An airport power transmission line unmanned aerial vehicle autonomous inspection method and system

Abstract

The application provides an unmanned aerial vehicle autonomous inspection method and system for an airport power transmission line, and belongs to the technical field of unmanned aerial vehicle intelligent inspection, and comprises the following steps: after receiving an inspection task, the unmanned aerial vehicle takes off, flies to the top of a target tower according to the longitude and latitude information of the tower in the inspection task, and completes the tower inspection task by acquiring a target tower and a component bounding box through a visual recognition algorithm, determining a tower image center based on the bounding box, acquiring a spatial position based on the tower image center, and designing a control law according to the spatial position; the start point of a target ground wire is acquired through the visual recognition algorithm, the unmanned aerial vehicle imitates a wire space coordinate by using a segmented catenary fitting, the left and right deviation, the height deviation and the heading angle deviation of the unmanned aerial vehicle are determined based on the imitated wire space coordinate and the current position of the unmanned aerial vehicle, and a control law of the unmanned aerial vehicle is designed to complete the ground wire line inspection task. The application can automatically generate a tower inspection route without a preset path.

Description

Technical Field

[0001] This invention belongs to the field of unmanned aerial vehicle (UAV) intelligent inspection technology, and in particular relates to a method and system for autonomous UAV inspection of airport power transmission lines. Background Technology

[0002] The statements in this section are merely background information related to the present invention and do not necessarily constitute prior art.

[0003] During emergency inspections of power transmission lines, personnel carry drones and related equipment to the vicinity of the power transmission line and manually control the drones to fly to the top of the towers and lines to carry out inspections.

[0004] However, existing technologies can only perform autonomous inspections according to pre-planned routes after receiving inspection tasks. In actual inspection operations, emergency inspections of towers and conductors with unknown routes are sometimes required. Existing technologies cannot autonomously perform inspections of towers, conductors, or related combinations. At the same time, conductors are subject to thermal expansion and contraction, and their sag is easily affected by changes in ambient temperature. Relying solely on pre-planned routes can easily lead to low conductor engagement during autonomous UAV inspections, ultimately resulting in problems such as blurry images, backlighting, and out-of-focus images. Summary of the Invention

[0005] To overcome the shortcomings of the existing technology, this invention proposes a method and system for autonomous inspection of airport power transmission lines by unmanned aerial vehicles (UAVs), which solves the problems of existing technologies that can only perform autonomous inspection operations according to pre-planned routes and the impact of weather and season on conductor sag.

[0006] To achieve the above objectives, one or more embodiments of the present invention provide the following technical solutions: In a first aspect, the present invention discloses a method for autonomous inspection of airport power transmission lines by unmanned aerial vehicles (UAVs), comprising: After receiving the inspection task, the drone takes off and flies to the top of the target tower according to the latitude and longitude information of the tower in the inspection task; the inspection task includes tower inspection task, conductor and ground wire line inspection task, and tower and conductor and ground wire combined inspection task. Specifically, the target tower and component boundary boxes are obtained through a visual recognition algorithm, the center of the key inspection target image of the tower is determined based on the boundary boxes, the spatial position is obtained based on the center of the key inspection target image of the tower, and a control law is designed according to the spatial position to complete the tower inspection task. The starting point of the target conductor is obtained by visual recognition algorithm. The conductor is fitted with a segmented catenary to obtain the UAV’s simulated line spatial coordinates. Based on the simulated line spatial coordinates and the current position of the UAV, the left and right deviations, altitude deviations and heading angle deviations of the UAV are determined and the UAV control law is designed to complete the conductor line inspection task.

[0007] A further technical solution involves obtaining the spatial location based on the center of the key inspection target image of the tower. The calculation process is as follows:

[0008] in, Let K be the expected inspection point of the UAV corresponding to the k-th component. The coordinates of the current desired waypoint. Let be the UTM coordinates of the k-th component. The vertical offset of the camera relative to the components; The horizontal azimuth angle of the component; The horizontal safe inspection distance between the drone and the inspection target; Position deviation is calculated by subtracting the UAV’s current expected target waypoint coordinates from its real-time UTM coordinates; The heading deviation is the difference between the expected heading angle and the real-time heading angle of the UAV camera.

[0009] A further technical solution involves designing a control law based on the spatial location, specifically as follows: Based on the error design control law, the northeast-bound speed control design is as follows:

[0010] in, For the eastward speed of the drone, For proportional gain, For integral gain, This is the differential gain; For the northbound speed of the drone, For proportional gain, For integral gain, This is the differential gain; The vertical speed control design is as follows:

[0011] in, The vertical velocity of the drone. For proportional gain, For integral gain, This is the differential gain; The yaw rate control design is as follows:

[0012] in, Angular velocity is the yaw angle. Yaw rate proportional gain The integral gain of yaw rate. This is the differential gain of the yaw rate.

[0013] A further technical solution, wherein the step of fitting the conductor with a segmented catenary to obtain the UAV's simulated line spatial coordinates, includes: fitting the three-dimensional space conductor with a segmented catenary according to the catenary equation and the conductor sag formula, that is, uniformly dividing the entire conductor into M segments, obtaining M+1 points as waypoints for UAV inspection, and then fitting each conductor segment with a catenary to obtain the three-dimensional coordinates of each point. , , ):

[0014]

[0015]

[0016] in, For the first The horizontal position of each segment point Let M be the step lengths of the conductor segments. Here are the coordinates of point A on the tower. Here are the coordinates of point B on the tower. The horizontal azimuth of the line. The height difference between the two hanging points. For conductor span, Let M be the catenary coefficient, and M be the number of segments into which the conductor is evenly divided.

[0017] A further technical solution involves generating the desired UAV-based linear coordinates based on the catenary, then:

[0018] in, For the desired UAV line-space coordinates, The analytical equation for a three-dimensional catenary is given. This refers to the constant horizontal distance of the drone when it flies alongside the guide wire. is the unit vector along the horizontal tangent direction of the conductor.

[0019] A further technical solution involves designing a UAV control law based on the UAV's left-right deviation, altitude deviation, and heading angle deviation during the conductor line inspection task. This yields the UAV's forward velocity, lateral velocity, vertical velocity, and yaw rate along the conductor direction, calculated as follows:

[0020]

[0021]

[0022]

[0023] in, For the forward speed of the drone, For the drone's lateral speed, For the vertical speed of the drone, These are the yaw rate of the drone; The drone's set speed; The proportional gain of the UAV in the y-direction, The integral gain in the y-direction. The differential gain in the y-direction; The proportional gain in the z-direction, The integral gain in the z-direction. The differential gain in the z-direction; These are the yaw angle proportional gains; These are the integral gains of the yaw angle, respectively. This is the differential gain for the yaw angle.

