Fan blade angle detection method and fan blade inspection method

Abstract

The present invention discloses a method for detecting and inspecting fan blade angles. The method comprises: determining first angle information of a previous frame of a fan blade; the first angle information is used to describe the angle between each target blade of the fan and a preset horizontal line; obtaining a first image of the current frame of the fan blade, and determining second angle information of the current frame of the fan blade based on the first image; determining third angle information of the current frame of the fan blade based on the matching result of the first angle information and the second angle information, until stopping the fan blade angle detection in response to a blade angle detection end instruction; the third angle information is used to describe the angle between each target blade of the fan and a preset horizontal line when the fan blade rotates from the previous frame to the current frame. The present invention determines the third angle information of the current frame of the fan blade through the matching result of the angle information of two adjacent frames, thereby improving the accuracy of real-time fan blade angle detection.

Description

Technical Field

[0001] The present invention relates to the technical field of fan detection, and in particular to a fan blade angle detection method and a fan blade inspection method. Background Art

[0002] Wind turbine inspections refer to the regular inspection and maintenance of wind turbines to ensure their safe and efficient operation. When using drones to inspect the condition of wind turbines (referred to as wind turbines) in a stopped, unlocked state, it is often necessary to pre-plan the drone's flight path to avoid collisions with the turbine blades during inspection, ensuring the safety of the drone during the inspection process. The "unlocked" state means the blades are not mechanically locked and can still rotate freely due to wind or inertia. Therefore, the change in blade angle is crucial during drone inspections.

[0003] Because it is impossible to obtain a complete image of the blade in one go during the inspection process, the information after image processing may be incomplete, affecting the accuracy of angle determination. In addition, the image processing process generally uses a point cloud segmentation algorithm to segment the information of each blade, tower and background object, but the point cloud segmentation efficiency is low and cannot guarantee real-time performance, thereby unable to guarantee the accuracy of the returned angle. Summary of the Invention

[0004] The present invention provides a fan blade angle detection method and a fan blade inspection method, so as to improve the accuracy of real-time fan blade angle detection.

[0005] According to one aspect of the present invention, a method for detecting a fan blade angle is provided, the method comprising:

[0006] Determine first angle information of the wind turbine blade in the previous frame; the first angle information is used to describe the angle between each target wind turbine blade and a preset horizontal line; the preset horizontal line is a straight line passing through the center point of the wind turbine hub, perpendicular to the wind turbine tower, and parallel to the plane on which the wind turbine blades are located;

[0007] Acquire a first image of a current frame of a wind turbine blade, and determine second angle information of the current frame of the wind turbine blade based on the first image; the second angle information is used to describe the angle between each wind turbine blade and a preset horizontal line; the second angle information does not match the target blade;

[0008] Based on the matching result of the first angle information and the second angle information, the third angle information of the current frame of the fan blade is determined until the fan blade angle detection is stopped in response to the blade angle detection end instruction; the third angle information is used to describe the angle between each target blade of the fan and the preset horizontal line when the fan blade rotates from the previous frame to the current frame; the third angle information corresponds to the first angle information.

[0009] According to another aspect of the present invention, a device for detecting an angle of a fan blade is provided, the device comprising:

[0010] a first angle determination module, configured to determine first angle information of a previous frame of a wind turbine blade; the first angle information is used to describe the angle between each target wind turbine blade and a preset horizontal line; the preset horizontal line is a straight line passing through the center point of the wind turbine hub, perpendicular to the wind turbine tower, and parallel to the plane on which the wind turbine blades are located;

[0011] a second angle determination module, configured to obtain a first image of a current frame of a wind turbine blade, and determine second angle information of the current frame of the wind turbine blade based on the first image; the second angle information is used to describe the angle between each wind turbine blade and a preset horizontal line; and the second angle information does not match the target blade;

[0012] A third angle determination module is used to determine the third angle information of the fan blade in the current frame based on the matching result of the first angle information and the second angle information, until the fan blade angle detection is stopped in response to the blade angle detection end instruction; the third angle information is used to describe the angle between each target blade of the fan and the preset horizontal line when the fan blade rotates from the previous frame to the current frame; the third angle information corresponds to the first angle information.

[0013] According to another aspect of the present invention, a method for inspecting fan blades is provided, which adopts the above-mentioned method for detecting the angle of fan blades, and the method comprises:

[0014] Based on the wind turbine blade angle detection method, the target angle of the wind turbine blades in each frame is determined; the target angle is used to describe the angle between each target wind turbine blade and a preset horizontal line; wherein the preset horizontal line is a straight line passing through the center point of the wind turbine hub, perpendicular to the wind turbine tower, and parallel to the plane on which the wind turbine blades are located;

[0015] Planning the inspection route of the UAV based on the target angle of each frame of the wind turbine blade;

[0016] The wind turbine blades are inspected based on the inspection route.

[0017] According to another aspect of the present invention, an electronic device is provided, comprising:

[0018] at least one processor; and

[0019] a memory communicatively connected to the at least one processor; wherein,

[0020] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the wind blade angle detection method or the wind blade inspection method described in any embodiment of the present invention.

[0021] According to another aspect of the present invention, a computer-readable storage medium is provided, which stores computer instructions, and the computer instructions are used to enable a processor to implement the wind turbine blade angle detection method or wind turbine blade inspection method described in any embodiment of the present invention when executed.

[0022] The technical solution of an embodiment of the present invention determines the first angle information of the wind turbine blade in the previous frame; the first angle information is used to describe the angle between each target blade of the wind turbine and a preset horizontal line; the preset horizontal line is a straight line passing through the center point of the wind turbine hub, perpendicular to the wind turbine tower, and parallel to the plane where the wind turbine blade is located; ensuring the accuracy of the angle detection of each target blade in the previous frame. Furthermore, the first image of the current frame of the fan blade is obtained, and the second angle information of the current frame of the fan blade is determined based on the first image; the second angle information is used to describe the angle between each blade of the fan and the preset horizontal line; at this time, the second angle information target blade is not matched, and only the angle information of each blade can be clarified, but the specific angle information of the target blade rotated from the previous frame to the target blade of the current frame is still unclear. Therefore, based on the matching result of the first angle information and the second angle information, the third angle information of the current frame of the fan blade is determined, and the third angle information is used to describe the angle between each target blade of the fan and the preset horizontal line when the fan blade rotates from the previous frame to the current frame; the third angle information corresponds to the first angle information, and the angle of each target blade in the current frame is accurately determined. Subsequently, the third angle information of the current frame of the fan blade is used to determine the angle information of each target blade in the next frame of the fan blade, until the fan blade angle detection is stopped in response to the blade angle detection end instruction, thereby realizing the tracking detection of the real-time angle information of each target blade and improving the accuracy of real-time fan blade angle detection.

