Insulator chain detection method and device, electronic equipment and storage medium

Abstract

The invention belongs to the technical field of insulator chain detection, and discloses an insulator chain detection method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining the position information of a target insulator chain, and obtaining the position information of the target insulator chain according to the position information; controlling the visual detection flying robot carrying the detection instrument through the mechanical arm to fly to a hovering position above the target insulator string, identifying the axis of the target insulator string so as to control the visual detection flying robot to rotate, and enabling the flying plane of the visual detection flying robot to be parallel to the axis, controlling the visual detection flying robot to drive a mechanical arm so as to place a detection instrument on the target insulator string, and enabling the detection instrument to complete the detection operation of the target insulator string; through the method, the detection efficiency of the insulator string is improved.

Description

Technical Field

[0001] This application relates to the technical field of insulator string testing, and more specifically, to an insulator string testing method, apparatus, electronic device, and storage medium. Background Technology

[0002] Insulators are indispensable insulating components in power transmission lines, and their performance directly affects the safe and stable operation of the power system. However, in actual operation, insulators are affected by various factors such as air pollution and environmental erosion, leading to a gradual decline in their insulation performance and creating serious safety hazards. Therefore, regular insulation performance testing of insulators is crucial for timely detection and elimination of these hazards.

[0003] In recent years, with the rapid development of intelligent robot technology, automated insulator testing instruments have emerged, improving testing efficiency and safety to some extent. However, current automated insulator testing instruments still face many challenges in practical applications. Traditional insulator testing methods mainly rely on manual inspections, requiring power line inspectors to manually inspect each insulator one by one in high-altitude working environments, using specialized testing devices. This manual inspection method is not only inefficient but also poses extremely high safety risks due to the nature of working at heights, seriously threatening the lives of inspection personnel.

[0004] To address the aforementioned issues, existing technologies urgently need improvement. Summary of the Invention

[0005] The purpose of this application is to provide an insulator string inspection method, device, electronic equipment, and storage medium. By controlling the rotation of a vision inspection flying robot at a hovering position above the target insulator string, and aligning the flight plane of the vision inspection flying robot with the axis, the inspection instrument is placed on the target insulator string for inspection. This solves the technical problems of existing insulator string inspection methods that rely on manual placement of inspection instruments, resulting in low efficiency and extremely high safety risks. By introducing a vision inspection flying robot and an automated placement mechanism, unmanned and precise placement of insulator inspection instruments is achieved, avoiding the risks of manual high-altitude operations, reducing the skill requirements for operators, and improving the inspection efficiency of insulator strings.

[0006] Firstly, this application provides a method for detecting insulator strings, comprising the following steps: Obtain the position information of the target insulator string; Based on the location information, the visual inspection flying robot, which carries the inspection instrument via a robotic arm, is controlled to fly to a hovering position above the target insulator string; The axis of the target insulator string is identified to control the rotation of the vision inspection flying robot so that the flight plane of the vision inspection flying robot is parallel to the axis. The visual inspection flying robot is controlled to drive the robotic arm to place the inspection instrument on the target insulator string, so that the inspection instrument can complete the inspection of the target insulator string; Identifying the axis of the target insulator string to control the rotation of the vision inspection flying robot, so that the flight plane of the vision inspection flying robot is parallel to the axis, includes: The target insulator string is photographed by the imaging device of the vision inspection flying robot to obtain an insulator image of the target insulator string; Based on the attitude and size information of each insulator in the captured image of the insulator, a straight line is fitted to the target insulator string to obtain the axis of the target insulator string; Based on the tilt angle of the axis, the visual inspection flying robot is controlled to rotate so that the flight plane of the visual inspection flying robot is parallel to the axis. Based on the attitude and size information of each insulator in the captured image, a straight line fit is performed on the target insulator string to obtain the axis of the target insulator string, including: Within a preset time period, the target insulator string is photographed multiple times to obtain multiple insulator images of the target insulator string; The attitude and size information of each insulator in the captured images of each insulator are identified; Based on the attitude and size information of each insulator in the captured images of each insulator, a straight line fit is performed on the target insulator string in each captured image to calculate the axis of the target insulator string.

[0007] The insulator string inspection method provided in this application enables the inspection of insulator strings. By controlling the rotation of a vision inspection flying robot at a hovering position above the target insulator string, and aligning the flight plane of the vision inspection flying robot with the axis, the inspection instrument is placed on the target insulator string for inspection. This solves the technical problems of existing insulator string inspection methods that rely on manual placement of inspection instruments, resulting in low efficiency and extremely high safety risks. By introducing a vision inspection flying robot and an automated placement mechanism, unmanned and precise placement of insulator inspection instruments is achieved, avoiding the risks of manual high-altitude operations, reducing the skill requirements for operators, and improving the inspection efficiency of insulator strings.

[0008] Optionally, based on the location information, controlling a vision inspection flying robot carrying inspection instruments via a robotic arm to fly to a hovering position above the target insulator string includes: Based on the location information, the visual inspection flying robot, which carries the inspection instruments via a robotic arm, is controlled to fly to a position above the target insulator string; After the visual inspection flying robot flies to the above position, the camera device of the visual inspection flying robot is used to take a picture of the target insulator string to obtain a picture of the target insulator string; Based on the coordinates of the target insulator string in the captured image, and combined with a preset flight speed calculation model, the visual inspection flying robot is controlled to fly to a hovering position above the target insulator string.

[0009] The insulator string detection method provided in this application can detect insulator strings. It acquires real-time image information of the target insulator string through the imaging device of the visual detection flying robot and combines it with a preset flight speed calculation model to achieve precise control of the hovering position of the flying robot, thereby improving the accuracy and stability of the detection instrument placement.

[0010] Optionally, based on the coordinate position of the target insulator string in the captured image, and combined with a preset flight speed calculation model, the visual inspection flying robot is controlled to fly to a hovering position above the target insulator string, including: Based on the coordinate position of the target insulator string in the captured image, and combined with a preset flight speed calculation model, the flight speed of the visual inspection flying robot in each direction is calculated. The visual inspection flying robot is controlled to fly at the specified flight speed to a hovering position above the target insulator string.