[0024] A further technical solution involves attaching the pole coordinates when issuing inspection tasks. After receiving the task, the drone first flies to the pole. The tower inspection is completed above, then the aircraft flies to the tower. The above-ground personnel will conduct pole and tower inspections; during the inspections, they will collect information on crossarm attachment points and conductors, and use the collected information to control a drone to complete the pole and tower inspections. and towers Inspection of the conductors and ground wires between them; Then, proceed with the tower construction. Inspection and tower and towers The inspection of conductors and ground wires is carried out sequentially until the last tower is completed. and ground wire Afterwards, the inspection task of the tower and conductor / ground wire combination is completed.

[0025] Secondly, this invention discloses an unmanned aerial vehicle (UAV) autonomous inspection system for airport power transmission lines, comprising: The task receiving module is configured such that: after receiving the inspection task, the UAV takes off and flies to the top of the target tower according to the latitude and longitude information of the tower in the inspection task; the inspection task includes tower inspection task, conductor and ground wire line inspection task, and combined tower and conductor and ground wire inspection task. The pole inspection module is configured to: acquire the target pole and component bounding box through a visual recognition algorithm; determine the center of the key inspection target image of the pole based on the bounding box; acquire the spatial position based on the center of the key inspection target image of the pole; and design a control law based on the spatial position to complete the pole inspection task. The conductor inspection module is configured to: obtain the starting point of the target conductor and ground wire through a visual recognition algorithm; obtain the UAV's simulated line spatial coordinates by fitting the conductor with a segmented catenary; determine the UAV's left and right deviations, altitude deviations, and heading angle deviations based on the simulated line spatial coordinates and the UAV's current position; design the UAV's control law; and complete the conductor and ground wire line inspection task.

[0026] Thirdly, the present invention discloses an electronic device, including a memory and a processor, and computer instructions stored in the memory and running on the processor, wherein the computer instructions, when run by the processor, complete the steps of the above-mentioned unmanned aerial vehicle (UAV) autonomous inspection method for airport power transmission lines.

[0027] Fourthly, the present invention discloses a computer-readable storage medium for storing computer instructions, which, when executed by a processor, complete the steps of the above-mentioned unmanned aerial vehicle (UAV) autonomous inspection method for airport power transmission lines.

[0028] Compared with the prior art, the beneficial effects of the present invention are as follows: This invention provides a method and system for autonomous inspection of transmission lines without a pre-defined route. During emergency inspection operations, when there is no flight path, personnel do not need to arrive at the work site. The inspection task is issued through the airport control system. After receiving the inspection task, the drone can take off autonomously and fly to the airspace above the transmission line towers to carry out inspection tasks on the towers, conductors, ground wires, or a combination thereof. There is no need for operators to manually control the drone, reducing personnel involvement in the task. This realizes the transformation from the traditional method of planning the flight path before inspection to a fully automated flight path planning and refined inspection operation mode. It eliminates the dependence on flight paths, overcomes the influence of weather and seasons on conductor sag, and relies on the position information of the towers for adaptive inspection to control the drone to achieve adaptive engagement flight of the conductors, realizing intelligent all-weather autonomous inspection operations and significantly improving the efficiency of inspection operations.

[0029] Advantages of additional aspects of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description

[0030] The accompanying drawings, which form part of this invention, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an improper limitation of the invention.

[0031] Figure 1 This is a flowchart of the unmanned aerial vehicle (UAV) autonomous inspection method for airport power transmission lines as described in Embodiment 1 of the present invention.

[0032] Figure 2 This is a schematic diagram of the conductor sag described in Embodiment 1 of the present invention. Detailed Implementation

[0033] It should be noted that the following detailed descriptions are exemplary and intended to provide further illustration of the invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0034] It should be noted that the terminology used herein is for the purpose of describing particular implementations only and is not intended to limit the exemplary implementations of the present invention.

[0035] Where there is no conflict, the embodiments and features in the embodiments of the present invention can be combined with each other.

[0036] During emergency inspections of power transmission lines, personnel carry drones and related equipment to the vicinity of the power transmission line, manually control the drone to fly above the tower and line, identify the target line on the tower through intelligent algorithms, calculate the relevant position information of the drone and the target based on the target's visual spatial position information, and realize autonomous and refined inspection operations of the drone for tower component inspection or conductor and ground wire line interlocking flight through control algorithms, as well as adaptive route generation.

[0037] Existing drone airport systems can perform routed tasks. However, for pole and line inspections without designated routes, drones cannot complete the expected inspection work. In such emergency inspections without designated routes, personnel often need to carry the drone and related equipment to the vicinity of the inspection route and manually control the drone to fly over the pole or line, which is labor-intensive and resource-intensive, and cannot carry out emergency inspections immediately, resulting in low efficiency. After the drone pole or line inspection is completed, the inspection target needs to be manually switched, i.e., manually selecting the pole or line to inspect, and after the inspection is completed, the drone needs to be manually controlled to return to base.

[0038] On the other hand, conductors are subject to thermal expansion and contraction, and their sag is easily affected by changes in ambient temperature. In summer, when the temperature rises, the conductor's sag increases due to thermal expansion and its own weight. In winter, when the temperature is low, the conductor contracts and the sag decreases. Relying solely on pre-planned flight paths can easily lead to low conductor engagement during UAV autonomous inspection operations, ultimately resulting in out-of-focus, backlit, and blurry images, all of which affect the quality of inspection image data.

[0039] Therefore, this invention proposes a method and system for autonomous inspection of transmission lines without a pre-defined path, thereby solving the above-mentioned problems.

[0040] Example 1 In one or more embodiments, a method for autonomous inspection of airport power transmission lines using unmanned aerial vehicles (UAVs) is disclosed, applicable to an inspection system including an airport control system, an airport, and UAVs, such as... Figure 1 As shown, it includes the following steps: Step S1: After receiving the inspection task, the UAV takes off and flies to the top of the target tower according to the latitude and longitude information of the tower in the inspection task; the inspection task includes tower inspection task, conductor and ground wire line inspection task, and tower and conductor and ground wire combined inspection task.

[0041] Step S1-1: Create an inspection task through the airport control system and send it to the target airport. The inspection task can be selected as a single tower or line inspection task, or a combination of tower and line continuous inspection task, depending on the actual operation needs.