[0023] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0025] Figure 1 This is a flow chart of a method for detecting a fan blade angle according to an embodiment of the present invention;

[0026] Figure 2 is a schematic diagram of a fan blade applicable to an embodiment of the present invention;

[0027] Figure 3 is a flow chart of another method for detecting the angle of a fan blade provided in accordance with an embodiment of the present invention;

[0028] Figure 4 2 is a schematic structural diagram of a fan blade angle detection device provided according to an embodiment of the present invention;

[0029] Figure 5 This is a flow chart of a wind turbine blade inspection method provided according to an embodiment of the present invention;

[0030] Figure 6 3 is a schematic structural diagram of an electronic device for implementing a method for detecting a fan blade angle according to an embodiment of the present invention. DETAILED DESCRIPTION

[0031] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0032] It should be noted that the terms "first", "second", "third", "fourth", "fifth", "sixth", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0033] Example 1

[0034] Figure 1 This is a flow chart of a method for detecting the angle of a fan blade provided by an embodiment of the present invention. This embodiment can be applied to the real-time detection of the angle of a fan blade during the inspection of the fan blade by a drone. The method can be executed by a fan blade angle detection device, which can be implemented in the form of hardware and / or software. The fan blade angle detection device can be configured in any electronic device with network communication function. Figure 1 As shown, the fan blade angle detection method of the present invention includes the following process:

[0035] S110. Determine first angle information of a previous frame of a wind turbine blade; the first angle information is used to describe the angle between each target wind turbine blade and a preset horizontal line; the preset horizontal line is a straight line passing through the center point of the wind turbine hub, perpendicular to the wind turbine tower, and parallel to the plane where the wind turbine blades are located.

[0036] The present invention uses a drone to inspect the blades of a wind turbine that is in a stopped but unlocked state. The stopped but unlocked state means that the blades are not mechanically locked and can still rotate freely due to wind or inertia. Therefore, it is very important to determine the inspection route of the drone during the inspection process. The inspection route of the drone is affected by the angles of the wind turbine blades at different times. Therefore, during the drone inspection process, it is necessary to obtain the angle of the wind turbine blades in real time. The angle of the wind turbine blade of the present invention can be the angle between the blade and a preset horizontal line. The preset horizontal line can be a straight line passing through the center point of the wind turbine hub and perpendicular to the wind turbine tower, as well as a straight line parallel to the plane where the wind turbine blades are located, such as Figure 2 The dashed line shown may be a preset horizontal line.

[0037] It should be noted that the images of the present invention include radar images and visual images. The radar images can be collected using a laser radar to collect three-dimensional point cloud data of the wind turbine blades. The visual images can be collected using a visible light camera.

[0038] Specifically, the wind turbine blade angles are determined by analyzing radar images captured by drones during inspections, either in real-time via lidar scanning or visual images captured by visible light cameras. The radar or visual images may contain 3D data of a particular blade. By analyzing the 3D data in these images, the angle of the current blade is determined. Furthermore, the angles of other blades are determined based on the 120° spacing between each blade.

[0039] Furthermore, after obtaining the radar image or visual image, the three-dimensional data information of the local blade contained in the radar image or visual image can be converted into three-dimensional data information of the wind turbine coordinate system. The specific process includes:

[0040] 1. The process of converting the 3D data information of the local blade contained in the radar image into the 3D data information of the wind turbine coordinate system is as follows: the 3D data information of the local blade contained in the radar image is transformed from the lidar coordinate system to the drone body coordinate system, then from the drone body coordinate system to the world coordinate system, and finally from the world coordinate system to the wind turbine coordinate system; the origin of the world coordinate system is the drone take-off point;

[0041] a. Transformation from LiDAR coordinate system to UAV body coordinate system

[0042] The laser radar is installed on the drone body, and there is a fixed rigid transformation relationship between the two:

[0043] ;

[0044] in: : point coordinates in the laser radar coordinate system; : Point coordinates in the drone body coordinate system; : The transformation matrix from the laser radar to the UAV body is obtained by external parameter calibration. The transformation matrix includes a rotation matrix and a translation vector , which has the following structure:

[0045] .

[0046] b. Transformation from the drone body coordinate system to the world coordinate system

[0047] The drone's posture during flight It can be obtained through IMU+GPS / NMEA fusion (such as from the flight control (NMEA) or odometer (IMU+GPS)). The specific formula is as follows:

[0048] ;

[0049] in: : Point coordinates in the world coordinate system; : Represents the transformation matrix from the drone body coordinates to the wind turbine coordinate system, which is updated over time.

[0050] c. Transformation from world coordinate system to wind turbine coordinate system (based on wind turbine GPS + altitude + wind turbine yaw angle)

[0051] The GPS (WGS84) and height of the wind turbine hub, the direction and attitude of the wind turbine tower, and the GPS coordinate origin of the take-off point are known. Use the WGS84→ECEF→ENU conversion to obtain the position of the wind turbine in the world coordinate system; among them, WGS84 is an Earth-centered, Earth-fixed geodetic datum and terrestrial reference system. 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 coordinate origin is fixed at the center of mass of the earth, and the coordinate axes are synchronized with the rotation of the earth, so it can stably describe the position of the surface and near-Earth objects. ENU (East-North-Up) is a right-handed rectangular coordinate system widely used in local space positioning. It is often used to describe the relative position or motion state of an object relative to a reference point. The specific formula is as follows:

[0052] ;

[0053] in: : The coordinates of the wind turbine in ENU; : The rotation matrix from the world coordinate system to the wind turbine coordinate system; is the coordinate of the point cloud in the world coordinate system; is the coordinate of the point cloud in the wind turbine coordinate system.

[0054] d. Transformation from LiDAR coordinate system to wind turbine coordinate system

[0055] From the above steps a, b, and c, the conversion formula from the radar coordinate system to the wind turbine coordinate system is:

[0056] ;

[0057] Among them, first the coordinate point of the laser radar coordinate system Transform the coordinate points to the drone body coordinate system , and then transform the coordinate point of the world coordinate system into the body posture , and finally converted to the fan body coordinate system This method is used to project radar point cloud data into the wind turbine coordinate system in real time, facilitating mapping, fusion, or perception decision-making.

[0058] 2. The process of converting the three-dimensional data information of the local blade contained in the visual image into the three-dimensional data information of the wind turbine coordinate system is as follows: the three-dimensional data information of the local blade contained in the visual image is transformed from the visual image coordinate system to the wind turbine coordinate system;

[0059] For pixels in visual images , if its corresponding depth d is known, it can be projected to the camera coordinate system through the camera intrinsic parameters:

[0060] ;

[0061] in: : Camera intrinsic parameter matrix, including focal length and principal point parameters; d: Depth value, which can be approximated by the preset "distance to wind turbine blades" in the inspection mission of the UAV.

[0062] Then, the external reference of the drone body is transmitted through the camera. And the transformation matrix from the drone body coordinate to the wind turbine coordinate system And the transformation matrix from the world coordinate system to the fan coordinate system , we can get the change formula of the fan coordinate system:

[0063] ;

[0064] in: The rigid transformation of the visual camera relative to the UAV body is obtained by offline calibration; : Provided in real time by the drone’s odometer (IMU+GPS); : Obtained by transforming the world coordinate system to the fan coordinate system.

