Rotating blade panoramic image acquisition method and system and unmanned equipment

Abstract

The invention provides a rotating blade panoramic image acquisition method and system and unmanned equipment, and is applied to the technical field of unmanned equipment automatic acquisition, and the method comprises the steps: collecting a plurality of high-definition images corresponding to a target segment of a rotating blade through a camera at each preset segment point; wherein the segmentation point is a camera position preset along the length direction of the blade in a plane parallel to the rotating blade; the target section is a blade section of the rotating blade appearing in the capture area corresponding to the segmentation point; marking the plurality of high-definition images based on a timestamp and a segmentation counter, and classifying the plurality of high-definition images to obtain an image data set corresponding to each leaf; according to the image data set corresponding to the blade, the whole-section image data corresponding to the blade is obtained through the splicing algorithm, so that the blade inspection efficiency and accuracy are improved, and the downtime and the maintenance cost are reduced.

Description

Technical Field

[0001] The present application relates to the technical field of automated data collection by unmanned equipment, and in particular to a leaf photographing method, system and unmanned equipment. Background Art

[0002] Although existing unmanned equipment can take pictures of dynamic blades, the images are often blurred, incompletely covered, or the unmanned equipment is damaged by collision. For example, when existing unmanned equipment is used to shoot the yaw changes of a wind turbine that is not shut down, it will also affect the relative position and motion state of the blades, thereby affecting the timing of shooting and the quality of the image. In addition, the high-speed rotation of the blade tip (linear speed of up to 100 meters / second) makes it difficult to capture clear images or incomplete shots, which increases the risk of equipment collision.

[0003] Based on this, a new method for acquiring panoramic images of rotating blades is needed. Summary of the invention

[0004] In view of this, the embodiments of this specification provide a method, system and unmanned equipment for collecting panoramic images of rotating blades. Through segmented shooting and combined with stitching algorithm processing, a complete three-blade stitching visual image is generated, thereby realizing all-round and high-precision blade status monitoring.

[0005] The embodiments of this specification provide the following technical solutions:

[0006] The embodiment of this specification provides a method for collecting panoramic images of rotating blades, including:

[0007] At each preset segmentation point, a camera is used to collect a number of high-definition images corresponding to the target segment of the rotating blade; wherein the segmentation point is a preset camera position along the length direction of the blade in a plane parallel to the rotating blade; the target segment is a blade segment of the rotating blade that appears in the capture area corresponding to the segmentation point;

[0008] Marking the plurality of high-definition images based on a timestamp and a segment counter, and classifying the plurality of high-definition images to obtain an image data set corresponding to each leaf;

[0009] According to the image data set corresponding to the leaf, the full-segment image data corresponding to the leaf is obtained through a stitching algorithm.

[0010] The embodiment of this specification also provides a rotating blade panoramic image acquisition system, the rotating blade panoramic image acquisition system comprising:

[0011] An image capture module is used to collect a number of high-definition images corresponding to a target segment of a rotating blade through a camera at each preset segmentation point; wherein a segmentation point is a preset camera position along the length direction of the blade in a plane parallel to the rotating blade; and a target segment is a blade segment of the rotating blade that appears in a capture area corresponding to the segmentation point;

[0012] An image processing module marks the plurality of high-definition images based on a timestamp and a segment counter, and classifies the plurality of high-definition images to obtain an image data set corresponding to each leaf;

[0013] The image stitching module is used to obtain the full-segment image data corresponding to the leaf through a stitching algorithm based on the image data set corresponding to the leaf.

[0014] The embodiment of this specification also provides an unmanned device, the unmanned device comprising: a flight module, a shooting module, and a prediction module;

[0015] The flight module is used to fly parallel to the blade rotation plane, execute forward and backward paths respectively, and stop at each preset segment point;

[0016] The forward path includes the leading edge and the trailing edge of the windward side of the blade, and the backward path includes the leading edge and the trailing edge of the leeward side of the blade;

[0017] The shooting module uses a laser radar to detect whether the blade enters a preset capture area; if so, the camera is triggered to shoot and obtain a high-definition image;

[0018] The prediction module is used to predict whether the blade enters the photo-taking area according to the angular velocity calculation, and if so, trigger the camera to take pictures to obtain a high-definition image.

