Unmanned aerial vehicle cooperative formation fan blade inspection method and device and storage medium

Abstract

The application relates to the field of wind power generation technology and discloses a wind turbine blade inspection method and device based on cooperation of unmanned aerial vehicles and a storage medium, which comprises the following steps: acquiring the length of a wind turbine blade; determining an imaging area based on the length of the wind turbine blade and dividing the imaging area into multiple identical sub-imaging areas; acquiring the central normal line of the rotating plane of the wind turbine blade; setting a first unmanned aerial vehicle at a second target distance in the direction of the central normal line; setting a second unmanned aerial vehicle at the center of each of the multiple sub-imaging areas based on the first unmanned aerial vehicle; simultaneously photographing the wind turbine blade based on the first unmanned aerial vehicle and the multiple second unmanned aerial vehicles to acquire multiple imaging pictures of the wind turbine blade; and transmitting the multiple imaging pictures to a ground control station and processing the multiple imaging pictures to form an inspection report. The multiple unmanned aerial vehicles are used for regional photographing, the entire wind turbine can be photographed and detected without stopping the wind turbine, the work efficiency is improved, and economic losses are reduced.

Description

Technical Field

[0001] This invention relates to the field of wind power generation technology, specifically to a method, device, and storage medium for inspecting wind turbine blades using a drone-coordinated formation. Background Technology

[0002] Wind power, as a clean and renewable energy source, is gaining increasing attention globally. China, a major global energy consumer and advocate of green energy, has achieved remarkable progress in wind power technology and large-scale construction in recent years. With the large-scale construction of wind turbines, the workload of daily inspection and maintenance is increasing. Due to the massive structure of wind turbines, traditional inspection methods typically involve manual visual inspection of the turbine blades using binoculars. This is inefficient, and manual inspections usually require shutdown, resulting in economic losses.

[0003] Currently, relying solely on manual inspections is insufficient. Drones, with their ability to autonomously fly close to the wind turbine for photographic inspection, are increasingly being used in wind turbine inspections and have become an important tool. Drone inspections typically involve photographing the wind turbine blades. The drone flies close to the wind turbine to take pictures, and the photos are then manually reviewed or intelligently identified to pinpoint defects. Because the blade tips of wind turbines travel at high speeds, drone photos are prone to blurring, affecting the observation results. Therefore, drone inspections require the wind turbine to be stopped and photographed while stationary. Furthermore, due to the enormous size of wind turbines, a full view can only be captured from a considerable distance, making it difficult to identify small defects on the blades. Summary of the Invention

[0004] In view of this, the present invention provides a method, device and storage medium for inspecting wind turbine blades in a coordinated formation of unmanned aerial vehicles (UAVs), in order to solve the problems that wind turbine blades can only be inspected when the wind turbine is stopped and that small defects are difficult to identify.

[0005] In a first aspect, the present invention provides a method for inspecting wind turbine blades using a drone-coordinated formation, the method comprising:

[0006] Obtain the length of the wind turbine blades;

[0007] The imaging area is determined based on the length of the wind turbine blades, and the imaging area is divided into multiple identical sub-imaging areas; the wind turbine blades are located within the imaging area; adjacent sub-imaging areas have an overlap length of a first target distance;

[0008] Obtain the center normal of the rotation plane of the wind turbine blades, and set up the first UAV at a second target distance along the direction of the center normal;

[0009] Based on the first drone, a second drone is set up at the center of each of the multiple sub-imaging regions;

[0010] Based on the simultaneous photography of the wind turbine blades by the first UAV and multiple second UAVs, multiple imaging images of the wind turbine blades are obtained;

[0011] Multiple imaging images are transmitted to a ground control station, and the ground control station processes the multiple imaging images to generate an inspection report.

[0012] Beneficial effects: By acquiring the length of the wind turbine blades and then determining the imaging area based on that length, the wind turbine blades are positioned within the imaging area. Dividing the wind turbine blade imaging area into multiple identical sub-imaging areas ensures that the entire wind turbine blade is captured during inspection, guaranteeing the integrity of the inspection. Furthermore, setting multiple sub-imaging areas facilitates clearer observation and analysis of the wind turbine blade's specific condition. Sufficient overlap between two adjacent sub-imaging areas allows for the use of mosaic technology to form a complete image of the wind turbine blade. Based on the center normal of the wind turbine blade's rotation plane, the first UAV is positioned at a second target distance along the direction of the center normal. Then, using the first UAV as the origin, a second UAV is positioned at the center of each surrounding sub-imaging area. This ensures that the imaging area of ​​multiple UAVs covers the entire wind turbine blade imaging area, completely capturing the blade's condition and achieving comprehensive monitoring of the wind turbine blades.