[0065] Optionally, the wind turbine coordinate system can be a target coordinate system. A target coordinate system is established with its origin at the center of the wind turbine hub. The target coordinate system is a three-dimensional coordinate system consisting of a first axis, a second axis, and a third axis. The first axis is perpendicular to the wind turbine tower and parallel to the plane of the wind turbine blades. The second axis is perpendicular to the wind turbine tower and perpendicular to the plane of the wind turbine blades. The third axis is parallel to the wind turbine tower. The first axis (y-axis), the second axis (x-axis), and the third axis (z-axis) are mutually perpendicular. Establishing the target coordinate system ensures that each radar image or visual image is processed within the same coordinate system, making the determination of angle information more accurate.

[0066] In an embodiment of the present invention, optionally, determining the first angle information of a previous frame of a wind turbine blade includes steps A1-A2:

[0067] Step A1: If the previous frame of the wind blade is the first frame of the wind blade, obtain a second image of the first frame, and determine first angle information of the previous frame of the wind blade according to the second image and the target coordinate system.

[0068] The second image is obtained by scanning a wind turbine blade with a drone. The second image can be a radar image or a visual image, and the data contained in the second image is three-dimensional point cloud data.

[0069] Specifically, in response to a blade angle detection start command, the drone begins laser radar imaging from the center of the wind turbine hub, obtains information about the center of the wind turbine hub, and then moves to a specific wind turbine blade to begin inspection. When moving to a specific wind turbine blade, a second image is obtained. The point cloud data of the second image is further analyzed in conjunction with the target coordinate system to obtain the angle value of the wind turbine blade in the second image. This angle value is then matched with the first target blade. Furthermore, based on a preset angle rule and the angle value of the wind turbine blade in the second image, the angle value of the second target blade and the angle value of the third target blade are determined, thereby accurately obtaining the angle value of each target blade. The preset angle rule is that the three blades are spaced 120 degrees apart.

[0070] Optionally, the first angle information of the previous frame of the wind turbine blade is determined based on the second image and the target coordinate system, including: obtaining a first point cloud value in the second image, the first point cloud value being the point cloud value corresponding to the first coordinate axis in the point cloud data contained in the second image. The point cloud value with the largest numerical value in the first point cloud value is used as the second point cloud value, and a third point cloud value corresponding to the second point cloud value is determined, the third point cloud value being the point cloud value of the third coordinate axis corresponding to the position information of the same point cloud data described together with the second point cloud value. Based on the second point cloud value y and the third point cloud value z, the first angle value between the first target blade and the preset horizontal line is determined; specifically, the first angle value can be expressed by the formula: θ=arctan(y / z). Further, based on the preset angle rule and the first angle value, the second angle value between the second target blade and the preset horizontal line, and the third angle value between the third target blade and the preset horizontal line are determined; the preset angle rule is that the three blades are spaced 120° apart. The first angle value, the second angle value and the third angle value are used as the first angle information of the previous frame of the wind turbine blade, and the first angle value corresponds to the first target blade, the second angle value corresponds to the second target blade, and the third angle value corresponds to the third target blade.

[0071] For example, Figure 2As shown, assuming that the second image is obtained by a UAV performing a lidar scan on the wind turbine blade A, the second image is analyzed to obtain the second point cloud value y and the third point cloud value z, and further based on the formula θ=arctan(y / z), the first angle value θ between the wind turbine blade A and the preset horizontal line is determined, and the wind turbine blade A is used as the first target blade; the second target blade B differs from the first target blade A by 120°, and the third target blade C differs from the second target blade B by 120°, then the second angle value of the second target blade B is θ+120°, and the third angle value of the third target blade C is θ+240°.

[0072] The embodiments of the present invention achieve the ability to calculate the angle of the current blade even when using local blade point cloud data, thereby greatly improving the robustness of the algorithm.

[0073] Step A2: If the previous frame of the fan blade is a frame other than the first frame of the fan blade, the first angle information of the previous frame of the fan blade is determined based on the matching result of the angle information of the previous frame of the fan blade determined according to the image of the previous frame of the fan blade and the angle information of the previous frame of the fan blade.

[0074] Specifically, the angle information of the previous frame of the fan blade is used to describe the angle between each target fan blade and a preset horizontal line, that is, to know the angle value corresponding to each target blade. The angle information of the previous frame of the fan blade determined based on the image of the previous frame of the fan blade cannot determine which angle information corresponds to the target blade. Therefore, it is necessary to match and compare the angle information of the previous frame of the fan blade determined based on the image of the previous frame of the fan blade with the angle information of the previous frame of the fan blade to accurately obtain the first angle information of the previous frame of the fan blade.

[0075] In an embodiment of the present invention, by determining whether the previous frame of the wind blade is the first frame of the wind blade, different methods are used to accurately obtain the first angle information of the previous frame of the wind blade, so as to facilitate the subsequent use of the first angle information to determine the accuracy of the third angle information of the current frame of the wind blade.

[0076] S120. Acquire a first image of a current frame of a wind turbine blade, and determine second angle information of the current frame of the wind turbine blade based on the first image; the second angle information is used to describe the angle between each wind turbine blade and a preset horizontal line; the second angle information does not match the target blade.

[0077] The first image is obtained by scanning the first blade with a drone. The first image may be a radar image or a visual image, and the data contained in the first image is three-dimensional point cloud data.

[0078] Specifically, determining the second angle information of the wind turbine blade in the current frame based on the first image may include: obtaining a fourth point cloud value in the first image, where the fourth point cloud value is the point cloud value corresponding to the first coordinate axis in the point cloud data contained in the first image. Using the point cloud value with the largest value among the fourth point cloud values ​​as the fifth point cloud value, and determining a sixth point cloud value in the first image corresponding to the fifth point cloud value, where the sixth point cloud value is the point cloud value of the third coordinate axis corresponding to the position information that the fifth point cloud value and the sixth point cloud value describe together. Based on the fifth point cloud value y1 and the sixth point cloud value z1, determining a fourth angle value between the first blade and a preset horizontal line; the fourth angle value θ1 can be expressed using the formula: θ1 = arctan(y1 / z1). Further, based on the preset angle rule and the first angle value, determining a fifth angle value between the second blade and the preset horizontal line, and a sixth angle value between the third blade and the preset horizontal line. The fourth, fifth, and sixth angle values ​​are determined as the second angle information of the wind turbine blade in the current frame.

[0079] S130. Determine the third angle information of the fan blade in the current frame based on the matching result of the first angle information and the second angle information, until the fan blade angle detection is stopped in response to the blade angle detection end instruction; the third angle information is used to describe the angle between each target blade of the fan and the preset horizontal line when the fan blade rotates from the previous frame to the current frame; the third angle information corresponds to the first angle information.