[0019] Compared with the prior art, the at least one technical solution adopted in the embodiments of this specification can achieve the following beneficial effects:

[0020] By capturing high-definition images at preset segmentation points, accurately marking and classifying them, and then stitching the images to generate a complete panoramic image of the blade, the efficiency and accuracy of blade inspection is improved, and downtime and maintenance costs are reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0022] Figure 1It is a schematic diagram of the flight path of the unmanned equipment during blade collection in this application (vertical perspective looking down from above the blade);

[0023] Figure 2 It is a schematic diagram of the dynamic flight path and real-time adjustment of the unmanned equipment during blade collection in this application;

[0024] Figure 3 It is a schematic diagram of the blade capture trigger area in this application. DETAILED DESCRIPTION

[0025] The embodiments of the present application are described in detail below with reference to the accompanying drawings.

[0026] The following describes the implementation methods of the present application through specific examples, and those skilled in the art can easily understand other advantages and effects of the present application from the contents disclosed in this specification. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. The present application can also be implemented or applied through other different specific implementation methods, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present application. It should be noted that, in the absence of conflict, the following embodiments and the features in the embodiments can be combined with each other. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work belong to the scope of protection of the present application.

[0027] It should be noted that various aspects of the embodiments within the scope of the appended claims are described below. It should be apparent that the aspects described herein can be embodied in a wide variety of forms, and any specific structure and / or function described herein is merely illustrative. Based on the present application, it should be understood by those skilled in the art that an aspect described herein can be implemented independently of any other aspect, and two or more of these aspects can be combined in various ways. For example, any number and aspect described herein can be used to implement the device and / or practice the method. In addition, other structures and / or functionalities other than one or more of the aspects described herein can be used to implement this device and / or practice this method.

[0028] It should also be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present application. The drawings only show components related to the present application rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed arbitrarily, and the component layout may also be more complicated.

[0029] Additionally, in the following description, specific details are provided to facilitate a thorough understanding of the examples. However, it will be understood by those skilled in the art that the examples can be practiced without these specific details.

[0030] Existing unmanned equipment has shortcomings in non-stop inspections, such as maintaining a safe distance from rotating blades in dynamic environments, adapting to changes in wind turbine yaw, and poor performance in high-speed blade tip imaging, which can easily cause image blur, incomplete coverage or equipment collision problems.

[0031] In view of this, the inventors discovered through research and improvement exploration that when collecting images of wind turbine blades, due to the significant speed difference between the blade tip and the blade root, especially the linear speed of the blade tip is often as high as 100 meters per second, this makes it difficult for unmanned equipment to accurately capture clear images in actual operation, resulting in problems such as blurred imaging and incomplete coverage, which in turn affects the efficiency and effectiveness of blade inspection.

[0032] Based on this, the embodiment of this specification proposes a method for capturing panoramic images of rotating blades: using segmented shooting combined with a stitching processing algorithm to generate a complete blade stitching visual image, thereby achieving all-round, high-precision blade acquisition images, such as Figure 1 As shown, the unmanned equipment captures high-definition images at multiple preset segmentation points along the length of the wind turbine blade, and marks and classifies these images through timestamps and segment counters to construct a blade data set. The high-definition images in the data set are then processed using a stitching algorithm to synthesize complete panoramic image data of the blade.

[0033] The technical solutions provided by various embodiments of the present application are described below in conjunction with the accompanying drawings.

[0034] like Figure 1 As shown, the embodiment of this specification provides a method for collecting a panoramic image of a rotating blade, comprising:

[0035] At each preset segmentation point, a camera is used to collect a number of high-definition images corresponding to the target segment of the rotating blade; wherein the segmentation point is a preset camera position along the length direction of the blade in a plane parallel to the rotating blade; the target segment is a blade segment of the rotating blade that appears in the capture area corresponding to the segmentation point;

[0036] Marking the plurality of high-definition images based on a timestamp and a segment counter, and classifying the plurality of high-definition images to obtain an image data set corresponding to each leaf;

[0037] According to the image data set corresponding to the leaf, the full-segment image data corresponding to the leaf is obtained through a stitching algorithm.