[0011] Optionally, based on the attitude and size information of each insulator in the captured images of each insulator, a straight line fit is performed on the target insulator string in each captured image to calculate the axis of the target insulator string, including: Based on the attitude and size information of each insulator in the captured images of each insulator, a straight line is fitted to the target insulator string in each captured image to obtain the instantaneous axis of each captured image; The average spatial position and average direction of the instantaneous axis of each insulator captured in an image are calculated to obtain the axis of the target insulator string.

[0012] Optionally, after controlling the visual inspection flying robot to drive the robotic arm to place the inspection instrument on the target insulator string, and after the inspection instrument completes the inspection of the target insulator string, the method further includes: Once the detection is complete, the detection instrument is driven to the placement position of the target insulator string, so that the visual inspection flying robot can return to the starting point according to the generated obstacle avoidance path after grasping the detection instrument.

[0013] Secondly, this application provides an insulator string testing device for testing insulator strings, including: The acquisition module is used to acquire the position information of the target insulator string; The flight module is used to control a vision inspection flying robot carrying inspection instruments via a robotic arm to fly to a hovering position above the target insulator string, based on the position information. The identification module is used to identify the axis of the target insulator string in order to control the rotation of the vision inspection flying robot so that the flight plane of the vision inspection flying robot is parallel to the axis. The detection module is used to control the visual inspection flying robot to drive the robotic arm to place the detection instrument on the target insulator string, so that the detection instrument can complete the detection operation on the target insulator string; The identification module is used to identify the axis of the target insulator string in order to control the rotation of the vision inspection flying robot so that the flight plane of the vision inspection flying robot is parallel to the axis, including: The target insulator string is photographed by the imaging device of the vision inspection flying robot to obtain an insulator image of the target insulator string; Based on the attitude and size information of each insulator in the captured image of the insulator, a straight line is fitted to the target insulator string to obtain the axis of the target insulator string; Based on the tilt angle of the axis, the visual inspection flying robot is controlled to rotate so that the flight plane of the visual inspection flying robot is parallel to the axis. Based on the attitude and size information of each insulator in the captured image, a straight line fit is performed on the target insulator string to obtain the axis of the target insulator string, including: Within a preset time period, the target insulator string is photographed multiple times to obtain multiple insulator images of the target insulator string; The attitude and size information of each insulator in the captured images of each insulator are identified; Based on the attitude and size information of each insulator in the captured images of each insulator, a straight line fit is performed on the target insulator string in each captured image to calculate the axis of the target insulator string.

[0014] This insulator string inspection device controls a visual inspection flying robot to rotate while hovering above the target insulator string. Once the robot's flight plane is parallel to the axis, the inspection instrument is placed on the target insulator string for inspection. This solves the technical problems of existing insulator string inspection methods, which rely on manual placement of inspection instruments, resulting in low efficiency and extremely high safety risks. By introducing a visual inspection flying robot and an automated placement mechanism, the device achieves unmanned and precise placement of insulator inspection instruments, avoiding the risks of manual high-altitude operations, reducing the skill requirements for operators, and improving the inspection efficiency of insulator strings.

[0015] Thirdly, this application provides an electronic device including a processor and a memory, the memory storing a computer program executable by the processor, wherein when the processor executes the computer program, it performs the steps in the insulator string detection method described above.

[0016] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the steps of the insulator string detection method described above.

[0017] Beneficial effects: The insulator string inspection method, device, electronic equipment, and storage medium provided in this application control the rotation of a vision inspection flying robot at a hovering position above the target insulator string. After the flight plane of the vision inspection flying robot is parallel to the axis, the inspection instrument is placed on the target insulator string to inspect it. This solves the technical problems of low efficiency and extremely high safety risks in existing insulator string inspection methods that rely on manual placement of inspection instruments. By introducing a vision inspection flying robot and an automated placement mechanism, unmanned and precise placement of insulator inspection instruments is achieved, avoiding the risks of manual high-altitude operations, reducing the skill requirements for operators, and improving the inspection efficiency of insulator strings. Attached Figure Description

[0018] Figure 1 This is a flowchart of an insulator string detection method provided in an embodiment of this application.

[0019] Figure 2 This is a schematic diagram of the insulator string detection device provided in an embodiment of this application.

[0020] Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0021] Labeling Explanation: 1. Acquisition Module; 2. Flight Module; 3. Identification Module; 4. Detection Module; 301. Processor; 302. Memory; 303. Communication Bus. Detailed Implementation

[0022] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. The components of the embodiments of this application described and shown in the accompanying drawings can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely represents selected embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0023] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this application, terms such as "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0024] Please refer to Figure 1 , Figure 1 This application provides a method for detecting insulator strings in some embodiments, used for detecting insulator strings, including: Step S1: Obtain the position information of the target insulator string; Step S2: Based on the position information, control the visual inspection flying robot, which carries the inspection instrument via a robotic arm, to fly to a hovering position above the target insulator string; Step S3: Identify the axis of the target insulator string to control the rotation of the vision inspection flying robot so that the flight plane of the vision inspection flying robot is parallel to the axis. Step S4: Control the visual inspection flying robot to drive the robotic arm to place the inspection instrument on the target insulator string, so that the inspection instrument can complete the inspection of the target insulator string.

[0025] This insulator string inspection method involves controlling a visual inspection flying robot to rotate while hovering above the target insulator string. Once the robot's flight plane is parallel to the axis, inspection instruments are placed on the target insulator string for inspection. This method solves the technical problems of existing insulator string inspection methods, which rely on manual placement of inspection instruments, resulting in low efficiency and extremely high safety risks. By introducing a visual inspection flying robot and an automated placement mechanism, unmanned and precise placement of insulator inspection instruments is achieved, avoiding the risks of manual high-altitude operations, reducing the skill requirements for operators, and improving the inspection efficiency of insulator strings.

[0026] Specifically, in step S1, the target insulator string is photographed by the imaging device in the vision inspection flying robot to obtain the position information of the target insulator string. The imaging device is pre-set with an insulator string target detection model, which is a pre-trained detection module capable of detecting insulator strings (such as existing YOLO series models and neural network models). Through the insulator string target detection model, the target insulator string can be tracked and detected to initially identify the relative position of the target insulator string and the vision inspection flying robot, obtain the coarse positioning of the target insulator string, and obtain the position information of the target insulator string.