[0080] Specifically, the second angle information cannot determine whether it matches the angle information of the target blade in the first angle information. Therefore, it is necessary to match the first angle information with the second angle information to accurately obtain the angle between each target blade of the fan and the preset horizontal line when the fan blade rotates from the previous frame to the current frame, that is, to accurately obtain the third angle information of the fan blade in the current frame.

[0081] Because the rotation angle of the blades in two adjacent frames is relatively small, the maximum rotation angle is set, and the angle value of each target blade in the first angle information is added to the maximum rotation angle to obtain the reference angle value of the target blade. Then, the angle value of each blade in the second angle information is compared with the reference angle value. If the difference between the reference angle values ​​is less than the preset value, it means that the angle in the second angle information is the angle of the target blade corresponding to the reference angle value in the current frame. For example, the first angle information is 20°, 140°, 260°; the second angle information is 148°, 28°, 268°, the maximum rotation angle is 10°, and the preset value is 2°; the reference angle values ​​are 30°, 150°, 270°; the difference between the reference angle value 30° and 28° in the second angle information is 2°; the difference between the reference angle values ​​150° and 148° is 2°; the difference between the reference angle values ​​270° and 268° is 2°; then the third angle information is 28°, 148°, 268°; that is, when the target table blade moves from the previous frame to the current frame, the angle changes from 20° to 28°, 140° to 148°, and 260° to 268°.

[0082] Furthermore, after determining the third angle information of the current frame of the fan blade, continue to obtain the next frame image of the fan blade, and determine the angle information of each blade in the next frame of the fan blade based on the next frame image of the fan blade, and then combine the third angle information of the current frame of the fan blade with the angle information of each blade in the next frame of the fan blade to determine the angle information of the target blade in the next frame of the fan blade, and so on. Each time, the angle information of the target blade in the current frame is determined based on the angle information of two consecutive frames, and the angle information of the previous frame accurately corresponds to the information of each target blade. Therefore, the angle value of a specific blade can be continuously output in real time until the blade angle detection end instruction is responded to and the fan blade angle detection is stopped to avoid inaccurate determination of the blade angle due to the accuracy of the information obtained from the picture.

[0083] The technical solution of an embodiment of the present invention determines the first angle information of the wind turbine blade in the previous frame; the first angle information is used to describe the angle between each target blade of the wind turbine and a preset horizontal line; the preset horizontal line is a straight line passing through the center point of the wind turbine hub, perpendicular to the wind turbine tower, and parallel to the plane where the wind turbine blade is located; ensuring the accuracy of the angle detection of each target blade in the previous frame. Furthermore, the first image of the current frame of the fan blade is obtained, and the second angle information of the current frame of the fan blade is determined based on the first image; the second angle information is used to describe the angle between each blade of the fan and the preset horizontal line; at this time, the second angle information target blade is not matched, and only the angle information of each blade can be clarified, but the specific angle information of the target blade rotated from the previous frame to the target blade of the current frame is still unclear. Therefore, based on the matching result of the first angle information and the second angle information, the third angle information of the current frame of the fan blade is determined, and the third angle information is used to describe the angle between each target blade of the fan and the preset horizontal line when the fan blade rotates from the previous frame to the current frame; the third angle information corresponds to the first angle information, and the angle of each target blade in the current frame is accurately determined. Subsequently, the third angle information of the current frame of the fan blade is used to determine the angle information of each target blade in the next frame of the fan blade, until the fan blade angle detection is stopped in response to the blade angle detection end instruction, thereby realizing the tracking detection of the real-time angle information of each target blade and improving the accuracy of real-time fan blade angle detection.

[0084] Example 2

[0085] Figure 3 This is a flow chart of another method for detecting the angle of a fan blade provided by an embodiment of the present invention. The technical solution of this embodiment further optimizes the aforementioned embodiment of "determining the third angle information of the current frame of the fan blade according to the matching result of the first angle information and the second angle information" on the basis of the above embodiment. This embodiment can be combined with various optional solutions in one or more of the above embodiments. Figure 3 As shown, the fan blade angle detection method includes the following processes:

[0086] S210. Determine the first angle information of the wind turbine blade in the previous frame; the first angle information is used to describe the angle between each target blade of the wind turbine and a preset horizontal line; the preset horizontal line is a straight line passing through the center point of the wind turbine hub, perpendicular to the wind turbine tower, and parallel to the plane where the wind turbine blades are located.

[0087] S220, obtaining a first image of a current frame of a wind turbine blade, and determining second angle information of the current frame of the wind turbine blade based on the first image; the second angle information is used to describe the angle between each wind turbine blade and a preset horizontal line; the second angle information does not match the target blade.

[0088] S230 , perform pairwise matching on each angle value included in the first angle information and each angle value included in the second angle information, to obtain 9 matching pairs.

[0089] For example, the first angle information is 20°, 140°, and 260°. The second angle information is 148°, 28°, and 268°. Each angle value included in the first angle information is matched with each angle value included in the second angle information. The resulting nine matching pairs are: 20° and 148°, 20° and 28°, 20° and 268°, 140° and 148°, 140° and 28°, 140° and 268°, 260° and 148°, 260° and 28°, and 260° and 268°.

[0090] S240 , calculating the difference between the angle value of the first angle information and the angle value of the second angle information of each matching pair to obtain a candidate difference value for each matching pair.

[0091] For example, the difference between the 9 matching pairs in the above example can be:

[0092] 20° and 28°: 28°-20°=8°;

[0093] 20° and 148°: 148° - 20° = 128°;

[0094] 20° and 268°: 268°-20°=248°;

[0095] 140° and 28°: 28° - 140° = - 112°;

[0096] 140° and 148°: 148°-140°=8°;

[0097] 140° and 268°: 268° - 140° = 128°;

[0098] 260° and 28°: 28° - 260° = - 232°;

[0099] 260° and 148°: 148° - 260° = - 112°;

[0100] 260° and 268°: 268°-260°=8°;

[0101] Specifically, the candidate difference values ​​include 8°, 128°, 248°, −112°, 8°, 128°, −232°, −112°, and 8°.

[0102] In an embodiment of the present invention, optionally, after subtracting the angle value of the first angle information from the angle value of the second angle information of each matching pair to obtain a candidate difference value for each matching pair, the method further includes: performing a preset operation on the candidate difference value to update the candidate difference value; the preset operation is an operation of adding 360° to the candidate difference value and then taking the modulus. Specifically, the operation of adding 360° to the candidate difference value and then taking the modulus can be to obtain a reference candidate difference value by adding 360° to the candidate difference value, and if the reference candidate difference value exceeds 360°, then the candidate difference value is not updated; if the reference candidate difference value does not exceed 360°, then the reference candidate difference value is used as the candidate difference value.

[0103] For example, the candidate difference values ​​include 8°, 128°, 248°, -112°, 8°, 128°, -232°, -112° and 8°. The candidate difference values ​​are subjected to a preset operation and updated. The updated candidate difference values ​​can be: 8°, 128°, 248°, 148°, 8°, 128°, 128°, 148° and 8°.

