A method and apparatus for measuring the length of wind turbine blades

Abstract

This invention relates to the field of wind turbine blade inspection technology, and particularly to a method for measuring the length of wind turbine blades. The method includes: S100, receiving visible light data in a two-dimensional coordinate system of the hub and three-dimensional point cloud data in a three-dimensional coordinate system of the hub, calibrating the visible light data and the three-dimensional point cloud data, extracting relevant point cloud information of the wind turbine blades, and detecting the wind turbine orientation angle; S200, combining the three-dimensional coordinate system with the two-dimensional coordinate system; S300, detecting visible light data of key points and establishing a model for calculating the blade length; S400, obtaining the calculation result of the first blade length. This method for measuring the length of wind turbine blades has the following advantages: easy on-site operation, high resolution, less susceptible to interference from surrounding active signals, no blind spots in certain areas, improved calculation accuracy, miniaturization of equipment, reduced weight of the UAV, and improved inspection performance of the UAV.

Description

Technical Field

[0001] This invention relates to the field of wind turbine blade inspection technology, and in particular to a method and equipment for measuring the length of wind turbine blades. Background Technology

[0002] Wind power generation has been widely used in open, windy areas such as mountainous regions. However, wind turbine blades are subject to varying degrees of damage due to wind, rain, sun exposure, and wear during long-term operation. Therefore, it is necessary to regularly inspect wind turbines, especially the blades, to ensure timely maintenance.

[0003] Wind turbine blade length is a crucial parameter for automated inspection, directly impacting inspection time and the generation of automated inspection paths by drones. Traditional methods typically require manual input of blade length, which increases operational complexity, especially in wind farms with multiple turbine models. Furthermore, due to prolonged use and poor management, blade length and other relevant information may be unavailable, hindering inspection and maintenance. During inspections, drones often employ a combination of visible light cameras and non-repeating solid-state or mechanical radar to scan blades. This method suffers from low resolution, susceptibility to interference from surrounding active signals, blind spots, and the bulky size and weight of the equipment, all of which negatively affect the drone's inspection capabilities. Summary of the Invention

[0004] In view of this, the present invention aims to provide a method for measuring the length of wind turbine blades. It adopts a combination of visible light data acquired by a visible light camera and three-dimensional point cloud data acquired by LiDAR radar, which solves the problems of increased complexity of on-site operation, low resolution, susceptibility to interference from surrounding active signals, blind spots in a certain area, large equipment size, increased weight of UAV, and impact on UAV inspection.

[0005] To achieve the above objectives, the technical solution of the present invention is implemented as follows:

[0006] A method for measuring the length of a wind turbine blade includes:

[0007] S100: Receive visible light data in the two-dimensional coordinate system of the hub and three-dimensional point cloud data in the three-dimensional coordinate system of the hub, calibrate the visible light data and the three-dimensional point cloud data, extract relevant point cloud information of the wind turbine blades, and detect the wind turbine orientation angle.

[0008] S200. Combine the three-dimensional coordinate system with the two-dimensional coordinate system;

[0009] S300. Detect the visible light data of key points and establish a model for calculating the blade length;

[0010] S400, Obtain the calculation result of the first blade length.

[0011] Furthermore, step S100 includes:

[0012] S110. Acquire the visible light data of the wheel hub using an image acquisition device;

[0013] S120. Acquire the three-dimensional point cloud data of the wheel hub using radar;

[0014] S130. Calibrate the rotation and translation between the two-dimensional coordinate system and the three-dimensional coordinate system;

[0015] S140, Obtain the fan orientation angle.

[0016] Furthermore, in step S130, the calibration method involves designing a calibration board to obtain matching points of the same name between the three-dimensional point cloud data and the visible light data, performing ICP or PNP matching, and obtaining the relative transformation relationship between the three-dimensional point cloud data and the visible light data.

[0017] Furthermore, in step S300, the key points include the hub center point and the tip of the blade.

[0018] Furthermore, in step S300,

[0019] S310, The visible light data is used to detect key points on the leaf using deep learning or traditional image algorithms;

[0020] S320. Using the three-dimensional point cloud data and the visible light data, the wind turbine plane is transformed from the three-dimensional coordinate system to the two-dimensional coordinate system, and the plane constraint relationship of the key points is provided by the plane equation.

[0021] S330. Obtain the direction of the ray through the key points of the visible light data;

[0022] S340: Combine the two constraints from steps S330 and S340 to obtain the three-dimensional coordinates of the key point.

[0023] Furthermore, the method for measuring the length of the wind turbine blades also includes:

[0024] S500: Confirm and correct the calculation results of step S400.

