Wind driven generator inspection method and device based on unmanned aerial vehicle and unmanned aerial vehicle

Abstract

The embodiment of the invention provides a wind driven generator inspection method and device based on an unmanned aerial vehicle and the unmanned aerial vehicle. The method comprises the following steps: acquiring a shot image of to-be-inspected equipment; determining blade orientation information of the to-be-inspected equipment according to the shot image of the to-be-inspected equipment; determining a local waypoint of the image shot by the unmanned aerial vehicle according to the blade orientation information; constructing an inspection route based on the local waypoints; according to the method, the blade orientation information is obtained, the inspection route information of the unmanned aerial vehicle is determined, the channel route information and the inspection route information are combined, the to-be-inspected equipment is photographed, manual adjustment of the position of a waypoint is avoided, and the inspection efficiency of the wind driven generator is improved.

Description

Technical Field

[0001] The present application relates to the technical field of unmanned aerial vehicles (UAVs), and more specifically, to a wind turbine inspection method and device based on UAVs, and a UAV. Background Art

[0002] Wind turbine inspection is an important part of ensuring the normal operation of wind power generation systems and extending the life of equipment. In the existing technology, high-altitude inspection can be used, such as using drones equipped with sensors, i.e., high-definition cameras, infrared thermal imaging, etc. to detect various parts of wind turbines for defects and fault point analysis. However, since the wind turbine will dynamically adjust the direction of the blades according to the wind direction during operation, the drone will take pictures of the wind turbine blades according to the preset route, but it is impossible to collect clear and angled photos, and it is impossible to understand the operating status of the wind turbine generator in time. In this way, it is necessary to manually adjust the angle of the route, and the inspection efficiency is not high. Therefore, how to improve the inspection efficiency of wind turbines by drones is an urgent problem to be solved. Summary of the invention

[0003] The present application provides a wind turbine inspection method, device and drone based on drone. Through the technical solution of the present application, images of the equipment to be inspected are obtained; blade orientation information of the equipment to be inspected is determined based on the images of the equipment to be inspected; local waypoints of the images taken by the drone are determined based on the blade orientation information; an inspection route is constructed based on the local waypoints; and the equipment to be inspected is inspected based on the inspection route. The present application obtains blade orientation information, and then determines the inspection route information of the drone, combines the channel route information and the inspection route information, takes pictures of the equipment to be inspected, avoids manual adjustment of waypoint positions, and improves the inspection efficiency of wind turbines.

[0004] In a first aspect, the present application provides a wind turbine inspection method based on a drone, the method comprising: Obtaining images of the equipment to be inspected; Determining blade orientation information of the device to be inspected based on the captured image of the device to be inspected; Determining a local waypoint of the image taken by the drone according to the blade orientation information; Based on the local waypoints, construct an inspection route; The equipment to be inspected is inspected according to the inspection route.

[0005] This application obtains the blade orientation information and then determines the inspection route information of the drone. It combines the channel route information and the inspection route information to take pictures of the inspection equipment, avoids manual adjustment of the waypoint position, and improves the inspection efficiency of wind turbines.

[0006] Optionally, the inspection route is constructed based on the local waypoints, including: Determining the photographing position information of the drone according to the blade orientation information; Determine the local waypoint of the image taken by the drone according to the photographing position information of the drone; The inspection route is determined according to the local waypoints of the images taken by the drone.

[0007] In the present application, images of the equipment to be inspected are obtained at waypoints in the channel route, and then the blade orientation information is identified. Based on the blade orientation information, the photo waypoint information of the UAV is determined, and the UAV is controlled to take photos at the photo waypoints. In this way, the photo position of the UAV is automatically adjusted until a photo that meets the requirements can be taken from the front or back.

[0008] Optionally, determining blade orientation information of the device to be inspected according to the captured image of the device to be inspected includes: Using a wind turbine component recognition model to identify blades and a nacelle in the captured image; Determining a deflection direction of the nacelle and a first direction of the blade according to relative positions of the blade and the nacelle in the captured image; The blade orientation information of the equipment to be inspected is determined according to the deflection direction of the nacelle or the first direction.