[0027] The image of the target insulator string obtained by taking a picture of the target insulator string may not contain all the insulators of the target insulator string. Therefore, only the insulators appearing in the target insulator string image are considered to determine the location information of the target insulator string, and the insulators of the target insulator string outside the target insulator string image are not considered.

[0028] The visual inspection flying robot is a drone equipped with a robotic arm. This drone is equipped with a camera and a target detection model for insulator strings, such as a depth camera and a neural network model, which can accurately identify the relative position of the insulator strings. The drone's robotic arm can grasp and place the inspection instruments, allowing the drone to carry the instruments close to the target insulator string and place them there, thus enabling the inspection of the target insulator string.

[0029] Specifically, in step S2, based on the position information, the visual inspection flying robot carrying the inspection instrument via a robotic arm is controlled to fly to a hovering position above the target insulator string, including: Based on the location information, the vision inspection flying robot, which carries the inspection instruments via a robotic arm, is controlled to fly to a position above the target insulator string; After the visual inspection flying robot flies to an upper position, the camera device of the visual inspection flying robot is used to take pictures of the target insulator string, and the pictures of the target insulator string are obtained. Based on the coordinates of the target insulator string in the captured image, and combined with a pre-set flight speed calculation model, the vision detection flying robot is controlled to fly to a hovering position above the target insulator string.

[0030] In step S2, after the visual inspection flying robot initially reaches a position above the target insulator string (the position above refers to a position higher than the target insulator string, not directly above it), its imaging device captures an image of the target insulator string to obtain real-time visual data. Based on the coordinate position of the target insulator string in the captured image, an analysis is performed using a preset flight speed calculation model. Closed-loop control based on real-time visual feedback continuously corrects its flight speed, ensuring it can smoothly and accurately fly to a hovering position above the target insulator string. The hovering position is a position directly above the target insulator string at a preset hovering distance, typically set to 0.8-2.0m.

[0031] Specifically, in step S2, based on the coordinate position of the target insulator string in the captured image, and combined with a preset flight speed calculation model, the visual detection flight robot is controlled to fly to a hovering position above the target insulator string, including: Based on the coordinate position of the target insulator string in the captured image, and combined with the preset flight speed calculation model, the flight speed of the visual inspection flying robot in each direction is calculated. Control the visual inspection flying robot to fly at a certain speed to a hovering position above the target insulator string.

[0032] In step S2, image processing technology is used to accurately identify and extract the coordinate position of the target insulator string in the captured image. This coordinate position can be the center point of the target insulator string. Based on the coordinate position of the target insulator string in the captured image, a preset flight speed calculation model is used to calculate the flight speed of the visual inspection flying robot in various directions, enabling the visual inspection flying robot to fly to a hovering position above the target insulator string based on the flight speed. The preset flight speed calculation model is as follows: ; ; ; in, To visually detect the flight speed of a flying robot in the horizontal direction; To visually detect the flight speed of a flying robot in the vertical direction; To visually detect the flight speed of a flying robot in the vertical direction; , and x and y represent the maximum permissible flight speeds of the visual inspection flying robot in the horizontal, vertical, and longitudinal directions, respectively, generally between 5 m / s and 10 m / s; x and y are the horizontal and vertical coordinates of the target insulator string in the captured image, respectively; x c y c These are the coordinates of the center point of the captured image on the horizontal (x-axis) and vertical (y-axis), respectively; x max y max These are the maximum coordinates of the captured image on the horizontal and vertical axes, respectively, representing the width and height of the image. For example, assuming the image resolution is 1920*1080 pixels, then x... max =1920, y max =1080, x c =960, y c =540. The x-coordinate of the target insulator string after normalization, with a value ranging from 0 to 0.5; Let be the normalized ordinate of the target insulator string, with a value ranging from 0 to 0.5; e is the natural constant. For flight speed and The steepness of the change is set between 10 and 20. The larger, and The steeper the slope, the faster the flight speed and The more sensitive the target object's position, specifically the more sensitive it is to changes in the coordinate position of the target insulator string within the captured image; c represents the flight speed. and The symmetrical midpoint, since the normalized coordinate range of the target insulator string is 0-0.5, in order to improve the safety and accuracy of this translational dynamic correction and enable the UAV to smoothly decelerate and align with the insulator string, c needs to be set to 0.25; z is the distance between the visual inspection flying robot and the target insulator string in the vertical coordinate direction. max To determine the maximum permissible distance between the visual detection flying robot and the target insulator string in the vertical direction, it is typically set to 10-20m; min This is the distance between the hovering position and the target insulator string, typically set to 0.8-2.0m.

[0033] By controlling the visual inspection flying robot to move translatably towards the hovering position above the target insulator string at flight speeds in all directions, the robot's jitter and positional deviation during hovering can be significantly reduced through precise calculation and control of flight speeds in all directions, thereby improving its efficiency and accuracy in reaching the target hovering position.

[0034] Specifically, in step S3, identifying the axis of the target insulator string to control the rotation of the vision inspection flying robot, so that the flight plane of the vision inspection flying robot is parallel to the axis, includes: The target insulator string is photographed by the imaging device of the visual inspection flying robot, and an image of the target insulator string is obtained. Based on the attitude and size information of each insulator in the captured image, a straight line is fitted to the target insulator string to obtain the axis of the target insulator string; Based on the tilt angle of the axis, the visual inspection flying robot is controlled to rotate so that the flight plane of the visual inspection flying robot is parallel to the axis.

