A wind turbine posture and rotating speed calculation method and system

Abstract

The present application belongs to the technical field of wind turbine blade inspection, and provides a wind turbine posture and rotating speed calculation method and system, which obtains a photo or / and video containing a wind turbine within a shooting field of view of a calculated yaw angle of a UAV at a second path point; performs image segmentation on the obtained photo to obtain a segmented region, fits a wind turbine blade center line and a tower center line, determines a wind turbine orientation according to the segmented wind turbine region, calculates an accurate wind turbine posture according to the wind turbine blade center line and the wind turbine orientation; decodes the obtained video into a time-ordered frame sequence, samples at a set time interval to form a wind turbine image sequence arranged in time sequence, calculates a rotation angle of each picture in the wind turbine image sequence, and performs segmentation; calculates an average value of the wind turbine rotating speed in each image sequence, and then calculates an average value of the rotating speed of the total wind turbine image sequence to obtain a final rotating speed, and the calculation result is accurate and fast.

Description

Technical Field

[0001] This invention belongs to the field of wind turbine blade inspection technology, specifically relating to a method and system for calculating the attitude and speed of a wind turbine. Background Technology

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

[0003] Wind turbine blades are susceptible to environmental erosion and mechanical fatigue during long-term operation, leading to surface damage (such as cracks and corrosion). Traditional inspection methods rely on manual climbing or fixed cameras, which are inefficient, risky, and lack comprehensive coverage.

[0004] In recent years, drone inspection technology has been gradually applied. Obtaining the attitude of wind turbines is the first step in performing fully automated inspections. Currently, there are several main technical approaches: The first method involves manually operating a drone to fly to the front of the wind turbine hub and perform an inspection. This method has a low degree of automation. The second method relies on lidar to perform point cloud modeling to determine the wind turbine's attitude, and then plans the inspection path based on the attitude. This method requires additional sensors, is more expensive, and is only suitable for determining the attitude of the wind turbine in a static state. The third method relies on photographs of the wind turbine taken by a camera. Some methods involve flying to the top of the turbine and taking a top-down view to determine its orientation; others involve drones flying around the turbine and observing the blade length from different angles to determine the orientation; still others involve taking multiple photographs of the turbine and then reconstructing it in 3D to determine the wind turbine's attitude. This method requires additional drone maneuvers, is time-consuming, reduces the drone's range, and is only suitable for attitude determination when the turbine is stopped. Summary of the Invention

[0005] To address the aforementioned problems, this invention proposes a method and system for calculating the attitude and speed of a wind turbine. This invention can automatically acquire the attitude and speed of the wind turbine in any operating state, such as when the turbine is stationary or rotating, relying solely on onboard cameras and navigation information, thus providing input for fully automated inspection and path planning.

[0006] According to some embodiments, the present invention adopts the following technical solution: A method for calculating the attitude and rotational speed of a wind turbine includes the following steps: Based on the positioning information, the highest altitude of the surrounding environment, and the coordinates of the takeoff point, calculate the coordinates and altitude of the first path point of the UAV's flight. Based on the first path point, the wind turbine coordinates, and the hub height, calculate the coordinates and altitude of the second path point of the UAV's flight. Based on the second path point and the wind turbine coordinates, calculate the yaw angle of the UAV so that the UAV is oriented toward the wind turbine. Acquire photos and / or videos of wind turbines within the field of view of the drone at the second waypoint with a calculated yaw angle; The acquired photos are segmented to obtain the segmented wind turbine blades, tower and nacelle. The center lines of the wind turbine blades and tower are fitted. The wind turbine orientation is determined according to the area where the segmented wind turbine is located. The accurate attitude of the wind turbine is calculated according to the center line of the wind turbine blades and the wind turbine orientation. The acquired video is decoded into a time-ordered frame sequence, and sampled at set time intervals to form a wind turbine image sequence arranged in chronological order. The rotation angle of each image in the wind turbine image sequence is calculated, and the wind turbine image sequence is segmented according to the rotation angle of each image. The average speed of the wind turbines within each image sequence is calculated, and then the average speed of the wind turbines in the total image sequence is calculated to obtain the final speed.

[0007] As an alternative implementation, the positioning information is RTK positioning information, the surrounding environment includes several of the following: buildings, power lines and utility poles, and the coordinates are GPS coordinates.