[0009] Optionally, determining a local waypoint of an image captured by a drone according to the blade orientation information includes: According to the preset moving distance and the blade orientation information, the local waypoint of the image taken by the drone is determined. In the present application, the drone is controlled to rotate from the waypoint of the channel route according to the blade orientation information, and fly a preset moving distance to reach the drone's photo-taking position, i.e., the local waypoint, and then take photos of the blades.

[0010] Optionally, determining a local waypoint of an image captured by a drone according to a preset moving distance and the blade orientation information includes: According to the preset shooting requirements, the photographing waypoint information corresponding to the local waypoint of the UAV is determined, wherein the preset shooting requirements at least include one or more of shooting the front side of the blade or shooting the back side of the blade, and the blade shooting area.

[0011] In the present application, after determining the photographing location information, the photographing waypoint can be determined according to the preset photographing requirements, such as the need to photograph the front side of the blade or the back side of the blade, or the location where the photographing is required. Optionally, inspecting the equipment to be inspected according to the inspection route includes: According to the current channel waypoint of the channel route, stay in the preset area above the equipment to be inspected; Taking photos of the equipment to be inspected according to the inspection route; After taking a photo of the device to be inspected at the current channel waypoint, the channel moves to the next channel waypoint of the channel route according to the channel route information to take a photo of the device to be inspected. In this application, the drone first flies to the channel waypoint, and then flies to the waypoint in the inspection route information based on the blade orientation information to take pictures of the inspection equipment. After the photo is taken, the drone flies to the waypoint of the next channel route and conducts inspection in the above manner to improve inspection efficiency.

[0012] Optionally, the method further comprises: The acquired photos of the equipment to be inspected are processed, and according to the processed results, fault diagnosis is performed on the equipment to be inspected.

[0013] In this application, the blade orientation information is obtained to determine the inspection route information of the drone. The channel route information and the inspection route information are combined to take photos of the inspection equipment. The obtained photos are subsequently processed to improve the accuracy of image processing and the accuracy of fault diagnosis.

[0014] Optionally, taking photos of the equipment to be inspected according to the inspection route includes: According to the inspection route, controlling the drone to move to a first designated position, wherein the first designated position is used to photograph the tip of the blade; The drone is controlled to move downward on a vertical line of the first designated position to a second designated position, where the second designated position is used to photograph the blades.

[0015] In a second aspect, the present application provides a wind turbine inspection device based on a drone, the device comprising: An acquisition module is used to acquire images of the equipment to be inspected; An identification module, used to determine blade orientation information of the device to be inspected based on the captured image of the device to be inspected; A determination module, used for determining the local waypoints of the image taken by the drone according to the blade orientation information of the inspection route; A generation module, used for constructing an inspection route based on the local waypoints; The inspection module is used to inspect the equipment to be inspected according to the inspection route.

[0016] This application obtains the blade orientation information and then determines the inspection route information of the drone. It combines the channel route information and the inspection route information to take pictures of the inspection equipment, avoids manual adjustment of the waypoint position, and improves the inspection efficiency of wind turbines.

[0017] Optionally, the generating module is used to: Determining the photographing position information of the drone according to the blade orientation information; Determine the local waypoint of the image taken by the drone according to the photographing position information of the drone; The inspection route is determined according to the local waypoints of the blade photographed by the drone.

[0018] In the present application, images of the equipment to be inspected are obtained at waypoints in the channel route, and then the blade orientation information is identified. Based on the blade orientation information, the photo waypoint information of the UAV is determined, and the UAV is controlled to take photos at the photo waypoints. In this way, the photo position of the UAV is automatically adjusted until a photo that meets the requirements can be taken from the front or back.

[0019] Optionally, the determining module is used to: Using a wind turbine component recognition model to identify blades and a nacelle in the captured image; Determining a deflection direction of the nacelle and a first direction of the blade according to relative positions of the blade and the nacelle in the captured image; The blade orientation information of the equipment to be inspected is determined according to the deflection direction of the nacelle or the first direction.

[0020] Optionally, the determining module is used to: According to the preset moving distance and the blade orientation information, the local waypoint of the image taken by the drone is determined. In the present application, the drone is controlled to rotate from the waypoint of the channel route according to the blade orientation information, and fly a preset moving distance to reach the drone's photo taking position, and then take photos of the blades.