[0035] In step S3, when controlling the robotic arm to place the detection instrument, it is typically required that the vision inspection flying robot be aligned with the axis of the insulator string. Therefore, after initially hovering, the tilt angle of the target insulator string needs to be determined to control the vision inspection flying robot to be parallel to the target insulator string. After acquiring images of the insulators, image processing techniques (e.g., deep learning-based target detection algorithms, edge detection algorithms, or feature point extraction algorithms) are used to analyze the images to identify the position, orientation (e.g., coordinate position and tilt angle), and dimensions (e.g., length, width, diameter) of each insulator in the image. Based on this identified insulator information (the orientation and dimension information of each insulator), the detection position center point of each insulator can be determined. By using existing linear fitting algorithms (e.g., using the least squares method or the RANSAC algorithm), linear fitting is performed on these detection position center points, and the axis representing the spatial orientation of the entire target insulator string can be calculated and determined. Based on the tilt angle of the aforementioned axis, the visual inspection flying robot is controlled to rotate so that its flight plane is parallel to the aforementioned axis (the flight plane refers to the plane parallel to the horizontal plane where the midpoint of the UAV is located during normal flight). The rotational angular velocity of the visual inspection flying robot can be calculated using a preset rotational angular velocity calculation formula, which is as follows: ; in, To visually detect the rotational angular velocity of a flying robot; The maximum permissible angular velocity for visual inspection of flying robots is typically set in the range of 0.2-0.3 rad / s; The angle of inclination of the axis (i.e., the angle between the axis and the horizontal plane). The range of values ​​is to When the tilt angle When the size is large, the drone performs rotation correction at a faster speed. or At that time, its absolute value of rotational angular velocity is the largest, that is As the rotation correction process proceeds, the tilt angle... Gradually getting smaller, It also decreases accordingly until it approaches zero, thus completing the rotation correction.

[0036] Specifically, in step S3, based on the attitude and size information of each insulator in the captured image, a straight line fit is performed on the target insulator string to obtain the axis of the target insulator string, including: Within a preset time period, the target insulator string is photographed multiple times to obtain multiple images of the target insulator string. The attitude and size information of each insulator in the captured images of each insulator were identified; Based on the attitude and size information of each insulator in the captured images, a straight line is fitted to the target insulator string in each captured image to calculate the axis of the target insulator string.

[0037] In step S3, multiple images of the target insulator string are captured by repeatedly photographing it within a preset time period, thereby capturing image data of the target insulator string at different moments or slight angles. By identifying the insulator's attitude and size information from these multiple images and performing linear fitting on the detection position center, multiple independent axis fitting results can be obtained. This multi-sample acquisition and processing method can effectively reduce the uncertainty caused by noise, momentary occlusion, or measurement errors in a single image. By comprehensively processing these multiple fitting results (e.g., averaging or weighted averaging), random errors can be eliminated, making the final calculated insulator string axis more stable and accurate, thus providing a more reliable basis for the subsequent rotation of the visual inspection flying robot to be parallel to the axis. The preset time can be set according to actual needs, such as 3 seconds or 4 seconds.

[0038] Specifically, in step S3, based on the attitude and size information of each insulator in the captured images of each insulator, a straight line fit is performed on the target insulator string in each captured image to calculate the axis of the target insulator string, including: Based on the attitude and size information of each insulator in the captured images, straight lines are fitted to the target insulator string in each captured image to obtain the instantaneous axis of each captured image; The average spatial position and average direction of the instantaneous axis of each insulator in the captured image are calculated to obtain the axis of the target insulator string.

[0039] In step S3, straight line fitting is performed on multiple insulator images to obtain multiple instantaneous axes. This allows the initial estimation of the insulator string axis to fully utilize the information from each frame of the image. Each image generates a corresponding instantaneous axis, which may vary slightly due to shooting conditions or recognition errors. Because multiple instantaneous axes are obtained, the spatial position and orientation of these axes can be further averaged. By calculating the average spatial position, positional shifts caused by slight drone jitter or image acquisition errors can be effectively smoothed, making the final determined axis more spatially stable. Simultaneously, by calculating the average orientation, directional deviations caused by insulator attitude recognition or fitting errors in a single image can be eliminated, resulting in a more accurate and robust insulator string axis orientation. This multi-frame averaging mechanism effectively suppresses the influence of random noise and instantaneous errors, significantly improving the accuracy and stability of axis determination.

[0040] For example, suppose a visual inspection drone hovers above a target insulator string and continuously captures 50 images of the insulator at a rate of 10 frames per second over a preset 5-second period. For each image, an image processing algorithm is first used to identify the detection center of each insulator, and then a straight line is fitted based on these center points to obtain 50 instantaneous axes. For example, the first image yields instantaneous axis L1, the second image yields instantaneous axis L2, and so on, until the 50th image yields instantaneous axis L50. Then, the average spatial position of these 50 instantaneous axes is calculated. For example, the geometric center point of each instantaneous axis can be selected as a representative of its spatial position, and the arithmetic mean of the three-dimensional coordinates (X, Y, Z) of these 50 center points is calculated to obtain an average center point (X_avg, Y_avg, Z_avg). Simultaneously, the average direction of these 50 instantaneous axes is calculated. For example, the direction vector of each instantaneous axis can be extracted and normalized. Then, by averaging these normalized direction vectors (e.g., by summing the vectors and then normalizing them again), an average direction vector representing the overall orientation of the insulator string is obtained. Finally, by combining the average center point and the average direction vector, a final axis representing the target insulator string can be determined. This final axis integrates information from multiple images, effectively smoothing out noise and errors that may exist in a single image, thus providing more accurate and stable information about the insulator string axis.

[0041] Specifically, in step S4, the visual inspection flying robot will drive its carried robotic arm to extend and place the inspection instrument on the target insulator string. When the inspection instrument is in place, it can be remotely controlled or the inspection instrument can autonomously perform the inspection task according to the preset program to complete the inspection of the target insulator string and obtain the inspection result of the target insulator string.

[0042] In an optional embodiment, considering the positional shift of the visual inspection flying robot due to factors such as strong winds, the steps S2, S3, and S4 are not executed in complete isolation and sequentially, but may be executed in an overlapping or simultaneous manner. Therefore, when the real-time wind speed is detected to be greater than the preset wind speed threshold, steps S2, S3, and S4 can be executed simultaneously, adjusting steps S2, S3, and S4 to: based on the position information and the preset flight speed calculation model, guide the visual inspection flying robot, which carries the inspection instrument via a robotic arm, to fly to a hovering position above the target insulator string. During the flight, the axis of the target insulator string is detected in real time to control the visual inspection flying robot to be parallel to the axis when it reaches the hovering position. Control the visual inspection flying robot to drive the robotic arm to place the inspection instrument on the target insulator string, so that the inspection instrument can complete the inspection operation on the target insulator string.

[0043] Specifically, in step S4, after controlling the visual inspection flying robot to drive the robotic arm to place the inspection instrument on the target insulator string, and after the inspection instrument completes the inspection of the target insulator string, the process further includes: Once the inspection is complete, the driving inspection instrument will move to the target insulator string's placement position (i.e., the position where the inspection instrument is placed on the target insulator string), so that the visual inspection flying robot can return to the starting point after grasping the inspection instrument and following the generated obstacle avoidance path.

