Unmanned aerial vehicle navigation route planning method for power grid line facility equipment

Abstract

The invention discloses an unmanned aerial vehicle navigation route planning method for power grid line facility equipment, which is a multi-rotor unmanned aerial vehicle intelligent inspection and unmanned aerial vehicle inspection navigation route planning method for power transmission lines and power facility equipment, and comprises the following steps: S1, constructing an unmanned aerial vehicle navigation knowledge graph; s2, carrying out flight shooting learning modeling on key facilities and equipment; and S3, planning the route of the unmanned aerial vehicle. The invention aims to solve the problems that targeted high-precision, close-range and multi-azimuth automatic patrol navigation planning is lacked for power grid transmission lines, facilities and equipment which are easy to fail, and linkage with shooting regulations of the power facilities and equipment cannot be realized. According to the invention, targeted, high-precision, close-range and multi-directional inspection, positioning and shooting can be carried out on power grid transmission lines and key facilities and equipment; through flight learning, three-dimensional scanning and three-dimensional modeling do not need to be carried out on electric power facilities and equipment with complex structures in the early stage, and popularization and application on a large number of electric power facilities and equipment scattered on a power grid transmission line are achieved.

Description

Technical Field

[0001] The present invention relates to a method for intelligent inspection of power transmission lines and power facilities by multi-rotor UAVs and a navigation route planning method for UAV inspection. Background Art

[0002] With the development and widespread adoption of drone technology, the use of drones in power grids has expanded from preliminary survey and design to grid operation and maintenance. Its application areas, technical means, and related extensions have all seen tremendous growth. The application of drone technology in power grid inspection operations has entered a period of rapid growth, moving from the exploratory stage. Traditional inspection and maintenance models suffer from traditional and limited information acquisition methods; equipment status awareness still primarily relies on power outages and offline testing; and data utilization rates for advanced methods such as online monitoring and live maintenance are low. Under these circumstances, the concept of intelligent inspection and maintenance, supported by modern information technology encompassing "big cloud, the Internet of Things, and mobile," has emerged. Drone-assisted power grid inspection is a crucial component of a comprehensive inspection system based on intelligent equipment. Inspection of power grid transmission lines and power equipment presents unique challenges. While ensuring safety, planning scientific and efficient inspection routes for drones while meeting grid inspection requirements is a crucial component of intelligent inspection.

[0003] The prior art similar to the present invention includes "A Method and Device for Autonomous Obstacle Avoidance Inspection Path Planning for UAVs" CN112327920A, which provides a method and device for autonomous obstacle avoidance inspection path planning for UAVs, belonging to the field of UAV inspection, wherein the UAV inspection path planning method includes: establishing a three-dimensional model of the inspection area, wherein the three-dimensional model includes point cloud data of the equipment in the inspection area; determining a three-dimensional inspection safety area based on the three-dimensional model and the no-fly policy; determining a first inspection target task point set based on the inspection plan and the three-dimensional model; establishing a first inspection path based on the three-dimensional inspection safety area, the first inspection target task point set and the UAV information. This embodiment can ensure the absolute safety of the UAV during inspections, and has the characteristics of low computational complexity, and can quickly, accurately and automatically plan inspection paths, so that the UAV can operate within the inspection area and avoid collisions with obstacles. "A method and system for dynamic planning and execution of drone inspection tasks" CN117519253A, this invention discloses a method and system for dynamic planning and execution of drone inspection tasks, the method comprising: in response to the initial route planning instruction issued by the background system, obtaining inspection point task data and information of the drone performing the inspection task, and generating an array of inspection points; based on the position information of the first inspection point in the inspection point array and the status information of the drone, planning a first route and uploading it to the drone to perform the inspection task. "A method for planning routes for electric drone inspections" CN111044044A, this invention discloses a method for planning routes for electric drone inspections, the method comprising three steps: environment modeling, task modeling, and route planning. The electric drone inspection route planning method proposed in the present invention performs spatial three-dimensional modeling of the power facilities such as towers, lines, and sites to be inspected and their surrounding environment; sorts out the parameters such as the position coordinates and shooting angles of each task point contained in the inspection task to obtain a subtask set; and calculates the optimal route based on the results of environment modeling and task modeling.