[0021] Optionally, the determining module is used to: According to the preset shooting requirements, the photographing waypoint information corresponding to the local waypoint of the UAV is determined, wherein the preset shooting requirements at least include one or more of shooting the front side of the blade or shooting the back side of the blade, and the blade shooting area.

[0022] In the present application, after determining the photographing location information, the photographing waypoint information can be determined according to the preset photographing requirements, such as the need to photograph the front side of the blade or the back side of the blade, or the location where the photographing is required. Optionally, the inspection module is used to: According to the current channel waypoint of the channel route, stay in the preset area above the equipment to be inspected; Inspection route: taking photos of the equipment to be inspected according to the inspection route; After taking a photo of the device to be inspected at the current channel waypoint, the channel moves to the next channel waypoint of the channel route according to the channel route information to take a photo of the device to be inspected. In this application, the drone first flies to the channel waypoint, and then flies to the waypoint in the inspection route information based on the blade orientation information to take pictures of the inspection equipment. After the photo is taken, the drone flies to the waypoint of the next channel route and conducts inspection in the above manner to improve inspection efficiency.

[0023] Optionally, the inspection module is further used for: The acquired photos of the equipment to be inspected are processed, and according to the processed results, fault diagnosis is performed on the equipment to be inspected.

[0024] In this application, the blade orientation information is obtained to determine the inspection route information of the drone. The channel route information and the inspection route information are combined to take photos of the inspection equipment. The obtained photos are subsequently processed to improve the accuracy of image processing and the accuracy of fault diagnosis.

[0025] Optionally, the inspection module is used to: According to the inspection route, controlling the drone to move to a first designated position, wherein the first designated position is used to photograph the tip of the blade; The drone is controlled to move downward on a vertical line of the first designated position to a second designated position, where the second designated position is used to photograph the blades.

[0026] In a third aspect, the present application provides a drone, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the drone-based wind turbine inspection method as described in any embodiment of the first aspect can be implemented. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the technical solutions of some embodiments of the present application, the drawings required for use in some embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0028] Figure 1A schematic diagram of a flow chart of a wind turbine inspection method based on a drone provided in an embodiment of the present application; Figure 2 A side view of a wind turbine inspection channel route provided in an embodiment of the present application; Figure 3 A top view of the wind turbine inspection channel route and local route provided in an embodiment of the present application; Figure 4 A schematic diagram of wind turbine direction identification provided in an embodiment of the present application; Figure 5 A schematic diagram of wind turbine direction identification provided by another embodiment of the present application; Figure 6 A schematic diagram of a flow chart of another wind turbine inspection method based on a drone provided in an embodiment of the present application; Figure 7 A schematic structural diagram of a wind turbine inspection device based on a drone provided in an embodiment of the present application. DETAILED DESCRIPTION

[0029] The technical solutions in some embodiments of the present application will be described below in conjunction with the drawings in some embodiments of the present application.

[0030] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0031] Wind turbine inspection is an important part of ensuring the normal operation of wind power generation systems and extending the life of equipment. In the existing technology, high-altitude inspection can be used, such as using drones equipped with sensors, i.e., high-definition cameras, infrared thermal imaging, etc. to detect various parts of wind turbines for defects and fault point analysis. However, since the wind turbine will dynamically adjust the direction of the blades according to the wind direction during operation, the drone will take pictures of the wind turbine blades according to the preset route, but it is impossible to collect clear and angled photos, and it is impossible to understand the operating status of the wind turbine generator in time. In this way, it is necessary to manually adjust the angle of the route, and the inspection efficiency is not high. Therefore, how to improve the inspection efficiency of wind turbines by drones is an urgent problem to be solved. In view of this, some embodiments of the present application provide a wind turbine inspection method based on a drone, by acquiring photographed images of the equipment to be inspected; determining the blade orientation information of the equipment to be inspected based on the photographed images of the equipment to be inspected; determining local waypoints of the images photographed by the drone based on the blade orientation information; constructing an inspection route based on the local waypoints; and inspecting the equipment to be inspected based on the inspection route. The present application acquires the blade orientation information, and then determines the inspection route of the drone, combines the channel route and the inspection route, takes pictures of the equipment to be inspected, avoids manual adjustment of the waypoint position, and improves the inspection efficiency of wind turbines.