[0044] In step S4, after obtaining the detection result of the target insulator string, the detection is confirmed to be complete. The detection instrument is then driven to the placement position of the target insulator string, ensuring that the detection instrument can be accurately and stably re-grabbed by the robotic arm carried by the vision inspection flying robot. After confirming that the grasping is complete, an obstacle avoidance path is generated to guide the vision inspection flying robot back to the starting point. This allows the vision inspection flying robot to actively avoid potential obstacles during the return journey, effectively reducing the risk of collision and ensuring the safety of the vision inspection flying robot and the detection instrument.

[0045] As described above, this insulator string inspection method acquires the position information of the target insulator string. Based on this information, it controls a vision inspection flying robot, carrying an inspection instrument via a robotic arm, to hover above the target insulator string. The robot identifies the axis of the target insulator string and then controls its rotation to align its flight plane with the axis. The robot then drives the robotic arm to place the inspection instrument on the target insulator string, allowing it to complete the inspection. By controlling the rotation of the vision inspection flying robot from its hovering position above the target insulator string, aligning its flight plane with the axis, and placing the inspection instrument on the string, this method solves the technical problems of low efficiency and high safety risks associated with existing insulator string inspection methods that rely on manual placement of the instrument. By introducing a vision inspection flying robot and an automated placement mechanism, it achieves unmanned and precise placement of the insulator inspection instrument, avoiding the risks of manual high-altitude operations, reducing the skill requirements for operators, and improving the inspection efficiency of insulator strings.

[0046] refer to Figure 2 This application provides an insulator string testing device for testing insulator strings, comprising: Module 1 is used to acquire the position information of the target insulator string; Flight module 2 is used to control the visual inspection flying robot, which carries the inspection instruments via a robotic arm, to fly to a hovering position above the target insulator string based on the position information. The identification module 3 is used to identify the axis of the target insulator string in order to control the rotation of the vision inspection flying robot so that the flight plane of the vision inspection flying robot is parallel to the axis. The detection module 4 is used to control the vision inspection flying robot to drive the robotic arm to place the detection instrument on the target insulator string, so that the detection instrument can complete the detection operation on the target insulator string.

[0047] This insulator string inspection device controls a visual inspection flying robot to rotate while hovering above the target insulator string. Once the robot's flight plane is parallel to the axis, the inspection instrument is placed on the target insulator string for inspection. This solves the technical problems of existing insulator string inspection methods, which rely on manual placement of inspection instruments, resulting in low efficiency and extremely high safety risks. By introducing a visual inspection flying robot and an automated placement mechanism, the device achieves unmanned and precise placement of insulator inspection instruments, avoiding the risks of manual high-altitude operations, reducing the skill requirements for operators, and improving the inspection efficiency of insulator strings.

[0048] Specifically, when module 1 is executed, it uses the imaging device in the visual inspection flying robot to photograph the target insulator string and obtain the position information of the target insulator string. The imaging device is pre-set with an insulator string target detection model, which is a pre-trained detection module capable of detecting insulator strings (such as existing YOLO series models and neural network models). Through the insulator string target detection model, the target insulator string can be tracked and detected to initially identify the relative position of the target insulator string and the visual inspection flying robot, obtain the coarse positioning of the target insulator string, and obtain the position information of the target insulator string.

[0049] The image of the target insulator string obtained by taking a picture of the target insulator string may not contain all the insulators of the target insulator string. Therefore, only the insulators appearing in the target insulator string image are considered to determine the location information of the target insulator string, and the insulators of the target insulator string outside the target insulator string image are not considered.

[0050] The visual inspection flying robot is a drone equipped with a robotic arm. This drone is equipped with a camera and a target detection model for insulator strings, such as a depth camera and a neural network model, which can accurately identify the relative position of the insulator strings. The drone's robotic arm can grasp and place the inspection instruments, allowing the drone to carry the instruments close to the target insulator string and place them there, thus enabling the inspection of the target insulator string.

[0051] Specifically, when flight module 2 controls the vision inspection flying robot, which carries the inspection instruments via a robotic arm, to fly to a hovering position above the target insulator string based on the position information, it performs the following: Based on the location information, the vision inspection flying robot, which carries the inspection instruments via a robotic arm, is controlled to fly to a position above the target insulator string; After the visual inspection flying robot flies to an upper position, the camera device of the visual inspection flying robot is used to take pictures of the target insulator string, and the pictures of the target insulator string are obtained. Based on the coordinates of the target insulator string in the captured image, and combined with a pre-set flight speed calculation model, the vision detection flying robot is controlled to fly to a hovering position above the target insulator string.

[0052] When flight module 2 is executed, after the visual inspection flying robot initially reaches a position above the target insulator string (the position above refers to a position higher than the target insulator string, not directly above it), it uses its imaging device to photograph the target insulator string to obtain real-time visual data and obtain an image of the target insulator string. Based on the coordinate position of the target insulator string in the photographed image, it analyzes the data using a preset flight speed calculation model. Closed-loop control based on real-time visual feedback continuously corrects its flight speed, ensuring that it can fly smoothly and accurately to the hovering position above the target insulator string. The hovering position is a position directly above the target insulator string at a preset hovering distance, typically set to 0.8-2.0m.

[0053] Specifically, when the flight module 2 controls the visual detection flight robot to hover above the target insulator string based on the coordinate position of the target insulator string in the captured image and a preset flight speed calculation model, it executes the following: Based on the coordinate position of the target insulator string in the captured image, and combined with the preset flight speed calculation model, the flight speed of the visual inspection flying robot in each direction is calculated. Control the visual inspection flying robot to fly at a certain speed to a hovering position above the target insulator string.