[0104] In order to take into account the 360° annular distribution characteristics of the blades, the embodiment of the present invention introduces an annular angle compensation mechanism to automatically correct the cross-cycle angle to avoid matching errors caused by angle cycles.

[0105] S250: Take the matching pairs corresponding to three candidate difference values ​​with the same numerical value among the candidate difference values ​​as target matching pairs.

[0106] For example, the candidate differences in the above example include 8°, 128°, 248°, -112°, 8°, 128°, -232°, -112° and 8°, then 8° is the three candidate differences with the same value in the candidate differences, and the matching pairs corresponding to the three candidate differences with the same value in the candidate differences are used as target matching pairs, and the target matching pairs are: 20° and 28°, 140° and 148°, and 260° and 268° respectively.

[0107] In an embodiment of the present invention, optionally, the matching pairs corresponding to three candidate difference values ​​with the same numerical value in the candidate difference values ​​are used as target matching pairs, including: if there are three first difference values ​​and three second difference values ​​in the candidate difference values, determining whether the first difference value and the second difference value are less than a preset angle. If the first difference value is less than the preset angle, the matching pair corresponding to the first difference value is used as the target matching pair. If the second difference value is less than the preset angle, the matching pair corresponding to the second difference value is used as the target matching pair. In this case, because the rotation angle of the blades of the wind turbine blades in the shutdown but not locked state is relatively small, the preset angle is set according to the actual situation. For example, the updated candidate difference values ​​can be: 8°, 128°, 248°, 148°, 8°, 128°, 128°, 148°, and 8°; the first difference value is 8°, the second difference value is 128°, and assuming the preset angle is 20°, the matching pair corresponding to 128° is an invalid matching pair, and the matching pair corresponding to 8° is the target matching pair. The embodiment of the present invention proposes invalid matching results by determining whether there are multiple groups of three candidate difference values ​​and comparing the multiple groups of three candidate difference values ​​with preset angles, thereby achieving accurate determination of target matching pairs.

[0108] S260. Determine the third angle information of the current frame of the fan blade according to the target matching pair, so as to determine the angle information of each target blade of the next frame of the fan blade based on the third angle information, until the fan blade angle detection is stopped in response to the blade angle detection end instruction; the angle value of the second angle information in the target matching pair and the angle value of the first angle information belong to the same target blade.

[0109] For example, the target matching pairs in the above example are: 20° and 28°, 140° and 148°, and 260° and 268°, respectively. Then, the third angle information of the wind turbine blade in the current frame is 28°, 148°, and 268°, that is, target blade A turns from 20° to 28°, target blade B turns from 140° to 148°, and target blade C turns from 260° to 268°. Similarly, the angle information of each target blade in subsequent frames is further determined according to the method of the present invention, that is, by matching the blade angles of two consecutive frames, the identity consistency of each target blade is ensured. For example, the present invention can obtain the angle sequence of target blade A: 20°→28°→36°..., and output the real-time angle change curve of the independent blade.

[0110] The technical solution of an embodiment of the present invention determines first angle information of a wind turbine blade in a previous frame; the first angle information is used to describe the angle between each target wind turbine blade and a preset horizontal line; the preset horizontal line is a line passing through the center point of the wind turbine hub, perpendicular to the wind turbine tower, and parallel to the plane on which the wind turbine blades lie. A first image of the wind turbine blade in the current frame is obtained, and second angle information of the wind turbine blade in the current frame is determined based on the first image; the second angle information is used to describe the angle between each wind turbine blade and the preset horizontal line; the second angle information does not match the target blade. Furthermore, each angle value included in the first angle information is matched with each angle value included in the second angle information to obtain 9 groups of matching pairs. The angle value of the first angle information of each matching pair is subtracted from the angle value of the second angle information to obtain candidate difference values ​​of each matching pair. Based on the principle of consistency of angle increments of homologous blades, the matching pairs corresponding to the three candidate difference values ​​with the same numerical values ​​in the candidate difference values ​​are taken as target matching pairs. Finally, the third angle information of the current frame of the wind turbine blade is determined based on the target matching pairs. The angle value of the second angle information in the target matching pair and the angle value of the first angle information belong to the same target blade, thereby realizing accurate determination of the third angle information, until the wind turbine blade angle detection is stopped in response to the blade angle detection end instruction, thereby realizing tracking and detection of the real-time angle information of each target blade, and improving the accuracy of real-time wind turbine blade angle detection.

[0111] Example 3

[0112] Figure 4 This is a schematic diagram of the structure of a fan blade angle detection device provided by an embodiment of the present invention. This embodiment can be used to detect the fan blade angle in real time during the inspection of the fan blades by a drone. The fan blade angle detection device can be implemented in the form of hardware and / or software. The fan blade angle detection device can be configured in any electronic device with network communication function. Figure 4 As shown, the fan blade angle detection device includes:

[0113] A first angle determination module 310 is configured to determine first angle information of a wind turbine blade in a previous frame; the first angle information is used to describe the angle between each target wind turbine blade and a preset horizontal line; the preset horizontal line is a straight line passing through the center point of the wind turbine hub, perpendicular to the wind turbine tower, and parallel to the plane on which the wind turbine blades are located;

[0114] A second angle determination module 320 is configured to obtain a first image of a wind turbine blade in a current frame and determine second angle information of the wind turbine blade in the current frame based on the first image; the second angle information is configured to describe the angle between each wind turbine blade and a preset horizontal line; and the second angle information does not match the target blade.

[0115] The third angle determination module 330 is used to determine the third angle information of the fan blade in the current frame based on the matching result of the first angle information and the second angle information, until the fan blade angle detection is stopped in response to the blade angle detection end instruction; the third angle information is used to describe the angle between each target blade of the fan and the preset horizontal line when the fan blade rotates from the previous frame to the current frame; the third angle information corresponds to the first angle information.

[0116] On the basis of the above embodiment, optionally, a target coordinate system is established, the coordinate origin of the target coordinate system is the center point of the wind turbine hub; the target coordinate system is a three-dimensional coordinate system, 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 tower of the wind turbine and parallel to the plane where the wind turbine blades are located; the second coordinate axis is perpendicular to the tower of the wind turbine and perpendicular to the plane where the wind turbine blades are located; the third coordinate axis is parallel to the tower of the wind turbine; the first coordinate axis, the second coordinate axis and the third coordinate axis are perpendicular to each other.

[0117] Based on the above embodiment, optionally, the first angle determination module includes a first judgment unit and a second judgment unit; the first judgment unit is used to obtain a second image of the first frame if the previous frame of the wind blade is the first frame of the wind blade, and determine the first angle information of the previous frame of the wind blade according to the second image and the target coordinate system; the second judgment unit is used to determine the first angle information of the previous frame of the wind blade based on a matching result of the angle information of the previous frame of the wind blade determined based on the image of the previous frame of the wind blade and the angle information of the previous frame of the wind blade if the previous frame of the wind blade is other frames except the first frame of the wind blade.