[0032] like Figure 1 As shown, an embodiment of the present application provides a wind turbine inspection method based on a drone, the method comprising: S101, obtaining a photographed image of the equipment to be inspected; Specifically, when the drone needs to inspect the equipment to be inspected, it sends a request to the background server, and the background server sends the channel route to the drone, and the drone inspects the equipment to be inspected according to the channel route.

[0033] During the inspection process, the drone stays at the waypoint position of the channel route, and the shooting device on the drone is used to collect the shooting image of the equipment to be inspected; wherein, the equipment to be inspected can be a wind turbine. Wherein, waypoints are set above each equipment to be inspected, and a channel route is generated based on these waypoints. The channel route is a channel route composed of the starting point of the drone and multiple channel waypoints. When the drone is at the channel waypoint, it can look down and shoot the wind turbine, and obtain the shooting image, and it can be obtained that the height of the channel waypoint is higher than the wind turbine. Wherein, the shooting image is a bird's-eye view of the wind turbine or an image of the wind turbine taken from a preset angle. The shooting image should include blades and a cabin. The cabin stores equipment such as generators.

[0034] S102, determining blade orientation information of the device to be inspected based on the captured image of the device to be inspected; Specifically, after acquiring the captured images of the equipment to be inspected, the UAV identifies the blades and cabin in the captured images, determines the deflection angle based on the deflection direction of the cabin, and obtains the blade orientation information through the deflection angle. The blade orientation information is due to the change in wind direction, which causes the direction of the wind turbine blades to change.

[0035] S103, the inspection route determines the local waypoints of the image taken by the drone according to the blade orientation information; Specifically, after determining the blade orientation information, the drone determines the inspection route waypoint of the drone according to the preset shooting requirements. The shooting waypoint can be on the front side of the blade or the back side of the blade, or it may be necessary to shoot a part or all of the blade.

[0036] S104, the inspection route is constructed based on the local waypoints; The UAV generates an inspection route based on the obtained local waypoints, and then combines the channel route and the inspection route to generate the target route for the equipment to be inspected. That is to say, after the UAV reaches each waypoint position on the channel route, it reaches the shooting position according to the inspection route.

[0037] S105. Inspect the equipment to be inspected according to the inspection route.

[0038] In the embodiment of the present application, the blade orientation information is obtained to determine the inspection route of the drone, and the channel route and the inspection route are combined to take photos of the inspection equipment, thereby avoiding manual adjustment of the waypoint position and improving the inspection efficiency of the wind turbine.

[0039] Another embodiment of the present application further supplements the UAV-based wind turbine inspection method provided in the above embodiment.

[0040] Optionally, based on local waypoints, an inspection route is constructed, including: Determine the drone's photo taking position information based on the blade orientation information; According to the photo taking position information of the drone, determine the local waypoints of the image taken by the drone; The inspection route is determined based on the local waypoints of the blades photographed by the drone.

[0041] In the present application, images of the equipment to be inspected are obtained at waypoints in the channel route, and then the blade orientation information is identified. Based on the blade orientation information, the photo waypoint information of the UAV is determined, and the UAV is controlled to take photos at the photo waypoints. In this way, the photo position of the UAV is automatically adjusted until a photo that meets the requirements can be taken from the front or back.

[0042] Optionally, a wind turbine component recognition model is used to determine the blades and the nacelle in the captured image; Determine the deflection direction of the nacelle and the first direction of the blade according to the relative positions of the blade and the nacelle in the captured image; The blade orientation information of the equipment to be inspected is determined according to the deflection direction or the first direction of the nacelle.

[0043] Specifically, Figure 2 As shown, the origin above the wind turbine in the figure is the waypoint of the channel route. The drone takes a bird's-eye view of the picture containing the blades of the wind turbine at the position above the wind turbine, i.e., the waypoint position, and determines the direction of the blades of the wind turbine from the bird's-eye view.

