Wind turbine blade inspection method and apparatus based on collaborative orchestration of unmanned aerial vehicles, and storage medium

Abstract

The present application relates to the technical field of wind power generation. Disclosed are a wind turbine blade inspection method and apparatus based on collaborative orchestration of unmanned aerial vehicles, and a storage medium. The method comprises: acquiring the length of a wind turbine blade; determining an imaging area on the basis of the length of the wind turbine blade, and dividing the imaging area into a plurality of identical imaging sub-areas; acquiring the central normal of a rotational plane of the wind turbine blade, and providing a first unmanned aerial vehicle at a second target distance in the direction of the central normal; on the basis of the first unmanned aerial vehicle, providing a second unmanned aerial vehicle at the center of each of the plurality of imaging sub-areas; photographing the wind turbine blade on the basis of both the first unmanned aerial vehicle and a plurality of second unmanned aerial vehicles, so as to acquire a plurality of imaging pictures of the wind turbine blade; and transmitting the plurality of imaging pictures to a ground control station, and processing the plurality of imaging pictures, so as to form an inspection report. In the present application, area-based photography is performed by means of a plurality of unmanned aerial vehicles, such that when a wind turbine is not shut down, photographic inspection can be performed on the entire wind turbine, thereby improving the work efficiency, and also reducing economic losses.

Description

Wind turbine blade inspection method and device based on unmanned aerial vehicle cooperative formation and storage medium

[0001] The present application claims priority to the Chinese patent application No. 202410758505.8, filed on June 12, 2024, and entitled "Wind turbine blade inspection method and device based on unmanned aerial vehicle cooperative formation and storage medium", the content of which is incorporated herein by reference in its entirety. TECHNICAL FIELD

[0002] The present application relates to the field of wind power generation, in particular to a wind turbine blade inspection method and device based on unmanned aerial vehicle cooperative formation and storage medium. BACKGROUND

[0003] Wind power generation, as a clean and renewable energy form, is getting more and more attention worldwide. As a global energy consumer, China is also an advocate and leader of green energy. In recent years, China has made remarkable achievements in the progress and large-scale construction of wind power generation technology. With the large-scale construction of wind turbines, the daily inspection and maintenance workload of wind turbines is increasing. Since the wind turbine structure is large, the traditional detection method is usually manual detection by telescope, which has low detection efficiency. Moreover, manual inspection generally requires stopping the machine for detection, resulting in economic losses.

[0004] At present, it is difficult to rely entirely on manual inspection. Unmanned aerial vehicles have gradually been applied in wind turbine inspection and have become an important means due to their advantages of autonomous flight and close-up photography. Unmanned aerial vehicles generally use photography to detect wind turbine blades. The unmanned aerial vehicle flies close to the wind turbine for photography, and the photographed photos are manually checked or intelligent recognition is used to find out the defects on the wind turbine. Since the wind turbine blade tip speed is very fast, the photographed photos are prone to be blurred, affecting the observation effect. Therefore, unmanned aerial vehicle inspection also requires the wind turbine to stop working, and the photos are taken in the wind turbine static state. Moreover, due to the large size of the wind turbine, the whole appearance of the wind turbine can only be photographed at a long distance, making it difficult to identify small defects on the wind turbine blade.

[0005] SUMMARY

[0006] Therefore, the present application provides a wind turbine blade inspection method and device based on unmanned aerial vehicle cooperative formation and storage medium to solve the problem that the wind turbine needs to stop working for detection of the wind turbine blade, and small defects are difficult to identify.

[0007] In a first aspect, the present application provides a wind turbine blade inspection method based on unmanned aerial vehicle cooperative formation, which comprises:

[0008] acquire the length of the fan blade;

[0009] determine an imaging area based on the length of the fan blade, divide the imaging area into a plurality of same sub-imaging areas; the fan blade is in the imaging area; two adjacent sub-imaging areas have an overlapping length of a first target distance;

[0010] acquire the central normal of the rotation plane of the fan blade, and set a first unmanned aerial vehicle at a second target distance in the direction of the central normal;

[0011] based on the first unmanned aerial vehicle, set a second unmanned aerial vehicle at the center of each of the plurality of sub-imaging areas;

[0012] based on the first unmanned aerial vehicle and the plurality of second unmanned aerial vehicles, simultaneously take pictures of the fan blade to acquire a plurality of imaging pictures of the fan blade;

[0013] transmit the plurality of imaging pictures to a ground control station, process the plurality of imaging pictures based on the ground control station, and form an inspection report.

[0014] Beneficial effects: by acquiring the length of the fan blade, and then determining the imaging area according to the length of the fan blade, the fan blade is in the imaging area; the fan blade divides the imaging area of the fan blade into a plurality of same sub-imaging areas, which can ensure that the entire fan blade is photographed when detecting the fan blade, ensuring the integrity of the detection, and the plurality of sub-imaging areas help to more clearly observe and analyze the specific condition of the fan blade; the sufficient overlap of two adjacent sub-imaging areas is conducive to using the puzzle technology to form a complete image of the fan blade. According to the central normal of the rotation plane of the fan blade, the first unmanned aerial vehicle is set at a second target distance in the direction of the central normal, and then a second unmanned aerial vehicle is set at the center of each sub-imaging area around the first unmanned aerial vehicle as the origin, which can ensure that the imaging area of the plurality of unmanned aerial vehicles can cover the fan blade, and can completely capture the state of the fan blade, making the imaging more complete, and achieving comprehensive monitoring of the fan blade.