[0013] Multiple drones simultaneously capture images of the wind turbine blades, generating multiple images that are then transmitted to a ground control station. The ground control station processes these images to produce a complete image of the wind turbine blades, allowing for the detection and marking of relevant defects and the generation of an inspection report. The ground control station enables faster and more efficient processing of large amounts of image data, performing complex image processing algorithms to display the processed images more clearly and accurately, significantly improving defect detection resolution. Furthermore, image processing is conducted in a safe ground environment, reducing the risks associated with operating in complex flight environments. Wind turbine blade inspection can be performed without downtime, avoiding economic losses caused by turbine shutdowns for inspection.

[0014] In one optional implementation, obtaining the center normal of the rotation plane of the wind turbine blades includes:

[0015] Control the third drone to fly above the wind turbine blade, and align the third drone with the installation center of the wind turbine blade;

[0016] A spatial coordinate system is established with the installation center of the wind turbine blade as the origin, and the origin coincides with the third UAV.

[0017] Based on the images of the wind turbine blades taken by the third UAV, an image of the wind turbine blades is generated;

[0018] The rotation plane of the wind turbine blades is determined based on the image of the wind turbine blades;

[0019] Based on the plane of rotation of the wind turbine blades, the normal line passing through the installation center is determined, and the center normal line of the plane of rotation of the wind turbine blades is determined.

[0020] Beneficial effects: By controlling a third drone equipped with a camera to fly above the wind turbine blades and taking vertical downward shots, the drone's position is adjusted horizontally to align the camera with the installation center of the wind turbine blades. A spatial coordinate system is established with the installation center of the wind turbine blades as the origin, ensuring the drone's position coincides with the origin of this system. This enables precise positioning of the drone and related blade positions, improving the accuracy of subsequent operations. Images of the wind turbine blades are obtained through the camera on the third drone. Analysis of these images determines the rotation plane of the wind turbine blades, and further, the normal passing through the installation center of the blades can be identified as the center normal of the rotation plane. By photographing the wind turbine blades, the rotation plane and center normal of the blades can be comprehensively analyzed and determined, improving the reliability of the results.

[0021] In one alternative implementation, determining the plane of rotation of the wind turbine blades based on the image of the wind turbine blades includes:

[0022] The image of the wind turbine blades is preprocessed;

[0023] The preprocessed image is identified using an image recognition algorithm to determine the rotation plane of the wind turbine blades.

[0024] Beneficial Effects: By preprocessing images of wind turbine blades through image denoising and enhancement, image quality is improved, making the images clearer and aiding subsequent analysis and detection. Then, image recognition algorithms are used to identify the preprocessed images, extracting features related to the wind turbine blades. These extracted features determine the specific position of the blades in the image, and the positional changes of the blades in different frames are analyzed to obtain their motion trajectory. Based on the position and trajectory data of the wind turbine blades, a plane is fitted, approximating the rotation plane of the blades. This fitted plane is then verified to determine the rotation plane of the wind turbine blades. Using image recognition algorithms enables the rapid processing of large amounts of image data and provides relatively accurate recognition results, reducing errors and time costs associated with manual identification and improving work efficiency.

[0025] In one optional implementation, positioning the first UAV at a second target distance along the direction of the central normal includes:

[0026] Obtain the GPS coordinates of the third UAV and determine the latitude and longitude of the origin of the spatial coordinate system;

[0027] The latitude and longitude of the first UAV are calculated based on the latitude and longitude of the origin of the spatial coordinate system.

[0028] Based on the GPS positioning of the first drone, the altitude of the first drone is determined;

[0029] Based on the latitude, longitude, and altitude of the first UAV, the first UAV is positioned at a second target distance along the direction of the central normal.

[0030] Beneficial effects: By obtaining the GPS coordinates of the third UAV, the latitude and longitude of the origin of the spatial coordinate system can be determined, i.e., the latitude and longitude of the wind turbine blade installation center. Since the first UAV is set along the direction of the center normal, its latitude and longitude can be confirmed. The first UAV is equipped with GPS, and its altitude can be determined through GPS positioning. After determining the latitude, longitude, and altitude of the first UAV, its specific location can be determined. Then, the first UAV is set at a second target distance along the direction of the center normal. By establishing a spatial coordinate system, it is convenient to determine the relative position, distance, angle, and other relationships between the first UAV and the wind turbine blade.

[0031] In one optional implementation, the imaging area is: L = H = 2.4 × R;

[0032] Where L is the width of the imaging area, H is the height of the imaging area, and R is the length of the wind turbine blade.

[0033] Beneficial effects: Setting the imaging area of ​​the wind turbine blade slightly larger than the blade's length ensures that the entire blade is captured completely, preventing missing parts due to an insufficiently small imaging area. This helps in more accurately analyzing the blade's outline and boundaries. Furthermore, even if the blade wobbles or changes angle during rotation, it remains within the imaging area, avoiding processing difficulties caused by incomplete image edges.

[0034] In one optional implementation, the step of simultaneously photographing the wind turbine blades by the first UAV and multiple second UAVs to obtain multiple images of the wind turbine blades includes:

[0035] The first drone and multiple second drones simultaneously take pictures in front of the wind turbine blades;

[0036] The first drone and multiple second drones move along a preset safety trajectory to the rear of the wind turbine blades to take pictures;

[0037] Multiple imaging images of the front and rear of the wind turbine blades are acquired.

