Clustered unmanned aerial vehicle inspection method based on power transmission line and related equipment

Abstract

The application relates to the technical field of electric power inspection, and discloses a cluster type unmanned aerial vehicle inspection method based on a power transmission line and related equipment. The method comprises the following steps: obtaining a three-dimensional laser point cloud model of a target power transmission line and sensing parameters of each unmanned aerial vehicle, extracting each inspection space information and a plurality of inspection points in the three-dimensional laser point cloud model, and generating an inspection tower directory tree; performing geographic coordinate conversion on each inspection point in the inspection tower directory tree to obtain a plurality of inspection point coordinates, and calculating sensing values of each unmanned aerial vehicle based on the sensing parameters of each unmanned aerial vehicle; matching corresponding inspection point coordinates based on the sensing values, and generating corresponding route inspection lines of each unmanned aerial vehicle according to the matching results; and controlling each unmanned aerial vehicle to form an unmanned aerial vehicle cluster to inspect each inspection point according to the route inspection lines, so that inspection data is obtained. The application realizes efficient cluster type unmanned aerial vehicle inspection of a power transmission line.

Description

Technical Field

[0001] This invention relates to the field of power line inspection technology, and in particular to a cluster-based unmanned aerial vehicle (UAV) inspection method and related equipment for power transmission lines. Background Technology

[0002] With the rapid development of my country's economy, the scale and structure of the power transmission network are becoming increasingly large and complex, with a growing number of high-grade, long-distance, and large-capacity transmission lines. Because these transmission lines are widely distributed, mostly far from urban areas, and in generally harsh environments, they are inevitably susceptible to damage. Failure to detect and address problems promptly can pose a significant threat to the stable operation of these lines. Therefore, routine inspections of transmission lines are necessary. Using drones for inspections can not only reduce inspection costs but also minimize losses caused by line faults, ensuring the normal operation of transmission lines.

[0003] Currently, the method of drone power line inspection is relatively simple, and it still mainly relies on manual operation of drones by personnel to carry out inspections, thereby ensuring the safe operation of transmission lines. However, this inspection method is greatly affected by factors such as the operator's experience, skill level, and sudden environmental changes. It has problems such as a single inspection control mode, large interference of control signals, and low operating efficiency. In other words, the existing drones have poor automatic inspection effect on transmission lines. Summary of the Invention

[0004] The main objective of this invention is to solve the problem that existing drones have poor automatic inspection capabilities for power transmission lines.

[0005] The first aspect of this invention provides a cluster-based UAV inspection method for power transmission lines, the method comprising:

[0006] A three-dimensional laser point cloud model of the target transmission line and the sensing parameters of each UAV are acquired. Inspection spatial information and multiple inspection points are extracted from the three-dimensional laser point cloud model to generate an inspection tower directory tree. Geographic coordinate transformation is performed on each inspection point in the inspection tower directory tree to obtain multiple inspection point coordinates. The sensing values ​​of each UAV are calculated based on its sensing parameters. The corresponding inspection point coordinates are matched based on the sensing values, and an inspection route corresponding to each UAV is generated according to the matching results. Based on the inspection route, the UAVs are controlled to form a UAV swarm to inspect each inspection point, obtaining inspection data.

[0007] Optionally, in a first implementation of the first aspect of the present invention, the step of extracting various inspection space information and multiple inspection points from the three-dimensional laser point cloud model to generate an inspection tower directory tree includes: extracting laser point cloud data, line coordinate data, multiple inspection tower information, and multiple inspection points from the three-dimensional laser point cloud model; classifying the laser point cloud data based on the inspection tower information; matching the corresponding line coordinate data according to the classified laser point cloud data, and generating an inspection tower directory tree according to the matching result and the inspection priority in the inspection tower information.

[0008] Optionally, in a second implementation of the first aspect of the present invention, the step of performing geographic coordinate transformation on each of the inspection points in the inspection pole directory tree to obtain multiple inspection point coordinates, and calculating the sensor values ​​of each of the drones based on the sensor parameters of each drone, includes: extracting multiple inspection item information from the inspection pole directory tree, and performing coordinate transformation on each of the inspection item information according to the inspection pole directory tree to obtain initial inspection coordinates; performing adaptive coordinate optimization on the initial inspection coordinates to obtain multiple inspection point coordinates; classifying the sensor parameters of each drone by sensor type, and using a preset parameter value conversion table to perform parameter value conversion on the classification results to obtain multiple sensor values ​​of each drone.

[0009] Optionally, in a third implementation of the first aspect of the present invention, the step of matching the corresponding inspection point coordinates based on each of the sensor values ​​and generating the corresponding flight path inspection route for each of the UAVs according to the matching result includes: numerically combining each of the sensor values ​​and matching the inspection point coordinates corresponding to each of the UAVs according to the combination result; extracting the parking point coordinate information and the inspection classification information corresponding to the pole directory tree from the three-dimensional laser point cloud model, and connecting the inspection coordinate points corresponding to each of the UAVs according to the inspection classification information based on the result of matching the inspection point coordinates of the parking point coordinate information, thereby obtaining the corresponding flight path inspection route for each of the UAVs.

[0010] Optionally, in a fourth implementation of the first aspect of the present invention, the step of controlling each of the UAVs to form a UAV swarm to inspect each of the inspection points according to the flight path inspection route and obtaining inspection data includes: using the three-dimensional laser point cloud model to perform model flight optimization on the flight path inspection route of each of the UAVs; controlling each of the UAVs to form a UAV swarm according to the optimized flight path inspection route; and controlling the UAV swarm to inspect each of the inspection points and obtain inspection data.