[0042] Step S1-2: The target airport receives, parses, and forwards the inspection task to the drone.

[0043] The types of inspection tasks include pole and tower inspection tasks, conductor and ground wire line inspection tasks, and combined pole and tower and conductor and ground wire inspection tasks.

[0044] Furthermore, the set of tasks issued will be denoted as... If the task type is pole inspection without a flight path, it is recorded as... ,in, This refers to the number of towers; if the task type is conductor and ground wire inspection without a flight path... ,in, The number of lines; if the task type is a combination of pole inspection and conductor / ground wire inspection without a route, it is denoted as ,in, This refers to the number of towers in the combined task.

[0045] Step S2: The drone performs inspection tasks according to different inspection tasks.

[0046] After receiving the mission, the drone begins a self-check. Once the self-check is successful, the drone takes off and, based on the target location in the mission information, autonomously flies to the target tower or conductor to begin intelligent inspection operations. It detects and identifies tower components through continuous video frames or calculates the drone's real-time position information, controls the drone's real-time movement, and completes tower target detection or controls the drone's wire engagement flight.

[0047] As one implementation method, when performing pole inspection tasks, the following steps are included: Step S2-1-1: After the UAV takes off, it flies to the top of the target tower based on the latitude and longitude information of the tower in the mission, and obtains the bounding box of the tower and related components through a visual recognition algorithm.

[0048] It should be understood that visual recognition algorithms can use the YOLO series of algorithms to train the YOLO model to recognize various targets on power transmission lines.

[0049] Step S2-1-2: After the drone flies above the tower, it performs real-time detection of key inspection target components of the tower through continuous frame detection, and extracts the center point position and the bounding box of the target detection rectangle. .

[0050] The positional relationship between image pixels and the camera coordinate system can be obtained using the camera imaging model, as shown below: (1) in, This is the origin of the image coordinate system, i.e., the center point of the image; , For camera focal length, This provides the three-dimensional coordinate information of the UAV's world coordinate system, which adopts the East-North-Sky coordinate system. The coordinates are in the image coordinate system. It is a rotation matrix; This is the position offset matrix; It is a zero matrix.

[0051] Furthermore, after identifying and outlining the target tower, the center of the target outline, i.e., the center of the image of the key inspection target component of the tower, is as follows: (2) (3) in,( , () is the image center of the key inspection target component of the tower.

[0052] Based on the coordinate deviation between the center point of the image of the key inspection target component of the tower and the center point of the image, as shown in equations (4)-(5), the horizontal control quantity of the UAV is designed, as shown in equations (6)-(7). The left and right positions of the UAV are adjusted to ensure that the crossarm of the tower is in the middle of the image field of view. When the deviation between the center position of the target component and the center position of the image is less than the set threshold, as shown in equations (8)-(9), the UAV is controlled to hover and then guided to land at the preset safe height. The pixel position deviation and control quantity of the UAV are defined as follows: (4) (5) (6) (7) (8) (9) in,( , () represents the coordinate deviation; for Directional control of drone speed (drone in image pixel coordinate system). for Directional speed control parameters for UAVs (UAVs in image pixel coordinate system); for Directional drone speed control for Directional drone speed control parameters; for The pixel deviation between the image center position and the image center position of the directional target component. for The pixel deviation between the center position of the target component in the image and the center position of the image.

[0053] Based on the aforementioned camera imaging model, the three-dimensional spatial vector of the UAV in the world coordinate system can be obtained. Using UTM projection, a local Cartesian coordinate system with the tower center as the origin can be established. Through coordinate transformation, the spatial positioning of the UAV can be achieved. Let the global UTM coordinates of the tower center point be... This is obtained from drone positioning data. Therefore, for any point in the world coordinate system... : (10) (11) (12) in, The tower is offset eastward from its east side. The tower is offset northward from its north side. This represents the vertical offset of the tower (above the top of the tower). To facilitate UAV flight control, it is converted to North-East coordinates, then: (13) The drone is used to take images of the top of the tower from different horizontal positions at the same elevation, and the tower height is calculated using parallax. The tower height is calculated as follows: (14) in, The horizontal distance between the two shooting positions. , For camera tilt angle, This is the elevation value of the camera. This is the elevation value of the bottom of the tower.

[0054] Based on the tower height obtained above, guide the drone to land at a certain height above the tower. In actual use, the landing height above the tower will vary depending on the tower type. Generally, the value is the sum of the tower height and the safety experience value. Throughout the process, ensure that the tower is always in the center of the field of vision and record the latitude, longitude and altitude information of the drone when it reaches the position. Record this point information as the starting point of the tower inspection route. After the inspection of all tower components is completed, the tower inspection route is generated.

[0055] Step S2-1-3: Based on the conversion relationship between image pixels and three-dimensional space established by the above camera imaging model, calculate the spatial location information of feature points of key inspection target components of the tower and the three-dimensional coordinates of the UAV. The key inspection target components of the tower include, but are not limited to, insulator strings, crossarms, and hanging points.

[0056] Assuming the tower has N critical inspection components, then: (15) in, For the first Eastward coordinates of the UTM of each inspection component; For the first The north-facing coordinates of the UTM of each inspected component; For the first The absolute altitude of each inspection component is calculated from the UTM elevation and the relative height of the tower. , This refers to the height of the component relative to the tower base.

[0057] To ensure inspection safety, the drone is controlled to deviate horizontally from the key components of the tower. Vertical relative height of the component Hover over the location. Generate the desired inspection points for the drone according to the above requirements. ,but: (16) in, Let be the UTM coordinates of the k-th component. The expected inspection point of the UAV corresponding to the kth component can be connected in series to form the inspection route of the UAV. The horizontal normal vector is the unit vector in the direction in which the UAV deflects towards the side of the tower. The vertical offset of the camera relative to the components; The horizontal azimuth angle of the component; The horizontal safe inspection distance between the drone and the inspection target.

[0058] Step S2-1-4: Define the real-time UTM coordinates of the UAV as follows The current desired waypoint is The positional deviation is calculated as follows: (17) in, Due to the positional deviation of the eastward-facing drone, Due to the positional deviation of the northbound drone, This refers to the vertical positional deviation of the UAV.

[0059] The real-time heading angle of the drone is The heading deviation is as follows: (18) in, The desired heading angle for the drone camera.

[0060] Step S2-1-5: Based on the position deviation and heading angle deviation between the real-time position calculation of the UAV and the desired position obtained, design the UAV control law.