[0015] Through the multiple unmanned aerial vehicles simultaneously shooting the imaging area of the fan blade, multiple imaging pictures of the fan blade are obtained, the imaging pictures are transmitted to the ground control station, and a complete fan blade image can be obtained through the ground control station processing to detect the related defects on the fan blade and mark them out to form an inspection report; a large amount of image data can be processed more quickly and efficiently through the ground control station, a complex image processing algorithm is completed, the processed image can be displayed more clearly and accurately, and the resolution of defect detection is greatly improved; and the image processing is performed in a safe ground environment, so that the risk of operation in a complex flight environment is reduced. When the fan blade is shot and detected, the fan does not need to be stopped, and economic loss caused by fan shutdown detection is avoided.

[0016] In an optional implementation, the obtaining the central normal line of the rotation plane of the fan blade comprises:

[0017] controlling a third unmanned aerial vehicle to fly above the fan blade, and aligning the third unmanned aerial vehicle with the mounting center of the fan blade;

[0018] establishing a space coordinate system with the mounting center of the fan blade as an origin, and the origin coincides with the third unmanned aerial vehicle;

[0019] generating an image of the fan blade based on the third unmanned aerial vehicle shooting the fan blade;

[0020] determining the rotation plane of the fan blade based on the image of the fan blade;

[0021] determining a normal line passing through the mounting center based on the rotation plane of the fan blade, and determining the central normal line of the rotation plane of the fan blade.

[0022] Advantages: the third unmanned aerial vehicle carrying a camera is controlled to fly above the fan blade, the third unmanned aerial vehicle vertically downwardly shoots, the position of the third unmanned aerial vehicle is adjusted in the horizontal direction, the camera is aligned with the mounting center of the fan blade, a space coordinate system is established with the mounting center of the fan blade as an origin, and the third unmanned aerial vehicle coincides with the origin of the coordinate system; the position of the unmanned aerial vehicle and the position related to the blade can be accurately positioned, and the accuracy of subsequent operations is improved. The camera on the third unmanned aerial vehicle shoots the fan blade to obtain an image of the fan blade; the image of the fan blade is analyzed to determine the rotation plane of the fan blade, and the normal line passing through the mounting center of the fan blade, that is, the central normal line of the rotation plane of the fan blade, can be further determined; the fan blade is shot by the camera, the rotation plane and the central normal line of the fan blade can be comprehensively analyzed and determined, and the reliability of the result is improved.

[0023] In an optional implementation, the determining the rotation plane of the fan blade based on the image of the fan blade comprises:

[0024] preprocessing the image of the fan blade;

[0025] identifying the preprocessed image based on an image recognition algorithm to determine the rotation plane of the fan blade.

[0026] Beneficial effects: By preprocessing the image of the fan blade through image denoising, image enhancement, etc., the quality of the image is improved, making the image clearer, which is helpful for subsequent analysis and detection; then using an image recognition algorithm to identify the preprocessed image, extracting features related to the fan blade from the preprocessed image, using the extracted features to determine the specific position of the fan blade in the image, analyzing the position change of the fan blade in different frames to obtain its motion trajectory, and fitting a plane according to the position and motion trajectory data of the fan blade, the fitted plane is approximately the rotation plane of the fan blade. The determined rotation plane is verified to determine the rotation plane of the fan blade. By using the image recognition algorithm, a large amount of image data can be quickly processed, and a more accurate recognition result can be provided, reducing the error and time cost of manual recognition and improving work efficiency.

[0027] In an optional embodiment, the first unmanned aerial vehicle is arranged at the second target distance in the direction of the central normal line, comprising:

[0028] obtaining the GPS coordinates of the third unmanned aerial vehicle to determine the longitude and latitude of the origin of the spatial coordinate system;

[0029] calculating the longitude and latitude of the first unmanned aerial vehicle based on the longitude and latitude of the origin of the spatial coordinate system;

[0030] determining the altitude of the first unmanned aerial vehicle based on the GPS positioning of the first unmanned aerial vehicle;

[0031] arranging the first unmanned aerial vehicle at the second target distance in the direction of the central normal line based on the longitude and latitude and the altitude of the first unmanned aerial vehicle.

[0032] Beneficial effects: By obtaining the GPS coordinates of the third unmanned aerial vehicle, the longitude and latitude of the origin of the spatial coordinate system, i.e. the longitude and latitude of the center of the fan blade installation, can be determined; since the first unmanned aerial vehicle is arranged along the central normal line, the longitude and latitude of the first unmanned aerial vehicle can be confirmed; the GPS is provided on the first unmanned aerial vehicle, and the altitude of the first unmanned aerial vehicle can be determined through GPS positioning; after the longitude and latitude and the altitude of the first unmanned aerial vehicle are determined, the specific position of the first unmanned aerial vehicle can be determined; then the first unmanned aerial vehicle is arranged at the second target distance in the direction of the central normal line. By establishing the spatial coordinate system, the relative position, distance, angle, etc. between the first unmanned aerial vehicle and the fan blade can be determined.

[0033] In an alternative embodiment, the imaging area is L=H=2.4×R;

[0034] wherein L is the width of the imaging area, H is the height of the imaging area, and R is the length of the fan blade.