[0011] Optionally, in the fifth implementation of the first aspect of the present invention, before controlling each of the UAVs to form a UAV cluster to inspect each of the inspection points according to the inspection route and obtaining inspection data, the method further includes: obtaining the control terminal information and control center information corresponding to the UAVs, and performing sequence marking on each of the UAVs, the control terminal and the control center to generate a corresponding initial inspection ad hoc network; and performing differential correction binding on the inspection point coordinates of the UAVs in the inspection ad hoc network based on the inspection route to obtain the final inspection ad hoc network.

[0012] Optionally, in a sixth implementation of the first aspect of the present invention, after controlling the drones to form a drone swarm to inspect each inspection point according to the flight path inspection route and obtaining inspection data, the method further includes: acquiring historical loss information of each drone, and performing nonlinear adaptive estimation on the historical loss information and the inspection data to obtain the efficiency loss coefficient of each drone; calculating the composite compensation parameter of each drone in the drone swarm according to the efficiency loss coefficient; adjusting the flight path inspection route of the drone swarm during inspection using the composite compensation parameter, and controlling the drone swarm to complete the inspection of each inspection point based on the adjustment result.

[0013] A second aspect of the present invention provides a cluster-type UAV inspection device based on power transmission lines, comprising: a point cloud extraction module, used to acquire a three-dimensional laser point cloud model of the target power transmission line and the sensing parameters of each UAV, and extract various inspection spatial information and multiple inspection points from the three-dimensional laser point cloud model to generate an inspection tower directory tree; a parameter conversion module, used to perform geographic coordinate conversion on each inspection point in the inspection tower directory tree to obtain multiple inspection point coordinates, and calculate the sensing value of each UAV based on the sensing parameters of each UAV; a coordinate matching module, used to match the corresponding inspection point coordinates based on each sensing value, and generate a corresponding flight path inspection route for each UAV according to the matching result; and a line inspection module, used to control each UAV to form a UAV cluster to inspect each inspection point according to the flight path inspection route, and obtain inspection data.

[0014] Optionally, in a first implementation of the second aspect of the present invention, the point cloud extraction module includes: a data extraction unit, used to extract laser point cloud data, line coordinate data, multiple inspection tower information, and multiple inspection points from the three-dimensional laser point cloud model; a data classification unit, used to classify the laser point cloud data based on the inspection tower information; and a directory establishment unit, used to match the corresponding line coordinate data with the classified laser point cloud data, and generate an inspection tower directory tree based on the matching result and the inspection priority in the inspection tower information.

[0015] Optionally, in a second implementation of the second aspect of the present invention, the parameter conversion module includes: a coordinate conversion unit, used to extract multiple inspection item information from the inspection tower directory tree, and perform coordinate conversion on each of the inspection item information according to the inspection tower directory tree to obtain initial inspection coordinates; a coordinate optimization unit, used to perform adaptive coordinate optimization on the initial inspection coordinates to obtain multiple inspection point coordinates; and a numerical conversion unit, used to classify the sensing parameters of each UAV by sensing type, and use a preset parameter numerical conversion table to perform parameter numerical conversion on the classification result to obtain multiple sensing values ​​of each UAV.

[0016] Optionally, in a third implementation of the second aspect of the present invention, the coordinate matching module includes: a numerical combination unit, used to perform numerical combination on each of the sensor values, and match the inspection point coordinates corresponding to each of the UAVs according to the combination result; and a flight path connection unit, used to extract the parking point coordinate information and the inspection classification information corresponding to the tower directory tree in the three-dimensional laser point cloud model, and connect the inspection coordinate points corresponding to each of the UAVs according to the inspection classification information based on the result of the parking point coordinate information and the inspection point coordinate matching result, to obtain the flight path inspection route corresponding to each of the UAVs.

[0017] Optionally, in a fourth implementation of the second aspect of the present invention, the route inspection module includes: a simulation optimization unit, used to perform model flight optimization on the route inspection lines of each of the UAVs using the three-dimensional laser point cloud model; a cluster formation unit, used to control the UAVs to form a UAV cluster according to the optimized route inspection lines; and an inspection and photography unit, used to control the UAV cluster to inspect each of the inspection points and obtain inspection data.

[0018] Optionally, in the fifth implementation of the second aspect of the present invention, before the route inspection module, a self-organizing network module is further included: an initial networking unit, used to obtain the control terminal information and control center information corresponding to the UAV, and to perform sequence marking on each UAV, the control terminal and the control center to generate a corresponding initial inspection self-organizing network; and a differential optimization unit, used to perform differential correction binding on the inspection point coordinates of the UAVs in the inspection self-organizing network based on the route inspection line to obtain the final inspection self-organizing network.

[0019] Optionally, in a sixth implementation of the second aspect of the present invention, after the route inspection module, an interference optimization module is further included: a coefficient calculation unit, used to acquire historical loss information of each UAV, and perform nonlinear adaptive estimation on the historical loss information and the inspection data to obtain the efficiency loss coefficient of each UAV; a parameter calculation unit, used to calculate the composite compensation parameter of each UAV in the UAV cluster based on the efficiency loss coefficient; and a parameter adjustment unit, used to adjust the route inspection line of the UAV cluster in the inspection using the composite compensation parameter, and control the UAV cluster to complete the inspection of each inspection point based on the adjustment result.

[0020] A third aspect of the present invention provides a clustered drone inspection device based on power transmission lines, comprising: a memory and at least one processor, wherein the memory stores instructions; the at least one processor invokes the instructions in the memory to cause the clustered drone inspection device based on power transmission lines to perform the various steps of the above-described clustered drone inspection method based on power transmission lines.

[0021] A fourth aspect of the present invention provides a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform the various steps of the above-described clustered UAV inspection method based on power transmission lines.