[0061] Then, based on the above error design control law, the northeast-direction speed control design is as follows: (19) (20) in, For the eastward speed of the drone, For proportional gain, For integral gain, This is the differential gain; For the northbound speed of the drone, For proportional gain, For integral gain, This is the differential gain.

[0062] The vertical speed control design is as follows: (twenty one) in, Let the vertical velocity of the UAV be in the North-East-Earth coordinate system. For proportional gain, For integral gain, This is the differential gain.

[0063] The yaw rate control design is as follows: (twenty two) in, Angular velocity is the yaw angle. Yaw rate proportional gain The integral gain of yaw rate. This is the differential gain of the yaw rate.

[0064] Control the drone to fly on one side of the tower and detect key components of the tower in real time (crossarm hanging point, conductor hanging point, insulator string, etc.). By identifying key components and following the above steps, control the drone to reach the vicinity of the key components. When all errors are less than the set threshold, as shown in formula (23), the drone reaches the effective shooting area of ​​the inspection and controls the drone to hover.

[0065] (twenty three) in, The permissible error threshold in the horizontal direction; The vertical error threshold is given by the subscript U, which represents the UAV in the North-East-Ground coordinate system. This is the allowable error threshold for the heading angle.

[0066] After the drone hovers, it identifies key components and obtains the pixel coordinates of the identification detection box of the components. Following the steps above (Equations (1)-(9)), it adjusts the position of the drone or the angle of the camera gimbal to ensure that the key component target is in the center of the camera's field of view.

[0067] When the above conditions are met, and the drone is within a safe distance and reaches the set shooting interval, the MSDK triggers automatic control of the drone camera to take pictures of the inspection target, achieving accurate photography of the tower target and recording the latitude, longitude, and elevation information of the photographed point. Based on the visual recognition results and position calculation information (including tower structure - crossarm, hanging point, etc.), the position information of the drone hovering and taking pictures obtained by the above spatial position calculation is combined with the point information of the inspection target, including the three-dimensional coordinates of the tower components, the gimbal angle when the camera takes pictures, the drone position information, etc. During the autonomous inspection, the latitude and longitude coordinates of all hovering points of the drone at key components are recorded sequentially. After the inspection is completed, the inspection route is automatically generated according to the prescribed route format.

[0068] According to the above steps, when the tower After the inspection is completed, the drone is controlled to fly to the lower pole based on the latitude and longitude coordinates of the pole issued by the backend. Repeat the above steps to complete the tower. Key component inspection and flight path generation, then guide the drone to automatically fly to the lower base tower. This enables continuous tower inspection operations and route generation.

[0069] When the tower When the inspection is completed or the drone triggers the safety policy, the drone autonomously returns to the airport and transmits the collected image data and generated flight path files back to the back-end management system.

[0070] When conducting the above-mentioned pole inspection operations again, in addition to the above methods, the inspection task can also be sent directly to the target airport using the generated flight path. The drone will not need to identify the pole target and control its motion again, which can effectively reduce the power consumption of the drone and improve the inspection efficiency.

[0071] As one implementation method, when performing a conductor / ground wire line inspection task, the following steps are included: Step S2-2-1: When the conductor inspection task is issued, the coordinate information of the towers at both ends of the conductor is attached. After the UAV takes off autonomously from the airport, it flies to the tower at the beginning of the conductor. Above, a visual recognition algorithm is used to identify the crossarm attachment point of the tower to determine the starting point of the conductor and the flight direction of the drone.

[0072] Step S2-2-2: Define point A of tower as and point B of tower as . Establish the analytical equation of the three-dimensional catenary : (twenty four) in, This is the arc length parameter of the conductor, which is the horizontal distance starting from point A. The horizontal azimuth of the line. , The height of the hanging points at both ends of the conductor. The height difference between the two hanging points. For conductor span, This is the catenary coefficient.

[0073] Based on the catenary equation and the sag formula, a piecewise catenary is used to fit the three-dimensional traverse. That is, the entire traverse is evenly divided into M segments, and M+1 points are obtained as waypoints for UAV inspection. Then, the three-dimensional coordinates of each point can be obtained by fitting the catenary to each traverse segment. , , ): (25) (26) (27) in, For the first The horizontal position of each segment point Let M be the step length of the conductor for each segment.

[0074] The desired UAV linear coordinates are generated based on the above catenary equation. ,but: (28) in, This refers to the constant horizontal distance of the drone when it flies alongside the guide wire. is the unit vector along the horizontal tangent direction of the conductor.

[0075] Step S2-2-3: Record the current position of the drone as... The drone's left-right (i.e., horizontal) position deviation Vertical height deviation Heading deviation The calculation is as follows: (29) in, The tangent direction angle of the conductor. This provides the real-time heading angle for the drone.

[0076] Step S2-2-4: Based on the above-mentioned left-right deviation, altitude deviation, and heading angle deviation of the UAV, design the UAV control law to obtain the forward velocity, lateral velocity, vertical velocity, and yaw rate of the UAV along the guide line. The specific calculations are as follows: (30) (31) (32) (33) in, For the forward speed of the drone, For the drone's lateral speed, For the vertical speed of the drone, These are the yaw rate of the drone; The drone's set speed; The proportional gain of the UAV in the y-direction, The integral gain in the y-direction. The differential gain in the y-direction; The proportional gain in the z-direction, The integral gain in the z-direction. The differential gain in the z-direction; These are the yaw angle proportional gains; These are the integral gains of the yaw angle, respectively. This is the differential gain for the yaw angle.

[0077] During UAV flight, the guide wire target is detected in real time through continuous frame detection, and the target bounding box and center point position are extracted. Based on the camera imaging model mentioned above, the relationship between image pixels and camera coordinate system points can be obtained: (34) (35) in, For camera coordinate system coordinates, These are the coordinates in the camera coordinate system.

[0078] Based on the relationship between the image pixel coordinate system and the camera coordinate system, the horizontal distance from the aircraft camera to the guide wire and the vertical height deviation between the UAV and the guide wire can be obtained as follows: (36) (37) in, For the left and right deviation of the drone; This refers to the altitude deviation of the drone.

[0079] When the above error meets the set left and right deviation thresholds and height deviation threshold When the conditions are met (as in equation (38)), the UAV flies smoothly along the guide wire. When this condition is not met, the UAV hovers and adjusts its position to ensure that the guide wire is always in the center of the camera's field of view. The UAV control law is designed as shown in equation (39): (38) (39) in, To control the speed of the drone in the horizontal direction, The velocity proportional gain in the y-direction; To control the speed of the drone in the vertical direction, The velocity proportional gain in the z-direction; Through the above steps, the UAV is controlled to maintain the optimal observation distance and angle with the ground wire, ultimately achieving parallel, equidistant, and stable adaptive engagement flight along the ground wire.