[0038] Beneficial Effects: By simultaneously photographing the front of the wind turbine blades using a first drone and multiple second drones, more comprehensive and detailed information about the front of the blades can be obtained. The collaborative work of multiple drones reduces blind spots, ensuring that various features and states in front of the blades are recorded as completely as possible. The drones move along preset safe trajectories to the rear of the wind turbine blades to ensure that they do not collide with the blades during flight, guaranteeing the safety of the photographing operation. Acquiring multiple images from both the front and rear of the wind turbine blades provides a rich data foundation for subsequent detailed analysis, evaluation, and diagnosis of the wind turbine blades.

[0039] In one optional implementation, the ground control station processes multiple imaging images to generate an inspection report, including:

[0040] The ground control station is used to stitch together multiple imaging images;

[0041] Defects are identified in the stitched images using image recognition algorithms, and an inspection report is generated.

[0042] Beneficial effects: After acquiring multiple images of the front and rear of the wind turbine blades, the ground control station stitches them together to create a coherent and complete image of the blades, allowing for a more comprehensive and macroscopic observation of their overall condition. Image recognition algorithms are then used to analyze the stitched images in detail, identifying various defects in the blade images. Precise location and classification of these defects generate an inspection report, providing accurate data support for subsequent maintenance and repair decisions.

[0043] Secondly, the present invention also provides a wind turbine blade inspection device for unmanned aerial vehicle (UAV) collaborative formation, comprising:

[0044] The first acquisition module is used to acquire the length of the wind turbine blades;

[0045] A segmentation module is used to determine the imaging region based on the length of the wind turbine blade, and to divide the imaging region into multiple identical sub-imaging regions; the wind turbine blade is located within the imaging region; adjacent sub-imaging regions have an overlap length of a first target distance;

[0046] The second acquisition module is used to acquire the center normal of the rotation plane of the wind turbine blades and set the first UAV at a second target distance along the direction of the center normal.

[0047] The drone distribution module is used to deploy a second drone at the center of each of the multiple sub-imaging areas, based on the first drone.

[0048] An imaging module is used to simultaneously capture images of the wind turbine blades using the first UAV and multiple second UAVs, thereby acquiring multiple imaging images of the wind turbine blades.

[0049] An image processing module is used to transmit multiple imaging images to a ground control station, and to process the multiple imaging images based on the ground control station to generate an inspection report.

[0050] Thirdly, the present invention also provides an unmanned aerial vehicle (UAV), comprising: a memory, a processor, a communication interface, and a communication bus, wherein the processor, the memory, and the communication interface communicate with each other through the communication bus;

[0051] The memory is used to store at least one executable instruction, which causes the processor to execute the above-described method for inspecting wind turbine blades in a UAV cooperative formation.

[0052] Fourthly, the present invention also provides a computer-readable storage medium storing at least one executable instruction, which, when executed on a wind turbine blade inspection device of a UAV / UAV collaborative formation, causes the wind turbine blade inspection device of the UAV / UAV collaborative formation to perform the above-described wind turbine blade inspection method of a UAV collaborative formation.

[0053] The above description is merely an overview of the technical solutions of the embodiments of the present invention. In order to better understand the technical means of the embodiments of the present invention and to implement them in accordance with the contents of the specification, and to make the above and other objects, features and advantages of the embodiments of the present invention more apparent and understandable, specific embodiments of the present invention are described below. Attached Figure Description

[0054] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0055] Figure 1 This is a flowchart illustrating a method for inspecting wind turbine blades using a drone collaborative formation, as provided in an embodiment of the present invention.

[0056] Figure 2 This is a flowchart illustrating another method for inspecting wind turbine blades using a drone collaborative formation, provided in an embodiment of the present invention.

[0057] Figure 3 This is a schematic diagram of the imaging area of ​​a wind turbine blade in a wind turbine blade inspection method for a drone collaborative formation provided in an embodiment of the present invention;

[0058] Figure 4 This is a schematic diagram of the safety trajectory in another method for inspecting wind turbine blades using a drone collaborative formation provided in this embodiment of the invention;

[0059] Figure 5 This is a schematic diagram of an embodiment of the wind turbine blade inspection device for drone collaborative formation provided in this invention.

[0060] Figure 6 This is a structural schematic diagram of an embodiment of the UAV provided in this invention. Detailed Implementation

[0061] Exemplary embodiments of the invention will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention can be implemented in various forms and should not be limited to the embodiments set forth herein.