[0044] Image feature (morphological) recognition or deep learning methods can be used to identify blades and nacelles in the image. The fan component recognition model in this application can be a trained fan component recognition model, or it can be a combination of a recognition frame and a recognition algorithm. The specific recognition algorithm is not specifically limited in this application.

[0045] like Figure 4 As shown, determining the blade orientation information of the equipment to be inspected based on the deflection direction of the cabin and the first direction includes: obtaining a first deflection angle; wherein the first deflection angle is the angle between the y-axis direction of the captured image and the north direction, and the north direction is the direction in the geodetic coordinate system; obtaining a second deflection angle; and determining the blade orientation information of the equipment to be inspected based on the second deflection angle and the first deflection angle.

[0046] In an embodiment of the present application, the captured image is input into a wind turbine component recognition model, and multiple bounding boxes are generated on the captured image. Each bounding box contains only one object, and the bounding box represents the minimum area surrounding the object in the captured image. Then, the wind turbine component model can identify the objects in the bounding box as blades and nacelle.

[0047] Determine the relative positions of the blades and the nacelle in the captured image to determine the deflection direction of the nacelle. Figure 4 As shown, the nacelle is on the right side of the blade, so the deflection direction of the nacelle is leftward. The nacelle is on the left side of the blade, so the deflection direction of the nacelle is rightward.

[0048] Specifically, after identifying the blade and the nacelle, the direction from the center point of the blade to the blade tip is determined, and the direction is defined as the first direction. Based on the relative position of the position of the first direction in the image and the nacelle, the deflection direction of the center point of the nacelle pointing to the first direction is determined, and the deflection direction coincides with the center line of the nacelle.

[0049] Further, the first deflection angle is obtained, and based on the deflection direction of the nacelle, the second deflection angle of the nacelle is determined, and according to the deflection direction of the nacelle, the second deflection angle and the first deflection angle, the blade orientation information of the device to be inspected is determined. The second deflection angle may be the deflection angle of the nacelle or the deflection angle of the blade.

[0050] In this embodiment, the blade orientation information is as follows: Figure 4 As shown, the blade orientation information includes the blade orientation angle, which is the angle between the geodetic coordinate true north (N) and the first direction of the blade. The first deflection angle is set to β, and the second deflection angle is set to α, wherein the second deflection angle is the angle between the y-axis of the captured image and the first direction. The blade orientation angle is calculated based on the first deflection angle β and the second deflection angle α. Specifically, the blade orientation angle is the sum of the first deflection angle, the second deflection angle, and the angle between the blade and the cabin, wherein the angle between the blade and the cabin may be the angle between the first direction and the deflection direction of the cabin.

[0051] Specifically, the blade orientation information is as follows: Figure 5 As shown, the blade orientation information includes the blade orientation angle, which is the angle between the true north (N) direction of the geodetic coordinates and the deflection direction of the cabin. A first deflection angle β and a second deflection angle γ are set, wherein the second deflection angle γ is the angle between the y-axis of the captured image and the deflection direction of the cabin, and the blade orientation angle is the sum of the first deflection angle β and the second deflection angle γ.

[0052] exist Figure 4 and Figure 5 In the embodiment, the blade orientation angle is a specific achievable method. Those skilled in the art can obtain the orientation of the blade in the actual physical space by obtaining information such as the target position of the wind turbine blades and cabin components and the geodetic coordinate system. The above embodiment is only an achievable path and is not the only limitation.

[0053] Optionally, according to the blade orientation information, determining a local waypoint of the image taken by the drone includes: According to the preset moving distance and blade orientation information, the local waypoints of the image taken by the drone are determined. In the present application, the drone is controlled to rotate from the waypoint of the channel route according to the blade orientation information, and fly a preset moving distance, that is, a preset horizontal distance from the wind turbine, to reach the drone's photo taking position, and then take photos of the blades.

[0054] Optionally, according to the preset moving distance and blade orientation information, determining a local waypoint of the image taken by the drone includes: According to the preset shooting requirements, the photographing waypoint information corresponding to the local waypoint of the UAV is determined, wherein the preset shooting requirements at least include one or more of shooting the front side of the blade or shooting the back side of the blade, and the blade shooting area.