[0008] As an alternative implementation, the process of calculating the coordinates and altitude of a second path point for the UAV flight based on the first path point, wind turbine coordinates, and hub height, and then calculating the UAV's yaw angle based on the second path point and wind turbine coordinates to orient the UAV toward the wind turbine includes: using the wind turbine's GPS coordinates... Using GPS coordinates of the wind turbine as the base point GPS coordinates of the first path point of the drone The safe distance is defined as a distance greater than the length of the wind turbine blades. Calculate the GPS coordinates of the second path point. ,in ; Calculate the yaw angle of the drone for: .

[0009] As an alternative implementation method, the process of determining the wind turbine orientation based on the segmented wind turbine area and calculating the accurate wind turbine attitude based on the wind turbine blade centerline and wind turbine orientation includes: determining the direction vector of the blade centerline; calculating the blade direction vector in the UAV coordinate system using a pattern matching method; introducing the wind turbine orientation information to obtain the unit direction vector of the wind turbine blade in the UAV coordinate system; and performing coordinate transformation on the wind turbine attitude in the UAV coordinate system to obtain the wind turbine attitude in the fixed coordinate system.

[0010] As a further defined implementation, the process of determining the direction vector of the blade centerline includes: selecting one of the centerlines as a reference line segment and recording the image coordinates of its two endpoints; for the other centerline, calculating the Euclidean distances from its two endpoints to the two endpoints of the reference line segment; if the distance between a certain endpoint of the other centerline and a certain endpoint of the reference line segment is the smallest, then these two endpoints are defined as the starting point of their respective centerlines, and the corresponding other end is taken as the ending point. For the third centerline, using the known reference starting point as the alignment benchmark, calculate the distances between its two endpoints and the reference starting point. The endpoint closer to the reference starting point is defined as the starting point of the third centerline, and the other end is defined as the ending point. After determining the start and end points of the centerline, the direction of the corresponding centerline is converted into a unit vector form.

[0011] As a further defined implementation, the process of calculating the blade orientation vector in the UAV coordinate system using pattern matching includes: assuming the actual blade orientation vector in the UAV coordinate system is... ,in Combined with the blade direction vector in the image coordinate system Calculations yielded ,in ; Assume there is a virtual wind turbine in the drone coordinate system, and the blade direction vectors are respectively , , The wind turbine first rotates around Yp by a rotation angle α, then rotates around Zp by a yaw angle γ, and finally becomes parallel to the actual direction of the wind turbine blades. Rotation matrix for rotation about the Yp axis ; Rotation matrix for rotation about the Zp axis ; Rotation matrix of the entire process ; get: ; ; ; Substitute them into By solving the three equations simultaneously, k, α, and γ are obtained, where k is a proportionality coefficient. By introducing the wind turbine orientation information, the unit direction vector of the wind turbine orientation in the UAV coordinate system is calculated, and then the unit direction vector of the wind turbine blade in the UAV coordinate system is obtained.

[0012] As an alternative implementation, the set time interval is a fixed time interval, and the time interval... Seconds, perform uniform sampling.

[0013] As an alternative implementation, the process of calculating the rotation angle of each image in the wind turbine image sequence and segmenting the wind turbine image sequence according to the rotation angle of each image includes: the rotation angle ranges from... Based on the distribution of rotation angles, each cycle constitutes a segment.

[0014] As an alternative implementation, when the wind turbine faces left or right, the three-dimensional information is compressed to two dimensions and cannot be restored, making it impossible to solve for the blade direction vector. In this case, the drone rotates 90° clockwise or counterclockwise around the wind turbine and then takes a new picture. The direction of rotation is determined by the classification result of the current wind turbine orientation: when the wind turbine is judged to be facing left, the drone flies 90° clockwise; when the wind turbine is judged to be facing right, it flies 90° counterclockwise. Based on the captured pictures or videos, the wind turbine attitude or speed is calculated.