[0035] Beneficial effects: The imaging area of the fan blade is set to be slightly larger than the length of the fan blade, ensuring that the entire fan blade can be captured completely, avoiding the situation that part of the blade is missing due to the small imaging area, which helps to more accurately analyze the profile and boundary conditions of the fan blade. Moreover, even if the fan blade has some swing or angle change during rotation, the fan blade can always be ensured to be within the imaging area, avoiding the situation that the image edge is incomplete, which brings processing difficulties.

[0036] In an alternative embodiment, the first unmanned aerial vehicle and the plurality of second unmanned aerial vehicles simultaneously capture the fan blade to obtain a plurality of imaging pictures of the fan blade, comprising:

[0037] The first unmanned aerial vehicle and the plurality of second unmanned aerial vehicles simultaneously capture the front of the fan blade;

[0038] The first unmanned aerial vehicle and the plurality of second unmanned aerial vehicles move along a preset safety trajectory to the rear of the fan blade for shooting;

[0039] Obtain a plurality of imaging pictures of the front and rear of the fan blade.

[0040] Beneficial effects: By simultaneously capturing the front of the fan blade by the first unmanned aerial vehicle and the plurality of second unmanned aerial vehicles, more comprehensive detail information of the front of the fan blade can be obtained. The cooperative work of multiple unmanned aerial vehicles can reduce the dead angle of shooting, ensuring that the various features and states of the front of the blade are recorded as completely as possible. The unmanned aerial vehicles move to the rear of the fan blade according to the preset safety trajectory for shooting, to ensure that the unmanned aerial vehicles do not collide with the fan blade during flight, and to ensure the safe performance of the shooting work. Obtaining a plurality of imaging pictures of the front and rear of the fan blade can provide a rich data basis for subsequent detailed analysis, evaluation and diagnosis of the fan blade.

[0041] In an alternative embodiment, the ground control station processes the plurality of imaging pictures to form an inspection report, comprising:

[0042] The ground control station splices the plurality of imaging pictures;

[0043] Based on the image recognition algorithm, the spliced imaging pictures are subjected to defect recognition to form an inspection report.

[0044] Beneficial effects: After the ground control station obtains the imaging pictures in front of and behind the fan blades, the pictures are combined into a coherent and complete fan blade image by splicing, so that the overall state of the fan blades can be observed more comprehensively and macroscopically. The imaging pictures after splicing are analyzed in detail by using an image recognition algorithm to identify various defects in the fan blade pictures. Through accurate positioning and classification of various defects, a patrol report is formed, which provides accurate data support for subsequent maintenance and repair decisions.

[0045] In a second aspect, the application further provides a fan blade inspection device for unmanned aerial vehicle cooperative formation, comprising:

[0046] A first acquisition module is configured to acquire the length of the fan blade.

[0047] A division module is configured to determine an imaging area based on the length of the fan blade, divide the imaging area into a plurality of identical sub-imaging areas, and determine that the fan blade is in the imaging area and that two adjacent sub-imaging areas have an overlapping length of a first target distance.

[0048] A second acquisition module is configured to acquire a central normal of a rotation plane of the fan blade and to set a first unmanned aerial vehicle at a second target distance in the direction of the central normal.

[0049] An unmanned aerial vehicle distribution module is configured to set a second unmanned aerial vehicle at the center of each of the plurality of sub-imaging areas based on the first unmanned aerial vehicle.

[0050] An imaging module is configured to simultaneously capture the fan blade based on the first unmanned aerial vehicle and the plurality of second unmanned aerial vehicles, and to acquire a plurality of imaging pictures of the fan blade.

[0051] An image processing module is configured to transmit the plurality of imaging pictures to a ground control station, process the plurality of imaging pictures based on the ground control station, and form a patrol report.

[0052] In a third aspect, the application further provides an unmanned aerial vehicle, 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.

[0053] The memory is configured to store at least one executable instruction, and the executable instruction causes the processor to execute the above-mentioned fan blade inspection method for unmanned aerial vehicle cooperative formation.

[0054] Fourthly, this application 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.

[0055] The above description is merely an overview of the technical solutions of the embodiments of this application. In order to better understand the technical means of the embodiments of this application 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 this application more obvious and understandable, specific implementation methods of this application are described below. Attached Figure Description

[0056] To more clearly illustrate the technical solutions in the specific embodiments of this application or 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 this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0057] Figure 1 is a flowchart illustrating a method for inspecting wind turbine blades using a drone collaborative formation, as provided in an embodiment of this application.

[0058] Figure 2 is a flowchart illustrating another method for inspecting wind turbine blades using a drone cooperative formation, as provided in an embodiment of this application.

[0059] Figure 3 is a schematic diagram of the imaging area of ​​the wind turbine blades in a wind turbine blade inspection method of UAV cooperative formation provided in an embodiment of this application;

[0060] Figure 4 is a schematic diagram of the safety trajectory in another method for inspecting wind turbine blades using a drone cooperative formation provided in an embodiment of this application;

[0061] Figure 5 is a structural schematic diagram of an embodiment of the wind turbine blade inspection device for UAV collaborative formation provided in this application;

[0062] Figure 6 is a structural schematic diagram of an embodiment of the UAV provided in this application. Detailed Implementation

[0063] Exemplary embodiments of the present application will now be described in more detail with reference to the accompanying drawings. Although exemplary embodiments of the present application are shown in the drawings, it should be understood that the present application may be implemented in various forms and should not be limited to the embodiments set forth herein.