[0054] During execution, flight module 2 uses image processing technology to accurately identify and extract the coordinates of the target insulator string from the captured image. This coordinates can be the center point of the target insulator string. Based on the coordinates of the target insulator string in the captured image, a preset flight speed calculation model is used to calculate the flight speed of the visual inspection robot in various directions, enabling the visual inspection robot to fly to a hovering position above the target insulator string based on its flight speed. The preset flight speed calculation model is as follows: ; ; ; in, To visually detect the flight speed of a flying robot in the horizontal direction; To visually detect the flight speed of a flying robot in the vertical direction; To visually detect the flight speed of a flying robot in the vertical direction; , and x and y represent the maximum permissible flight speeds of the visual inspection flying robot in the horizontal, vertical, and longitudinal directions, respectively, generally between 5 m / s and 10 m / s; x and y are the horizontal and vertical coordinates of the target insulator string in the captured image, respectively; x c y c These are the coordinates of the center point of the captured image on the horizontal (x-axis) and vertical (y-axis), respectively; x max y max These are the maximum coordinates of the captured image on the horizontal and vertical axes, respectively, representing the width and height of the image. For example, assuming the image resolution is 1920*1080 pixels, then x... max =1920, y max =1080, x c =960, y c =540. The x-coordinate of the target insulator string after normalization, with a value ranging from 0 to 0.5; Let be the normalized ordinate of the target insulator string, with a value ranging from 0 to 0.5; e is the natural constant. For flight speed and The steepness of the change is set between 10 and 20. The larger, and The steeper the slope, the faster the flight speed and The more sensitive the target object's position, specifically the more sensitive it is to changes in the coordinate position of the target insulator string within the captured image; c represents the flight speed. and The symmetrical midpoint, since the normalized coordinate range of the target insulator string is 0-0.5, in order to improve the safety and accuracy of this translational dynamic correction and enable the UAV to smoothly decelerate and align with the insulator string, c needs to be set to 0.25; z is the distance between the visual inspection flying robot and the target insulator string in the vertical coordinate direction. maxTo determine the maximum permissible distance between the visual detection flying robot and the target insulator string in the vertical direction, it is typically set to 10-20m; min This is the distance between the hovering position and the target insulator string, typically set to 0.8-2.0m.

[0055] By controlling the visual inspection flying robot to move translatably towards the hovering position above the target insulator string at flight speeds in all directions, the robot's jitter and positional deviation during hovering can be significantly reduced through precise calculation and control of flight speeds in all directions, thereby improving its efficiency and accuracy in reaching the target hovering position.

[0056] Specifically, when the identification module 3 identifies the axis of the target insulator string to control the rotation of the visual inspection flying robot so that the flight plane of the visual inspection flying robot is parallel to the axis, it performs the following: The target insulator string is photographed by the imaging device of the visual inspection flying robot, and an image of the target insulator string is obtained. Based on the attitude and size information of each insulator in the captured image, a straight line is fitted to the target insulator string to obtain the axis of the target insulator string; Based on the tilt angle of the axis, the visual inspection flying robot is controlled to rotate so that the flight plane of the visual inspection flying robot is parallel to the axis.

[0057] When the recognition module 3 is executed, it typically requires the visual inspection flying robot to align with the axis of the insulator string when controlling the robotic arm to place the inspection instrument. Therefore, after initially hovering, it is necessary to determine the tilt angle of the target insulator string to control the visual inspection flying robot to be parallel to the target insulator string. After acquiring images of the insulators, image processing techniques (e.g., deep learning-based target detection algorithms, edge detection algorithms, or feature point extraction algorithms) are used to analyze the images to identify the position, orientation (e.g., coordinate position and tilt angle), and dimensions (e.g., length, width, diameter) of each insulator in the image. Based on this identified insulator information (the orientation and dimension information of each insulator), the detection position center point of each insulator can be determined. By using existing linear fitting algorithms (e.g., using the least squares method or the RANSAC algorithm), linear fitting is performed on these detection position center points, and the axis representing the spatial orientation of the entire target insulator string can be calculated and determined. Based on the tilt angle of the aforementioned axis, the visual inspection flying robot is controlled to rotate so that its flight plane is parallel to the aforementioned axis (the flight plane refers to the plane parallel to the horizontal plane where the midpoint of the UAV is located during normal flight). The rotational angular velocity of the visual inspection flying robot can be calculated using a preset rotational angular velocity calculation formula, which is as follows: ; in, To visually detect the rotational angular velocity of a flying robot; The maximum permissible angular velocity for visual inspection of flying robots is typically set in the range of 0.2-0.3 rad / s; The angle of inclination of the axis (i.e., the angle between the axis and the horizontal plane). The range of values ​​is to When the tilt angle When the size is large, the drone performs rotation correction at a faster speed. or At that time, its absolute value of rotational angular velocity is the largest, that is As the rotation correction process proceeds, the tilt angle... Gradually getting smaller, It also decreases accordingly until it approaches zero, thus completing the rotation correction.

[0058] Specifically, when the recognition module 3 performs linear fitting on the target insulator string based on the posture and size information of each insulator in the captured image to obtain the axis of the target insulator string, it executes the following: Within a preset time period, the target insulator string is photographed multiple times to obtain multiple images of the target insulator string. The attitude and size information of each insulator in the captured images of each insulator were identified; Based on the attitude and size information of each insulator in the captured images, a straight line is fitted to the target insulator string in each captured image to calculate the axis of the target insulator string.

[0059] During execution, the recognition module 3 captures multiple images of the target insulator string within a preset time period, thereby capturing image data of the target insulator string at different moments or slight angles. By recognizing the insulator's attitude and size information from these multiple images and performing linear fitting on the detection position center, multiple independent axis fitting results can be obtained. This multi-sample acquisition and processing method can effectively reduce the uncertainty caused by noise, momentary occlusion, or measurement errors in a single image. By comprehensively processing these multiple fitting results (e.g., averaging or weighted averaging), random errors can be eliminated, making the final calculated insulator string axis more stable and accurate, thus providing a more reliable basis for the subsequent rotation of the visual inspection flying robot to be parallel to the axis. The preset time can be set according to actual needs, such as 3 seconds or 4 seconds.

[0060] Specifically, when the identification module 3 performs linear fitting on the target insulator string in each insulator image based on the posture and size information of each insulator in the captured images, and calculates the axis of the target insulator string, it executes the following: Based on the attitude and size information of each insulator in the captured images, straight lines are fitted to the target insulator string in each captured image to obtain the instantaneous axis of each captured image; The average spatial position and average direction of the instantaneous axis of each insulator in the captured image are calculated to obtain the axis of the target insulator string.