[0038] Specifically, in order to ensure that every part of the blade can be captured, it is necessary to preset multiple segmentation points along the length direction of the blade.

[0039] The unmanned device flies parallel to the blade rotation plane. At each preset segmentation point, the camera on the unmanned device is used to capture high-definition images to ensure complete and clear coverage. The captured high-definition images are marked based on timestamps and segment counters.

[0040] The timestamp records the exact time of image capture, and the segment counter indicates which segment of the leaf the image belongs to, thus facilitating subsequent image processing and analysis, ensuring that each image is correctly classified into the corresponding leaf part.

[0041] For example, wind turbine blades are scanned in space or path segments, and each flight path and stop point (shooting a certain section of the blade) has a corresponding segment ID. When the unmanned device hovers and shoots at a specific segment position, the corresponding segment ID is assigned to the batch of images.

[0042] Then, the labeled high-definition images are classified to form a leaf data set. Finally, the high-definition images in the leaf data set are processed by a stitching algorithm, and these scattered images are stitched into a complete leaf panoramic image, thereby providing overall visual information of the leaf.

[0043] In one embodiment, the rotating blade panoramic image acquisition method further includes: using a laser radar to detect whether the blade enters a capture area; if so, triggering a camera to shoot to obtain a high-definition image.

[0044] Specifically, when the laser radar detects that the blade enters the field of view, it triggers the camera to shoot. Each time the shooting is triggered, the system records the current precise timestamp (t), which can come from a high-precision clock.

[0045] In one embodiment, the rotating blade panoramic image acquisition method further includes: at the high-speed blade tip, using angular velocity calculation to predict whether the blade enters the capture area, and if so, triggering the camera to shoot to obtain a high-definition image.

[0046] Specifically, in the high-speed blade tip area, the angular velocity calculation is used to predict the blade position as a backup trigger signal to compensate for possible signal loss or noise effects of the lidar.

[0047] When the blade rotates at a high speed, the linear velocity and frequency of the blade tip are high, and the real-time signal detection of the lidar may be temporarily lost or interfered by noise. To this end, the system calculates and utilizes the blade angular velocity (i.e. the angular frequency of the blade rotation) in real time to predict when and where the blade enters the camera's field of view (FOV). The specific steps are as follows:

[0048] Get the initial parameters:

[0049] At the beginning of the detection, the system obtains the time point data of single or multiple blade appearances through lidar or other sensors to estimate the average rotational angular velocity (ω) of the current blade, which can be expressed in radians / second or revolutions / second.

[0050] Establishing a time base:

[0051] Set a time reference point t0, for example, the time when a blade (named Blade A) passes through the laser radar FOV is recorded as t0. At this time, the system already knows the appearance time of Blade A and the corresponding angle position θ0 (which can be set as the reference angle zero point).

[0052] Predict next occurrence:

[0053] Since the blades rotate at a relatively stable speed, assuming that the rotor has N blades, based on the measured average angular velocity ω, the time when the blade enters the camera FOV again can be predicted. For example, if the last position of the blade appeared at time t0 and the corresponding angle is θ0, then the time when the blade appears in the field of view next time is t ′ Available from:

[0054]

[0055] Among them, Δθ is the angle that the blade needs to rotate to enter the FOV again (usually it can be determined based on the known camera FOV orientation and blade distribution position. For example, a three-blade fan that appears every 120° can simply be set to Δθ=360° in equal parts, and the time interval between adjacent blades can be calculated by 360° / N).

[0056] Real-time updates and forecast corrections:

[0057] In subsequent inspections, the LiDAR may detect blade signals again. The system can continuously correct the angular velocity and prediction model parameters by comparing the deviation between the actual detection time and the predicted time, thereby maintaining a high-precision prediction when the LiDAR signal is unstable. If the LiDAR does not detect the upcoming blade at a certain moment, the system triggers the camera system to shoot based on the latest angular velocity, the last valid detection data, and the distribution characteristics of the rotor blades.

[0058] Trigger backup shooting signal:

[0059] When the prediction time t ′ When approaching, regardless of whether the lidar successfully detects the blade at the moment, the system will actively trigger the camera to shoot (or prepare the camera focus and exposure time in advance) to ensure that a valid image can be obtained even if the lidar signal is wrong.