[0055] The drone can generate corresponding photo waypoint information according to different shooting requirements, such as shooting location and shooting area. For example, the drone flies to the stop position of the photo waypoint and shoots a front view containing the blade.

[0056] In the present application, after determining the photographing location information, the photographing waypoint information can be determined according to the preset photographing requirements, such as the need to photograph the front side of the blade or the back side of the blade, or the location where the photographing is required. Optionally, the equipment to be inspected is inspected according to the inspection route, including: According to the current channel waypoint of the channel route, stay in the preset area above the equipment to be inspected; Inspection route: Take photos of the equipment to be inspected according to the inspection route; After taking a photo of the device to be inspected at the current channel waypoint, move to the next channel waypoint on the channel route according to the channel route to take a photo of the device to be inspected.

[0057] Take photos of the equipment to be inspected according to the inspection route, including: According to the inspection route, the drone is controlled to move to a first designated position, where the first designated position is used to photograph the tip of the blade; The drone is controlled to move downward on a vertical line of the first designated position to a second designated position, where the second designated position is used to photograph the blades.

[0058] like Figure 3 As shown, according to the orientation of the blades of the wind turbine, the stop position of the drone, that is, the photo waypoint, is determined. Specifically, when the orientation of the blades of the wind turbine is determined, the flight distance and deflection angle of the drone are automatically generated. The drone flies according to the flight distance and deflection angle and arrives at the first designated position (the first designated position is a waypoint). Figure 3 The first designated position is used to shoot the blade tip first, and then the drone is gradually controlled to move downward on the vertical line of the first designated position to the second designated position (the second designated position is a waypoint), and the second designated position is used to shoot the blade).

[0059] In this application, the drone first flies to the channel waypoint, and then flies to the waypoint in the inspection route based on the blade orientation information to take pictures of the equipment to be inspected. After the photo is taken, the drone flies to the waypoint of the next channel route and conducts inspection in the above manner to improve inspection efficiency.

[0060] Optionally, the method further comprises: The acquired photos of the equipment to be inspected are processed, and according to the processed results, fault diagnosis is performed on the equipment to be inspected.

[0061] The drone processes the photos of the equipment to be inspected. For example, it can use AI recognition algorithms to identify faults in the pictures and determine whether there are any abnormalities on the blades.

[0062] In this application, the blade orientation information is obtained to determine the inspection route of the drone. The channel route and the inspection route are combined to take photos of the inspection equipment. The obtained photos are subsequently processed to improve the accuracy of image processing and the accuracy of fault diagnosis.

[0063] like Figure 6 As shown, the embodiment of the present application provides a wind turbine inspection method based on a drone, comprising: Step 1: The drone starts inspection; Step 2: The backend server selects the inspection range; Step 3: Obtain all wind turbine locations and wind turbine attributes from the backend server (backend system); There is a backend system on the backend server, which obtains information from user records or outdoor points. Most of the information is records provided by users, including the actual location (latitude and longitude), height, blade length and other information of the wind turbine.

[0064] The background system obtains the designated area where the drone is flying based on the actual position of the wind turbine and the highest height of the wind turbine. The flight altitude of the designated area is greater than the highest height of the wind turbine. The vertical line of the given position of the drone corresponds to the channel waypoint. After receiving the drone request, the background system sends the channel route to the drone.

[0065] Step 4: The backend server generates a channel route; Step 5: The backend server sends the channel route to the drone; Step 6: The drone executes the route; The drone flies toward the wind turbine according to its actual location and designated area, and stays in the stop area (fixed point).

[0066] Step 7: The drone reaches waypoint i=0; Step 8: The drone determines whether the waypoint is less than the total waypoints; Step 9. If the waypoint is smaller than the total waypoint, adjust the gimbal pitch angle to 90° downward; Step 10: The drone takes an orthographic photo; Step 11: The drone identifies the direction of the wind turbine blades in the photo; Step 12: The drone generates a local inspection waypoint, i.e., a photo taking waypoint, according to the direction of the blade; Step 13: The drone flies to the front of the wind turbine to take inspection photos; Step 14: The drone flies behind the wind turbine to take inspection photos; Step 15: The drone arrives at the next wind turbine waypoint i=i+1; Step 16: If the waypoint is equal to the total waypoint, the drone inspection result.