[0004] However, existing knowledge graph construction methods in the prior art have at least the following defects:

[0005] (1) The core issues that UAV inspections of power transmission lines and facilities and equipment need to address are status detection and fault diagnosis. Existing technologies do not take into account the status and fault factors of power transmission lines and facilities and equipment in UAV navigation route planning. There is a lack of targeted, high-precision, close-range, and multi-directional inspections of power transmission lines and facilities and equipment that are prone to faults.

[0006] (2) The existing technology lacks the linkage of the status and fault information of the lines and facilities and equipment and the shooting procedures before the drone navigation route rules are established. After the drone navigation inspection, it cannot automatically locate and shoot the status and fault images of key lines and facilities and equipment according to the shooting procedures, which makes the subsequent inspection data processing more difficult.

[0007] (3) For the inspection of power facilities and equipment with complex structures, existing technologies either require human intervention, with drone operators controlling the equipment on the ground to complete high-precision, close-range flights, which is time-consuming and labor-intensive, and is prone to flight accidents due to improper operation; or they require three-dimensional scanning and three-dimensional modeling of the complex power facilities and equipment in advance, which requires huge initial investment, is time-consuming and labor-intensive, and cannot be promoted for use on a large number of power facilities and equipment scattered on the power grid transmission lines. Summary of the Invention

[0008] The purpose of the present invention is to propose a multi-rotor drone intelligent inspection and drone inspection navigation route planning method for power transmission lines and power facilities equipment to solve the problems raised in the above background technology.

[0009] To achieve the above object, the present invention provides the following technical solutions:

[0010] A method for planning a drone navigation route for power grid line facilities and equipment, characterized by:

[0011] S1,Construction of UAV navigation knowledge graph;

[0012] S2. Flight photography and modeling of key facilities and equipment;

[0013] S3. Drone route planning.

[0014] Preferably, step S2 includes sub-steps: knowledge representation modeling of geographical distribution of power transmission and transformation lines, knowledge representation modeling of power facilities and equipment, knowledge representation modeling of procedures for shooting key equipment with drones, drone knowledge representation model modeling, and association knowledge representation model modeling.

[0015] (1) Modeling the knowledge representation of the geographical distribution of power transmission and transformation lines. The node information of the geographical distribution of the power transmission lines is represented by triples, and the connection relationship between the nodes is represented by triples. The represented information includes the length of the line, geographical coordinates, and the direction of the line connection. The triples are mapped to points and edges in the knowledge graph, which are used to represent the inspection power transmission lines in the knowledge graph space, providing a basis for the subsequent automatic planning of drone navigation channels.

[0016] (2) Modeling of knowledge representation of power facilities and equipment: The power facilities and important components on the transmission lines, as well as the physical structure information of the power equipment, are represented by triples. The represented information includes the geographical coordinates of the equipment and facilities, important components, three-dimensional structure, and connection status with the transmission lines. The triples are mapped to points and edges in the knowledge graph, which are used to represent the facilities and equipment to be inspected in the knowledge graph space, providing a basis for the subsequent automatic planning of multi-method inspections and fixed shooting positions of key facilities and equipment using drones;

[0017] (3) Modeling the knowledge representation of the procedures for photographing key equipment using drones. The procedures for photographing different types of power facilities and equipment that drones are supposed to photograph are represented by triples. The represented information includes the shooting order, shooting object, shooting distance, number of shots, shooting angle, shooting latitude and longitude, shooting altitude, and shooting type (optical shooting, point cloud shooting, etc.). The triples are mapped to points and edges in the knowledge graph to represent the procedures and requirements for photographing key facilities using drones in the knowledge graph space.