[0060] Through the above steps, the average angular velocity of the blade is used to predict the blade's appearance position and time, which can be used as a backup trigger signal in the high-speed blade tip area to improve the continuity and integrity of image capture.

[0061] In one embodiment, the rotating blade panoramic image acquisition method further includes:

[0062] Different trigger camera shooting conditions are preset according to different parts of the leaf, including:

[0063] For high-speed blade tips, the camera is triggered in advance to take pictures to cope with signal processing and transmission delays;

[0064] And / or, for the blade root, wait before triggering the camera to shoot, so as to adapt to the difference in blade movement speed.

[0065] Specifically, the linear speed of the tip part of the blade is very high, which can reach more than 100 meters per second. Due to the delay in signal processing and transmission, if the camera is triggered to shoot when the blade enters the field of view according to the conventional method, the actual captured image may become blurred due to the rapid movement of the blade. Therefore, the system needs to predict the position of the blade and trigger the camera to shoot in advance before the blade reaches the optimal shooting position, so as to compensate for the delay in signal processing and transmission and ensure that a clear image can be obtained when the blade reaches the ideal position.

[0066] As opposed to the tip of the leaf, the root of the leaf has a lower linear speed. Therefore, a waiting strategy can be adopted to trigger the camera to shoot after a slight delay after the leaf reaches the optimal shooting position. This helps ensure that the camera shoots when the leaf passes steadily and reduces image blur caused by leaf movement. At the same time, this time can also be used to make more precise focus and exposure settings to improve image quality.

[0067] This differentiated triggering strategy can improve the accuracy and clarity of image acquisition, thereby improving the efficiency and accuracy of blade non-stop inspection.

[0068] In one embodiment, if Figure 3 As shown, before capturing a high-definition image of each blade, capture areas of different sizes are preset according to the linear velocity differences of different parts of the blade;

[0069] Among them, the capture area at the tip of the blade is larger than that at the root of the blade.

[0070] Specifically, the linear speed of the blade tip is high. In order to ensure that the image of the blade tip can be captured, a larger capture area is set to increase the "window period" when the camera is triggered to shoot. Even if the camera trigger is slightly delayed, it can ensure that the blade tip is captured within the capture area.

[0071] The linear speed at the blade root is low, and setting a relatively small capture area can reduce unnecessary image data, thereby improving the efficiency of image processing.

[0072] In one embodiment, the size of the capture area can be dynamically adjusted based on the actual blade speed and the performance of the unmanned equipment camera.

[0073] Specifically, the optimal capture area size can be calculated according to the speed of the blade and the response time of the camera.

[0074] In one embodiment, the rotating blade panoramic image acquisition method further includes:

[0075] Use LiDAR to measure the distance between unmanned equipment and blades in real time and generate a depth map;

[0076] According to the depth map, dynamically adjust the focal length of the camera and the flight path of the unmanned equipment to adapt to the change of the yaw angle of the wind turbine;

[0077] Wherein, the flight path includes: flying parallel to the blade rotation plane, executing forward and backward paths respectively; wherein, the forward path includes the leading edge and trailing edge of the windward side of the blade, and the backward path includes the leading edge and trailing edge of the leeward side of the blade.

[0078] Specifically, Figure 2 As shown in the figure, during the flight, the unmanned device will plan the path according to the dynamic path of the wind turbine blades. At the same time, the lidar will measure the distance between the device and the blades in real time and generate a depth map. Based on this information, the focal length of the camera will be automatically adjusted to optimize the clarity of the image. In this way, no matter how the distance between the camera and the blades changes, it can ensure that the camera is vertically aligned with the blades to obtain high-quality and clear images.

[0079] To ensure flight safety, the drone will dynamically adjust its flight path based on the depth map to ensure it can safely fly around the blades and maintain the optimal shooting angle and distance even if the yaw angle of the wind turbine changes.

[0080] The flight path planning includes four flights: two forward and two backward. The forward path flies along the windward side of the blade, covering the leading and trailing edges of the blade; the backward path flies along the leeward side of the blade, also covering the leading and trailing edges. The flight distance is controlled within an appropriate range, neither too close to avoid collision nor too far to affect the shooting effect, ensuring full coverage of the blade. No matter how the blade rotates, the unmanned device can capture images of the blade from different angles.