[0118] Based on the above embodiment, optionally, the second image is obtained by performing a laser radar scan of a wind turbine blade by a drone; the first judgment unit is used to obtain a first point cloud value in the second image, the first point cloud value being the point cloud value corresponding to the first coordinate axis in the point cloud data contained in the second image; the point cloud value with the largest value in the first point cloud value is used as the second point cloud value, and a third point cloud value corresponding to the second point cloud value is determined, the third point cloud value being the point cloud value corresponding to the third coordinate axis that jointly describes the position information of the same point cloud data with the second point cloud value; based on the second point cloud value and the third point cloud value, a first angle value between the first target blade and the preset horizontal line is determined; according to the preset angle rule and the first angle value, a second angle value between the second target blade and the preset horizontal line, and a third angle value between the third target blade and the preset horizontal line are determined; the preset angle rule is that the three blades are spaced 120° apart; the first angle value, the second angle value and the third angle value are used as the first angle information of the previous frame of the wind turbine blade, and the first angle value corresponds to the first target blade, the second angle value corresponds to the second target blade, and the third angle value corresponds to the third target blade.

[0119] Based on the above embodiment, optionally, the first image is obtained by a UAV performing a laser radar scan on a wind turbine blade, and the second angle determination module is used to obtain a fourth point cloud value in the first image, the fourth point cloud value being the point cloud value corresponding to the first coordinate axis in the point cloud data contained in the first image; taking the point cloud value with the largest value in the fourth point cloud value as the fifth point cloud value, and determining the sixth point cloud value corresponding to the fifth point cloud value in the first image, the sixth point cloud value being the point cloud value of the third coordinate axis corresponding to the position information of the same point cloud data described together with the fifth point cloud value; determining the fourth angle value between the first blade and the preset horizontal line based on the fifth point cloud value and the sixth point cloud value; determining the fifth angle value between the second blade and the preset horizontal line and the sixth angle value between the third blade and the preset horizontal line according to the preset angle rule and the first angle value; determining the fourth angle value, the fifth angle value and the sixth angle value as the second angle information of the current frame of the wind blade.

[0120] Based on the above embodiment, optionally, the third angle determination module includes a first matching pair determination unit, a difference determination unit, a second matching pair determination unit and an angle determination unit; the first matching pair determination unit is used to match each angle value included in the first angle information with each angle value included in the second angle information in pairs to obtain 9 groups of matching pairs; the difference determination unit is used to differ the angle value of the first angle information of each matching pair from the angle value of the second angle information to obtain candidate difference values ​​for each matching pair; the second matching pair determination unit is used to take the matching pairs corresponding to the three candidate difference values ​​with the same numerical value in the candidate difference values ​​as target matching pairs; the angle determination unit is used to determine the third angle information of the current frame of the wind blade according to the target matching pair; the angle value of the second angle information in the target matching pair and the angle value of the first angle information belong to the same target blade.

[0121] Based on the above embodiment, optionally, the difference determination unit is further used to: perform a preset operation on the candidate difference to update the candidate difference; the preset operation is an operation of adding 360° to the candidate difference and then taking the modulus.

[0122] Based on the above embodiment, optionally, the second matching pair determination unit is further used to: if there are three first differences and three second differences in the candidate differences, determine whether the first difference and the second difference are less than a preset angle; if the first difference is less than the preset angle, use the matching pair corresponding to the first difference as the target matching pair; if the second difference is less than the preset angle, use the matching pair corresponding to the second difference as the target matching pair.

[0123] The fan blade angle detection device provided in the embodiment of the present invention can execute the fan blade angle detection method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0124] Example 4

[0125] Figure 5 This is a flow chart of a wind turbine blade inspection method provided by an embodiment of the present invention. This embodiment is applicable to situations where a UAV inspects wind turbine blades. The method can be executed by a wind turbine blade inspection device. The wind turbine blade inspection device can be implemented in the form of hardware and / or software. The wind turbine blade inspection device can be configured in any electronic device with network communication function. Figure 5 As shown, the wind turbine blade inspection method of the present invention includes the following process:

[0126] S410. Based on the wind turbine blade angle detection method, determine the target angle of the wind turbine blades in each frame; the target angle is used to describe the angle between each target blade of the wind turbine and a preset horizontal line; wherein the preset horizontal line is a straight line passing through the center point of the wind turbine hub and perpendicular to the wind turbine tower, and parallel to the plane where the wind turbine blades are located.

[0127] S420. Plan an inspection route for the drone based on the angle of each frame of the wind turbine blades.

[0128] S430: Inspect the wind turbine blades based on the inspection route.

[0129] Based on the above embodiment, optionally, determining the target angle of the fan blades for each frame based on the fan blade angle detection method includes:

[0130] Determine first angle information of the wind turbine blade in the previous frame; the first angle information is used to describe the angle between each target wind turbine blade and a preset horizontal line; wherein the preset horizontal line is a straight line passing through the center point of the wind turbine hub, perpendicular to the wind turbine tower, and parallel to the plane on which the wind turbine blades are located;

[0131] Acquire a first image of a current frame of a wind turbine blade, and determine second angle information of the current frame of the wind turbine blade based on the first image; wherein the second angle information is used to describe the angle between each wind turbine blade and a preset horizontal line; and the second angle information does not match the target blade;

[0132] Based on the matching result of the first angle information and the second angle information, the third angle information of the current frame of the fan blade is determined, and the third angle information of the current frame of the fan blade is used as the target angle of the current frame of the fan blade until the fan blade angle detection is stopped in response to the blade angle detection end instruction; the third angle information is used to describe the angle between each target blade of the fan and the preset horizontal line when the fan blade rotates from the previous frame fan blade to the current frame fan blade; the third angle information corresponds to the first angle information.

[0133] On the basis of the above embodiment, optionally: a target coordinate system is established, the coordinate origin of the target coordinate system is the center point of the wind turbine hub; the target coordinate system is a three-dimensional coordinate system, 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 tower of the wind turbine and parallel to the plane where the wind turbine blades are located; the second coordinate axis is perpendicular to the tower of the wind turbine and perpendicular to the plane where the wind turbine blades are located; the third coordinate axis is parallel to the tower of the wind turbine; the first coordinate axis, the second coordinate axis, and the third coordinate axis are perpendicular to each other;

[0134] Based on the above embodiment, optionally, determining the first angle information of the wind turbine blade in a previous frame includes:

[0135] If the previous frame of the wind blade is the first frame of the wind blade, obtaining a second image of the first frame, and determining first angle information of the previous frame of the wind blade according to the second image and the target coordinate system;

[0136] If the previous frame of the fan blade is a frame other than the first frame of the fan blade, the first angle information of the previous frame of the fan blade is determined based on the matching result of the angle information of the previous frame of the fan blade determined according to the image of the previous frame of the fan blade and the angle information of the previous frame of the fan blade.