[0064] The following introduces a specific embodiment of a wind turbine blade inspection method of a UAV cooperative formation, and FIG. 1 is a flowchart of a wind turbine blade inspection method of a UAV cooperative formation according to an embodiment of the present application. The present specification provides method operation steps such as embodiments or flowcharts, but more or fewer operation steps can be included based on conventional or non-creative labor. The order of steps listed in the embodiments is only one of the many execution orders of the steps, and does not represent the only execution order. In actual system or server product execution, the method order shown in the embodiments or the drawings can be executed in sequence or in parallel (for example, in a parallel processor or multi-threaded processing environment). Specifically, as shown in FIG. 1, the method can include the following steps:

[0065] Step S100, obtaining the length of the wind turbine blade;

[0066] Step S200, determining an imaging area based on the length of the wind turbine blade, dividing the imaging area into a plurality of identical sub-imaging areas; the wind turbine blade is in the imaging area; adjacent two sub-imaging areas have an overlapping length of a first target distance;

[0067] Step S300, obtaining the central normal of the wind turbine blade rotation plane, and setting a first UAV at a second target distance in the direction of the central normal;

[0068] Step S400, based on the first UAV, setting a second UAV at the center of each of the plurality of sub-imaging areas;

[0069] Step S500, based on the first UAV and the plurality of second UAVs, simultaneously shooting the wind turbine blade to obtain a plurality of imaging pictures of the wind turbine blade;

[0070] Step S600, transmitting the plurality of imaging pictures to a ground control station, processing the plurality of imaging pictures based on the ground control station, and forming an inspection report.

[0071] In the embodiment, the parameters of the fan blade can be obtained according to the parameters of the components when the fan is built, and the length of the fan blade is obtained, and then the imaging area in which the fan blade is located is determined according to the length of the fan blade. The imaging area is divided into a plurality of identical sub-imaging areas, which can ensure that the entire fan blade is captured when the fan blade is detected, and the integrity of the detection is ensured. In addition, the plurality of sub-imaging areas can help to more clearly observe and analyze the specific conditions of the fan blade. The two adjacent sub-imaging areas are fully overlapped, which is conducive to forming a complete image of the fan blade using the puzzle technology. According to the central normal of the rotation plane of the fan blade, the first unmanned aerial vehicle is arranged at a second target distance in the direction of the central normal, and a second unmanned aerial vehicle is arranged at the center of each sub-imaging area around the first unmanned aerial vehicle as the origin. This can ensure that the imaging areas of the plurality of unmanned aerial vehicles can cover the imaging area of the fan blade, and the state of the fan blade can be completely captured, so that the imaging is more complete, and the fan blade can be comprehensively monitored.

[0072] The cameras are installed on the unmanned aerial vehicles, and the imaging area of the fan blade is simultaneously imaged by the cameras on the plurality of unmanned aerial vehicles to obtain a plurality of imaging pictures of the fan blade. The imaging pictures are transmitted to the ground control station, and a complete fan blade image can be obtained by processing the imaging pictures by the ground control station. The related defects on the fan blade can be detected and marked to form an inspection report. The ground control station can process a large amount of image data more quickly and efficiently, complete complex image processing algorithms, and clearly and accurately display the processed images, which greatly improves the resolution of defect detection. In addition, the image processing is performed in a safe ground environment, which reduces the risk of operation in a complex flight environment. When the fan blade is imaged and detected, the fan does not need to be stopped, which avoids economic losses caused by stopping the fan for detection.

[0073] In one embodiment, the imaging area is L = H = 2.4 x 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 fan blade.

[0074] In the embodiment, the imaging area is set to be slightly larger than the length of the fan blade to ensure that the entire fan blade can be completely captured, and the part of the blade missing due to the small imaging area is avoided, which helps to more accurately analyze the profile and boundary conditions of the fan blade. In addition, even if the fan blade has a certain swing or angle change during rotation, the fan blade can always be ensured to be in the imaging area, which avoids the difficulty in processing caused by the incomplete image edge.

[0075] In other embodiments, the sub-imaging area can be divided into N 2Wherein, N is a positive integer. The more the sub-imaging area divisions are, the more detailed the shooting is, and the smaller the defect size that can be found through image recognition is. The number of sub-imaging area divisions can be set according to actual use requirements and is not specifically limited.

[0076] In one of the embodiments, as shown in FIG. 2, step S300 includes the following steps:

[0077] Step S310, control the third unmanned aerial vehicle to fly above the fan blade, so that the third unmanned aerial vehicle is aligned with the mounting center of the fan blade;

[0078] Step S320, establish a space coordinate system with the mounting center of the fan blade as the origin, and the origin coincides with the third unmanned aerial vehicle;

[0079] Step S330, based on the third unmanned aerial vehicle, shoot the fan blade to generate an image of the fan blade;

[0080] Step S340, determine the rotation plane of the fan blade based on the image of the fan blade;

[0081] Step S350, determine the normal line through the mounting center based on the rotation plane of the fan blade, and determine the central normal line of the rotation plane of the fan blade.

[0082] In this embodiment, by controlling the third unmanned aerial vehicle carrying a camera to fly above the fan blade, the third unmanned aerial vehicle is vertically downwardly shot, the position of the third unmanned aerial vehicle is adjusted in the horizontal direction, so that the camera is aligned with the mounting center of the fan blade; a space coordinate system is established with the mounting center of the fan blade as the origin, so that the third unmanned aerial vehicle coincides with the origin of the coordinate system; the accurate positioning of the position of the unmanned aerial vehicle and the related position of the blade can be realized, and the accuracy of subsequent operations is improved. The fan blade is shot by the camera on the third unmanned aerial vehicle to obtain an image of the fan blade; the image of the fan blade is analyzed to determine the rotation plane of the fan blade, and further the normal line through the mounting center of the fan blade, i.e. the central normal line of the rotation plane of the fan blade; the rotation plane and the central normal line of the fan blade can be comprehensively analyzed and determined through the camera shooting the fan blade, and the reliability of the result is improved.