[0015] A wind turbine attitude and speed calculation system includes: The UAV flight adjustment module is configured to calculate the coordinates and altitude of the first path point of the UAV flight based on the positioning information, the highest altitude of the surrounding environment, and the coordinates of the takeoff point; Based on the first path point, the wind turbine coordinates, and the hub height, calculate the coordinates and altitude of the second path point for the UAV's flight; based on the second path point and the wind turbine coordinates, calculate the UAV's yaw angle so that the UAV faces the wind turbine. The data acquisition module is configured to acquire photos and / or videos of wind turbines within the field of view of the UAV at a calculated yaw angle at the second waypoint; The wind turbine attitude confirmation module is configured to perform image segmentation on the acquired photos to obtain the segmented wind turbine blades, tower and nacelle, fit the center line of the wind turbine blades and the center line of the tower, determine the wind turbine orientation based on the area where the segmented wind turbine is located, and calculate the accurate wind turbine attitude based on the center line of the wind turbine blades and the wind turbine orientation. The wind turbine speed calculation module is configured to decode the acquired video into a time-ordered frame sequence, sample the frames at set time intervals to form a wind turbine image sequence arranged in chronological order, calculate the rotation angle of each image in the wind turbine image sequence, segment the wind turbine image sequence according to the rotation angle of each image, calculate the average wind turbine speed in each segment, and then calculate the average speed of the total wind turbine image sequence to obtain the final speed.

[0016] Compared with the prior art, the beneficial effects of the present invention are as follows: This invention can calculate the attitude of a wind turbine with just a single simple photo and the rotational speed with just a video. Furthermore, through precise calculation, it eliminates the need for additional flight paths, significantly improving inspection efficiency. Even if the turbine blades are obscured by the tower, the turbine attitude can be calculated from a single image, demonstrating high robustness.

[0017] This invention is applicable to attitude calculation of wind turbines under both static and dynamic conditions, and is highly adaptable. It calculates wind turbine speed through machine vision, and the calculation results are accurate and fast.

[0018] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0019] 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 improper limitation of the invention.

[0020] Figure 1 This is a schematic flowchart of a wind turbine attitude recognition method according to one embodiment. Figure 2 This is a schematic diagram of the structure of a wind turbine generator according to one embodiment; Figure 3 This is a schematic diagram of the yaw angle and blade rotation angle of a wind turbine according to one embodiment; Figure 4 This is a schematic diagram of the path of a drone from a takeoff point to a first waypoint, according to one embodiment. Figure 5 This is a schematic diagram of the path of a drone from a first waypoint to a second waypoint, according to one embodiment. Figure 6 This is a schematic diagram illustrating the orientation of a drone at the second waypoint, according to one embodiment. Figure 7 A schematic diagram showing the general orientation of a wind turbine in a photograph taken by a drone according to one embodiment; Figure 8 A schematic diagram of the centerline of a wind turbine blade in a photograph taken by a drone according to one embodiment; Figure 9 This is a schematic diagram illustrating the required equipment and their communication relationships in one embodiment. Detailed Implementation

[0021] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0022] It should be noted that the following detailed description is illustrative and intended to provide further explanation of the invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0023] It should be noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the scope of exemplary embodiments according to the invention. As used herein, the singular form is intended to include the plural form as well, unless the context clearly indicates otherwise. Furthermore, it should be understood that when the terms "comprising" and / or "including" are used in this specification, they indicate the presence of features, steps, operations, devices, components, and / or combinations thereof.

[0024] Where there is no conflict, the embodiments and features described in this application may be combined with each other.

[0025] Example 1 To achieve fully automated inspection of wind turbines, this embodiment discloses a method for calculating the attitude of wind turbines based on monocular vision of unmanned aerial vehicles under normal circumstances.

[0026] like Figure 9 As shown, the drone model selected in this embodiment is the DJI Matrice 4T. This drone comes with a gimbal and camera, and has RTK high-precision positioning and automatic obstacle avoidance functions. Information is transmitted between the drone and the computing platform / processor.

[0027] Of course, in other embodiments, other models of drones may be selected.

[0028] A method for calculating the attitude and rotational speed of a wind turbine includes the following steps: Before implementing this embodiment, step S1-0 requires placing the drone in an unobstructed location above it.

[0029] Step S1-1: The drone takes off, first flying vertically upwards to a certain height to reach the first waypoint to pass over surrounding obstacles such as trees, houses, and power lines. Figure 4 As shown.