[0137] Based on the above embodiment, optionally, the second image is obtained by scanning a wind turbine blade by a drone;

[0138] Correspondingly, determining first angle information of a previous frame of the wind turbine blade according to the second image and the target coordinate system includes:

[0139] Acquire a first point cloud value in the second image, where the first point cloud value is a point cloud value corresponding to a first coordinate axis in point cloud data contained in the second image;

[0140] The point cloud value with the largest value among the first point cloud values ​​is used as the second point cloud value, and a third point cloud value corresponding to the second point cloud value is determined, where the third point cloud value is a point cloud value of a third coordinate axis corresponding to position information that describes the same point cloud data as the second point cloud value;

[0141] determining a first angle value between a first target blade and a preset horizontal line based on the second point cloud value and the third point cloud value;

[0142] Determining a second angle value between the second target blade and the preset horizontal line, and a third angle value between the third target blade and the preset horizontal line according to a preset angle rule and the first angle value; the preset angle rule is that the three blades are spaced 120 degrees apart;

[0143] The first angle value, the second angle value and the third angle value are used as the first angle information of the previous frame of the wind turbine blade, and the first angle value corresponds to the first target blade, the second angle value corresponds to the second target blade, and the third angle value corresponds to the third target blade.

[0144] Based on the above embodiment, optionally, the first image is obtained by a drone performing a laser radar scan on a wind turbine blade, and determining the second angle information of the wind turbine blade in the current frame according to the first image includes:

[0145] Acquire a fourth point cloud value in the first image, where the fourth point cloud value is a point cloud value corresponding to the first coordinate axis in the point cloud data contained in the first image;

[0146] The point cloud value with the largest value among the fourth point cloud values ​​is used as the fifth point cloud value, and a sixth point cloud value corresponding to the fifth point cloud value in the first image is determined, where the sixth point cloud value is a point cloud value of the third coordinate axis corresponding to position information that describes the same point cloud data as the fifth point cloud value;

[0147] determining a fourth angle value between the first blade and a preset horizontal line based on the fifth point cloud value and the sixth point cloud value;

[0148] Determining a fifth angle value between the second blade and the preset horizontal line, and a sixth angle value between the third blade and the preset horizontal line according to a preset angle rule and the first angle value;

[0149] The fourth angle value, the fifth angle value and the sixth angle value are determined as the second angle information of the wind turbine blade in the current frame.

[0150] Based on the above embodiment, optionally, determining third angle information of the wind turbine blade in the current frame according to a matching result of the first angle information and the second angle information includes:

[0151] Match each angle value included in the first angle information with each angle value included in the second angle information in pairs, to obtain 9 matching pairs;

[0152] Subtracting the angle value of the first angle information from the angle value of the second angle information of each matching pair to obtain a candidate difference value for each matching pair;

[0153] The matching pairs corresponding to three candidate differences with the same value among the candidate differences are taken as target matching pairs;

[0154] The third angle information of the wind turbine blade in the current frame is determined according to the target matching pair; the angle value of the second angle information and the angle value of the first angle information in the target matching pair belong to the same target blade.

[0155] Based on the above embodiment, optionally, after subtracting the angle value of the first angle information from the angle value of the second angle information of each matching pair to obtain a candidate difference value for each matching pair, the method further includes:

[0156] The candidate difference is subjected to a preset operation to update the candidate difference; the preset operation is an operation of adding 360° to the candidate difference and then taking the modulus.

[0157] Based on the above embodiment, optionally, taking matching pairs corresponding to three candidate difference values ​​with the same numerical value among the candidate difference values ​​as target matching pairs includes:

[0158] If there are three first differences and three second differences in the candidate differences, determining whether the first differences and the second differences are less than a preset angle;

[0159] If the first difference is smaller than the preset angle, taking the matching pair corresponding to the first difference as the target matching pair;

[0160] If the second difference is smaller than the preset angle, the matching pair corresponding to the second difference is used as a target matching pair.

[0161] The technical solution of the embodiments of the present invention determines the target angle of each wind blade in each frame based on a wind blade angle detection method, enabling drones to accurately determine the angle between each target blade and a preset horizontal line during inspection. Furthermore, based on the angle of each wind blade in each frame, drone inspection routes are planned, and wind blades are inspected based on these inspection routes, improving the efficiency and accuracy of drone inspections of wind blades.

[0162] Example 5

[0163] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0164] Figure 6 The following is a schematic diagram of the structure of an electronic device that can be used to implement the wind turbine blade angle detection method according to an embodiment of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, 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 assistants, cellular phones, smart phones, 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 examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0165] like Figure 6As shown, electronic device 10 includes at least one processor 11 and memory, such as read-only memory (ROM) 12 and random access memory (RAM) 13, communicatively connected to at least one processor 11. The memory stores computer programs executable by the at least one processor. Processor 11 can perform various appropriate actions and processes based on the computer programs stored in ROM 12 or loaded from storage unit 18 into RAM 13. RAM 13 can also store various programs and data required for the operation of electronic device 10. Processor 11, ROM 12, and RAM 13 are interconnected via bus 14. An input / output (I / O) interface 15 is also connected to bus 14.

[0166] Multiple components in the electronic device 10 are connected to the I / O interface 15, including an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0167] The processor 11 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any other suitable processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the wind turbine blade angle detection method or the wind turbine blade inspection method.

[0168] In some embodiments, the wind blade angle detection method or the wind blade inspection method can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the wind blade angle detection method or the wind blade inspection method described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to execute the wind blade angle detection method or the wind blade inspection method by any other appropriate means (for example, by means of firmware).

[0169] Various embodiments of the systems and techniques described 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), systems on a chip (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0170] Computer programs for implementing 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 the computer program is executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer program may be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0171] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, device, or apparatus. A computer-readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or apparatus, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media may include an electrical connection based on one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0172] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device that has: 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 can provide input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, the 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 acoustic input, voice input, or tactile input).

[0173] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0174] A computing system may include clients and servers. The clients and servers are typically remote from each other and typically interact via a communication network. This client-server relationship arises through computer programs running on the respective computers, creating a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host. This server is a hosting product within the cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosting and VPS services.

[0175] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in the present invention can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved. This is not limited herein.

[0176] The above specific embodiments do not limit the scope of protection of the present invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.