[0025] Furthermore, step S500 includes:

[0026] S510. Using the positioning coordinates of the detection device at at least two locations and the detected key points, the three-dimensional coordinates of the blade tip of the wind turbine are obtained by triangulation, the distance from the blade tip to the center of the hub is calculated, and the length of the second blade is obtained.

[0027] S520. Obtain the difference between the length of the first blade and the length of the second blade, and determine whether the difference is within a specified threshold range;

[0028] S530. If the difference exceeds the specified threshold range, correct the blade length value to obtain the final blade length.

[0029] A device for measuring the length of a wind turbine blade, comprising measuring the blade length using any one of the methods described above, including:

[0030] The detection device uses unmanned aerial vehicles (UAVs);

[0031] An image acquisition device is installed on the UAV to acquire visible light data;

[0032] A Lidar radar device is installed on the UAV to acquire three-dimensional point cloud data.

[0033] A processing device, installed on the UAV, receives the visible light data and the three-dimensional point cloud data, and obtains the length of the blade by processing the visible light data and the three-dimensional point cloud data.

[0034] Furthermore, the image acquisition device employs a visible light camera.

[0035] Furthermore, the device for measuring the length of the wind turbine blades also includes:

[0036] A positioning device is installed on the drone to locate the drone's spatial position through a positioning system.

[0037] Compared with existing technologies, the method for measuring the length of wind turbine blades described in this invention has the following advantages:

[0038] The advantages of this technical solution are that it is easy to operate on site, has high resolution, is not easily affected by interference from surrounding active signals, has no blind spots in a certain area, improves calculation accuracy, realizes the miniaturization of equipment, reduces the weight of the UAV, and improves the inspection performance of the UAV. Attached Figure Description

[0039] The accompanying drawings, which form part of this invention, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an undue limitation of the invention. In the drawings:

[0040] Figure 1 This is a flowchart of the method for measuring the length of wind turbine blades according to an embodiment of the present invention;

[0041] Figure 2 This is a flowchart of step S100 of the wind turbine blade length measurement method according to an embodiment of the present invention;

[0042] Figure 3 This is a schematic diagram of the coordinate system of LiDAR as described in an embodiment of the present invention;

[0043] Figure 4 This is a schematic diagram of the coordinate system of the visible light camera according to an embodiment of the present invention.

[0044] Figure 5 This is a structural block diagram of the wind turbine blade length measurement device according to an embodiment of the present invention.

[0045] Explanation of reference numerals in the attached figures:

[0046] 100 - Detection device, 200 - Image acquisition device, 300 - Lidar radar device, 400 - Processing device, 500 - Positioning device. Detailed Implementation

[0047] It should be noted that, unless otherwise specified, the embodiments and features described in the present invention can be combined with each other.

[0048] In this invention, the terms "first," "second," "upper," and "lower," etc., are used for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined with "first," "second," "upper," or "lower" may explicitly or implicitly include at least one of those features. Furthermore, the technical solutions of the various embodiments can be combined with each other, but this must be based on the ability of those skilled in the art to implement them. Where the technical solutions of the embodiments can be combined, they are all within the scope of protection claimed by this invention.

[0049] The present invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0050] like Figure 1 As shown, a method for measuring the length of a wind turbine blade includes:

[0051] S100: Receive visible light data in the two-dimensional coordinate system of the hub and three-dimensional point cloud data in the three-dimensional coordinate system of the hub, calibrate the visible light data and the three-dimensional point cloud data, extract relevant point cloud information of the wind turbine blades, and detect the wind turbine orientation angle.

[0052] S200. Combine the three-dimensional coordinate system with the two-dimensional coordinate system;

[0053] S300. Detect the visible light data of key points and establish a model for calculating the blade length;

[0054] S400, Obtain the calculation result of the first blade length.

[0055] By calibrating visible light data in a two-dimensional coordinate system and three-dimensional point cloud data in a three-dimensional coordinate system, extracting relevant point cloud information, detecting the wind turbine orientation angle, and detecting visible light data of key points, a model for calculating blade length is established, and the length of the first blade is calculated using this model.

[0056] The above method improves computational accuracy by combining two-dimensional and three-dimensional data.

[0057] Specifically, such as Figure 2 As shown, step S100 includes:

[0058] S110. Acquire the visible light data of the wheel hub using an image acquisition device;

[0059] S120. Acquire the three-dimensional point cloud data of the wheel hub using radar;

[0060] S130. Calibrate the rotation and translation between the two-dimensional coordinate system and the three-dimensional coordinate system;

[0061] S140, Obtain the fan orientation angle.