[0081] This application uses a drone to fly parallel to the rotation plane of the wind turbine blades, uses lidar to measure and generate depth maps in real time, and dynamically adjusts the camera focal length and drone flight path to adapt to the challenges of detection and image data collection that the wind turbine will track in real time according to wind direction changes during operation to maximize power generation, thereby achieving a comprehensive inspection of the windward and leeward sides of the blades without stopping the machine, ensuring the efficient and safe operation of the wind turbine.

[0082] In one embodiment, different trigger areas are set and specific lead and delay amounts are configured for each area to adapt to different environmental conditions. In addition, the system integrates two trigger mechanisms: one is an immediate response when the radar signal is detected in the trigger area, and the other is a predictive trigger based on the angular velocity of the blade. The two mechanisms work together to ensure that the position of the blade can be accurately captured in different situations, achieving efficient and accurate shooting effects.

[0083] Based on the same inventive concept, the present application also provides a rotating blade panoramic image acquisition system, the rotating blade panoramic image acquisition system comprising:

[0084] An image capture module is used to collect a number of high-definition images corresponding to a target segment of a rotating blade through a camera at each preset segmentation point; wherein a segmentation point is a preset camera position along the length direction of the blade in a plane parallel to the rotating blade; and a target segment is a blade segment of the rotating blade that appears in a capture area corresponding to the segmentation point;

[0085] An image processing module marks the plurality of high-definition images based on a timestamp and a segment counter, and classifies the plurality of high-definition images to obtain an image data set corresponding to each leaf;

[0086] The image stitching module is used to obtain the full-segment image data corresponding to the leaf through a stitching algorithm based on the image data set corresponding to the leaf.

[0087] Preferably, the image capture module further includes:

[0088] The laser radar is used to detect whether the blade enters the capture area; if so, the camera is triggered to shoot and obtain a high-definition image.

[0089] Preferably, the image capture module further includes:

[0090] At the high-speed blade tip, angular velocity calculation is used to predict whether the blade enters the capture area. If so, the camera is triggered to capture and obtain a high-definition image.

[0091] Preferably, the rotating blade panoramic image acquisition system further comprises:

[0092] Adjust the module to use LiDAR to measure the distance between the unmanned equipment and the blades in real time and generate a depth map;

[0093] According to the depth map, the focal length of the camera and the flight path of the unmanned equipment are dynamically adjusted to adapt to the change in the yaw angle of the wind turbine.

[0094] Based on the same inventive concept, the present application also provides an unmanned device, the unmanned device comprising: a flight module, a shooting module, and a prediction module;

[0095] The flight module is used to fly parallel to the blade rotation plane, execute forward and backward paths respectively, and stop at each preset segment point;

[0096] The forward path includes the leading edge and the trailing edge of the windward side of the blade, and the backward path includes the leading edge and the trailing edge of the leeward side of the blade;

[0097] The shooting module uses a laser radar to detect whether the blade enters a preset capture area; if so, the camera is triggered to shoot and obtain a high-definition image;

[0098] The prediction module is used to predict whether the blade enters the photo-taking area according to the angular velocity calculation, and if so, trigger the camera to take pictures to obtain a high-definition image.

[0099] This application can be used for wind energy operation and maintenance, such as regular detection of blade lightning strikes, corrosion, wear, cracks and other structural abnormalities; it can also be used for industrial maintenance, such as automated detection of moving parts of rotating machinery; it can also be used in aerospace and maritime, such as monitoring the operating status of helicopter rotor blades or ship propellers.

[0100] In this specification, the same or similar parts between the various embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the embodiments described later, the description is relatively simple, and the relevant parts can be referred to the partial description of the previous embodiments.

[0101] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A method for collecting panoramic images of rotating blades, characterized in that: include: At each preset segmentation point, a camera is used to collect a number of high-definition images corresponding to the target segment of the rotating blade; wherein the segmentation point is a preset camera position along the length direction of the blade in a plane parallel to the rotating blade; the target segment is a blade segment of the rotating blade that appears in the capture area corresponding to the segmentation point; Marking the plurality of high-definition images based on a timestamp and a segment counter, and classifying the plurality of high-definition images to obtain an image data set corresponding to each leaf; According to the image data set corresponding to the leaf, the full-segment image data corresponding to the leaf is obtained through a stitching algorithm.