[0062] The following describes a specific embodiment of the wind turbine blade inspection method of the present invention, which involves UAV collaborative formation. Figure 1 This is a flowchart illustrating a method for inspecting wind turbine blades using a drone collaborative formation, as provided in an embodiment of the present invention. This specification provides the method operation steps as shown in the embodiments or flowcharts, but based on conventional or non-inventive methods, more or fewer operation steps may be included. The order of steps listed in the embodiments is merely one possible execution order among many and does not represent the only possible execution order. In actual system or server product execution, the method can be executed sequentially according to the embodiments or drawings, or in parallel (e.g., in a parallel processor or multi-threaded processing environment). Specifically, as shown... Figure 1 As shown, the method may include the following steps:

[0063] Step S100: Obtain the length of the wind turbine blades;

[0064] Step S200: Determine the imaging area based on the length of the wind turbine blades, and divide the imaging area into multiple identical sub-imaging areas; the wind turbine blades are within the imaging area; adjacent sub-imaging areas have an overlap length of the first target distance;

[0065] Step S300: Obtain the center normal of the wind turbine blade rotation plane, and set the first UAV at the second target distance along the direction of the center normal;

[0066] Step S400: Based on the first UAV, a second UAV is set up at the center of each of the multiple sub-imaging areas;

[0067] Step S500: Simultaneously photograph the wind turbine blades using the first UAV and multiple second UAVs to obtain multiple imaging images of the wind turbine blades;

[0068] Step S600: Transmit multiple imaging images to the ground control station, process the multiple imaging images based on the ground control station, and generate an inspection report.

[0069] In this embodiment, the parameters of the wind turbine blades can be obtained based on the parameters of each component during wind turbine construction, thereby obtaining the length of the wind turbine blades. The imaging area is then determined based on the length of the wind turbine blades, with the wind turbine blades falling within this area. Dividing the imaging area into multiple identical sub-imaging areas ensures that the entire wind turbine blade is captured during inspection, guaranteeing the integrity of the inspection. Furthermore, setting multiple sub-imaging areas facilitates clearer observation and analysis of the wind turbine blades' specific condition. Sufficient overlap between two adjacent sub-imaging areas allows for the use of mosaic technology to form a complete image of the wind turbine blades. Based on the center normal of the wind turbine blade's rotation plane, a first UAV is positioned at a second target distance along the direction of the center normal. Then, using the first UAV as the origin, a second UAV is positioned at the center of each surrounding sub-imaging area. This ensures that the imaging area of ​​multiple UAVs covers the wind turbine blade's imaging area, completely capturing the wind turbine blade's state and achieving comprehensive monitoring of the wind turbine blades.

[0070] Each drone is equipped with a camera, allowing multiple drones to simultaneously capture images of the wind turbine blades, resulting in multiple images of the blades. These images are then transmitted to a ground control station, where processing yields a complete image of the wind turbine blades. This allows for the detection and marking of relevant defects, generating an inspection report. The ground control station enables faster and more efficient processing of large amounts of image data, performing complex image processing algorithms to display the processed images more clearly and accurately, significantly improving defect detection resolution. Furthermore, image processing is conducted in a safe ground environment, reducing the risks associated with operating in complex flight environments. Wind turbine blade inspection can be performed without stopping the drones, avoiding economic losses caused by turbine shutdowns for inspection.

[0071] In one embodiment, the imaging area is: L = H = 2.4 × R; where L is the width of the imaging area, H is the height of the imaging area, and R is the length of the wind turbine blade.

[0072] In this embodiment, the imaging area is set slightly larger than the length of the wind turbine blade to ensure that the entire blade can be captured completely. This avoids missing parts of the blade due to an insufficiently small imaging area, which helps to more accurately analyze the contour and boundary of the wind turbine blade. Moreover, even if the wind turbine blade swings or changes its angle during rotation, it can be ensured that the blade remains within the imaging area, avoiding processing difficulties caused by incomplete image edges.

[0073] In other embodiments, the sub-imaging region can be divided into N 2There are N sub-imaging regions; where N is a positive integer. The more sub-imaging regions there are, the finer the details captured, and the smaller the size of defects that can be detected through image recognition. The number of sub-imaging regions can be set according to actual usage needs and is not specifically limited.

[0074] In one embodiment, such as Figure 2 As shown, step S300 includes the following steps:

[0075] Step S310: Control the third drone to fly above the wind turbine blades and align the third drone with the installation center of the wind turbine blades;

[0076] Step S320: Establish a spatial coordinate system with the installation center of the wind turbine blades as the origin, and the origin coincides with the third UAV;

[0077] Step S330: Take pictures of the wind turbine blades based on the third UAV and generate images of the wind turbine blades;

[0078] Step S340: Determine the rotation plane of the wind turbine blades based on the image of the wind turbine blades;

[0079] Step S350: Determine the center normal of the wind turbine blade rotation plane based on the normal of the installation center.

[0080] In this embodiment, a third drone equipped with a camera is controlled to fly above the wind turbine blades, taking vertical downward shots. The drone's position is adjusted horizontally to align the camera with the installation center of the wind turbine blades. A spatial coordinate system is established with the installation center of the wind turbine blades as the origin, ensuring the drone's position coincides with the origin. This allows for precise positioning of the drone and related blade positions, improving the accuracy of subsequent operations. Images of the wind turbine blades are obtained by photographing them with the camera on the third drone. These images are then analyzed to determine the wind turbine blade's plane of rotation. Furthermore, the normal passing through the installation center of the wind turbine blades can be determined, which is the center normal of the wind turbine blade's plane of rotation. By photographing the wind turbine blades, the plane of rotation and center normal of the wind turbine blades can be comprehensively analyzed and determined, improving the reliability of the results.