[0080] The drone can complete the task autonomously using the above method. to After all lines have been inspected or the drone's safe return-to-base strategy has been triggered, the inspection mission for this flight of conductor and ground wire lines will end, and the drone will automatically return to the airport.

[0081] As one implementation method, when performing a combined inspection task of towers and conductors, the following steps are performed: When an inspection task is issued, the coordinates of the pole / tower are included. After receiving the task, the drone first flies to the pole / tower. The system uses visual recognition and drone posture adjustment to perform adaptive inspection of tower components, and then flies to the tower. The system performs autonomous inspections of the tower components. During the inspection, it collects information on crossarm mounting points and conductors, and uses this information to control a drone to complete the tower inspection. and towers Inspect the conductors and ground wires between them.

[0082] Further, the towers will be constructed. Component inspection and tower and towers The inspection of conductors and ground wires is carried out sequentially until the last tower is completed. and ground wire After the combined inspection mission is completed, the drone autonomously returns to the airport; if the drone safety policy is triggered during the inspection mission, the current inspection mission will be terminated and the drone will automatically return to the airport to ensure the drone's flight safety.

[0083] Step S3: After the drone inspection mission is completed, the image data is transmitted back to the airport's back-end control system. The image data is processed according to the mission type, and AI algorithms are used to identify the relevant targets of the towers and conductors and identify defects. After the identification is completed, an intelligent analysis report is automatically generated and alarm prompts are given for the defects of the relevant targets.

[0084] Example 2 In one or more embodiments, an airport power transmission line unmanned aerial vehicle (UAV) autonomous inspection system is disclosed, including an airport control system, an airport, a UAV, and the following modules: The task receiving module is configured such that: after receiving the inspection task, the UAV takes off and flies to the top of the target tower according to the latitude and longitude information of the tower in the inspection task; the inspection task includes tower inspection task, conductor and ground wire line inspection task, and combined tower and conductor and ground wire inspection task. The pole inspection module is configured to: acquire the target pole and component bounding box through a visual recognition algorithm, determine the center of the key inspection target image of the pole based on the bounding box, acquire the spatial position based on the center of the key inspection target image of the pole, design a control law according to the spatial position, and complete the pole inspection task. The conductor inspection module is configured to: obtain the starting point of the target conductor and ground wire through a visual recognition algorithm; obtain the UAV's simulated line spatial coordinates by fitting the conductor with a segmented catenary; determine the UAV's left and right deviations, altitude deviations, and heading angle deviations based on the simulated line spatial coordinates and the UAV's current position; design the UAV's control law; and complete the conductor and ground wire line inspection task.

[0085] It also includes a combined inspection module, which is configured to include the tower coordinates when an inspection task is issued. After receiving the task, the drone first flies to the tower. The tower inspection is completed above, then the aircraft flies to the tower. The above-ground personnel will conduct pole and tower inspections; during the inspections, they will collect information on crossarm attachment points and conductors, and use the collected information to control a drone to complete the pole and tower inspections. and towers Inspection of the conductors and ground wires between them; Then, proceed with the tower construction. Inspection and tower and towers The inspection of conductors and ground wires is carried out sequentially until the last tower is completed. and ground wire Afterwards, the inspection task of the tower and conductor / ground wire combination is completed.

[0086] In the task receiving module, the UAV takes off after receiving the inspection task and flies to the top of the target tower according to the latitude and longitude information of the tower in the inspection task; the inspection task includes tower inspection task, conductor and ground wire line inspection task, and tower and conductor and ground wire combined inspection task.

[0087] First, inspection tasks are created and sent to the target airport through the airport control system. The inspection tasks can be selected as single tower or line inspection tasks, or a combination of tower and line continuous inspection tasks, depending on the actual operation needs.

[0088] Secondly, the target airport receives and analyzes the inspection tasks and forwards them to the drone.

[0089] The types of inspection tasks include pole and tower inspection tasks, conductor and ground wire line inspection tasks, and combined pole and tower and conductor and ground wire inspection tasks.

[0090] Furthermore, the set of tasks issued will be denoted as... If the task type is pole inspection without a flight path, it is recorded as... ,in, This refers to the number of towers; if the task type is conductor and ground wire inspection without a flight path... ,in, The number of lines; if the task type is a combination of pole inspection and conductor / ground wire inspection without a route, it is denoted as ,in, This refers to the number of towers in the combined task.

[0091] Depending on the inspection task, the drone can perform the inspection task through the tower inspection module, the conductor inspection module, or a combination of inspection modules.

[0092] After receiving the mission, the drone begins a self-check. Once the self-check is successful, the drone takes off and, based on the target location in the mission information, autonomously flies to the target tower or conductor to begin intelligent inspection operations. It detects and identifies tower components through continuous video frames or calculates the drone's real-time position information, controls the drone's real-time movement, and completes tower target detection or controls the drone's wire engagement flight.

[0093] As one implementation method, when performing a pole inspection task, the pole inspection module executes the following process: After takeoff, the drone flies to the top of the target tower based on the latitude and longitude information of the tower in the mission, and obtains the bounding box of the tower and related components through a visual recognition algorithm.

[0094] It should be understood that visual recognition algorithms can use the YOLO series of algorithms to train the YOLO model to recognize various targets on power transmission lines.

[0095] After the drone flies above the tower, it detects key inspection target components of the tower in real time through continuous frame detection, and extracts the center point position and the bounding box of the target detection rectangle. .

[0096] The positional relationship between image pixels and the camera coordinate system can be obtained using the camera imaging model, as shown below: (1) in, This is the origin of the image coordinate system, i.e., the center point of the image; , For camera focal length, This provides the three-dimensional coordinate information of the UAV's world coordinate system, which adopts the East-North-Sky coordinate system. The coordinates are in the image coordinate system. It is a rotation matrix; This is the position offset matrix; It is a zero matrix.

[0097] Furthermore, after identifying and outlining the target tower, the center of the target outline, i.e., the center of the image of the key inspection target component of the tower, is as follows: (2) (3) in,( , () is the image center of the key inspection target component of the tower.