[0030] Step S1-2: The drone flies from the first waypoint to the second waypoint. This path is calculated based on the drone's GPS coordinates, the wind turbine's GPS coordinates, and altitude. When the horizontal distance from the drone's first waypoint to the wind turbine is less than the safe distance, the drone moves away from the wind turbine; when the horizontal distance is greater than the safe distance, the drone moves closer to the wind turbine. For example... Figure 5 As shown.

[0031] Steps S1-3: The drone adjusts its course based on its own GPS coordinates and the wind turbine's GPS coordinates to ensure the camera is directly facing the wind turbine. Figure 6 As shown. And perform the photo-taking function.

[0032] Steps S1-4: When the drone is not equipped with an onboard computing platform, the drone uploads the acquired images and its flight attitude at the time of image capture to the ground station. There are two methods: one is that the drone directly connects wirelessly to the ground station and uploads the images; the other is that the drone first uploads the images to the remote controller or hangar, and then the remote controller or hangar uploads the images to the ground station. When the drone is equipped with onboard computing power, it directly uploads the acquired images and its flight attitude at the time of image capture to the onboard computing platform. Hereinafter, the ground station or onboard computing platform will be collectively referred to as the computing platform.

[0033] Steps S1-5: The computing platform calculates the centerlines of the wind turbine blades and tower using a neural network. There are two specific methods: The first method uses existing image segmentation techniques (such as YOLOv8) to segment the wind turbine blades, tower, and nacelle in the image. Then, it fits the centerlines of the wind turbine blades and tower. The dataset label for this method is the segmentation image of each component of the wind turbine. The second method uses a deep neural network to directly obtain the centerline of the wind turbine blades. The dataset label for this method is the centerline of the wind turbine blades.

[0034] The computing platform calculates the approximate orientation of wind turbines using a neural network. Specifically, the wind turbine region from the image segmentation results is input into a classification network (e.g., ResNet18) to roughly classify the turbine orientation. The neural network dataset for this method uses an eight-category classification for wind turbine orientation: wind turbine facing directly at the drone, wind turbine facing away from the drone, wind turbine facing left, wind turbine facing right, wind turbine facing the drone slightly to the right, wind turbine facing the drone slightly to the left, wind turbine facing away from the drone slightly to the right, and wind turbine facing away from the drone slightly to the left. Figure 7 As shown.

[0035] Steps S1-6: Calculate the wind turbine attitude (yaw angle and rotation angle) based on the attitude of the image taken by the UAV, the general orientation of the wind turbine, and the centerline of the wind turbine blades. The wind turbine attitude is as follows: Figure 3 As shown.

[0036] Three coordinate systems are established: a fixed coordinate system, a UAV coordinate system, and an image coordinate system.

[0037] Fixed world coordinate system OXYZ: This coordinate system is used to describe the absolute attitude of the wind turbine in real geographic space. The positive X-axis points due east, the positive Y-axis points due north, and the positive Z-axis points vertically upward. All GPS signals, the actual attitude of the wind turbine, and the target points of the path planning are defined in this fixed coordinate system.

[0038] The UAV coordinate system OuavXuavYuavZuav: This coordinate system is referenced to the current UAV body and dynamically changes with the UAV's movement and attitude. The positive direction of the Yuav axis points to the UAV's current orientation (the camera direction is the same as the orientation direction), and the positive direction of the Zuav axis is perpendicular to the UAV's plane and upwards. The positive direction of the Xuav axis is determined by the right-hand rule of coordinate systems to form a standard Cartesian coordinate system. This coordinate system is used to derive the relative attitude relationship between the target wind turbine and the UAV. The coordinate transformation relationship between this system and the fixed world coordinate system is shown in the formula.

[0039]

[0040] in, and Let be the coordinates of the wind turbine blade direction vector in the fixed world coordinate system and the UAV coordinate system, respectively. For ZYX Euler angles (yaw) Looking up and down , roll A rotation matrix constructed sequentially.

[0041] Image coordinate system OpXpYpZp: This coordinate system is defined on the image plane and is used to describe the projection structure of the wind turbine in the image. The lower left corner of the image is defined as the origin Op. The positive direction of the Xp axis points horizontally (to the right) of the image, the positive direction of the Yp axis is perpendicular to the image plane and points inward, and the positive direction of the Zp axis points vertically (upward) of the image.

[0042] Step S1-7: Determine the direction vector of the blade centerline. The specific method is to determine the starting point and ending point of the blade centerline and convert them into a unit vector.