[0022] The technical solution provided by this invention involves acquiring a three-dimensional laser point cloud model of the target power transmission line and the sensing parameters of each UAV, extracting various inspection spatial information and multiple inspection points from the three-dimensional laser point cloud model, and generating an inspection tower directory tree. Geographic coordinate transformation is performed on each inspection point in the inspection tower directory tree to obtain multiple inspection point coordinates, and the sensing values ​​of each UAV are calculated based on the sensing parameters of each UAV. The corresponding inspection point coordinates are matched based on the sensing values, and a corresponding flight path inspection route for each UAV is generated according to the matching results. Based on the flight path inspection route, the UAVs are controlled to form a UAV swarm to inspect each inspection point, obtaining inspection data. Compared to existing technologies, this application utilizes a three-dimensional laser point cloud model to construct an inspection tower directory tree and convert it into corresponding inspection coordinates. Then, based on the sensing parameters of each UAV, the corresponding inspection coordinates are matched to generate flight path inspection routes for each UAV in the UAV swarm, and the corresponding UAVs are controlled to complete the inspection. This achieves the planning of flight paths for swarm-type UAVs to complete efficient inspection of power transmission lines. Attached Figure Description

[0023] Figure 1 This is a schematic diagram of the first embodiment of the clustered UAV inspection method based on power transmission lines in this invention.

[0024] Figure 2 This is a schematic diagram of the second embodiment of the clustered UAV inspection method based on power transmission lines in this invention.

[0025] Figure 3 This is a schematic diagram of an embodiment of a cluster-type unmanned aerial vehicle (UAV) inspection device based on power transmission lines according to the present invention;

[0026] Figure 4 This is a schematic diagram of another embodiment of the cluster-type UAV inspection device based on power transmission lines in this invention.

[0027] Figure 5 This is a schematic diagram of an embodiment of a cluster-type drone inspection device based on power transmission lines in this invention. Detailed Implementation

[0028] This invention provides a method and related equipment for clustered UAV inspection of power transmission lines. The method includes: acquiring a three-dimensional laser point cloud model of the target power transmission line and the sensing parameters of each UAV; extracting spatial information and multiple inspection points from the three-dimensional laser point cloud model to generate an inspection tower directory tree; performing geographic coordinate transformation on each inspection point in the inspection tower directory tree to obtain multiple inspection point coordinates, and calculating the sensing values ​​of each UAV based on its sensing parameters; matching the corresponding inspection point coordinates based on the sensing values, and generating corresponding flight path inspection routes for each UAV based on the matching results; and controlling the UAVs to form a UAV cluster to inspect each inspection point according to the flight path inspection routes, thereby obtaining inspection data. This invention achieves efficient inspection of power transmission lines using clustered UAVs.

[0029] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” or “having,” and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0030] For ease of understanding, the specific process of the embodiments of the present invention is described below. Please refer to [link / reference]. Figure 1 The first embodiment of the cluster-based UAV inspection method for power transmission lines in this invention includes:

[0031] 101. Obtain the three-dimensional laser point cloud model of the target transmission line and the sensing parameters of each UAV, and extract the inspection space information and multiple inspection points from the three-dimensional laser point cloud model to generate an inspection tower directory tree.

[0032] The embodiments of this application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence (AI) refers to the theories, methods, technologies, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0033] Foundational technologies in artificial intelligence generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, operating / interactive systems, and mechatronics. AI software technologies mainly encompass computer vision, robotics, biometrics, speech processing, natural language processing, and machine learning / deep learning.

[0034] In this embodiment, laser point cloud data, line coordinate data, multiple inspection tower information, and multiple inspection points are extracted from the three-dimensional laser point cloud model. Then, based on the information of each inspection tower, the laser point cloud data is classified. Based on the classified laser point cloud data, the corresponding line coordinate data is matched, and an inspection tower directory tree is generated according to the matching results and the inspection priority in the inspection tower information.

[0035] Here, the 3D laser point cloud model refers to the precise measurement of the distances from various features (especially trees, houses, and crossings) to the conductors in the transmission line corridor by synchronously constructing a 3D digital model of the corridor, ensuring that the distances meet safety operation requirements. A high-precision 3D point cloud model of the corridor is then acquired using lidar, providing centimeter-level precision 3D point cloud maps for fully autonomous UAV inspections. The laser point cloud data refers to a set of vectors in a 3D coordinate system, sometimes including color information, reflection intensity information, and echo count information. The line coordinate data refers to the simulated inspection coordinate data in the 3D laser point cloud model. The tower inspection information refers to the information on key components such as ground wire attachment points and insulator strings on the tower to be inspected. The inspection priority refers to the classification of the importance of the components on the tower that require priority inspection and photography.

[0036] In practical applications, after data correction by calling a pre-built 3D laser point cloud model, laser point cloud data, line coordinate data, multiple inspection tower data, and inspection points are extracted from the 3D laser point cloud model. Then, based on the information of each inspection tower, the point cloud data is segmented by inspection tower, and the laser point cloud data is classified to obtain the laser point cloud data corresponding to each inspection tower. Then, based on the classified laser point cloud data, the line coordinate data of each inspection tower is matched, and based on the matching results and the inspection priority in the inspection tower information, the laser point cloud data and the line coordinate data in the inspection tower are precisely registered to form a tower directory tree.

[0037] 102. Perform geographic coordinate transformation on each inspection point in the inspection tower directory tree to obtain the coordinates of multiple inspection points, and calculate the sensor value of each UAV based on the sensor parameters of each UAV.

[0038] In this embodiment, multiple inspection item information is extracted from the inspection tower directory tree, and coordinate transformation is performed on each inspection item information according to the inspection tower directory tree to obtain initial inspection coordinates. Then, adaptive coordinate optimization is performed on the initial inspection coordinates to obtain multiple inspection point coordinates. Then, the sensing parameters of each UAV are classified by sensing type, and the classification results are converted by using a preset parameter value conversion table to obtain multiple sensing values ​​of each UAV.