[0098] Based on the coordinate deviation between the center point of the image of the key inspection target component of the tower and the center point of the image, as shown in equations (4)-(5), the horizontal control quantity of the UAV is designed, as shown in equations (6)-(7). The left and right positions of the UAV are adjusted to ensure that the crossarm of the tower is in the middle of the image field of view. When the deviation between the center position of the target component and the center position of the image is less than the set threshold, as shown in equations (8)-(9), the UAV is controlled to hover and then guided to land at the preset safe height. The pixel position deviation and control quantity of the UAV are defined as follows: (4) (5) (6) (7) (8) (9) in,( , () represents the coordinate deviation; for Directional control of drone speed (drone in image pixel coordinate system). for Directional speed control parameters for UAVs (UAVs in image pixel coordinate system); for Directional drone speed control for Directional drone speed control parameters; for The pixel deviation between the image center position and the image center position of the directional target component. for The pixel deviation between the center position of the target component in the image and the center position of the image.

[0099] Based on the aforementioned camera imaging model, the three-dimensional spatial vector of the UAV in the world coordinate system can be obtained. Using UTM projection, a local Cartesian coordinate system with the tower center as the origin can be established. Through coordinate transformation, the spatial positioning of the UAV can be achieved. Let the global UTM coordinates of the tower center point be... This is obtained from drone positioning data. Therefore, for any point in the world coordinate system... : (10) (11) (12) in, The tower is offset eastward from its east side. The tower is offset northward from its north side. This represents the vertical offset of the tower (above the top of the tower). To facilitate UAV flight control, it is converted to North-East coordinates, then: (13) The drone is used to take images of the top of the tower from different horizontal positions at the same elevation, and the tower height is calculated using parallax. The tower height is calculated as follows: (14) in, The horizontal distance between the two shooting positions. , For camera tilt angle, This is the elevation value of the camera. This is the elevation value of the bottom of the tower.

[0100] Based on the tower height obtained above, guide the drone to land at a certain height above the tower. In actual use, the landing height above the tower will vary depending on the tower type. Generally, the value is the sum of the tower height and the safety experience value. Throughout the process, ensure that the tower is always in the center of the field of vision and record the latitude, longitude and altitude information of the drone when it reaches the position. Record this point information as the starting point of the tower inspection route. After the inspection of all tower components is completed, the tower inspection route is generated.

[0101] Based on the conversion relationship between image pixels and three-dimensional space established by the above camera imaging model, the spatial location information of feature points of key inspection target components of the tower and the three-dimensional coordinates of the UAV are calculated. The key inspection target components of the tower include, but are not limited to, insulator strings, crossarms, and hanging points.

[0102] Assuming the tower has N critical inspection components, then: (15) in, For the first Eastward coordinates of the UTM of each inspection component; For the first The north-facing coordinates of the UTM of each inspected component; For the first The absolute altitude of each inspection component is calculated from the UTM elevation and the relative height of the tower. , This refers to the height of the component relative to the tower base.

[0103] To ensure inspection safety, the drone is controlled to deviate horizontally from the key components of the tower. Vertical relative height of the component Hover over the location. Generate the desired inspection points for the drone according to the above requirements. ,but: (16) in, Let be the UTM coordinates of the k-th component. The expected inspection point of the UAV corresponding to the kth component can be connected in series to form the inspection route of the UAV. The horizontal normal vector is the unit vector in the direction in which the UAV deflects towards the side of the tower. The vertical offset of the camera relative to the components; The horizontal azimuth angle of the component; The horizontal safe inspection distance between the drone and the inspection target.

[0104] Define the real-time UTM coordinates of the UAV as The current desired waypoint is The positional deviation is calculated as follows: (17) in, Due to the positional deviation of the eastward-facing drone, Due to the positional deviation of the northbound drone, This refers to the vertical positional deviation of the UAV.

[0105] The real-time heading angle of the drone is The heading deviation is as follows: (18) in, The desired heading angle for the drone camera.

[0106] Based on the position deviation and heading angle deviation between the real-time position calculation and the desired position obtained by the UAV, the UAV control law is designed.

[0107] Then, based on the above error design control law, the northeast-direction speed control design is as follows: (19) (20) in, For the eastward speed of the drone, For proportional gain, For integral gain, This is the differential gain; For the northbound speed of the drone, For proportional gain, For integral gain, This is the differential gain.

[0108] The vertical speed control design is as follows: (twenty one) in, Let the vertical velocity of the UAV be in the North-East-Earth coordinate system. For proportional gain, For integral gain, This is the differential gain.

[0109] The yaw rate control design is as follows: (twenty two) in, Angular velocity is the yaw angle. Yaw rate proportional gain The integral gain of yaw rate. This is the differential gain of the yaw rate.

[0110] Control the drone to fly on one side of the tower and detect key components of the tower in real time (crossarm hanging point, conductor hanging point, insulator string, etc.). By identifying key components and following the above steps, control the drone to reach the vicinity of the key components. When all errors are less than the set threshold, as shown in formula (23), the drone reaches the effective shooting area of ​​the inspection and controls the drone to hover.

[0111] (twenty three) in, The permissible error threshold in the horizontal direction; The vertical error threshold is given by the subscript U, which represents the UAV in the North-East-Ground coordinate system. This is the allowable error threshold for the heading angle.

[0112] After the drone hovers, it identifies key components and obtains the pixel coordinates of the identification detection box of the components. Following the steps above (Equations (1)-(9)), it adjusts the position of the drone or the angle of the camera gimbal to ensure that the key component target is in the center of the camera's field of view.

[0113] When the above conditions are met, and the drone is within a safe distance and reaches the set shooting interval, the MSDK triggers automatic control of the drone camera to take pictures of the inspection target, achieving accurate photography of the tower target and recording the latitude, longitude, and elevation information of the photographed point. Based on the visual recognition results and position calculation information (including tower structure - crossarm, hanging point, etc.), the position information of the drone hovering and taking pictures obtained by the above spatial position calculation is combined with the point information of the inspection target, including the three-dimensional coordinates of the tower components, the gimbal angle when the camera takes pictures, the drone position information, etc. During the autonomous inspection, the latitude and longitude coordinates of all hovering points of the drone at key components are recorded sequentially. After the inspection is completed, the inspection route is automatically generated according to the prescribed route format.

[0114] According to the above steps, when the tower After the inspection is completed, the drone is controlled to fly to the lower pole based on the latitude and longitude coordinates of the pole issued by the backend. Repeat the above steps to complete the tower. Key component inspection and flight path generation, then guide the drone to automatically fly to the lower base tower. This enables continuous tower inspection operations and route generation.