[0083] In other embodiments, a northeast celestial coordinate system is established with the mounting center of the fan blade as the origin, and the origin coincides with the third unmanned aerial vehicle; the position and direction of the third unmanned aerial vehicle can be more conveniently described through the establishment of the northeast celestial coordinate system.

[0084] In one of the embodiments, step S340 includes:

[0085] The image of the fan blade is preprocessed;

[0086] An image recognition algorithm is used to recognize the preprocessed image to determine the rotation plane of the fan blade.

[0087] In this embodiment, the image of the fan blade is preprocessed by image denoising, image enhancement, etc. to improve the quality of the image, make the details of the fan blade clearer and more identifiable, highlight the key features of the fan blade, facilitate accurate extraction and identification of relevant information, and help subsequent analysis and detection. Then, an image recognition algorithm is used to recognize the preprocessed image, extract features related to the fan blade from the preprocessed image, determine the specific position of the fan blade in the image using the extracted features, analyze the position change of the fan blade in different frames to obtain its motion trajectory, and fit a plane according to the position and motion trajectory data of the fan blade. The fitted plane is approximately the rotation plane of the fan blade. The determined rotation plane is verified to determine the rotation plane of the fan blade. Using the image recognition algorithm can quickly process a large amount of image data and provide more accurate recognition results, reducing the error and time cost of manual identification and improving work efficiency.

[0088] In one embodiment, step S300 includes:

[0089] The GPS coordinates of the third unmanned aerial vehicle are obtained to determine the longitude and latitude of the origin of the spatial coordinate system;

[0090] The longitude and latitude of the first unmanned aerial vehicle are calculated based on the longitude and latitude of the origin of the spatial coordinate system;

[0091] The altitude of the first unmanned aerial vehicle is determined based on the GPS positioning of the first unmanned aerial vehicle;

[0092] The first unmanned aerial vehicle is arranged at a second target distance along the direction of the central normal based on the longitude and latitude and the altitude of the first unmanned aerial vehicle.

[0093] In this embodiment, the longitude and latitude of the origin of the spatial coordinate system, i.e. the longitude and latitude of the fan blade mounting center, can be determined by obtaining the GPS coordinates of the third unmanned aerial vehicle. Since the first unmanned aerial vehicle is arranged along the central normal, the longitude and latitude of the first unmanned aerial vehicle can be calculated based on the distance between the first unmanned aerial vehicle and the fan blade mounting center. The altitude of the first unmanned aerial vehicle can be determined by GPS positioning. After the longitude and latitude and the altitude of the first unmanned aerial vehicle are determined, the specific position of the first unmanned aerial vehicle can be determined. The first unmanned aerial vehicle is arranged at a second target distance along the direction of the central normal. By establishing the spatial coordinate system, the relative position, distance, angle, etc. between the first unmanned aerial vehicle and the fan blade can be determined. The second target distance includes 20-40 meters, for example, 20 meters, 30 meters, 40 meters, etc. It can be set according to actual use requirements and is not limited in particular.

[0094] As shown in FIG. 3, in one specific embodiment, the length R of the fan blade is obtained according to the parameters of the fan blade; the imaging area is determined as L = H = 2.4 x R according to the length of the fan blade; the imaging area is divided into 9 identical sub-imaging areas, which are represented as 1-9 respectively; the length of each sub-imaging area is 4H / 9, and the overlapping length of the length of adjacent two sub-imaging areas is H / 6; a UAV is arranged at the center of each of the 9 sub-imaging areas, and the distance between adjacent two UAVs is 5H / 18. The UAV at the center of the area 5 is the first UAV, which is arranged along the central normal of the rotating plane of the fan blade, and the distance from the fan blade is 30 meters; each UAV is installed with a three-axis stabilized gimbal, and a high-resolution full-frame camera with a high-speed shutter is hung on the three-axis stabilized gimbal; the effective imaging area of each camera is the 9 sub-imaging areas divided in FIG. 2. The 9 UAVs form a plane parallel to the rotating plane of the fan blade, and the 9 areas of the fan blade are photographed by the 9 UAVs to obtain imaging pictures of the 9 areas, which are transmitted to the ground control station, and the complete fan blade image can be obtained by processing by the ground control station to detect and mark the related defects on the fan blade and form an inspection report. By arranging one UAV at the center of each of the 9 areas to photograph the fan blade, the entire fan can be photographed and detected at one time without stopping the work of the fan, which greatly improves the work efficiency and reduces the economic loss; in addition, the multiple UAVs form a network to perform sub-area photography, which can greatly improve the resolution of defect detection.

[0095] In one of the embodiments, the step S500 comprises:

[0096] The first UAV and the plurality of second UAVs simultaneously photograph the front of the fan blade;

[0097] The first UAV and the plurality of second UAVs move along a preset safety trajectory to the rear of the fan blade to perform photographing;

[0098] A plurality of imaging pictures of the front and the rear of the fan blade are obtained.