[0039] The inspection item information here refers to the inspection items of the tower to be inspected, such as key components like ground wire hanging points and insulator strings; the parameter value conversion table here refers to the conversion table that can convert various parameters of the drone into corresponding numerical values ​​based on the key components and photo points being inspected; the sensor parameters here refer to information such as the drone's camera focal length, shooting distance, gimbal angle, drone model, flight time, and operation efficiency.

[0040] In practical applications, by extracting multiple inspection item information from the inspection tower directory tree, the inspection item information of each tower to be inspected in the inspection tower directory tree is converted into corresponding initial inspection coordinates. Then, the initial inspection coordinates are automatically identified to identify components with errors. The initial inspection coordinates are checked for coordinate errors using a 3D laser point cloud model, and manual assistance can be called to pick and optimize the initial inspection coordinates, thus obtaining multiple inspection point coordinates. Then, by acquiring parameters such as camera focal length, shooting distance, and gimbal angle of each UAV, based on the key components to be inspected and the photo points, and considering sensor parameters such as UAV model, flight time, and operation efficiency, the sensor parameter types of each UAV are classified. Then, the sensor parameters of different UAVs after classification are converted into corresponding parameter values ​​using a preset parameter value conversion table, resulting in multiple sensor values ​​for each UAV. For example, based on the UAV sensor parameters, the inspection photo points and flight assistance points of each UAV are converted into corresponding sensor values.

[0041] 103. Based on the coordinates of the corresponding inspection points matched by each sensor value, and based on the matching results, generate the corresponding flight path inspection route for each UAV.

[0042] In this embodiment, the sensor values ​​are combined, and the inspection point coordinates corresponding to each UAV are matched according to the combination result. The parking point coordinate information and the inspection classification information corresponding to the tower directory tree in the three-dimensional laser point cloud model are extracted. According to the parking point coordinate information and the inspection point coordinate matching result, the inspection coordinate points corresponding to each UAV are connected by the flight path according to the inspection classification information to obtain the flight path inspection route corresponding to each UAV.

[0043] The inspection classification information here refers to the classification information in the pole and tower directory tree; the parking point coordinate information here refers to the coordinate information of the drone's parking location.

[0044] In practical applications, based on the multiple sensor values ​​obtained from the above processing, the sensor values ​​corresponding to each UAV are combined by Cartesian product. Then, the optimal total sensor value is calculated from the result of the numerical combination, and the combination value is selected according to a preset sensor value range. Based on the combination result, the corresponding inspection point coordinate information is assigned using the sensor values ​​corresponding to each UAV. Then, the parking point coordinate information and the inspection classification information corresponding to the pole directory tree are extracted from the 3D laser point cloud model. According to the inspection classification information, the inspection coordinate points of each UAV are connected by flight paths. Based on the distance of each pole and the priority of the pole inspection items, the corresponding flight path inspection route for each UAV is determined.

[0045] 104. Based on the inspection route, control the various drones to form a drone swarm to inspect each inspection point and obtain inspection data.

[0046] In this embodiment, the flight path of each UAV is optimized by using a three-dimensional laser point cloud model; based on the optimized flight path, the UAVs are controlled to form a UAV cluster; the UAV cluster is controlled to inspect each inspection point to obtain inspection data.

[0047] The model flight optimization here refers to using a 3D laser point cloud model to conduct model flight tests, and adjusting and optimizing issues such as collisions and excessively close inspection photos encountered during the inspection. In addition, optimization can also be achieved through manual inspection by flight personnel.

[0048] In practical applications, based on the flight path inspection routes obtained from the above processing for each UAV, a 3D laser point cloud model is used to simulate and test the flight path inspection routes of each UAV. By simulating the situation of each UAV forming a UAV swarm for inspection in the spatial model, the system checks whether collisions will occur between UAVs and whether usable data can be detected. Based on this simulation data, the flight path inspection routes of each UAV are optimized accordingly, and waypoints that deviate from the actual flight path or pose safety hazards are fine-tuned. The order of waypoints can also be adjusted to avoid collisions between UAVs in the swarm. Alternatively, flight personnel can perform safety checks and verifications on the generated waypoints. The system allows for manual editing of generated waypoints, including adding or modifying flight aids. It also allows for fine-tuning of waypoints that deviate from the actual flight path or pose safety hazards, and adjusting the waypoint order. After previewing and confirming the final generated flight path and number of sorties through flight simulation, the optimized flight path is exported. Based on the optimized flight path, the system inspects the route coordinates (KML), tower model point cloud data packages, and flight path (JSON) data packages. The exported flight path data is then imported into the autonomous driving intelligent control systems of various UAVs to form a UAV swarm. This swarm then performs high-precision, intelligent, and refined inspections of tower inspection points according to the planned flight path, generating inspection data.

[0049] In this embodiment of the invention, a three-dimensional laser point cloud model of the target transmission line and the sensing parameters of each UAV are acquired. The spatial information of each inspection point and multiple inspection points in the three-dimensional laser point cloud model are extracted to generate an inspection tower directory tree. Geographic coordinate transformation is performed on each inspection point in the inspection tower directory tree to obtain multiple inspection point coordinates. The sensing values ​​of each UAV are calculated based on its sensing parameters. The corresponding inspection point coordinates are matched based on each sensing value, and a corresponding flight path inspection route for each UAV is generated according to the matching results. Based on the flight path inspection route, the UAVs are controlled to form a UAV swarm to inspect each inspection point, obtaining inspection data. Compared to existing technologies, this application utilizes a three-dimensional laser point cloud model to construct an inspection tower directory tree and convert it into corresponding inspection coordinates. Then, based on the sensing parameters of each UAV, the corresponding inspection coordinates are matched to generate flight path inspection routes for each UAV in the UAV swarm, and the corresponding UAVs are controlled to complete the inspection. This achieves the planning of flight paths for swarm-type UAVs to complete efficient inspection of transmission lines.