[0115] When the tower When the inspection is completed or the drone triggers the safety policy, the drone autonomously returns to the airport and transmits the collected image data and generated flight path files back to the back-end management system.

[0116] When conducting the above-mentioned pole inspection operations again, in addition to the above methods, the inspection task can also be sent directly to the target airport using the generated flight path. The drone will not need to identify the pole target and control its motion again, which can effectively reduce the power consumption of the drone and improve the inspection efficiency.

[0117] As one implementation method, when performing tower inspection tasks, the conductor inspection module executes the following process: When the conductor inspection task is issued, the coordinate information of the towers at both ends of the conductor is included. After the drone takes off autonomously from the airport, it flies to the tower at the beginning of the conductor. Above, a visual recognition algorithm is used to identify the crossarm attachment point of the tower to determine the starting point of the conductor and the flight direction of the drone.

[0118] Define point A of tower as and point B of tower as . Establish the analytical equation of the three-dimensional catenary : (twenty four) in, This is the arc length parameter of the conductor, which is the horizontal distance starting from point A. The horizontal azimuth of the line. , The height of the hanging points at both ends of the conductor. The height difference between the two hanging points. For conductor span, This is the catenary coefficient.

[0119] Based on the catenary equation and the sag formula, a piecewise catenary is used to fit the three-dimensional traverse. That is, the entire traverse is evenly divided into M segments, and M+1 points are obtained as waypoints for UAV inspection. Then, the three-dimensional coordinates of each point can be obtained by fitting the catenary to each traverse segment. , , ): (25) (26) (27) in, For the first The horizontal position of each segment point Let M be the step length of the conductor for each segment.

[0120] The desired UAV linear coordinates are generated based on the above catenary equation. ,but: (28) in, This refers to the constant horizontal distance of the drone when it flies alongside the guide wire. is the unit vector along the horizontal tangent direction of the conductor.

[0121] Record the current position of the drone as The drone's left-right (i.e., horizontal) position deviation Vertical height deviation Heading deviation The calculation is as follows: (29) in, The tangent direction angle of the conductor. This provides the real-time heading angle for the drone.

[0122] Based on the aforementioned left-right deviation, altitude deviation, and heading angle deviation of the UAV, a control law for the UAV is designed, yielding the forward velocity, lateral velocity, vertical velocity, and yaw rate of the UAV along the guide line. The specific calculations are as follows: (30) (31) (32) (33) in, For the forward speed of the drone, For the drone's lateral speed, For the vertical speed of the drone, These are the yaw rate of the drone; The drone's set speed; The proportional gain of the UAV in the y-direction, The integral gain in the y-direction. The differential gain in the y-direction; The proportional gain in the z-direction, The integral gain in the z-direction. The differential gain in the z-direction; These are the yaw angle proportional gains; These are the integral gains of the yaw angle, respectively. This is the differential gain for the yaw angle.

[0123] During UAV flight, the guide wire target is detected in real time through continuous frame detection, and the target bounding box and center point position are extracted. Based on the camera imaging model mentioned above, the relationship between image pixels and camera coordinate system points can be obtained: (34) (35) in, For camera coordinate system coordinates, These are the coordinates in the camera coordinate system.

[0124] Based on the relationship between the image pixel coordinate system and the camera coordinate system, the horizontal distance from the aircraft camera to the guide wire and the vertical height deviation between the UAV and the guide wire can be obtained as follows: (36) (37) in, For the left and right deviation of the drone; This refers to the altitude deviation of the drone.

[0125] When the above error meets the set left and right deviation thresholds and height deviation threshold When the conditions are met (as in equation (38)), the UAV flies smoothly along the guide wire. When this condition is not met, the UAV hovers and adjusts its position to ensure that the guide wire is always in the center of the camera's field of view. The UAV control law is designed as shown in equation (39): (38) (39) in, To control the speed of the drone in the horizontal direction, The velocity proportional gain in the y-direction; To control the speed of the drone in the vertical direction, The velocity proportional gain in the z-direction; Through the above steps, the UAV is controlled to maintain the optimal observation distance and angle with the ground wire, ultimately achieving parallel, equidistant, and stable adaptive engagement flight along the ground wire.

[0126] The drone can complete the task autonomously using the above method. to After all lines have been inspected or the drone's safe return-to-base strategy has been triggered, the inspection mission for this flight of conductor and ground wire lines will end, and the drone will automatically return to the airport.

[0127] As one implementation method, when performing a combined inspection task of towers and conductors, the combined inspection module executes the following process: When an inspection task is issued, the coordinates of the pole / tower are included. After receiving the task, the drone first flies to the pole / tower. The system uses visual recognition and drone posture adjustment to perform adaptive inspection of tower components, and then flies to the tower. The system performs autonomous inspections of the tower components. During the inspection, it collects information on crossarm mounting points and conductors, and uses this information to control a drone to complete the tower inspection. and towers Inspect the conductors and ground wires between them.

[0128] Further, the towers will be constructed. Component inspection and tower and towers The inspection of conductors and ground wires is carried out sequentially until the last tower is completed. and ground wire After the combined inspection mission is completed, the drone autonomously returns to the airport; if the drone safety policy is triggered during the inspection mission, the current inspection mission will be terminated and the drone will automatically return to the airport to ensure the drone's flight safety.

[0129] Finally, after the drone inspection mission is completed, the image data is transmitted back to the airport's back-end control system. The image data is processed according to the mission type, and AI algorithms are used to identify and detect defects in the relevant targets such as towers and conductors. After the identification is completed, an intelligent analysis report is automatically generated and alarm prompts are issued for the defects of the relevant targets.

[0130] Example 3 This embodiment provides an electronic device, including a memory and a processor, as well as computer instructions stored in the memory and running on the processor. When the computer instructions are executed by the processor, they complete the steps of the above-mentioned method for autonomous inspection of airport power transmission lines by UAVs.

[0131] Example 4 This embodiment provides a computer-readable storage medium for storing computer instructions, which, when executed by a processor, complete the steps of the above-described method for autonomous inspection of airport power transmission lines by unmanned aerial vehicles.