[0081] In other embodiments, a northeast-sky coordinate system is established with the installation center of the wind turbine blade as the origin, and the origin coincides with the third UAV; by establishing a northeast-sky coordinate system, it is easier to describe the position and direction of the third UAV.

[0082] In one embodiment, step S340 includes:

[0083] Preprocess the image of the wind turbine blades;

[0084] The preprocessed image is identified using an image recognition algorithm to determine the rotation plane of the wind turbine blades.

[0085] In this embodiment, image quality is improved by preprocessing the wind turbine blade image through image denoising and image enhancement, making the details of the wind turbine blades clearer and highlighting their key features. This facilitates accurate extraction and identification of relevant information, aiding subsequent analysis and detection. Then, an image recognition algorithm is used to identify the preprocessed image, extracting features related to the wind turbine blades. These extracted features determine the specific position of the wind turbine blades in the image, and the positional changes of the wind turbine blades in different frames are analyzed to obtain their motion trajectory. Based on the position and trajectory data of the wind turbine blades, a plane is fitted, approximating the rotation plane of the wind turbine blades. This determined rotation plane is then verified to confirm the rotation plane of the wind turbine blades. Using image recognition algorithms enables rapid processing of large amounts of image data and provides relatively accurate recognition results, reducing errors and time costs associated with manual identification and improving work efficiency.

[0086] In one embodiment, step S300 includes:

[0087] Obtain the GPS coordinates of the third UAV and determine the latitude and longitude of the origin of the spatial coordinate system;

[0088] The latitude and longitude of the first UAV are calculated based on the origin of the spatial coordinate system.

[0089] The altitude of the first UAV is determined based on its GPS positioning.

[0090] Based on the latitude, longitude, and altitude of the first UAV, the first UAV is positioned at a second target distance along the direction of the center normal.

[0091] In this embodiment, the latitude and longitude of the origin of the spatial coordinate system, i.e., the latitude and longitude of the wind turbine blade installation center, can be determined by obtaining the GPS coordinates of the third UAV. Since the first UAV is set along the direction of the center normal, the latitude and longitude of the first UAV can be calculated by the distance between the first UAV and the wind turbine blade installation center. The first UAV is equipped with GPS, and its altitude can be determined by GPS positioning. After determining the latitude, longitude, and altitude of the first UAV, its specific location can be determined. Then, the first UAV is set at a second target distance along the direction of the center normal. By establishing a spatial coordinate system, it is convenient to determine the relative position, distance, angle, and other relationships between the first UAV and the wind turbine blade. The second target distance includes 20 meters to 40 meters; for example, 20 meters, 30 meters, 40 meters, etc.; it can be set according to actual usage requirements and is not specifically limited.

[0092] like Figure 3 As shown, in a specific embodiment, the length R of the wind turbine blade is obtained based on its parameters; based on the length of the wind turbine blade, the imaging area is determined to be L = H = 2.4 × R; the imaging area is divided into 9 identical sub-imaging areas, denoted by 1-9; the side length of each sub-imaging area is 4H / 9, and the overlap length between adjacent sub-imaging areas is H / 6; a drone is placed at the center of each of the 9 sub-imaging areas, with a distance of 5H / 18 between adjacent drones. The drone at the center of area 5 is the first drone, which is arranged along the center normal of the wind turbine blade's rotation plane, 30 meters away from the wind turbine blade; each drone is equipped with a three-axis stabilized gimbal, and a high-resolution full-frame camera with a high-speed shutter is mounted on the three-axis stabilized gimbal, with an effective imaging area of ​​each camera being... Figure 2 The system is divided into nine sub-imaging regions. Nine drones form a plane parallel to the rotation plane of the wind turbine blades. These nine drones photograph nine areas of the blades, acquiring images of each area. These images are transmitted to a ground control station, where processing yields a complete image of the wind turbine blades. This allows for the detection and marking of relevant defects, generating an inspection report. By deploying a drone at the center of each of the nine regions to photograph the wind turbine blades, the entire turbine can be inspected simultaneously without stopping operation, significantly improving efficiency and reducing economic losses. Furthermore, the networked formation of multiple drones for regional imaging greatly enhances the resolution of defect detection.

[0093] In one embodiment, step S500 includes:

[0094] The images were taken simultaneously from the front of the wind turbine blades by a first drone and multiple second drones.

[0095] The first drone and multiple second drones moved along a preset safety trajectory to the rear of the wind turbine blades to take pictures;

[0096] Acquire multiple imaging images of the front and rear of the wind turbine blades.