[0018] (4) Modeling of UAV knowledge representation model, which represents information such as UAV model, aircraft parameters, flight time, battery capacity, and maximum flight altitude through triples. This is used to represent inspection UAVs in the knowledge graph space, providing a basis for the automatic planning of flight routes for different types of UAVs in the future.

[0019] (5) Modeling of the associated knowledge representation model: associating the transmission line knowledge representation model with the facility equipment knowledge representation model, and representing it as the connection between the transmission line and the facility equipment in the knowledge graph space; associating the drone key equipment shooting procedure knowledge representation model with the drone knowledge representation model, the transmission line knowledge representation model, and the facility equipment knowledge representation model, and representing it as the transmission line and facility equipment that a specific type of drone will inspect in the knowledge graph space.

[0020] Preferably, step S2 includes sub-steps: selecting a drone model, searching for key facilities and equipment, learning by flying photography of key facilities and equipment, and memorizing flight of key facilities and equipment.

[0021] (1) UAV parameter retrieval: Retrieve the entity information of the corresponding UAV to be learned in the UAV navigation knowledge graph, and extract the UAV model, aircraft parameters, flight time, battery capacity, maximum flight altitude and other information from the triple;

[0022] (1) Retrieval of key facilities and equipment: Retrieve entity information of key facilities and equipment from the UAV navigation knowledge graph, and extract information such as the geographical coordinates, important components, three-dimensional structure, and connection status with transmission lines of key facilities and equipment from triples;

[0023] (2) Key facilities and equipment positioning learning modeling: input key facilities and equipment into the UAV navigation knowledge graph to match the corresponding UAV key facilities and equipment shooting procedure triples, extract the shooting order, shooting object, shooting distance, shooting number, shooting angle, shooting longitude and latitude, shooting altitude, shooting type information, according to the key equipment shooting procedure, the UAV operator operates in the order of shooting order, shooting object, shooting distance, shooting number, shooting angle, etc. After the UAV takes off, the learning mode is triggered, and the corresponding UAV model, UAV hovering time, UAV shooting longitude and latitude, shooting altitude, shooting angle and other parameters are automatically recorded;

[0024] (3) After completing the flight and shooting of each facility or equipment object, the memory mode is triggered to update and record the drone key equipment shooting procedure information in the drone navigation knowledge map in real time;

[0025] (4) After completing the flight photography study of one of the key facilities and equipment, continue with step (2) until the search results for key facilities and equipment in the UAV navigation knowledge graph are empty;

[0026] (5) If the inspection uses multiple types of drones (with different flight parameters), repeat step (1) for the newly added types of drones to achieve shooting and learning of different types of drones.

[0027] Preferably, the step S3 includes sub-steps: macro inspection channel planning, detailed inspection planning of key facilities and equipment, and flight instruction generation.

[0028] (1) Macro inspection channel planning: read the associated knowledge representation model in the UAV navigation knowledge graph, generate an undirected graph consisting of nodes such as transmission lines and transmission facilities in the memory, convert the undirected graph into a linear sequence through topological sorting, and generate the UAV macro inspection channel according to the sorting of the linear sequence;

[0029] (2) Detailed inspection planning of key facilities and equipment: According to the linear sequence generated in step (1), the node (facility and equipment) triple information is read. If the facility and equipment is a key inspection facility, the detailed inspection planning of key facilities and equipment is triggered. Based on the key facility and equipment flight shooting learning modeling and key facility and equipment positioning learning modeling in step S2, the corresponding drone key facility and equipment shooting procedure triple is retrieved from the drone navigation knowledge graph, and the triple information is inserted into the linear sequence node.

[0030] (3) Repeat step (2) until there are no more key facilities and equipment in the linear sequence;

[0031] (4) Generate the corresponding flight instruction set based on the linear sequence.