[0067] It should be noted that each implementable method in this embodiment may be implemented separately, or may be implemented in combination in any combination without conflict, and this application is not limited thereto.

[0068] Another embodiment of the present application provides a drone-based wind turbine inspection device, which is used to execute the drone-based wind turbine inspection method provided in the above embodiment.

[0069] like Figure 7 The figure is a schematic diagram of the structure of a wind turbine inspection device based on a drone provided in an embodiment of the present application. The wind turbine inspection device based on a drone comprises at least: an acquisition module 601, an identification module 602, a determination module 603, a generation module 604 and an inspection module 605, wherein: The acquisition module 601 is used to acquire the captured image of the device to be inspected; The identification module 602 is used to determine the blade orientation information of the device to be inspected based on the captured image of the device to be inspected; The determination module 603 is used to determine the local waypoint of the image taken by the drone according to the blade orientation information; The generation module 604 is used to construct an inspection route based on local waypoints; The inspection module 605 is used to inspect the equipment to be inspected according to the inspection route.

[0070] Regarding the device in this embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0071] This application obtains the blade orientation information and then determines the inspection route information of the drone. It combines the channel route information and the inspection route information to take pictures of the inspection equipment, avoids manual adjustment of the waypoint position, and improves the inspection efficiency of wind turbines.

[0072] Another embodiment of the present application further supplements the description of the drone-based wind turbine inspection device provided in the above embodiment.

[0073] Optionally, generate a module for: Determine the drone's photo taking position information based on the blade orientation information; According to the photo taking position information of the drone, determine the local waypoints of the image taken by the drone; The inspection route is determined based on the local waypoints of the blades photographed by the drone.

[0074] In the present application, images of the equipment to be inspected are obtained at waypoints in the channel route, and then the blade orientation information is identified. Based on the blade orientation information, the photo waypoint information of the UAV is determined, and the UAV is controlled to take photos at the photo waypoints. In this way, the photo position of the UAV is automatically adjusted until a photo that meets the requirements can be taken from the front or back.

[0075] Optionally, a module is determined to: Using the wind turbine component recognition model, the blades and nacelle in the captured image are identified; Determine the deflection direction of the nacelle and the first direction of the blade according to the relative positions of the blade and the nacelle in the captured image; The blade orientation information of the equipment to be inspected is determined according to the deflection direction or the first direction of the nacelle.

[0076] Optionally, a module is determined to: According to the preset moving distance and blade orientation information, the local waypoints of the image taken by the drone are determined. In the present application, the drone is controlled to rotate from the waypoint of the channel route according to the blade orientation information, and fly a preset moving distance to reach the drone's photo taking position, and then take photos of the blades.

[0077] Optionally, a module is determined to: According to the preset shooting requirements, the photographing waypoint information corresponding to the local waypoint of the UAV is determined, wherein the preset shooting requirements at least include one or more of shooting the front side of the blade or shooting the back side of the blade, and the blade shooting area.

[0078] In the present application, after determining the photographing location information, the photographing waypoint information can be determined according to the preset photographing requirements, such as the need to photograph the front side of the blade or the back side of the blade, or the location where the photographing is required. Optionally, the inspection module is used to: According to the current channel waypoint of the channel route, stay in the preset area above the equipment to be inspected; Take photos of the equipment to be inspected according to the inspection route; After taking a photo of the device to be inspected at the current channel waypoint, move to the next channel waypoint on the channel route according to the channel route information to take a photo of the device to be inspected. In this application, the drone first flies to the channel waypoint, and then flies to the waypoint in the inspection route information based on the blade orientation information to take pictures of the inspection equipment. After the photo is taken, the drone flies to the waypoint of the next channel route and conducts inspection in the above manner to improve inspection efficiency.

[0079] Optionally, the inspection module is also used to: The acquired photos of the equipment to be inspected are processed, and according to the processed results, fault diagnosis is performed on the equipment to be inspected.

[0080] In this application, the blade orientation information is obtained to determine the inspection route information of the drone. The channel route information and the inspection route information are combined to take photos of the inspection equipment. The obtained photos are subsequently processed to improve the accuracy of image processing and the accuracy of fault diagnosis.