[0099] In this embodiment, the first UAV and the plurality of second UAVs simultaneously photograph the front of the fan blade, which can more comprehensively obtain the detailed information of the front of the fan blade. The cooperative work of the plurality of UAVs can reduce the dead angle of photography and ensure to record as completely as possible the various features and states of the front of the blade. The UAVs move along the preset safety trajectory to the rear of the fan blade to perform photographing, so as to ensure that the UAVs do not collide with the fan blade during the flight process and ensure the safe performance of the photographing work. The plurality of imaging pictures of the front and the rear of the fan blade can provide a rich data basis for subsequent detailed analysis, evaluation and diagnosis of the fan blade.

[0100] In a specific embodiment, as shown in FIG. 4, the mirror positions of the unmanned aerial vehicles 1-9 relative to the plane of the fan blades are 1'-9' respectively. First, the unmanned aerial vehicles 1, 4 and 7 fly along the safe trajectories shown in FIG. 4 from above the fan blades to the positions 3', 6' and 9' respectively. Then, the unmanned aerial vehicles 2, 5 and 8 fly along the safe trajectories shown in FIG. 4 to the positions 2', 5' and 8' respectively. Finally, the unmanned aerial vehicles 3, 6 and 9 fly along the safe trajectories shown in FIG. 4 to the positions 1', 4' and 7' respectively. The highest position X of the unmanned aerial vehicles is 30-40 m away from the plane of the fan blades, which can be set according to actual needs. The unmanned aerial vehicles fly along the preset safe trajectories to the rear of the fan blades, and take pictures of the front and rear of the fan blades, which can provide a rich data basis for subsequent detailed analysis, evaluation and diagnosis of the fan blades. The safe trajectories of the unmanned aerial vehicles can be set according to the use requirements, and are not limited to this.

[0101] In one embodiment, step S600 includes:

[0102] The ground control station splices the multiple imaging pictures;

[0103] The ground control station identifies defects in the spliced imaging pictures based on an image recognition algorithm, and forms an inspection report.

[0104] In this embodiment, the ground control station is in wireless communication connection with the unmanned aerial vehicles. After the ground control station obtains multiple imaging pictures of the front and rear of the fan blades, the ground control station combines the pictures into a coherent and complete fan blade image by splicing, so as to more comprehensively and macroscopically observe the overall state of the fan blades. The ground control station analyzes the spliced imaging pictures in detail by using an image recognition algorithm, so as to identify various defects existing in the fan blade pictures, such as cracks, wear, corrosion and deformation. Through accurate positioning and classification of various defects, the ground control station forms an inspection report, which provides accurate data support for subsequent maintenance and repair decisions. For example, the image recognition algorithm can identify a small crack in the leading edge of the fan blade from the spliced pictures, and accurately describe the position, length and width of the crack in the inspection report. Or it is found that there is an abnormal wear area on the surface of the fan blade, which is also recorded in detail in the report. In this way, relevant personnel can take targeted measures in time according to the inspection report to ensure the normal operation and safety of the fan.

[0105] In a second aspect, as shown in FIG. 5, the application also provides a fan blade inspection device with unmanned aerial vehicle coordination formation, which includes:

[0106] The first acquisition module 100 is configured to acquire the length of the fan blades.

[0107] The dividing module 200 is configured to determine an imaging area based on the length of the fan blade, divide the imaging area into a plurality of same sub-imaging areas, and arrange the fan blade in the imaging area; two adjacent sub-imaging areas have an overlapping length of a first target distance; the imaging area is L=H=2.4×R; wherein L is the width of the imaging area, H is the height of the imaging area, and R is the length of the fan blade.

[0108] The second acquisition module 300 is configured to acquire a central normal of a rotation plane of the fan blade, and arrange a first unmanned aerial vehicle at a second target distance in the direction of the central normal;

[0109] The unmanned aerial vehicle distribution module 400 is configured to arrange one second unmanned aerial vehicle at the center of each of the plurality of sub-imaging areas based on the first unmanned aerial vehicle;

[0110] The imaging module 500 is configured to simultaneously capture the fan blade based on the first unmanned aerial vehicle and the plurality of second unmanned aerial vehicles, and acquire a plurality of imaging pictures of the fan blade;

[0111] The image processing module 600 is configured to transmit the plurality of imaging pictures to a ground control station, process the plurality of imaging pictures based on the ground control station, and form an inspection report.

[0112] In one of the embodiments, the second acquisition module 300 includes:

[0113] The unmanned aerial vehicle control unit is configured to control the third unmanned aerial vehicle to fly above the fan blade, and align the third unmanned aerial vehicle with the mounting center of the fan blade;

[0114] The coordinate system establishment unit is configured to establish a space coordinate system with the mounting center of the fan blade as an origin, and the origin coincides with the third unmanned aerial vehicle;

[0115] The unmanned aerial vehicle photographing unit is configured to capture the fan blade based on the third unmanned aerial vehicle, and generate an image of the fan blade;

[0116] The rotation plane determination unit is configured to determine the rotation plane of the fan blade based on the image of the fan blade;

[0117] The central normal determination unit is configured to determine a normal line passing through the mounting center based on the rotation plane of the fan blade, and determine the central normal of the rotation plane of the fan blade.

[0118] In one of the embodiments, the rotation plane determination unit includes:

[0119] The preprocessing unit is configured to pre-process the image of the fan blade;

[0120] The first image recognition unit is configured to recognize the pre-processed image based on an image recognition algorithm, and determine the rotation plane of the fan blade.

