vector and the second vector is defined as the third vector. Determine the first dot product result between the third vector and the direction vector of the positive direction of the second coordinate axis; If the first dot product result is less than zero, then the first angle of the first blade is the difference between 360° and the third angle; If the first dot product result is greater than zero, then the first angle of the first blade is the third angle.

4. The method according to claim 2, characterized in that, Based on the comparison between the first angle of the first blade and the angle value of each target blade of the wind turbine in the previous frame, the target blade corresponding to the first blade is determined, including: The result of determining the difference between the first angle of the first blade and the angle value of each target blade of the wind turbine in the previous frame; The target blade with the smallest angle difference in the difference results is taken as the target blade corresponding to the first blade.

5. The method according to claim 4, characterized in that, The process of determining the angle value of each target blade of the wind turbine in the previous frame includes: If the previous frame is the first frame, then the second point cloud data of the wind turbine obtained by the drone scanning the second blade is acquired, and the angle value of each target blade of the wind turbine in the previous frame is determined based on the second point cloud data and the target coordinate system. If the previous frame is not the first frame, then the angle value of the third blade of the wind turbine in the previous frame is determined. Based on the comparison result between the angle value of the third blade of the wind turbine and the angle value of each target blade of the wind turbine in the frame before the previous one, the target blade corresponding to the third blade and the target blades corresponding to the other blades besides the third blade are determined.

6. The method according to claim 5, characterized in that, Based on the second point cloud data and the target coordinate system, the angle value of each target blade of the wind turbine in the previous frame is determined, including: Based on the second point cloud data, the angle value of the second blade is determined. According to the preset angle rule and the angle value of the second blade, the angle values ​​between the other blades and the preset horizontal line are determined. The preset angle rule is that the three blades are spaced 120° apart from each other. All angle values ​​of the wind turbine blades are sorted in ascending order to obtain a first angle value, a second angle value, and a third angle value; the first angle value is less than the second angle value, and the second angle value is less than the third angle value; The blade corresponding to the first angle value is taken as the first target blade, the blade corresponding to the second angle value is taken as the second target blade, and the blade corresponding to the third angle value is taken as the third target blade.

7. The method according to any one of claims 1 to 6, characterized in that, Adjusting the center point of the field of view of the gimbal camera mounted on the UAV to align with the target position of the first blade includes: The centerline of the first blade is obtained by fitting the first point cloud data. A perpendicular line is drawn from the center point of the gimbal camera to the centerline of the first blade to obtain the first perpendicular line. The intersection of the first perpendicular line and the centerline of the first blade is determined as the target position. The first coordinate point information of the target location is converted into the second coordinate point information relative to the center point of the field of view of the gimbal camera; Based on the second coordinate point information, determine and adjust the pitch and yaw angles of the gimbal camera; Based on the pitch and yaw angles of the gimbal camera, the center point of the field of view of the gimbal camera mounted on the UAV is adjusted to align with the target position of the first blade.

8. The method according to any one of claims 1 to 6, characterized in that, The drone performs wind turbine blade inspections based on the updated global flight path, including: Based on the updated global flight path and the nonlinear model, the control parameters of the UAV are determined; the nonlinear model is used to predict the control parameters of the UAV based on the flight path; the control parameters include state variables and control variables. The control parameters of the UAV are sent to the UAV control actuator, which controls the UAV to perform wind turbine blade inspection based on the control parameters of the UAV.

9. A wind turbine blade inspection device, characterized in that, The device includes: The data acquisition module is used to acquire the first point cloud data of the wind turbine obtained by the UAV scanning the first blade in the current frame, and to determine the first angle of the first blade based on the first point cloud data; the first angle is used to describe the angle between the center line of the first blade and a preset horizontal line; the preset horizontal line is a straight line that passes through the center point of the wind turbine hub, is perpendicular to the tower of the wind turbine, and is parallel to the plane where the wind turbine blade is located. The blade determination module is used to determine the target blade corresponding to the first blade based on the comparison result between the first angle of the first blade and the angle value of each target blade of the wind turbine in the previous frame, and to obtain the second angle of the target blade corresponding to the first blade in the previous frame. The first control module is used to adjust the center point of the field of view of the gimbal camera on the UAV to align with the target position of the first blade if the difference between the second angle and the first angle is less than a preset angle threshold, so that the UAV can perform wind turbine blade inspection based on the global flight path of the previous frame; the target position is determined based on the first point cloud data. The second control module is used to update the global flight path of the previous frame based on the first angle if the difference between the second angle and the first angle is greater than a preset angle threshold, and simultaneously adjust the center point of the field of view of the gimbal camera on the UAV to align with the target position of the first blade, so that the UAV can perform wind turbine blade inspection based on the updated global flight path.

10. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the wind turbine blade inspection method according to any one of claims 1-8.

11. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that are used to cause a processor to execute the wind turbine blade inspection method according to any one of claims 1-8.

12. A computer program product comprising a computer program that, when executed by a processor, implements the wind turbine blade inspection method according to any one of claims 1-8.

Images