[0050] Please see Figure 2 The second embodiment of the cluster-based UAV inspection method for power transmission lines in this invention includes:

[0051] 201. Obtain the three-dimensional laser point cloud model of the target transmission line and the sensing parameters of each UAV, and extract the inspection space information and multiple inspection points from the three-dimensional laser point cloud model to generate an inspection tower directory tree.

[0052] 202. Perform geographic coordinate transformation on each inspection point in the inspection tower directory tree to obtain the coordinates of multiple inspection points, and calculate the sensor value of each UAV based on the sensor parameters of each UAV.

[0053] 203. Based on the coordinates of the corresponding inspection points matched by each sensor value, and based on the matching results, generate the corresponding flight path inspection route for each UAV.

[0054] 204. Obtain the control terminal information and control center information corresponding to the UAV, and mark the sequence of each UAV, control terminal and control center to generate the corresponding initial inspection self-organizing network;

[0055] In this embodiment, the control terminal information refers to the control terminal corresponding to each UAV; the control center information refers to the overall data interaction processing and control center of the UAV cluster; and the sequence labeling refers to the labeling of different devices using a preset sequence. The control center, managed by the UAV inspection business platform, performs comprehensive management, collection, organization, and data storage of all relevant UAV inspection data, task data, flight path planning data, and other types of data. It also has business functions such as task planning, task issuance, multi-UAV collaborative control, and data display. All UAV task instructions and work order information are uniformly issued and tasks are assigned by the control center.

[0056] In practical applications, by acquiring information from the control center and the corresponding control terminals of each UAV, the information from the UAVs, control center, and control terminals used for flight path planning is sequentially marked. Then, at the transport layer, the marked information is used to build an initial inspection ad hoc network for data transmission and interaction, thereby connecting the control center information, UAVs, and control terminals (such as individual soldier terminals) to achieve data interaction. For example, photo data collected by the UAV can be processed on the onboard computer before being transmitted to the data center.

[0057] 205. Based on the flight path inspection route, differential correction and binding are performed on the inspection point coordinates of UAVs in the inspection ad hoc network to obtain the final inspection ad hoc network.

[0058] In this embodiment, differential correction binding refers to using RTK differential positioning technology to continuously monitor the same satellites by the base station of the control center and the receiver of the UAV. While the UAV receives and observes the visible satellite signals, the base station of the control center sends the carrier phase measurement value to the UAV receiver in real time via a data link. The UAV receiver processes its own carrier phase measurement value and the received carrier phase measurement value in real time to calculate its own spatial coordinates and complete high-precision positioning. The positioning accuracy of carrier phase differential can reach the centimeter level.

[0059] In practical applications, based on the flight path inspection route, the coordinates of the inspection points of the UAVs in the inspection ad hoc network are differentially positioned and bound using RTK differential positioning technology, and the position of each UAV is located in real time during subsequent inspections, thereby forming the final inspection ad hoc network.

[0060] 206. Based on the inspection route, control each UAV to form a UAV swarm to inspect each inspection point and obtain inspection data.

[0061] 207. Obtain historical loss information for each UAV, and perform nonlinear adaptive estimation on the historical loss information and inspection data to obtain the efficiency loss coefficient for each UAV.

[0062] In this embodiment, the historical loss information refers to the historical execution efficiency loss fault data of each UAV; the nonlinear adaptive estimation refers to using a nonlinear adaptive state observer to estimate the efficiency loss coefficient of each UAV's execution altitude and attitude, etc., by performing nonlinear calculations on the state (altitude and attitude, etc.) of each UAV during execution, thereby obtaining the corresponding efficiency loss coefficient.

[0063] By acquiring historical loss information for each UAV, and then using a pre-set nonlinear adaptive state observer to nonlinearly and adaptively estimate the flight state (altitude and attitude, etc.) of the UAV based on the historical loss information and inspection data, the efficiency loss coefficient of each UAV is obtained.

[0064] 208. Based on the efficiency loss coefficient, calculate the composite compensation parameters for each drone in the drone swarm;

[0065] In this embodiment, a preset interference observer is used to estimate the external interference of the current environment to be inspected, and then the composite compensation parameters of each drone in the drone cluster are calculated by combining the efficiency loss coefficient obtained above and the estimated value of external interference.

[0066] 209. Adjust the flight path of the UAV cluster during inspection using composite compensation parameters, and control the UAV cluster to complete the inspection of each inspection point based on the control results.

[0067] In this embodiment, the flight path of the UAV swarm during inspection is adjusted using calculated composite compensation parameters. Based on the adjustment results, the UAV swarm is controlled to complete the inspection of each inspection point, thus achieving anti-interference and fault-tolerant control of the quadcopter UAV. This allows for rapid decoupling and estimation of actuator efficiency loss faults and external interference, and ensures the safety of the quadcopter UAV under conditions of simultaneous actuator failure and external interference through autonomous control reconfiguration.