[0061] During execution, recognition module 3 performs linear fitting on multiple insulator images to obtain multiple instantaneous axes. This allows the initial estimation of the insulator string axis to fully utilize the information from each frame of the image. Each image generates a corresponding instantaneous axis, which may vary slightly due to shooting conditions or recognition errors. It is precisely because multiple instantaneous axes are obtained that the spatial position and orientation of these axes can be further averaged. By calculating the average spatial position, positional shifts caused by slight drone jitter or image acquisition errors can be effectively smoothed, making the final determined axis more spatially stable. Simultaneously, by calculating the average orientation, directional deviations caused by insulator attitude recognition or fitting errors in a single image can be eliminated, resulting in a more accurate and robust insulator string axis orientation. This multi-frame averaging mechanism effectively suppresses the influence of random noise and instantaneous errors, significantly improving the accuracy and stability of axis determination.

[0062] For example, suppose a visual inspection drone hovers above a target insulator string and continuously captures 50 images of the insulator at a rate of 10 frames per second over a preset 5-second period. For each image, an image processing algorithm is first used to identify the detection center of each insulator, and then a straight line is fitted based on these center points to obtain 50 instantaneous axes. For example, the first image yields instantaneous axis L1, the second image yields instantaneous axis L2, and so on, until the 50th image yields instantaneous axis L50. Then, the average spatial position of these 50 instantaneous axes is calculated. For example, the geometric center point of each instantaneous axis can be selected as a representative of its spatial position, and the arithmetic mean of the three-dimensional coordinates (X, Y, Z) of these 50 center points is calculated to obtain an average center point (X_avg, Y_avg, Z_avg). Simultaneously, the average direction of these 50 instantaneous axes is calculated. For example, the direction vector of each instantaneous axis can be extracted and normalized. Then, by averaging these normalized direction vectors (e.g., by summing the vectors and then normalizing them again), an average direction vector representing the overall orientation of the insulator string is obtained. Finally, by combining the average center point and the average direction vector, a final axis representing the target insulator string can be determined. This final axis integrates information from multiple images, effectively smoothing out noise and errors that may exist in a single image, thus providing more accurate and stable information about the insulator string axis.

[0063] Specifically, when the detection module 4 is executed, the visual inspection flying robot will drive its carried robotic arm to extend and place the detection instrument on the target insulator string. When the detection instrument is in place, it can be remotely controlled or the detection instrument can autonomously perform the detection task according to the preset program to complete the detection operation on the target insulator string and obtain the detection result of the target insulator string.

[0064] In an optional embodiment, considering the positional shift of the visual inspection flying robot due to factors such as strong winds, the steps S2, S3, and S4 are not executed in complete isolation and sequentially, but may be executed in an overlapping or simultaneous manner. Therefore, when the real-time wind speed is detected to be greater than the preset wind speed threshold, steps S2, S3, and S4 can be executed simultaneously, adjusting steps S2, S3, and S4 to: based on the position information and the preset flight speed calculation model, guide the visual inspection flying robot, which carries the inspection instrument via a robotic arm, to fly to a hovering position above the target insulator string. During the flight, the axis of the target insulator string is detected in real time to control the visual inspection flying robot to be parallel to the axis when it reaches the hovering position. Control the visual inspection flying robot to drive the robotic arm to place the inspection instrument on the target insulator string, so that the inspection instrument can complete the inspection operation on the target insulator string.

[0065] Specifically, the insulator string testing device also includes: The return-to-home module is used to determine the location of the detection instrument after the detection is completed, and drive the detection instrument to the target insulator string (i.e., the location where the detection instrument is placed on the target insulator string), so that the vision inspection flying robot can return to the starting point according to the generated obstacle avoidance path after grasping the detection instrument.

[0066] After obtaining the detection results of the target insulator string, the return-to-home module confirms the detection is complete and drives the detection instrument to the placement position of the target insulator string, ensuring that the detection instrument can be accurately and stably re-grabbed by the robotic arm carried by the vision inspection flying robot. Once the grasping is complete, the return-to-home module generates an obstacle avoidance path to guide the vision inspection flying robot back to the starting point. This allows the vision inspection flying robot to actively avoid potential obstacles during the return process, effectively reducing the risk of collision and ensuring the safety of both the vision inspection flying robot and the detection instrument.

[0067] As described above, this insulator string inspection device acquires the position information of the target insulator string. Based on this information, it controls a vision inspection flying robot, carrying an inspection instrument via a robotic arm, to hover above the target insulator string. The robot identifies the axis of the target insulator string and then controls its rotation to align its flight plane with the axis. The robot then drives the robotic arm to place the inspection instrument on the target insulator string, allowing it to complete the inspection. By controlling the rotation of the vision inspection flying robot from its hovering position above the target insulator string, aligning its flight plane with the axis, and placing the inspection instrument on the string, this device solves the technical problems of existing insulator string inspection methods that rely on manual placement of the instrument, resulting in low efficiency and high safety risks. By introducing a vision inspection flying robot and an automated placement mechanism, it achieves unmanned and precise placement of the insulator inspection instrument, avoiding the risks of manual high-altitude operations, reducing the skill requirements for operators, and improving the inspection efficiency of insulator strings.

[0068] Please refer to Figure 3 , Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device includes a processor 301 and a memory 302. The processor 301 and the memory 302 are interconnected and communicate with each other via a communication bus 303 and / or other forms of connection mechanisms (not shown). The memory 302 stores a computer program executable by the processor 301. When the electronic device is running, the processor 301 executes the computer program to perform the insulator string detection method in any optional implementation of the above embodiments, to achieve the following functions: obtaining the position information of the target insulator string; controlling a vision inspection flying robot carrying a detection instrument via a robotic arm to fly to a hovering position above the target insulator string based on the position information; identifying the axis of the target insulator string; controlling the rotation of the vision inspection flying robot to make its flight plane parallel to the axis; controlling the vision inspection flying robot to drive the robotic arm to place the detection instrument on the target insulator string, so that the detection instrument completes the detection operation on the target insulator string.