[0121] In one embodiment, the second acquisition module 300 further comprises:

[0122] The first latitude and longitude acquisition unit is configured to acquire the GPS coordinates of the third UAV and determine the latitude and longitude of the origin of the space coordinate system.

[0123] The second latitude and longitude acquisition unit is configured to calculate the latitude and longitude of the first UAV based on the latitude and longitude of the origin of the space coordinate system.

[0124] The height acquisition unit is configured to determine the altitude of the first UAV based on the GPS positioning of the first UAV.

[0125] The first UAV setting unit is configured to set the first UAV at the second target distance along the normal direction of the center based on the latitude and longitude and the altitude of the first UAV.

[0126] In one embodiment, the imaging module 500 comprises:

[0127] The first shooting unit is configured to shoot the front of the fan blade based on the first UAV and the plurality of second UAVs.

[0128] The second shooting unit is configured to move the first UAV and the plurality of second UAVs to the rear of the fan blade along the preset safety track and shoot the rear of the fan blade.

[0129] The picture acquisition unit is configured to acquire a plurality of imaging pictures of the front and rear of the fan blade.

[0130] In one embodiment, the image processing module 600 comprises:

[0131] The splicing unit is configured to splice the imaging pictures based on the ground control station.

[0132] The second image recognition unit is configured to recognize defects of the spliced imaging pictures based on the image recognition algorithm and form an inspection report.

[0133] The device and method embodiments in the present application are based on the same application concept.

[0134] In a third aspect, the present application further provides a UAV, comprising a memory, a processor, a communication interface and a communication bus, the processor, the memory and the communication interface complete communication with each other through the communication bus; the memory is used to store at least one executable instruction, and the executable instruction makes the processor execute the above-mentioned wind turbine blade inspection method of UAV cooperative formation.

[0135] As shown in FIG. 6, the UAV can include a processor 502, a communications interface 504, a memory 506, and a communications bus 508.

[0136] The processor 502, the communications interface 504, and the memory 506 can communicate with each other through the communications bus 508. The communications interface 504 is configured to communicate with network elements such as clients or other servers. The processor 502 is configured to execute the program 510, and can execute the related steps in the above-described method for UAV cooperative formation fan blade inspection.

[0137] Specifically, the program 510 can include program codes including computer-executable instructions.

[0138] The processor 502 can be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement one or more embodiments of the present application. The one or more processors of the UAV can be the same type of processor, such as one or more CPUs; or can be different types of processors, such as one or more CPUs and one or more ASICs.

[0139] The memory 506 is configured to store the program 510. The memory 506 can include a high-speed RAM memory, and can also include a non-volatile memory such as at least one disk memory.

[0140] The program 510 can be specifically invoked by the processor 502 to cause the UAV to execute the related steps in the above-described method for UAV cooperative formation fan blade inspection.

[0141] Those skilled in the art can understand that the structure shown in FIG. 6 is only schematic, and does not limit the structure of the above-described device. For example, the UAV can include more or fewer components than those shown in FIG. 6, or have a different configuration from that shown in FIG. 6.

[0142] In a fourth aspect, the embodiments of the present application also provide a computer-readable storage medium, which stores at least one executable instruction. When the executable instruction is run on the UAV / UAV cooperative formation fan blade inspection device, the UAV / UAV cooperative formation fan blade inspection device executes the above-described method for UAV cooperative formation fan blade inspection.

[0143] The algorithms and displays presented herein are not inherently related to any particular computer, virtual system, or other apparatus. Furthermore, embodiments of the present application are not described with reference to any particular programming language.

[0144] In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the application can be practiced without these specific details. In other instances, well-known methods, structures and techniques have not been described in detail in order to not obscure aspects of the embodiments of the application. Like numbers refer to like elements throughout. Also, in the following description, various functions and operations can be described or depicted as being performed by or controlled by one or more specific devices. It will be understood that in practice, the functions and operations can be performed by one or more devices, which can include devices that have multiple functions, can form part of one or more systems, and / or can perform operations specially configured for the function (e.g., a microprocessor configured as a particular device). In addition, unless otherwise specified, "a" or "an" shall not be construed to mean only one instance but instead potentially one or more instances.

[0145] Those skilled in the art will understand that the modules in the devices in the embodiments can be adapted and placed in one or more devices other than the embodiments. The modules or units or components in the embodiments can be combined into one module or unit or component, and further can be divided into multiple sub-modules or sub-units or sub-components. Except that at least some of such features and / or processes or units are mutually exclusive.

[0146] It is noted that the foregoing examples have been provided merely for the purpose of explanation and are in no way to be construed as limiting of the present application. While the application has been described with reference to preferred embodiments, it is understood that the words which have been used herein are words of description and illustration, rather than words of limitation. Changes can be made, within the purview of the appended claims, as presently set forth, and as amended, without departing from the scope and spirit of the present application in its aspects. The appended claims are hereby incorporated into this detailed description, to make the detailed description a part of the application. The use of the terms "including", "containing", "comprising", "having" and the like are meant to be equivalent to the term "comprising" and, therefore, should not be interpreted as limiting. The use of the term "or" is meant to encompass both a single element having the pore qualities or a plurality of elements each having the pore qualities. The use of the terms "first", "second" and the like can so modified so as to refer to a different one of the similar elements other than the first "second" element. The use of the terms "at least one" and "one or more" is meant to encompass both the singular and the plural, unless the context clearly indicates otherwise.