[0068] In this embodiment of the invention, based on the flight path inspection route, the coordinates of the inspection points of the UAVs in the inspection ad hoc network are differentially corrected and bound to obtain the final inspection ad hoc network; according to the flight path inspection route, the UAVs are controlled to form a UAV swarm to inspect each inspection point, and inspection data is obtained; historical loss information of each UAV is acquired, and nonlinear adaptive estimation is performed on the historical loss information and inspection data to obtain the efficiency loss coefficient of each UAV; based on the efficiency loss coefficient, the composite compensation parameter of each UAV in the UAV swarm is calculated; the flight path inspection route of the UAV swarm in the inspection is adjusted using the composite compensation parameter, and based on the adjustment result, the UAV swarm is controlled to complete the inspection of each inspection point. Compared to existing technologies, this application constructs navigation inspection routes for each UAV, then performs self-organizing networking and differential binding on each UAV, enabling precise control and data exchange for each UAV in the entire cluster. Furthermore, it calculates corresponding interference compensation parameters for the UAV cluster based on the inspection data during the inspection, thereby enhancing the anti-interference capability of the UAVs and improving the stability of the clustered UAVs. This achieves planned control and stable inspection of the clustered UAVs' routes, enabling efficient inspection of power transmission lines.

[0069] The above describes the clustered drone inspection method based on power transmission lines in the embodiments of the present invention. The following describes the clustered drone inspection device based on power transmission lines in the embodiments of the present invention. Please refer to [link / reference]. Figure 3 One embodiment of the cluster-type unmanned aerial vehicle (UAV) inspection device based on power transmission lines in this invention includes:

[0070] The point cloud extraction module 301 is used to acquire the three-dimensional laser point cloud model of the target transmission line and the sensing parameters of each UAV, and extract the inspection space information and multiple inspection points in the three-dimensional laser point cloud model to generate an inspection tower directory tree.

[0071] The parameter conversion module 302 is used to perform geographic coordinate conversion on each of the inspection points in the inspection tower directory tree to obtain multiple inspection point coordinates, and to calculate the sensing value of each of the UAVs based on the sensing parameters of each UAV.

[0072] The coordinate matching module 303 is used to match the corresponding inspection point coordinates based on each of the sensor values, and generate the corresponding flight path inspection route for each of the UAVs based on the matching results.

[0073] The route inspection module 304 is used to control the drones to form a drone swarm to inspect each inspection point according to the route inspection line, and obtain inspection data.

[0074] In this embodiment of the invention, a three-dimensional laser point cloud model of the target transmission line and the sensing parameters of each UAV are acquired. The spatial information of each inspection point and multiple inspection points in the three-dimensional laser point cloud model are extracted to generate an inspection tower directory tree. Geographic coordinate transformation is performed on each inspection point in the inspection tower directory tree to obtain multiple inspection point coordinates. The sensing values ​​of each UAV are calculated based on its sensing parameters. The corresponding inspection point coordinates are matched based on the sensing values, and a corresponding flight path inspection route for each UAV is generated according to the matching results. Based on the flight path inspection route, the UAVs are controlled to form a UAV swarm to inspect each inspection point, obtaining inspection data. Compared to existing technologies, this application utilizes a three-dimensional laser point cloud model to construct an inspection tower directory tree and convert it into corresponding inspection coordinates. Then, based on the sensing parameters of each UAV, the corresponding inspection coordinates are matched to generate flight path inspection routes for each UAV in the UAV swarm, and the corresponding UAVs are controlled to complete the inspection. This achieves the planning of flight paths for swarm-type UAVs to complete efficient inspection of transmission lines.

[0075] Please see Figure 4 Another embodiment of the cluster-type unmanned aerial vehicle (UAV) inspection device based on power transmission lines in this invention includes:

[0076] The point cloud extraction module 301 is used to acquire the three-dimensional laser point cloud model of the target transmission line and the sensing parameters of each UAV, and extract the inspection space information and multiple inspection points in the three-dimensional laser point cloud model to generate an inspection tower directory tree.

[0077] The parameter conversion module 302 is used to perform geographic coordinate conversion on each of the inspection points in the inspection tower directory tree to obtain multiple inspection point coordinates, and to calculate the sensing value of each of the UAVs based on the sensing parameters of each UAV.

[0078] The coordinate matching module 303 is used to match the corresponding inspection point coordinates based on each of the sensor values, and generate the corresponding flight path inspection route for each of the UAVs based on the matching results.

[0079] The route inspection module 304 is used to control the drones to form a drone swarm to inspect each inspection point according to the route inspection line, and obtain inspection data.

[0080] Furthermore, the point cloud extraction module 301 includes:

[0081] Data extraction unit 3011 is used to extract laser point cloud data, line coordinate data, multiple inspection tower information and multiple inspection points from the three-dimensional laser point cloud model;

[0082] The data classification unit 3012 is used to classify the laser point cloud data based on the information of each of the inspection towers;

[0083] The directory creation unit 3013 is used to match the corresponding line coordinate data according to the classified laser point cloud data, and generate an inspection tower directory tree according to the matching result and the inspection priority in the inspection tower information.

[0084] Furthermore, the parameter conversion module 302 includes:

[0085] The coordinate transformation unit 3021 is used to extract multiple inspection item information from the inspection tower directory tree, and perform coordinate transformation on each inspection item information according to the inspection tower directory tree to obtain the initial inspection coordinates;

[0086] The coordinate optimization unit 3022 is used to perform adaptive coordinate optimization on the initial inspection coordinates to obtain the coordinates of multiple inspection points.

[0087] The numerical conversion unit 3023 is used to classify the sensing parameters of each UAV by sensing type, and to convert the classification results by using a preset parameter numerical conversion table to obtain multiple sensing values ​​of each UAV.

[0088] Furthermore, the coordinate matching module 303 includes:

[0089] The numerical combination unit 3031 is used to perform numerical combination on each of the sensor values, and match the inspection point coordinates corresponding to each of the UAVs based on the combination result.

[0090] The route connection unit 3032 is used to extract the parking point coordinate information and the inspection classification information corresponding to the tower directory tree in the three-dimensional laser point cloud model, and connect the inspection coordinate points corresponding to each UAV according to the inspection classification information based on the result of the parking point coordinate information and the inspection coordinate matching, so as to obtain the route inspection line corresponding to each UAV.