2. The method for collecting panoramic images of rotating blades according to claim 1, characterized in that: The rotating blade panoramic image acquisition method further comprises: The laser radar is used to detect whether the blade enters the capture area; if so, the camera is triggered to shoot and obtain a high-definition image.

3. The method for collecting panoramic images of rotating blades according to claim 2, characterized in that: The rotating blade panoramic image acquisition method further comprises: At the high-speed blade tip, angular velocity calculation is used to predict whether the blade enters the capture area. If so, the camera is triggered to capture and obtain a high-definition image.

4. The method for collecting panoramic images of rotating blades according to claim 3, characterized in that: The rotating blade panoramic image acquisition method further comprises: Different trigger camera shooting conditions are preset according to different parts of the leaf, including: For high-speed blade tips, the camera is triggered in advance to take pictures to cope with signal processing and transmission delays; And / or, for the blade root, wait before triggering the camera to shoot, so as to adapt to the difference in blade movement speed.

5. The method for collecting panoramic images of rotating blades according to claim 1, characterized in that: Before capturing the high-definition image of each blade, different sizes of capture areas are preset according to the linear speed differences of different parts of the blade; Among them, the capture area at the tip of the blade is larger than that at the root of the blade.

6. The method for acquiring a panoramic image of a rotating blade according to claim 1, characterized in that: The rotating blade panoramic image acquisition method further comprises: Use LiDAR to measure the distance between unmanned equipment and blades in real time and generate a depth map; According to the depth map, dynamically adjust the focal length of the camera and the flight path of the unmanned equipment to adapt to the change of the yaw angle of the wind turbine; Wherein, the flight path includes: flying parallel to the blade rotation plane, executing forward and backward paths respectively; wherein, the forward path includes the leading edge and trailing edge of the windward side of the blade, and the backward path includes the leading edge and trailing edge of the leeward side of the blade.

7. A rotating blade panoramic image acquisition system, characterized in that: The rotating blade panoramic image acquisition system comprises: An image capture module is used to collect a number of high-definition images corresponding to a target segment of a rotating blade through a camera at each preset segmentation point; wherein a segmentation point is a preset camera position along the length direction of the blade in a plane parallel to the rotating blade; and a target segment is a blade segment of the rotating blade that appears in a capture area corresponding to the segmentation point; An image processing module marks the plurality of high-definition images based on a timestamp and a segment counter, and classifies the plurality of high-definition images to obtain an image data set corresponding to each leaf; The image stitching module is used to obtain the full-segment image data corresponding to the leaf through a stitching algorithm based on the image data set corresponding to the leaf.

8. The rotating blade panoramic image acquisition system according to claim 7, characterized in that: The image capture module also includes: The laser radar is used to detect whether the blade enters the capture area; if so, the camera is triggered to shoot and obtain a high-definition image. And / or, at the high-speed blade tip, the angular velocity calculation is used to predict whether the blade enters the capture area. If so, the camera is triggered to capture and obtain a high-definition image.

9. The rotating blade panoramic image acquisition system according to claim 7, characterized in that: The rotating blade panoramic image acquisition system also includes: Adjust the module to use LiDAR to measure the distance between the unmanned equipment and the blades in real time and generate a depth map; According to the depth map, the focal length of the camera and the flight path of the unmanned equipment are dynamically adjusted to adapt to the change in the yaw angle of the wind turbine.

10. An unmanned device, characterized in that: The unmanned equipment includes: a flight module, a shooting module, and a prediction module; The flight module is used to fly parallel to the blade rotation plane, execute forward and backward paths respectively, and stop at each preset segment point; The forward path includes the leading edge and the trailing edge of the windward side of the blade, and the backward path includes the leading edge and the trailing edge of the leeward side of the blade; The shooting module uses a laser radar to detect whether the blade enters a preset capture area; if so, the camera is triggered to shoot and obtain a high-definition image; The prediction module is used to predict whether the blade enters the photo-taking area according to the angular velocity calculation, and if so, trigger the camera to take pictures to obtain a high-definition image.

Images