[0081] Optionally, the inspection module is used to: According to the inspection route, the drone is controlled to move to a first designated position, where the first designated position is used to photograph the tip of the blade; The drone is controlled to move downward on a vertical line of the first designated position to a second designated position, where the second designated position is used to photograph the blades.

[0082] Regarding the device in this embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0083] It should be noted that each implementable method in this embodiment may be implemented separately, or may be implemented in combination in any combination without conflict, and this application is not limited thereto.

[0084] The above are only embodiments of the present application and are not intended to limit the scope of protection of the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the scope of protection of the present application. It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings.

[0085] The above are only specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0086] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

Claims

1. A wind turbine inspection method based on drone, characterized in that: The method comprises: Obtaining images of the equipment to be inspected; Determining blade orientation information of the device to be inspected based on the captured image of the device to be inspected; Determining a local waypoint of the image taken by the drone according to the blade orientation information; Based on the local waypoints, construct an inspection route; According to the inspection route, the equipment to be inspected is inspected.

2. The wind turbine inspection method based on a drone according to claim 1 is characterized in that: The step of constructing an inspection route based on the local waypoints includes: Determining the photographing position information of the drone according to the blade orientation information; Determine the local waypoint of the image taken by the drone according to the photographing position information of the drone; The inspection route is determined according to the local waypoints of the blade photographed by the drone.

3. The wind turbine inspection method based on drone according to claim 1 is characterized in that: The step of determining blade orientation information of the device to be inspected based on the captured image of the device to be inspected includes: Using a wind turbine component recognition model to identify blades and a nacelle in the captured image; Determining a deflection direction of the nacelle and a first direction of the blade according to relative positions of the blade and the nacelle in the captured image; The blade orientation information of the equipment to be inspected is determined according to the deflection direction of the nacelle or the first direction.

4. The wind turbine inspection method based on drone according to claim 2 is characterized in that: Determining the local waypoint of the image taken by the drone according to the blade orientation information includes: According to the preset moving distance and the blade orientation information, the local waypoint of the image taken by the drone is determined.

5. The wind turbine inspection method based on drone according to claim 4 is characterized in that: The determining of the local waypoint of the image taken by the drone according to the preset moving distance and the blade orientation information includes: According to the preset shooting requirements, the photographing waypoint information corresponding to the local waypoint of the UAV is determined, wherein the preset shooting requirements at least include one or more of shooting the front side of the blade or shooting the back side of the blade, and the blade shooting area.

6. The wind turbine inspection method based on drone according to claim 5 is characterized in that: The inspecting the equipment to be inspected according to the inspection route includes: According to the current channel waypoint of the channel route, stay in the preset area above the equipment to be inspected; Taking photos of the equipment to be inspected according to the inspection route; After taking a photo of the device to be inspected at the current channel waypoint, move to the next channel waypoint of the channel route according to the channel route and take a photo of the device to be inspected.

7. The wind turbine inspection method based on a drone according to claim 6 is characterized in that: The method further comprises: The acquired photos of the equipment to be inspected are processed, and according to the processed results, fault diagnosis is performed on the equipment to be inspected.

8. The wind turbine inspection method based on drone according to claim 6 is characterized in that: The taking photos of the equipment to be inspected according to the inspection route includes: According to the inspection route, controlling the drone to move to a first designated position, wherein the first designated position is used to photograph the tip of the blade; The drone is controlled to move downward on a vertical line of the first designated position to a second designated position, where the second designated position is used to photograph the blades.

9. A wind turbine inspection device based on a drone, characterized in that: The device comprises: An acquisition module is used to acquire images of the equipment to be inspected; An identification module, used to determine blade orientation information of the device to be inspected based on the captured image of the device to be inspected; A determination module, used to determine a local waypoint of an image taken by a drone according to the blade orientation information; A generation module, used for constructing an inspection route based on the local waypoints; The inspection module is used to inspect the equipment to be inspected according to the inspection route.

10. A drone, characterized in that: The invention comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the wind turbine inspection method based on a drone as described in any one of claims 1 to 8 can be implemented.

Images