[0043] First, select one centerline as a reference (e.g., denoted as line segment AB) and record the image coordinates of its two endpoints. Then, for the other centerline (denoted as EF), calculate the Euclidean distances from its two endpoints E and F to the two endpoints A and B of the reference line segment AB. If the distance between one endpoint of EF and one endpoint of AB is minimized, these two endpoints are defined as the starting points of their respective centerlines, and the corresponding other endpoint is designated as the ending point. For example, if the distance between point B and point E is minimized, then B is defined as the starting point of AB, and E as the starting point of EF, thus constructing a direction vector with a consistent starting point.

[0044] Next, for the third centerline (denoted as CD), using the known reference starting point B as the alignment benchmark, calculate the distances between its two endpoints and point B. The endpoint closer to B is defined as the starting point of CD, and the other endpoint as the ending point.

[0045] After determining the start and end points of the centerlines, their directions are further converted into unit vector form to standardize the measurement scale and facilitate subsequent geometric calculations of the attitude. For each centerline, its unit direction vector can be expressed as:

[0046] in, and The image coordinates represent the starting and ending points of the centerline, respectively.

[0047] Steps S1-8: Calculate the blade direction vector in the UAV coordinate system using mathematical calculations. The specific method is as follows: The actual direction vector of the blade in the UAV coordinate system is ,in The blade direction vector in the image coordinate system was obtained earlier. Therefore, we can obtain... ,in

[0048] Assume there is a wind turbine in the UAV coordinate system, and the blade direction vectors are respectively , , The wind turbine blades first rotate around Yp by an angle α, and then around Zp by a yaw angle γ, so that they can be parallel to the actual direction of the blades.

[0049] Rotation matrix for rotation about the Yp axis

[0050] Rotation matrix for rotation about the Zp axis

[0051] Rotation matrix of the entire process

[0052] Therefore, we can obtain the following formula:

[0053]

[0054] Substitute them into By combining any three equations, we can solve for k, α, and γ, where k is the proportionality constant.

[0055] Step S1-9: Since the fan blades are evenly distributed at 120°, the range of the rotation angle α is adjusted to 0° to 120°.

[0056] Step S1-10: Since different 3D poses may project almost identical combinations of direction vectors onto the image plane, leading to ambiguity in the direction solution, the calculated value is actually the absolute value of γ. To determine the true yaw angle γ of the wind turbine, it is necessary to introduce the wind turbine's orientation information. The specific method is as follows: When the wind turbine faces the drone directly, its yaw angle is 180°. When the back of the wind turbine faces the drone, its yaw angle is 0°. When the wind turbine faces left, its yaw angle is 270°. When it faces right, its yaw angle is 90°. When the wind turbine faces the drone and yaws to the right, its yaw angle is 180°-γ. When the wind turbine faces the drone and yaws to the left, its yaw angle is 180°+γ. When the wind turbine faces away from the drone and yaws to the right, its yaw angle is γ. When the wind turbine faces away from the drone and yaws to the left, its yaw angle is -γ. Therefore, the unit direction vector of the wind turbine's orientation in the drone's coordinate system can be obtained.

[0057] Once the true yaw and rotation angles in the UAV coordinate system are obtained, the unit direction vector of the wind turbine blades in the UAV coordinate system can be obtained. .

[0058] Step S1-11: To obtain the wind turbine's attitude in a fixed coordinate system, the wind turbine's attitude in the UAV coordinate system needs to be transformed. The specific method is as follows:

[0059]

[0060] Example 2: To achieve fully automated inspection of wind turbines, this embodiment discloses a method for calculating wind turbine rotation speed based on monocular vision from a UAV under normal circumstances.

[0061] Steps S2-0 to S2-2 are the same as steps S1-0 to S1-2.

[0062] Steps S2-3: The drone adjusts its course based on its own GPS coordinates and the wind turbine's GPS coordinates to ensure the camera is directly facing the wind turbine. Figure 6 As shown. And execute the recording function.

[0063] Steps S2-4: The video is uploaded to the computing platform. The video is decoded into a time-ordered frame sequence, and then uniformly sampled at fixed time intervals to form a sequence of wind turbine images arranged in chronological order. Time interval .