[0062] Image acquisition devices, such as visible light cameras (e.g., traditional RGB cameras), capture two-dimensional images of the wind turbine, obtaining visible light images within a certain field of view. However, acquiring three-dimensional point cloud data via radar, which can be LiDAR, solid-state, or mechanical radar, presents challenges. Solid-state or mechanical radar suffers from low resolution, susceptibility to interference from surrounding active signals, blind spots, and bulky equipment, increasing the weight of the drone and hindering its inspection capabilities. Therefore, it is preferable to use a LiDAR device to acquire three-dimensional point cloud data at different emission angles within a certain field of view.

[0063] Furthermore, in step S130, the calibration method involves designing a calibration board to obtain matching points of the same name between the three-dimensional point cloud data and the visible light data, performing ICP or PNP matching, and obtaining the relative transformation relationship between the three-dimensional point cloud data and the visible light data.

[0064] The 3D point cloud data includes the (x, y, z) three-dimensional coordinates of the point and the LiDAR reflection intensity of the point. For example... Figure 3 and Figure 4As shown, the data acquired by the visible light camera and LiDAR are based on their respective coordinate systems. Example diagrams of the visible light and LiDAR coordinate systems are shown below. To unify the data acquired by the visible light camera and the LiDAR, it is necessary to calibrate the rotation and translation between the two coordinate systems. Calibration can be achieved by designing a calibration board to obtain matching points of the same name between the LiDAR 3D point cloud and the camera image, performing ICP (Iterative Closest Points) or PNP (Perspective N Points) matching to obtain the relative transformation relationship between the two.

[0065] Furthermore, in step S300, the key points include the hub center point and the tip of the blade.

[0066] To calculate the blade length, only the coordinates of the hub center point and the blade tip endpoint are detected, and the blade length can be obtained after calculation.

[0067] Furthermore, in step S300,

[0068] S310, The visible light data is used to detect key points on the leaf using deep learning or traditional image algorithms;

[0069] S320. Using the three-dimensional point cloud data and the visible light data, the wind turbine plane is transformed from the three-dimensional coordinate system to the two-dimensional coordinate system, and the plane constraint relationship of the key points is provided by the plane equation.

[0070] S330. Obtain the direction of the ray through the key points of the visible light data;

[0071] S340: Combine the two constraints from steps S330 and S340 to obtain the three-dimensional coordinates of the key point.

[0072] The above method can accurately measure the blade length. This provides crucial data for drone inspections of wind turbines. To ensure accurate reflection of blade condition during inspections, precise initial parameters must be input beforehand. Furthermore, the calculated blade length needs to be reconfirmed to guarantee accuracy. If the error exceeds a threshold, the blade length must be corrected before being used as an initial parameter.

[0073] Furthermore, the method for measuring the length of the wind turbine blades also includes:

[0074] S500: Confirm and correct the calculation results of step S400.

[0075] S510. Using the positioning coordinates of the detection device at at least two locations and the detected key points, the three-dimensional coordinates of the blade tip of the wind turbine are obtained by triangulation, the distance from the blade tip to the center of the hub is calculated, and the length of the second blade is obtained.

[0076] S520. Obtain the difference between the length of the first blade and the length of the second blade, and determine whether the difference is within a specified threshold range;

[0077] S530. If the difference exceeds the specified threshold range, correct the blade length value to obtain the final blade length.

[0078] By detecting key points at at least two locations using a drone, obtaining the drone's location information using a positioning device such as GPS, calculating the length of the second blade using triangulation, comparing the difference between the lengths of the first and second blades, determining whether the difference is within a specified threshold range, and then merging the length of the second blade into the length of the first blade to correct the blade length.

[0079] The fusion method employs weighted data fusion, namely, L f = (W1×L1+W2×L2) / (W1+W2), where,

[0080] L f : The final blade length after fusion;

[0081] W1: Weight of the first blade length;

[0082] L1: Length of the first blade;

[0083] W2: Weight of the second blade length;

[0084] L2: Length of the second blade.

[0085] A device for measuring the length of wind turbine blades, such as Figure 5 As shown, the method for measuring wind turbine blade length using any of the above-described methods includes: a detection device 100, an image acquisition device 200, a LiDAR radar device 300, and a processing device 400. The detection device 100 is a drone. The image acquisition device 200, mounted on the drone, acquires visible light data. The LiDAR radar device 300, mounted on the drone, acquires three-dimensional point cloud data. The processing device 400, mounted on the drone, receives the visible light data and the three-dimensional point cloud data, and obtains the blade length by processing the visible light data and the three-dimensional point cloud data.