[0091] Furthermore, the line inspection module 304 includes:

[0092] The simulation optimization unit 3041 is used to perform model flight optimization on the flight path inspection route of each of the UAVs using the three-dimensional laser point cloud model.

[0093] Cluster building unit 3042 is used to control the various UAVs to form a UAV cluster according to the optimized flight path inspection route;

[0094] The inspection and photography unit 3043 is used to control the drone cluster to inspect each of the inspection points and obtain inspection data.

[0095] Furthermore, before the line inspection module 304, a self-organizing network module 305 is also included:

[0096] The initial networking unit 3051 is used to obtain the control terminal information and control center information corresponding to the UAV, and to perform sequence marking on each UAV, the control terminal and the control center to generate the corresponding initial inspection self-organizing network;

[0097] The differential optimization unit 3052 is used to perform differential correction and binding of the inspection point coordinates of the UAVs in the inspection ad hoc network based on the route inspection line, so as to obtain the final inspection ad hoc network.

[0098] Furthermore, following the line inspection module 304, an interference optimization module 306 is also included:

[0099] The coefficient calculation unit 3061 is used to acquire the historical loss information of each UAV and perform nonlinear adaptive estimation on the historical loss information and the inspection data to obtain the efficiency loss coefficient of each UAV.

[0100] The parameter calculation unit 3062 is used to calculate the composite compensation parameters of each drone in the drone cluster based on the efficiency loss coefficient.

[0101] The parameter adjustment unit 3063 is used to adjust the flight path of the UAV cluster during the inspection using the composite compensation parameters, and based on the adjustment results, control the UAV cluster to complete the inspection of each inspection point.

[0102] In this embodiment of the invention, a three-dimensional laser point cloud model of the target transmission line and the sensing parameters of each UAV are acquired. The spatial information of each inspection point and multiple inspection points in the three-dimensional laser point cloud model are extracted to generate an inspection tower directory tree. Geographic coordinate transformation is performed on each inspection point in the inspection tower directory tree to obtain multiple inspection point coordinates. The sensing values ​​of each UAV are calculated based on its sensing parameters. The corresponding inspection point coordinates are matched based on the sensing values, and a corresponding flight path inspection route for each UAV is generated according to the matching results. Based on the flight path inspection route, the UAVs are controlled to form a UAV swarm to inspect each inspection point, obtaining inspection data. Compared to existing technologies, this application utilizes a three-dimensional laser point cloud model to construct an inspection tower directory tree and convert it into corresponding inspection coordinates. Then, based on the sensing parameters of each UAV, the corresponding inspection coordinates are matched to generate flight path inspection routes for each UAV in the UAV swarm, and the corresponding UAVs are controlled to complete the inspection. This achieves the planning of flight paths for swarm-type UAVs to complete efficient inspection of transmission lines.

[0103] above Figure 3 and Figure 4 The clustered drone inspection device based on power transmission lines in this embodiment of the invention will be described in detail from the perspective of modular functional entities. The clustered drone inspection device based on power transmission lines in this embodiment of the invention will be described in detail from the perspective of hardware processing.

[0104] Figure 5 This is a schematic diagram of a swarm-type drone inspection device based on a power transmission line according to an embodiment of the present invention. The swarm-type drone inspection device 500 based on power transmission lines can vary significantly due to different configurations or performance. It may include one or more central processing units (CPUs) 510 (e.g., one or more processors) and a memory 520, and one or more storage media 530 (e.g., one or more mass storage devices) for storing application programs 533 or data 532. The memory 520 and storage media 530 can be temporary or persistent storage. The program stored in the storage media 530 may include one or more modules (not shown in the diagram), each module may include a series of instruction operations on the swarm-type drone inspection device 500 based on the power transmission line. Furthermore, the processor 510 may be configured to communicate with the storage media 530 and execute the series of instruction operations in the storage media 530 on the swarm-type drone inspection device 500 based on the power transmission line.

[0105] The swarm-type drone inspection equipment 500 based on power transmission lines may also include one or more power supplies 540, one or more wired or wireless network interfaces 550, one or more input / output interfaces 560, and / or one or more operating systems 531, such as Windows Server, Mac OS X, Unix, Linux, FreeBSD, etc. Those skilled in the art will understand that... Figure 5 The illustrated structure of the swarm-type drone inspection equipment based on power transmission lines does not constitute a limitation on swarm-type drone inspection equipment based on power transmission lines. It may include more or fewer components than illustrated, or combine certain components, or have different component arrangements.

[0106] The present invention also provides a cluster-type drone inspection device based on power transmission lines. The computer device includes a memory and a processor. The memory stores computer-readable instructions. When the computer-readable instructions are executed by the processor, the processor performs each step of the cluster-type drone inspection method based on power transmission lines in the above embodiments.

[0107] The present invention also provides a computer-readable storage medium, which can be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium, wherein the computer-readable storage medium stores instructions that, when the instructions are executed on a computer, cause the computer to perform the various steps of the clustered UAV inspection method based on power transmission lines.