[0064] Steps S2-5 to S2-9 are the same as steps S1-5 to S1-9: The rotation angle of each image in the wind turbine image sequence is calculated using a general method for determining the wind turbine attitude based on UAV monocular vision. .

[0065] S2-10: Because the range of rotation angle is... Therefore, it is necessary to adjust the image sequence according to the rotation angle of each image. The image sequence is segmented. For example, the entire image sequence contains 12 images, with a time interval of 0.2 seconds between images, and the rotation angle corresponding to each image is... The angles are 0°, 24°, 48°, 72°, 96°, 0°, 24°, 48°, 72°, 96°, 0°, and 24°. Therefore, the images are divided into three segments: the first segment consists of the first five images, the second segment consists of images 6 through 10, and the third segment consists of the last two images.

[0066] S2-11: To reduce errors, it is necessary to calculate the average fan speed within each segment, and then calculate the average speed of the entire sequence. The calculation method for the average fan speed within each segment is as follows: ,in Let represent the average rotational speed of the fan within the nth segment, m represent the number of images within each segment, and i represent the image number. Therefore, the average fan speed over the total time is .

[0067] Example 3 To achieve fully automated inspection of wind turbines, this embodiment discloses a method for calculating turbine attitude and speed under special circumstances. The "special circumstances" refer to situations where the turbine is facing left or right, such as... Figure 8 As shown.

[0068] Steps S3-0 to S3-5 are the same as steps S1-0 to S1-5 or steps S2-0 to S2-5, and the selected method is determined according to the type of task to be performed.

[0069] Step S3-6: When the wind turbine orientation classification result indicates that the wind turbine is facing left or right, the drone rotates 90° clockwise or counterclockwise around the wind turbine and then takes another picture. The rotation direction is determined by the current wind turbine orientation classification result: when the wind turbine is judged to be facing left, the drone flies 90° clockwise; when the wind turbine is judged to be facing right, it flies 90° counterclockwise. At this point, the drone has flown to the front of the wind turbine. Then, perform the photo or video recording action and execute steps S1-4~S1-11 or steps S2-4~S2-11 to obtain the wind turbine attitude or rotation speed.

[0070] Those skilled in the art will understand that the modules or steps of the present invention described above can be implemented using general-purpose computer devices. Optionally, they can be implemented using computer-executable program code, thereby allowing them to be stored in a storage device for execution by a computer device, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. The present invention is not limited to any particular combination of hardware and software.

[0071] Example 4 A wind turbine attitude and speed calculation system includes: The UAV flight adjustment module is configured to calculate the coordinates and altitude of the first path point of the UAV flight based on the positioning information, the highest altitude of the surrounding environment, and the coordinates of the takeoff point; Based on the first path point, the wind turbine coordinates, and the hub height, calculate the coordinates and altitude of the second path point for the UAV's flight; based on the second path point and the wind turbine coordinates, calculate the UAV's yaw angle so that the UAV faces the wind turbine. The data acquisition module is configured to acquire photos and / or videos of wind turbines within the field of view of the UAV at a calculated yaw angle at the second waypoint; The wind turbine attitude confirmation module is configured to perform image segmentation on the acquired photos to obtain the segmented wind turbine blades, tower and nacelle, fit the center line of the wind turbine blades and the center line of the tower, determine the wind turbine orientation based on the area where the segmented wind turbine is located, and calculate the accurate wind turbine attitude based on the center line of the wind turbine blades and the wind turbine orientation. The wind turbine speed calculation module is configured to decode the acquired video into a time-ordered frame sequence, sample the frames at set time intervals to form a wind turbine image sequence arranged in chronological order, calculate the rotation angle of each image in the wind turbine image sequence, segment the wind turbine image sequence according to the rotation angle of each image, calculate the average wind turbine speed in each segment, and then calculate the average speed of the total wind turbine image sequence to obtain the final speed.

[0072] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of one or more computer-usable storage media (including, but not limited to, disk storage, etc.) containing computer-usable program code. CD - ROM It takes the form of a computer program product implemented on (such as optical memory, etc.).