[0086] The blade length is obtained by acquiring visible light data in a two-dimensional coordinate system using an image acquisition device 200 mounted on the UAV and three-dimensional point cloud data in a three-dimensional coordinate system using a Lidar radar device mounted on the UAV.

[0087] Facilitating on-site operation, LiDAR radar offers higher resolution compared to solid-state or mechanical radar, is less susceptible to interference from surrounding active signals, eliminates blind spots in certain areas, improves calculation accuracy, enables miniaturization of equipment, reduces the weight of the UAV, and enhances the UAV's inspection performance.

[0088] Furthermore, the image acquisition device 200 employs a visible light camera.

[0089] Furthermore, the device for measuring the length of the wind turbine blades also includes:

[0090] The positioning device 500 is installed on the UAV and uses a positioning system to locate the spatial position of the UAV.

[0091] The positioning system employs, for example, a GPS positioning system. The positioning device 500 locates the drone's position, acquires its location information, and inputs this information into the processing device 400. This allows for the confirmation and correction steps described in step 500, further ensuring the accuracy of the blade length.

[0092] Other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of the invention are indicated by the following claims.

[0093] It should be understood that the present invention is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A method of measuring the length of a fan blade, characterized by, include: S100: Receive visible light data in the two-dimensional coordinate system of the hub and three-dimensional point cloud data in the three-dimensional coordinate system of the hub, calibrate the visible light data and the three-dimensional point cloud data, extract relevant point cloud information of the wind turbine blades, and detect the wind turbine orientation angle. S110. Acquire the visible light data of the wheel hub using an image acquisition device; S120. Acquire the three-dimensional point cloud data of the wheel hub using radar; S130. Calibrate the rotation and translation between the two-dimensional coordinate system and the three-dimensional coordinate system; S140, Obtain the fan orientation angle; S200. Combine the three-dimensional coordinate system with the two-dimensional coordinate system; S300. Detect the visible light data of key points and establish a model for calculating the blade length. The key points include the hub center point and the tip of the blade. S310, The visible light data is used to detect key points on the leaf using deep learning or traditional image algorithms; S320. Using the three-dimensional point cloud data and the visible light data, the wind turbine plane is transformed from the three-dimensional coordinate system to the two-dimensional coordinate system, and the plane constraint relationship of the key points is provided by the plane equation. S330. Obtain the direction of the ray through the key points of the visible light data; S340. Combine the planar constraint relationship described in step S320 and the ray direction described in S330 to obtain the three-dimensional coordinates of the key point; S400. The calculation result of the length of the first blade is obtained based on the coordinate values ​​of the center point of the hub and the endpoint of the blade tip.

2. The method for measuring the length of wind turbine blades according to claim 1, characterized in that, In step S130, the calibration method involves designing a calibration board to obtain matching points of the same name between the three-dimensional point cloud data and the visible light data, performing ICP or PNP matching, and obtaining the relative transformation relationship between the three-dimensional point cloud data and the visible light data.

3. The method of fan blade length measurement of claim 1, wherein, Also includes: S500: Confirm and correct the calculation results of step S400.

4. The method for measuring the length of wind turbine blades according to claim 3, characterized in that, Step S500 includes: S510. Using the positioning coordinates of the detection device at at least two locations and the detected key points, the three-dimensional coordinates of the blade tip of the wind turbine are obtained by triangulation, the distance from the blade tip to the center of the hub is calculated, and the length of the second blade is obtained. S520. Obtain the difference between the length of the first blade and the length of the second blade, and determine whether the difference is within a specified threshold range; S530. If the difference exceeds the specified threshold range, correct the blade length value to obtain the final blade length.

5. An apparatus for measuring the length of a wind turbine blade, characterized in that Measuring the blade length using the method for measuring wind turbine blade length as described in any one of claims 1 to 4 includes: The detection device (100) uses a drone; An image acquisition device (200) is installed on the UAV to acquire visible light data; A Lidar radar device (300) is installed on the UAV to acquire three-dimensional point cloud data; A processing device (400) is installed on the UAV to receive the visible light data and the three-dimensional point cloud data, and to obtain the length of the blade by processing the visible light data and the three-dimensional point cloud data.

6. The device for measuring the length of wind turbine blades according to claim 5, characterized in that, The image acquisition device (200) is a visible light camera.

7. The apparatus for fan blade length measurement of claim 5, wherein, Also includes: A positioning device (500) is installed on the UAV and uses a positioning system to locate the spatial position of the UAV.

Images