[0132] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0133] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0134] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment, whereby a series of operational steps are performed to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0135] The descriptions of each embodiment in the above embodiments have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0136] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for autonomous inspection of airport power transmission lines by unmanned aerial vehicles (UAVs), characterized in that, include: After receiving the inspection mission, the drone takes off and flies to the top of the target tower based on the latitude and longitude information of the tower in the inspection mission. The inspection tasks include pole and tower inspection tasks, conductor and ground wire line inspection tasks, and pole and tower and conductor and ground wire combined inspection tasks. Specifically, the target tower and component boundary boxes are obtained through a visual recognition algorithm, the center of the key inspection target image of the tower is determined based on the boundary boxes, the spatial position is obtained based on the center of the key inspection target image of the tower, and a control law is designed according to the spatial position to complete the tower inspection task. The starting point of the target conductor is obtained by visual recognition algorithm. The conductor is fitted with a segmented catenary to obtain the UAV’s simulated line spatial coordinates. Based on the simulated line spatial coordinates and the current position of the UAV, the left and right deviations, altitude deviations and heading angle deviations of the UAV are determined and the UAV control law is designed to complete the conductor line inspection task.

2. The method for autonomous inspection of airport power transmission lines by unmanned aerial vehicles as described in claim 1, characterized in that, The spatial position is obtained based on the center of the key inspection target image of the tower, and the calculation process is as follows: in, Let K be the expected inspection point of the UAV corresponding to the k-th component. The coordinates of the current desired waypoint. Let be the UTM coordinates of the k-th component. The vertical offset of the camera relative to the components; The horizontal azimuth angle of the component; The horizontal safe inspection distance between the drone and the inspection target; Position deviation is calculated by subtracting the UAV’s current expected target waypoint coordinates from its real-time UTM coordinates; The heading deviation is the difference between the expected heading angle and the real-time heading angle of the UAV camera.

3. The method for autonomous inspection of airport power transmission lines by unmanned aerial vehicles as described in claim 2, characterized in that, The control law is designed based on the aforementioned spatial location, specifically as follows: Based on the error design control law, the northeast-bound speed control design is as follows: in, For the eastward speed of the drone, For proportional gain, For integral gain, This is the differential gain; For the northbound speed of the drone, For proportional gain, For integral gain, This is the differential gain; The vertical speed control design is as follows: in, The vertical velocity of the drone. For proportional gain, For integral gain, This is the differential gain; The yaw rate control design is as follows: in, Angular velocity is the yaw angle. Yaw rate proportional gain The integral gain of yaw rate. This is the differential gain of the yaw rate.

4. The method for autonomous inspection of airport power transmission lines by unmanned aerial vehicles as described in claim 1, characterized in that, The process of fitting the traverse with a segmented catenary to obtain the UAV's spatial coordinates for the traverse includes: fitting the three-dimensional traverse with a segmented catenary based on the catenary equation and the traverse sag formula, that is, dividing the entire traverse into M segments, obtaining M+1 points as waypoints for UAV inspection, and then fitting each traverse segment with a catenary to obtain the three-dimensional coordinates of each point. , , ): in, For the first The horizontal position of each segment point Let M be the step lengths of the conductor segments. Here are the coordinates of point A on the tower. Here are the coordinates of point B on the tower. The horizontal azimuth of the line. The height difference between the two hanging points. For conductor span, Let M be the catenary coefficient, and M be the number of segments into which the conductor is evenly divided.

5. The method for autonomous inspection of airport power transmission lines by unmanned aerial vehicles as described in claim 4, characterized in that, Based on the catenary curve, the desired UAV linear coordinates are generated, then: in, For the desired UAV line-space coordinates, The analytical equation for a three-dimensional catenary is given. This refers to the constant horizontal distance of the drone when it flies alongside the guide wire. is the unit vector along the horizontal tangent direction of the conductor.

6. The method for autonomous inspection of airport power transmission lines by unmanned aerial vehicles as described in claim 1, characterized in that, In the aforementioned conductor line inspection task, the UAV control law is designed based on the UAV's left-right deviation, altitude deviation, and heading angle deviation. The forward velocity, lateral velocity, vertical velocity, and yaw rate of the UAV along the conductor direction are obtained, and the specific calculations are as follows: in, For the forward speed of the drone, For the drone's lateral speed, For the vertical speed of the drone, These are the yaw rate of the drone; The drone's set speed; The proportional gain of the UAV in the y-direction, The integral gain in the y-direction. The differential gain in the y-direction; The proportional gain in the z-direction, The integral gain in the z-direction. The differential gain in the z-direction; These are the yaw angle proportional gains; These are the integral gains of the yaw angle, respectively. This is the differential gain for the yaw angle.

7. The method for autonomous inspection of airport power transmission lines by unmanned aerial vehicles as described in claim 1, characterized in that, When an inspection task is issued, the coordinates of the pole / tower are included. After receiving the task, the drone first flies to the pole / tower. The tower inspection was completed above, and then the aircraft flew to the tower. The above-ground personnel will conduct pole and tower inspections; during the inspections, they will collect information on crossarm attachment points and conductors, and use the collected information to control a drone to complete the pole and tower inspections. and towers Inspection of the conductors and ground wires between them; Then, proceed with the tower construction. Inspection and tower and towers The inspection of conductors and ground wires is carried out sequentially until the last tower is completed. and ground wire Afterwards, the inspection task of the tower and conductor / ground wire combination is completed.

8. An autonomous unmanned aerial vehicle (UAV) inspection system for airport power transmission lines, characterized in that, include: The task receiving module is configured such that: after receiving the inspection task, the UAV takes off and flies to the top of the target tower according to the latitude and longitude information of the tower in the inspection task; The inspection tasks include pole and tower inspection tasks, conductor and ground wire line inspection tasks, and pole and tower and conductor and ground wire combined inspection tasks. The pole inspection module is configured to: acquire the target pole and component bounding box through a visual recognition algorithm, determine the center of the key inspection target image of the pole based on the bounding box, acquire the spatial position based on the center of the key inspection target image of the pole, design a control law according to the spatial position, and complete the pole inspection task. The conductor inspection module is configured to: obtain the starting point of the target conductor and ground wire through a visual recognition algorithm; obtain the UAV's simulated line spatial coordinates by fitting the conductor with a segmented catenary; determine the UAV's left and right deviations, altitude deviations, and heading angle deviations based on the simulated line spatial coordinates and the UAV's current position; design the UAV's control law; and complete the conductor and ground wire line inspection task.

9. An electronic device, characterized in that, The method includes a memory and a processor, as well as computer instructions stored in the memory and running on the processor. When the processor executes the computer instructions, it completes the autonomous inspection method for airport power transmission lines by unmanned aerial vehicles as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, Used to store computer instructions, which, when executed by a processor, complete the unmanned aerial vehicle (UAV) autonomous inspection method for airport power transmission lines as described in any one of claims 1-7.

Images