[0073] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0074] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0075] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0076] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made by those skilled in the art without creative effort within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for calculating the attitude and rotational speed of a wind turbine generator, characterized in that, Includes the following steps: Based on the positioning information, the highest altitude of the surrounding environment, and the coordinates of the takeoff point, calculate the coordinates and altitude of the first path point of the UAV's flight. Based on the first path point, the wind turbine coordinates, and the hub height, calculate the coordinates and altitude of the second path point of the UAV's flight. Based on the second path point and the wind turbine coordinates, calculate the yaw angle of the UAV so that the UAV is oriented toward the wind turbine. Based on the first path point, wind turbine coordinates, and hub height, the coordinates and altitude of the second path point for the UAV's flight are calculated. Then, based on the second path point and wind turbine coordinates, the UAV's yaw angle is calculated to orient itself toward the wind turbine. This process includes: using the wind turbine's GPS coordinates... Using GPS coordinates of the wind turbine as the base point GPS coordinates of the first path point of the drone The safe distance is defined as a distance greater than the length of the wind turbine blades. Calculate the GPS coordinates of the second path point. ,in ; Calculate the yaw angle of the drone for: ； Acquire photos and / or videos of wind turbines within the field of view of the drone at the second waypoint with a calculated yaw angle; The acquired photos are segmented to obtain the segmented wind turbine blades, tower, and nacelle. The centerlines of the wind turbine blades and tower are fitted. The wind turbine orientation is determined based on the area where the segmented wind turbine is located. The accurate attitude of the wind turbine is calculated based on the centerline of the wind turbine blades and the wind turbine orientation. The process includes: determining the direction vector of the blade centerline; calculating the blade direction vector in the UAV coordinate system using pattern matching; introducing the wind turbine orientation information to obtain the unit direction vector of the wind turbine blade in the UAV coordinate system; and performing coordinate transformation on the wind turbine attitude in the UAV coordinate system to obtain the wind turbine attitude in the fixed coordinate system. The process of calculating the blade orientation vector in the UAV coordinate system using pattern matching includes: assuming the actual blade orientation vector in the UAV coordinate system is... ,in Combined with the blade direction vector in the image coordinate system Calculations yielded ,in ; Assume there is a wind turbine in the UAV coordinate system, and the blade direction vectors are respectively , , The wind turbine first rotates around Yp by a rotation angle α, then rotates around Zp by a yaw angle γ, and finally becomes parallel to the actual direction of the blades. Rotation matrix for rotation about the Yp axis ; Rotation matrix for rotation about the Zp axis ; Rotation matrix of the entire process ; get: ； ； ； Substitute them into By solving the three equations simultaneously, k, α, and γ are obtained, where k is a proportionality coefficient. By introducing the wind turbine orientation information, the unit direction vector of the wind turbine orientation in the UAV coordinate system is calculated, and then the unit direction vector of the wind turbine blade in the UAV coordinate system is obtained. The acquired video is decoded into a time-ordered frame sequence, and sampled at set time intervals to form a wind turbine image sequence arranged in chronological order. The rotation angle of each image in the wind turbine image sequence is calculated, and the wind turbine image sequence is segmented according to the rotation angle of each image. The average speed of the wind turbines within each image sequence is calculated, and then the average speed of the wind turbines in the total image sequence is calculated to obtain the final speed.

2. The method for calculating the attitude and speed of a wind turbine generator as described in claim 1, characterized in that, The location information is RTK location information, and the surrounding environment includes several of the following: buildings, power lines, and utility poles. The coordinates are GPS coordinates.

3. The method for calculating the attitude and speed of a wind turbine generator as described in claim 1, characterized in that, The process of determining the direction vector of the blade centerline includes: selecting one centerline as a reference line segment and recording the image coordinates of its two endpoints; for the other centerline, calculating the Euclidean distances from its two endpoints to the two endpoints of the reference line segment; if the distance between one endpoint of the other centerline and one endpoint of the reference line segment is the smallest, then these two endpoints are defined as the starting point of their respective centerlines, and the corresponding other end is taken as the ending point. For the third centerline, using the known reference starting point as the alignment benchmark, calculate the distances between its two endpoints and the reference starting point. The endpoint closer to the reference starting point is defined as the starting point of the third centerline, and the other end is defined as the ending point. After determining the start and end points of the centerline, the direction of the corresponding centerline is converted into a unit vector form.

4. The method for calculating the attitude and speed of a wind turbine generator as described in claim 1, characterized in that, The set time interval is a fixed time interval, and the time interval Seconds, perform uniform sampling.