Claims

1. A method for inspecting wind turbine blades by a drone cooperative formation, characterized in that, The method comprises: acquiring the length of a fan blade; determining an imaging area based on the length of the fan blade, dividing the imaging area into a plurality of identical sub-imaging areas; the fan blade is in the imaging area; two adjacent sub-imaging areas have an overlapping length of a first target distance; acquiring the central normal of the rotating plane of the fan blade, and setting a first unmanned aerial vehicle at a second target distance in the direction of the central normal; based on the first unmanned aerial vehicle, setting a second unmanned aerial vehicle at the center of each of the plurality of sub-imaging areas; based on the first unmanned aerial vehicle and the plurality of second unmanned aerial vehicles, simultaneously photographing the fan blade to acquire a plurality of imaging pictures of the fan blade; transmitting the plurality of imaging pictures to a ground control station, and based on the ground control station, processing the plurality of imaging pictures to form an inspection report.

2. The method of claim 1, wherein, The acquisition of the central normal of the rotating plane of the fan blade comprises: controlling a third unmanned aerial vehicle to fly above the fan blade, and aligning the third unmanned aerial vehicle with the mounting center of the fan blade; establishing a space coordinate system with the mounting center of the fan blade as the origin, and the origin coincides with the third unmanned aerial vehicle; based on the third unmanned aerial vehicle, photographing the fan blade to generate an image of the fan blade; based on the image of the fan blade, determining the rotating plane of the fan blade; based on the rotating plane of the fan blade, determining the normal line through the mounting center to determine the central normal of the rotating plane of the fan blade. 3.The UAV coordinated formation wind blade inspection method of claim 2, wherein, The determination of the rotating plane of the fan blade based on the image of the fan blade comprises: preprocessing the image of the fan blade; based on an image recognition algorithm, recognizing the preprocessed image to determine the rotating plane of the fan blade. 4.The UAV coordinated formation wind blade inspection method of claim 2, wherein, The setting of the first unmanned aerial vehicle at a second target distance in the direction of the central normal comprises: acquiring the GPS coordinates of the third unmanned aerial vehicle to determine the longitude and latitude of the origin of the space coordinate system; based on the longitude and latitude of the origin of the space coordinate system, calculating the longitude and latitude of the first unmanned aerial vehicle; based on the GPS positioning of the first unmanned aerial vehicle, determining the altitude of the first unmanned aerial vehicle; based on the longitude, latitude and altitude of the first unmanned aerial vehicle, setting the first unmanned aerial vehicle at a second target distance in the direction of the central normal. 5.The UAV coordinated formation wind blade inspection method of claim 1, wherein, The imaging area is L=H=2.4×R; wherein L is the width of the imaging area, H is the height of the imaging area, and R is the length of the fan blade. 6.The UAV coordinated formation wind blade inspection method of claim 1, wherein, The photographing of the fan blade by the first unmanned aerial vehicle and the plurality of second unmanned aerial vehicles to acquire a plurality of imaging pictures of the fan blade comprises: based on the first unmanned aerial vehicle and the plurality of second unmanned aerial vehicles, simultaneously photographing the front of the fan blade; the first unmanned aerial vehicle and the plurality of second unmanned aerial vehicles move along a preset safety trajectory to the rear of the fan blade for photographing; acquiring a plurality of imaging pictures of the front and rear of the fan blade. 7.The UAV coordinated formation wind blade inspection method of claim 1, wherein, The processing of the plurality of imaging pictures by the ground control station to form an inspection report comprises: based on the ground control station, splicing the plurality of imaging pictures; The imaging pictures after splicing are recognized based on an image recognition algorithm to form an inspection report.

8. A wind turbine blade inspection device for unmanned aerial vehicle cooperative formation, characterized in that, The method comprises the steps of: The first acquisition module is configured to acquire the length of the fan blade. The division module is configured to determine an imaging area based on the length of the fan blade, divide the imaging area into a plurality of identical sub-imaging areas, and determine the first target distance overlap length of adjacent two sub-imaging areas. The second acquisition module is configured to acquire the central normal of the rotation plane of the fan blade and set the first unmanned aerial vehicle at the second target distance along the direction of the central normal. The unmanned aerial vehicle distribution module is configured to set a second unmanned aerial vehicle at the center of each of the plurality of sub-imaging areas based on the first unmanned aerial vehicle. The imaging module is configured to simultaneously capture the fan blade based on the first unmanned aerial vehicle and the plurality of second unmanned aerial vehicles, and acquire a plurality of imaging pictures of the fan blade. The image processing module is configured to transmit the plurality of imaging pictures to a ground control station, process the plurality of imaging pictures based on the ground control station, and form an inspection report.

9. A drone, characterized in that, The method comprises the steps of: The memory, the processor, the communication interface and the communication bus complete mutual communication through the communication bus. The memory is configured to store at least one executable instruction, and the executable instruction causes the processor to execute the fan blade inspection method of the unmanned aerial vehicle cooperative formation according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The storage medium stores at least one executable instruction, and the executable instruction causes the unmanned aerial vehicle / unmanned aerial vehicle cooperative formation fan blade inspection device to execute the fan blade inspection method of the unmanned aerial vehicle cooperative formation according to any one of claims 1-7 when the executable instruction runs on the unmanned aerial vehicle / unmanned aerial vehicle cooperative formation fan blade inspection device.

Images