[0108] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0109] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0110] This application can be used in a wide variety of general-purpose or special-purpose computer system environments or configurations. Examples include: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices. This application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific tasks or implement specific abstract data types. This application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0111] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for clustered UAV inspection of power transmission lines, used to control each UAV in a UAV cluster to inspect power transmission lines, characterized in that, The cluster-based UAV inspection method for power transmission lines includes: The three-dimensional laser point cloud model of the target transmission line and the sensing parameters of each UAV are obtained, and the inspection space information and multiple inspection points in the three-dimensional laser point cloud model are extracted to generate an inspection tower directory tree. Geographic coordinate transformation is performed on each of the inspection points in the inspection tower directory tree to obtain multiple inspection point coordinates, and the sensing value of each of the UAVs is calculated based on the sensing parameters of each UAV. Based on the sensor values, the corresponding inspection point coordinates are matched, and the corresponding flight path inspection route for each UAV is generated according to the matching results. According to the inspection route, control the drones to form a drone swarm to inspect each inspection point and obtain inspection data. Historical loss information of each UAV is obtained, and nonlinear adaptive estimation is performed on the historical loss information and the inspection data to obtain the efficiency loss coefficient of each UAV; based on the efficiency loss coefficient, the composite compensation parameter of each UAV in the UAV cluster is calculated; the flight path of the UAV cluster in the inspection is adjusted using the composite compensation parameter, and based on the adjustment result, the UAV cluster is controlled to complete the inspection of each inspection point.

2. The cluster-based UAV inspection method for power transmission lines according to claim 1, characterized in that, The step of extracting various inspection spatial information and multiple inspection points from the three-dimensional laser point cloud model to generate an inspection tower directory tree includes: Extract the laser point cloud data, line coordinate data, information on multiple inspection towers, and multiple inspection points from the three-dimensional laser point cloud model; Based on the inspection tower information, the laser point cloud data is classified. Based on the classified laser point cloud data, the corresponding line coordinate data is matched, and an inspection tower directory tree is generated according to the matching results and the inspection priority in the inspection tower information.

3. The cluster-based UAV inspection method for power transmission lines according to claim 2, characterized in that, The process of performing geographic coordinate transformation on each inspection point in the inspection tower directory tree to obtain multiple inspection point coordinates, and calculating the sensing value of each UAV based on the sensing parameters of each UAV, includes: Extract multiple inspection item information from the inspection tower directory tree, and perform coordinate transformation on each inspection item information according to the inspection tower directory tree to obtain the initial inspection coordinates; Adaptive coordinate optimization is performed on the initial inspection coordinates to obtain the coordinates of multiple inspection points; The sensing parameters of each UAV are classified by sensing type, and the classification results are converted into multiple sensing values ​​for each UAV using a preset parameter value conversion table.

4. The cluster-based UAV inspection method for power transmission lines according to claim 1, characterized in that, The step of matching the coordinates of the corresponding inspection points based on each of the sensor values, and generating the corresponding flight path inspection route for each of the UAVs based on the matching results, includes: The sensor values ​​are numerically combined, and the coordinates of the inspection points corresponding to each UAV are matched based on the combination results. Extract the parking point coordinates from the 3D laser point cloud model and the inspection classification information corresponding to the tower directory tree. Based on the result of matching the inspection point coordinates with the parking point coordinates, connect the inspection coordinates of each UAV according to the inspection classification information to obtain the inspection route corresponding to each UAV.

5. The cluster-based UAV inspection method for power transmission lines according to claim 1, characterized in that, The step of controlling the drones to form a drone swarm to inspect each inspection point according to the inspection route, and obtaining inspection data, includes: The three-dimensional laser point cloud model is used to optimize the flight path of each UAV for inspection. Based on the optimized flight path inspection route, control the various drones to form a drone swarm; The drone cluster is controlled to inspect each of the inspection points and obtain inspection data.

6. The cluster-based UAV inspection method for power transmission lines according to any one of claims 1-5, characterized in that, Before controlling the drones to form a drone swarm to inspect each inspection point according to the inspection route and obtaining inspection data, the method further includes: Obtain the control terminal information and control center information corresponding to the UAV, and perform sequence marking on each UAV, control terminal and control center to generate the corresponding initial inspection self-organizing network; Based on the aforementioned inspection route, the coordinates of the inspection points of the UAVs in the inspection ad hoc network are differentially corrected and bound to obtain the final inspection ad hoc network.

7. A cluster-type unmanned aerial vehicle (UAV) inspection device based on power transmission lines, characterized in that, The cluster-type unmanned aerial vehicle (UAV) inspection device based on power transmission lines includes: The point cloud extraction module is used to acquire the three-dimensional laser point cloud model of the target transmission line and the sensing parameters of each UAV, and extract the inspection space information and multiple inspection points in the three-dimensional laser point cloud model to generate an inspection tower directory tree. The parameter conversion module is used to perform geographic coordinate conversion on each of the inspection points in the inspection tower directory tree to obtain multiple inspection point coordinates, and to calculate the sensing value of each of the UAVs based on the sensing parameters of each UAV. The coordinate matching module is used to match the corresponding inspection point coordinates based on each of the sensor values, and generate the corresponding flight path inspection route for each of the UAVs based on the matching results. The route inspection module is used to control the drones to form a drone swarm to inspect each inspection point according to the route inspection line, and obtain inspection data. The interference optimization module is used to acquire historical loss information of each UAV, and perform nonlinear adaptive estimation on the historical loss information and the inspection data to obtain the efficiency loss coefficient of each UAV; based on the efficiency loss coefficient, calculate the composite compensation parameter of each UAV in the UAV cluster; use the composite compensation parameter to adjust the flight path of the UAV cluster during inspection, and based on the adjustment result, control the UAV cluster to complete the inspection of each inspection point.

8. A cluster-type unmanned aerial vehicle (UAV) inspection device based on power transmission lines, characterized in that, The cluster-type UAV inspection equipment based on power transmission lines includes: a memory and at least one processor, wherein the memory stores instructions; The at least one processor invokes the instructions in the memory to cause the power line-based swarm drone inspection equipment to perform the steps of the power line-based swarm drone inspection method as described in any one of claims 1-6.

9. A computer-readable storage medium storing instructions thereon, characterized in that, When the instructions are executed by the processor, they implement the various steps of the clustered UAV inspection method based on power transmission lines as described in any one of claims 1-6.

Images