5. The method for calculating the attitude and speed of a wind turbine generator as described in claim 1, characterized in that, The process of calculating the rotation angle of each image in the wind turbine image sequence and segmenting the sequence based on the rotation angle includes: the rotation angle ranges from [value missing]. Based on the distribution of rotation angles, each cycle constitutes a segment.

6. The method for calculating the attitude and speed of a wind turbine generator as described in claim 1, characterized in that, When the wind turbine faces left or right, the three-dimensional information is compressed to two dimensions, making it impossible to reconstruct and thus the blade direction vector cannot be solved. In this case, the drone rotates 90° clockwise or counterclockwise around the wind turbine and then takes a new picture. The direction of rotation is determined by the classification result of the current wind turbine orientation: when the wind turbine is judged to be facing left, the drone flies 90° clockwise; when the wind turbine is judged to be facing right, it flies 90° counterclockwise. Based on the captured pictures or videos, the wind turbine attitude or speed is calculated.

7. A wind turbine attitude and speed calculation system, characterized in that, include: The UAV flight adjustment module is configured to calculate the coordinates and altitude of the first path point of the UAV flight based on positioning information, the highest altitude of the surrounding environment, and the coordinates of the takeoff point; Based on the first path point, the wind turbine coordinates, and the hub height, calculate the coordinates and altitude of the second path point for the UAV's flight; based on the second path point and the wind turbine coordinates, calculate the UAV's yaw angle so that the UAV faces the wind turbine. Based on the first path point, wind turbine coordinates, and hub height, the coordinates and altitude of the second path point for the UAV's flight are calculated. Then, based on the second path point and wind turbine coordinates, the UAV's yaw angle is calculated to orient itself toward the wind turbine. This process includes: using the wind turbine's GPS coordinates... Using GPS coordinates of the wind turbine as the base point GPS coordinates of the first path point of the drone The safe distance is defined as a distance greater than the length of the wind turbine blades. Calculate the GPS coordinates of the second path point. ,in ; Calculate the yaw angle of the drone for: ； The data acquisition module is configured to acquire photos and / or videos of wind turbines within the field of view of the UAV at a calculated yaw angle at the second waypoint; The wind turbine attitude confirmation module is configured to perform image segmentation on the acquired photos to obtain the segmented wind turbine blades, tower, and nacelle; fit the center lines of the wind turbine blades and the tower; determine the wind turbine orientation based on the area where the segmented wind turbine is located; and calculate the accurate wind turbine attitude based on the center lines of the wind turbine blades and the wind turbine orientation. The process includes: determining the direction vector of the blade center line; calculating the blade direction vector in the UAV coordinate system using a pattern matching method; introducing the wind turbine orientation information to obtain the unit direction vector of the wind turbine blade in the UAV coordinate system; and performing coordinate transformation on the wind turbine attitude in the UAV coordinate system to obtain the wind turbine attitude in the fixed coordinate system. The process of calculating the blade orientation vector in the UAV coordinate system using pattern matching includes: assuming the actual blade orientation vector in the UAV coordinate system is... ,in Combined with the blade direction vector in the image coordinate system Calculations yielded ,in ; Assume there is a wind turbine in the UAV coordinate system, and the blade direction vectors are respectively , , The wind turbine first rotates around Yp by a rotation angle α, then rotates around Zp by a yaw angle γ, and finally becomes parallel to the actual direction of the blades. Rotation matrix for rotation about the Yp axis ; Rotation matrix for rotation about the Zp axis ; Rotation matrix of the entire process ; get: ； ； ； Substitute them into By solving the three equations simultaneously, k, α, and γ are obtained, where k is a proportionality coefficient. By introducing the wind turbine orientation information, the unit direction vector of the wind turbine orientation in the UAV coordinate system is calculated, and then the unit direction vector of the wind turbine blade in the UAV coordinate system is obtained. The wind turbine speed calculation module is configured to decode the acquired video into a time-ordered frame sequence, sample the frames at set time intervals to form a wind turbine image sequence arranged in chronological order, calculate the rotation angle of each image in the wind turbine image sequence, segment the wind turbine image sequence according to the rotation angle of each image, calculate the average wind turbine speed in each segment, and then calculate the average speed of the total wind turbine image sequence to obtain the final speed.

Images