Claims

1. A method for detecting the angle of a fan blade, characterized in that: The method comprises: Determine first angle information of the wind turbine blade in the previous frame; the first angle information is used to describe the angle between each target wind turbine blade and a preset horizontal line; wherein the preset horizontal line is a straight line passing through the center point of the wind turbine hub, perpendicular to the wind turbine tower, and parallel to the plane on which the wind turbine blades are located; Acquire a first image of a current frame of a wind turbine blade, and determine second angle information of the current frame of the wind turbine blade based on the first image; wherein the second angle information is used to describe the angle between each wind turbine blade and a preset horizontal line; and the second angle information does not match the target blade; determining third angle information of the fan blade in the current frame based on a matching result between the first angle information and the second angle information, until stopping the fan blade angle detection in response to a blade angle detection end instruction; the third angle information is used to describe the angle between each target blade of the fan and a preset horizontal line as the fan blade rotates from the previous frame to the current frame; the third angle information corresponds to the first angle information; Determining the third angle information of the wind turbine blade in the current frame according to the matching result of the first angle information and the second angle information includes: Match each angle value included in the first angle information with each angle value included in the second angle information in pairs, to obtain 9 matching pairs; Subtracting the angle value of the first angle information from the angle value of the second angle information of each matching pair to obtain a candidate difference value for each matching pair; The matching pairs corresponding to three candidate differences with the same value among the candidate differences are taken as target matching pairs; The third angle information of the wind turbine blade in the current frame is determined according to the target matching pair; the angle value of the second angle information and the angle value of the first angle information in the target matching pair belong to the same target blade.

2. The method according to claim 1, characterized in that The method further includes: establishing a target coordinate system, wherein the coordinate origin of the target coordinate system is the center point of the wind turbine hub; the target coordinate system is a three-dimensional coordinate system, 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 tower of the wind turbine and parallel to the plane where the wind turbine blades are located; the second coordinate axis is perpendicular to the tower of the wind turbine and perpendicular to the plane where the wind turbine blades are located; the third coordinate axis is parallel to the tower of the wind turbine; and the first coordinate axis, the second coordinate axis, and the third coordinate axis are perpendicular to each other; Accordingly, determining the first angle information of the wind turbine blade in the previous frame includes: If the previous frame of the wind blade is the first frame of the wind blade, obtaining a second image of the first frame, and determining first angle information of the previous frame of the wind blade according to the second image and the target coordinate system; If the previous frame of the fan blade is a frame other than the first frame of the fan blade, the first angle information of the previous frame of the fan blade is determined based on the matching result of the angle information of the previous frame of the fan blade determined according to the image of the previous frame of the fan blade and the angle information of the previous frame of the fan blade.

3. The method according to claim 2, characterized in that The second image is obtained by scanning a wind turbine blade by a drone; Correspondingly, determining first angle information of a previous frame of the wind turbine blade according to the second image and the target coordinate system includes: Acquire a first point cloud value in the second image, where the first point cloud value is a point cloud value corresponding to a first coordinate axis in point cloud data contained in the second image; The point cloud value with the largest value among the first point cloud values ​​is used as the second point cloud value, and a third point cloud value corresponding to the second point cloud value is determined, where the third point cloud value is a point cloud value of a third coordinate axis corresponding to position information that describes the same point cloud data as the second point cloud value; determining a first angle value between a first target blade and a preset horizontal line based on the second point cloud value and the third point cloud value; Determining a second angle value between the second target blade and the preset horizontal line, and a third angle value between the third target blade and the preset horizontal line according to a preset angle rule and the first angle value; the preset angle rule is that the three blades are spaced 120 degrees apart; The first angle value, the second angle value and the third angle value are used as the first angle information of the previous frame of the wind turbine blade, and the first angle value corresponds to the first target blade, the second angle value corresponds to the second target blade, and the third angle value corresponds to the third target blade.

4. The method according to claim 3, characterized in that The first image is obtained by performing a laser radar scan of a wind turbine blade by a drone, and determining second angle information of a current frame of the wind turbine blade according to the first image includes: Acquire a fourth point cloud value in the first image, where the fourth point cloud value is a point cloud value corresponding to the first coordinate axis in the point cloud data contained in the first image; The point cloud value with the largest value among the fourth point cloud values ​​is used as the fifth point cloud value, and a sixth point cloud value corresponding to the fifth point cloud value in the first image is determined, where the sixth point cloud value is a point cloud value of the third coordinate axis corresponding to position information that describes the same point cloud data as the fifth point cloud value; determining a fourth angle value between the first blade and a preset horizontal line based on the fifth point cloud value and the sixth point cloud value; Determining a fifth angle value between the second blade and the preset horizontal line, and a sixth angle value between the third blade and the preset horizontal line according to a preset angle rule and the first angle value; The fourth angle value, the fifth angle value and the sixth angle value are determined as the second angle information of the wind turbine blade in the current frame.

5. The method according to claim 1, wherein After subtracting the angle value of the first angle information from the angle value of the second angle information of each matching pair to obtain a candidate difference value for each matching pair, the method further includes: Perform a preset operation on the candidate difference to update the candidate difference; the preset operation is an operation of adding 360° to the candidate difference and then taking the modulus.

6. The method according to any one of claims 1 to 5, characterized in that: The matching pairs corresponding to three candidate differences with the same values ​​among the candidate differences are taken as target matching pairs, including: If there are three first differences and three second differences in the candidate differences, determining whether the first differences and the second differences are less than a preset angle; If the first difference is smaller than the preset angle, taking the matching pair corresponding to the first difference as the target matching pair; If the second difference is smaller than the preset angle, the matching pair corresponding to the second difference is used as a target matching pair.

7. A fan blade angle detection device, characterized in that: The device comprises: a first angle determination module, configured to determine first angle information of a previous frame of a wind turbine blade; the first angle information is used to describe the angle between each target wind turbine blade and a preset horizontal line; the preset horizontal line is a straight line passing through the center point of the wind turbine hub, perpendicular to the wind turbine tower, and parallel to the plane on which the wind turbine blades are located; a second angle determination module, configured to obtain a first image of a current frame of a wind turbine blade, and determine second angle information of the current frame of the wind turbine blade based on the first image; the second angle information is used to describe the angle between each wind turbine blade and a preset horizontal line; and the second angle information does not match the target blade; a third angle determination module, configured to determine third angle information of the fan blade in the current frame based on a matching result between the first angle information and the second angle information, and to stop fan blade angle detection in response to a blade angle detection end instruction; the third angle information is used to describe an angle between each target blade of the fan and a preset horizontal line as the blade rotates from the previous frame to the current frame; the third angle information corresponds to the first angle information; Among them, the third angle determination module includes a first matching pair determination unit, a difference determination unit, a second matching pair determination unit and an angle determination unit; the first matching pair determination unit is used to match each angle value included in the first angle information with each angle value included in the second angle information in pairs to obtain 9 groups of matching pairs; the difference determination unit is used to differ the angle value of the first angle information of each group of matching pairs from the angle value of the second angle information to obtain candidate difference values ​​for each group of matching pairs; the second matching pair determination unit is used to take the matching pairs corresponding to the three candidate difference values ​​with the same numerical value in the candidate difference values ​​as target matching pairs; the angle determination unit is used to determine the third angle information of the current frame of the wind turbine blade based on the target matching pair; the angle value of the second angle information in the target matching pair and the angle value of the first angle information belong to the same target blade.

8. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor. The computer program is executed by the at least one processor so that the at least one processor can execute the wind turbine blade angle detection method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the wind turbine blade angle detection method according to any one of claims 1 to 6 when executed.

Images