[0097] In this embodiment, by simultaneously photographing the front of the wind turbine blades using a first drone and multiple second drones, more comprehensive and detailed information about the front of the blades can be obtained. The collaborative work of multiple drones reduces blind spots, ensuring that various features and states in front of the blades are recorded as completely as possible. The drones move to the rear of the wind turbine blades according to a preset safe trajectory to ensure that they do not collide with the blades during flight, guaranteeing the safe conduct of the photographing work. Acquiring multiple images of the front and rear of the wind turbine blades provides a rich data foundation for subsequent detailed analysis, evaluation, and diagnosis of the wind turbine blades.

[0098] In a specific embodiment, such as Figure 4 As shown, the mirror images of UAVs 1-9 relative to the wind turbine blade plane are 1'-9' respectively. First, UAVs 1, 4, and 7 follow... Figure 4 The safety trajectory shown bypasses the wind turbine blades from above, reaching positions 3', 6', and 9'; then drones 2, 5, and 8 follow... Figure 4 The indicated safe trajectory reached positions 2', 5', and 8'; finally, drones 3, 6, and 9 followed... Figure 4 The shown safe trajectory reaches positions 1', 4', and 7'. The highest point of the drone's flight, X, is 30m-40m from the wind turbine's rotation plane. This highest flight position can be set according to actual needs. By guiding the drone along the preset safe trajectory to the rear of the wind turbine blades and capturing images from both the front and rear, a rich data foundation can be provided for subsequent detailed analysis, evaluation, and diagnosis of the wind turbine blades. The drone's safe trajectory can be customized according to usage requirements, and is not limited to this.

[0099] In one embodiment, step S600 includes:

[0100] Multiple imaging images are stitched together based on the ground control station;

[0101] Defects are identified in the stitched images using image recognition algorithms, and an inspection report is generated.

[0102] In this embodiment, the ground control station is wirelessly connected to the UAV. After acquiring multiple images of the front and rear of the wind turbine blades, the ground control station stitches them together to create a coherent and complete image of the wind turbine blades, allowing for a more comprehensive and macroscopic observation of the overall condition of the blades. Image recognition algorithms are used to analyze the stitched images in detail to identify various defects in the wind turbine blade images, such as cracks, wear, corrosion, and deformation. Through precise location and classification of these defects, an inspection report is generated, providing accurate data support for subsequent maintenance and repair decisions. For example, the image recognition algorithm can identify a tiny crack on the leading edge of the blade in the stitched image and accurately describe the crack's location, length, and width in the inspection report. Similarly, an abnormal wear area on the wind turbine blade surface will be recorded in detail in the report. This allows relevant personnel to take timely and targeted measures based on the inspection report to ensure the normal operation and safety of the wind turbine.

[0103] Secondly, such as Figure 5 As shown, the present invention also provides a wind turbine blade inspection device for UAV collaborative formation, comprising:

[0104] The first acquisition module 100 is used to acquire the length of the wind turbine blades;

[0105] The segmentation module 200 is used to determine the imaging area based on the length of the wind turbine blades and divide the imaging area into multiple identical sub-imaging areas; the wind turbine blades are within the imaging area; adjacent sub-imaging areas have an overlap length of a first target distance; the imaging area is: L = H = 2.4 × R; where L is the width of the imaging area, H is the height of the imaging area, and R is the length of the wind turbine blades.

[0106] The second acquisition module 300 is used to acquire the center normal of the wind turbine blade rotation plane and set the first UAV at a second target distance along the direction of the center normal.

[0107] The UAV distribution module 400 is used to set up a second UAV at the center of multiple sub-imaging areas based on the first UAV;

[0108] The imaging module 500 is used to simultaneously photograph the wind turbine blades based on the first UAV and multiple second UAVs, and acquire multiple imaging images of the wind turbine blades.

[0109] The image processing module 600 is used to transmit multiple imaging images to the ground control station, and to process the multiple imaging images based on the ground control station to generate an inspection report.

[0110] In one embodiment, the second acquisition module 300 includes:

[0111] The drone control unit is used to control the third drone to fly above the wind turbine blades and align the third drone with the installation center of the wind turbine blades;

[0112] The coordinate system establishment unit is used to establish a spatial coordinate system with the installation center of the wind turbine blade as the origin, and the origin coincides with the third UAV.

[0113] The drone imaging unit is used to capture images of the wind turbine blades based on a third drone, generating images of the wind turbine blades;

[0114] A rotation plane determination unit is used to determine the rotation plane of the wind turbine blades based on the image of the wind turbine blades;

[0115] The center normal determination unit is used to determine the center normal of the rotating plane of the wind turbine blade based on the normal through the installation center.

[0116] In one embodiment, the rotation plane determination unit includes:

[0117] The preprocessing unit is used to preprocess the image of the wind turbine blades;

[0118] The first image recognition unit is used to identify the preprocessed image based on the image recognition algorithm and determine the rotation plane of the wind turbine blades.

[0119] In one embodiment, the second acquisition module 300 further includes:

[0120] The first latitude and longitude acquisition unit is used to acquire the GPS coordinates of the third UAV and determine the latitude and longitude of the origin of the spatial coordinate system.