[0069] This application provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it executes the insulator string detection method in any optional implementation of the above embodiments to achieve the following functions: obtaining the position information of the target insulator string; controlling a vision inspection flying robot carrying a detection instrument via a robotic arm to fly to a hovering position above the target insulator string based on the position information; identifying the axis of the target insulator string; controlling the rotation of the vision inspection flying robot to make its flight plane parallel to the axis; controlling the vision inspection flying robot to drive the robotic arm to place the detection instrument on the target insulator string; and enabling the detection instrument to complete the detection operation on the target insulator string. The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Red-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0070] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. Furthermore, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Additionally, the displayed or discussed mutual couplings, direct couplings, or communication connections may be through some communication interfaces; indirect couplings or communication connections between devices or units may be electrical, mechanical, or other forms.

[0071] Furthermore, the units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0072] Furthermore, the functional modules in the various embodiments of this application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0073] In this document, relational terms such as first and second are used only to distinguish one entity or operation from another entity or operation, without necessarily requiring or implying any such actual relationship or order between these entities or operations.

[0074] The above description is merely an embodiment of this application and is not intended to limit the scope of protection of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A method for detecting insulator strings, characterized in that, Including the following steps: Obtain the position information of the target insulator string; Based on the location information, the visual inspection flying robot, which carries the inspection instrument via a robotic arm, is controlled to fly to a hovering position above the target insulator string; The axis of the target insulator string is identified to control the rotation of the vision inspection flying robot so that the flight plane of the vision inspection flying robot is parallel to the axis. The visual inspection flying robot is controlled to drive the robotic arm to place the inspection instrument on the target insulator string, so that the inspection instrument can complete the inspection of the target insulator string; Identifying the axis of the target insulator string to control the rotation of the vision inspection flying robot, so that the flight plane of the vision inspection flying robot is parallel to the axis, includes: The target insulator string is photographed by the imaging device of the vision inspection flying robot to obtain an insulator image of the target insulator string; Based on the attitude and size information of each insulator in the captured image of the insulator, a straight line is fitted to the target insulator string to obtain the axis of the target insulator string; Based on the tilt angle of the axis, the visual inspection flying robot is controlled to rotate so that the flight plane of the visual inspection flying robot is parallel to the axis. Based on the attitude and size information of each insulator in the captured image, a straight line fit is performed on the target insulator string to obtain the axis of the target insulator string, including: Within a preset time period, the target insulator string is photographed multiple times to obtain multiple insulator images of the target insulator string; The attitude and size information of each insulator in the captured images of each insulator are identified; Based on the attitude and size information of each insulator in the captured images of each insulator, a straight line fit is performed on the target insulator string in each captured image to calculate the axis of the target insulator string.

2. The insulator string detection method according to claim 1, characterized in that, Based on the location information, controlling a vision inspection flying robot carrying inspection instruments via a robotic arm to fly to a hovering position above the target insulator string includes: Based on the location information, the visual inspection flying robot, which carries the inspection instruments via a robotic arm, is controlled to fly to a position above the target insulator string; After the visual inspection flying robot flies to the above position, the camera device of the visual inspection flying robot is used to take a picture of the target insulator string to obtain a picture of the target insulator string; Based on the coordinates of the target insulator string in the captured image, and combined with a preset flight speed calculation model, the visual inspection flying robot is controlled to fly to a hovering position above the target insulator string.

3. The insulator string detection method according to claim 2, characterized in that, Based on the coordinates of the target insulator string in the captured image, and combined with a preset flight speed calculation model, the visual inspection flying robot is controlled to fly to a hovering position above the target insulator string, including: Based on the coordinate position of the target insulator string in the captured image, and combined with a preset flight speed calculation model, the flight speed of the visual inspection flying robot in each direction is calculated. The visual inspection flying robot is controlled to fly at the specified flight speed to a hovering position above the target insulator string.

4. The insulator string detection method according to claim 1, characterized in that, Based on the attitude and size information of each insulator in the captured images of each insulator, a straight line fit is performed on the target insulator string in each captured image to calculate the axis of the target insulator string, including: Based on the attitude and size information of each insulator in the captured images of each insulator, a straight line is fitted to the target insulator string in each captured image to obtain the instantaneous axis of each captured image; The average spatial position and average direction of the instantaneous axis of each insulator captured in an image are calculated to obtain the axis of the target insulator string.

5. The insulator string detection method according to claim 1, characterized in that, Controlling the visual inspection flying robot to drive the robotic arm to place the inspection instrument on the target insulator string, and after the inspection instrument completes the inspection of the target insulator string, further includes: Once the detection is complete, the detection instrument is driven to the placement position of the target insulator string, so that the visual inspection flying robot can return to the starting point according to the generated obstacle avoidance path after grasping the detection instrument.

6. An insulator string testing device for testing insulator strings, characterized in that, include: The acquisition module is used to acquire the position information of the target insulator string; The flight module is used to control a vision inspection flying robot carrying inspection instruments via a robotic arm to fly to a hovering position above the target insulator string, based on the position information. The identification module is used to identify the axis of the target insulator string in order to control the rotation of the vision inspection flying robot so that the flight plane of the vision inspection flying robot is parallel to the axis. The detection module is used to control the visual inspection flying robot to drive the robotic arm to place the detection instrument on the target insulator string, so that the detection instrument can complete the detection operation on the target insulator string; The identification module is used to identify the axis of the target insulator string in order to control the rotation of the vision inspection flying robot so that the flight plane of the vision inspection flying robot is parallel to the axis, including: The target insulator string is photographed by the imaging device of the vision inspection flying robot to obtain an insulator image of the target insulator string; Based on the attitude and size information of each insulator in the captured image of the insulator, a straight line is fitted to the target insulator string to obtain the axis of the target insulator string; Based on the tilt angle of the axis, the visual inspection flying robot is controlled to rotate so that the flight plane of the visual inspection flying robot is parallel to the axis. Based on the attitude and size information of each insulator in the captured image, a straight line fit is performed on the target insulator string to obtain the axis of the target insulator string, including: Within a preset time period, the target insulator string is photographed multiple times to obtain multiple insulator images of the target insulator string; The attitude and size information of each insulator in the captured images of each insulator are identified; Based on the attitude and size information of each insulator in the captured images of each insulator, a straight line fit is performed on the target insulator string in each captured image to calculate the axis of the target insulator string.

7. An electronic device, characterized in that, It includes a processor and a memory, the memory storing a computer program executable by the processor, which, when executing the computer program, performs the steps of the insulator string detection method as described in any one of claims 1-5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it performs the steps in the insulator string detection method as described in any one of claims 1-5.

Images