[0121] The second latitude and longitude acquisition unit is used to calculate the latitude and longitude of the first UAV based on the origin of the spatial coordinate system.

[0122] An altitude acquisition unit is used to determine the altitude of the first UAV based on its GPS positioning.

[0123] The first UAV setting unit is used to set the first UAV at a second target distance along the normal direction of the center, based on the latitude, longitude and altitude of the first UAV.

[0124] In one embodiment, the imaging module 500 includes:

[0125] The first shooting unit is used to simultaneously shoot in front of the wind turbine blades based on the first UAV and multiple second UAVs;

[0126] The second shooting unit is used to move the first drone and multiple second drones along a preset safety trajectory to the rear of the wind turbine blades for shooting.

[0127] The image acquisition unit is used to acquire multiple imaging images of the front and rear of the wind turbine blades.

[0128] In one embodiment, the image processing module 600 includes:

[0129] The stitching unit is used to stitch together images based on ground control stations;

[0130] The second image recognition unit is used to identify defects in the stitched image based on image recognition algorithms and generate an inspection report.

[0131] The apparatus and method embodiments in this application are based on the same application concept.

[0132] Thirdly, the present invention also provides a drone, comprising: a memory, a processor, a communication interface, and a communication bus, wherein the processor, the memory, and the communication interface communicate with each other through the communication bus; the memory is used to store at least one executable instruction, which causes the processor to execute the aforementioned method for inspecting wind turbine blades in a drone cooperative formation.

[0133] like Figure 6As shown, the drone may include: a processor 502, a communications interface 504, a memory 506, and a communications bus 508.

[0134] The processor 502, communication interface 504, and memory 506 communicate with each other via communication bus 508. Communication interface 504 is used to communicate with other network elements, such as clients or other servers. Processor 502 executes program 510, specifically performing the relevant steps in the above-described embodiment of the wind turbine blade inspection method for UAV collaborative formation.

[0135] Specifically, program 510 may include program code, which includes computer-executable instructions.

[0136] Processor 502 may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the present invention. The one or more processors included in the drone may be processors of the same type, such as one or more CPUs; or they may be processors of different types, such as one or more CPUs and one or more ASICs.

[0137] Memory 506 is used to store program 510. Memory 506 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0138] Specifically, program 510 can be called by processor 502 to cause the drone to perform the relevant steps in the above embodiment of the wind turbine blade inspection method for drone collaborative formation.

[0139] Those skilled in the art will understand that Figure 6 The structure shown is for illustrative purposes only and does not limit the structure of the aforementioned equipment. For example, a drone may also include components that are larger than... Figure 6 The more or fewer components shown, or having the same Figure 6 The different configurations shown.

[0140] Fourthly, embodiments of the present invention also provide a computer-readable storage medium storing at least one executable instruction. When the executable instruction is executed on the wind turbine blade inspection device of the UAV / UAV collaborative formation, the wind turbine blade inspection device of the UAV / UAV collaborative formation performs the above-described wind turbine blade inspection method of the UAV collaborative formation.

[0141] The algorithms or displays provided herein are not inherently related to any particular computer, virtual system, or other device. Furthermore, the embodiments of this invention are not directed to any particular programming language.

[0142] Numerous specific details are set forth in the specification provided herein. However, it will be understood that embodiments of the invention may be practiced without these specific details. Similarly, for the sake of brevity and to aid in understanding one or more aspects of the invention, in the description of exemplary embodiments of the invention above, various features of the embodiments are sometimes grouped together in a single embodiment, figure, or description thereof. The claims, which follow the detailed description, are hereby expressly incorporated into that detailed description, wherein each claim itself is a separate embodiment of the invention.

[0143] Those skilled in the art will understand that the modules in the device of the embodiment can be adaptively changed and placed in one or more devices different from that embodiment. Modules, units, or components in the embodiment can be combined into a single module, unit, or component, and further, they can be divided into multiple sub-modules, sub-units, or sub-components, except that at least some of such features and / or processes or units are mutually exclusive.

[0144] It should be noted that the above embodiments are illustrative of the invention and not restrictive, and that those skilled in the art can devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses should not be construed as limiting the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention can be implemented by means of hardware comprising several different elements and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third, etc., does not indicate any order. These words can be interpreted as names. The steps in the above embodiments, unless otherwise specified, should not be construed as limiting the order of execution.

Claims

1. A method for inspecting wind turbine blades using a drone cooperative formation, characterized in that, The method includes: Obtain the length of the wind turbine blades; The imaging area is determined based on the length of the wind turbine blades, and the imaging area is divided into multiple identical sub-imaging areas; the wind turbine blades are located within the imaging area; adjacent sub-imaging areas have an overlap length of a first target distance; Obtain the center normal of the rotation plane of the wind turbine blades, and set up the first UAV at a second target distance along the direction of the center normal; Obtaining the center normal of the rotation plane of the wind turbine blade includes: Control the third drone to fly above the wind turbine blade, and align the third drone with the installation center of the wind turbine blade; A spatial coordinate system is established with the installation center of the wind turbine blade as the origin, and the origin coincides with the third UAV. Based on the images of the wind turbine blades taken by the third UAV, an image of the wind turbine blades is generated; The rotation plane of the wind turbine blades is determined based on the image of the wind turbine blades; Based on the plane of rotation of the wind turbine blades, the normal line passing through the installation center is determined, and the center normal line of the plane of rotation of the wind turbine blades is determined. Based on the first drone, a second drone is set up at the center of each of the multiple sub-imaging regions; Based on the simultaneous photography of the wind turbine blades by the first UAV and multiple second UAVs, multiple imaging images of the wind turbine blades are obtained; Multiple imaging images are transmitted to a ground control station, and the ground control station processes the multiple imaging images to generate an inspection report.

2. The method for inspecting wind turbine blades using UAV collaborative formation according to claim 1, characterized in that, Determining the plane of rotation of the wind turbine blades based on the image of the wind turbine blades includes: The image of the wind turbine blades is preprocessed; The preprocessed image is identified using an image recognition algorithm to determine the rotation plane of the wind turbine blades.

3. The method for inspecting wind turbine blades using UAV collaborative formation according to claim 1, characterized in that, The placement of the first UAV at the second target distance along the direction of the central normal includes: Obtain the GPS coordinates of the third UAV and determine the latitude and longitude of the origin of the spatial coordinate system; The latitude and longitude of the first UAV are calculated based on the latitude and longitude of the origin of the spatial coordinate system. Based on the GPS positioning of the first drone, the altitude of the first drone is determined; Based on the latitude, longitude, and altitude of the first UAV, the first UAV is positioned at a second target distance along the direction of the central normal.

4. The method for inspecting wind turbine blades using UAV collaborative formations according to claim 1, characterized in that, The imaging area is: L=H=2.4×R; Where L is the width of the imaging area, H is the height of the imaging area, and R is the length of the wind turbine blade.

5. The method for inspecting wind turbine blades using UAV collaborative formation according to claim 1, characterized in that, The method of simultaneously photographing the wind turbine blades by the first drone and multiple second drones to obtain multiple images of the wind turbine blades includes: The first drone and multiple second drones simultaneously take pictures in front of the wind turbine blades; The first drone and multiple second drones move along a preset safety trajectory to the rear of the wind turbine blades to take pictures; Multiple imaging images of the front and rear of the wind turbine blades are acquired.

6. The method for inspecting wind turbine blades using UAV collaborative formation according to claim 1, characterized in that, Based on the ground control station, multiple imaging images are processed to generate an inspection report, including: The ground control station is used to stitch together multiple imaging images; Defects are identified in the stitched images using image recognition algorithms, and an inspection report is generated.

7. A wind turbine blade inspection device for unmanned aerial vehicle (UAV) collaborative formation, characterized in that, include: The first acquisition module is used to acquire the length of the wind turbine blades; A segmentation module is used to determine the imaging region based on the length of the wind turbine blade, and to divide the imaging region into multiple identical sub-imaging regions; the wind turbine blade is located within the imaging region; adjacent sub-imaging regions have an overlap length of a first target distance; The second acquisition module is used to acquire the center normal of the rotation plane of the wind turbine blades and set the first UAV at a second target distance along the direction of the center normal. The second acquisition module includes: The drone control unit is used to control the third drone to fly above the wind turbine blades and align the third drone with the installation center of the wind turbine blades; The coordinate system establishment unit is used to establish a spatial coordinate system with the installation center of the wind turbine blade as the origin, and the origin coincides with the third UAV. The drone imaging unit is used to capture images of the wind turbine blades based on the third drone, and generate images of the wind turbine blades. A rotation plane determination unit is used to determine the rotation plane of the wind turbine blades based on the image of the wind turbine blades; The center normal determination unit is used to determine the normal passing through the installation center based on the rotation plane of the wind turbine blade, and to determine the center normal of the rotation plane of the wind turbine blade; The drone distribution module is used to deploy a second drone at the center of each of the multiple sub-imaging areas, based on the first drone. An imaging module is used to simultaneously capture images of the wind turbine blades using the first UAV and multiple second UAVs, thereby acquiring multiple imaging images of the wind turbine blades. An image processing module is used to transmit multiple imaging images to a ground control station, and to process the multiple imaging images based on the ground control station to generate an inspection report.

8. A drone, characterized in that, include: The system includes a memory, a processor, a communication interface, and a communication bus, wherein the processor, the memory, and the communication interface communicate with each other via the communication bus. The memory is used to store at least one executable instruction, which causes the processor to execute the wind turbine blade inspection method of UAV cooperative formation as described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The storage medium stores at least one executable instruction, which, when executed on the wind turbine blade inspection device of the UAV / UAV collaborative formation, causes the wind turbine blade inspection device of the UAV / UAV collaborative formation to perform the wind turbine blade inspection method of the UAV collaborative formation as described in any one of claims 1-6.

Images