[0032] Compared with the prior art, the present invention has the following beneficial effects:

[0033] (1) The present invention can achieve targeted, high-precision, close-range, multi-directional inspection, positioning, and photography of power grid transmission lines and key facilities and equipment;

[0034] (2) The present invention uses flight learning to achieve high-precision, fine-grained flight and inspection without the need for preliminary 3D scanning and 3D modeling of complex power facility equipment;

[0035] (3) The present invention can be used on a large number of power facilities and equipment distributed on the power grid transmission lines in a lower cost and higher efficiency manner;

[0036] (4) The present invention can be linked with the operation and maintenance data of power equipment to achieve more targeted inspections of power equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 Schematic diagram of the workflow of the present invention. DETAILED DESCRIPTION

[0038] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0039] See also Figure 1 As shown, the present invention provides a method for planning a UAV navigation route for power grid line facilities and equipment, which specifically includes the following steps:

[0040] A method for planning a UAV navigation route for power grid line facilities and equipment, characterized by:

[0041] S1,Construction of UAV navigation knowledge graph;

[0042] S2. Flight photography and modeling of key facilities and equipment;

[0043] S3. Drone route planning.

[0044] Preferably, step S2 includes sub-steps: knowledge representation modeling of geographical distribution of power transmission and transformation lines, knowledge representation modeling of power facilities and equipment, knowledge representation modeling of procedures for shooting key equipment with drones, drone knowledge representation model modeling, and association knowledge representation model modeling.

[0045] (1) Modeling the knowledge representation of the geographical distribution of power transmission and transformation lines. The node information of the geographical distribution of the power transmission lines is represented by triples, and the connection relationship between the nodes is represented by triples. The represented information includes the length of the line, geographical coordinates, and the direction of the line connection. The triples are mapped to points and edges in the knowledge graph, which are used to represent the inspection power transmission lines in the knowledge graph space, providing a basis for the subsequent automatic planning of drone navigation channels.

[0046] (2) Modeling of knowledge representation of power facilities and equipment: The power facilities and important components on the transmission lines, as well as the physical structure information of the power equipment, are represented by triples. The represented information includes the geographical coordinates of the equipment and facilities, important components, three-dimensional structure, and connection status with the transmission lines. The triples are mapped to points and edges in the knowledge graph, which are used to represent the facilities and equipment to be inspected in the knowledge graph space, providing a basis for the subsequent automatic planning of multi-method inspections and fixed shooting positions of key facilities and equipment using drones;

[0047] (3) Modeling the knowledge representation of the procedures for photographing key equipment using drones. The procedures for photographing different types of power facilities and equipment that drones are supposed to photograph are represented by triples. The represented information includes the shooting order, shooting object, shooting distance, number of shots, shooting angle, shooting latitude and longitude, shooting altitude, and shooting type (optical shooting, point cloud shooting, etc.). The triples are mapped to points and edges in the knowledge graph to represent the procedures and requirements for photographing key facilities using drones in the knowledge graph space.

[0048] (4) Modeling of UAV knowledge representation model, which represents information such as UAV model, aircraft parameters, flight time, battery capacity, and maximum flight altitude through triples. This is used to represent inspection UAVs in the knowledge graph space, providing a basis for the automatic planning of flight routes for different types of UAVs in the future.

[0049] (5) Modeling of the associated knowledge representation model: associating the transmission line knowledge representation model with the facility equipment knowledge representation model, and representing it as the connection between the transmission line and the facility equipment in the knowledge graph space; associating the drone key equipment shooting procedure knowledge representation model with the drone knowledge representation model, the transmission line knowledge representation model, and the facility equipment knowledge representation model, and representing it as the transmission line and facility equipment that a specific type of drone will inspect in the knowledge graph space.

[0050] Preferably, step S2 includes sub-steps: selecting a drone model, searching for key facilities and equipment, learning by flying photography of key facilities and equipment, and memorizing flight of key facilities and equipment.

[0051] (1) UAV parameter retrieval: Retrieve the entity information of the corresponding UAV to be learned in the UAV navigation knowledge graph, and extract the UAV model, aircraft parameters, flight time, battery capacity, maximum flight altitude and other information from the triple;

[0052] (1) Retrieval of key facilities and equipment: Retrieve entity information of key facilities and equipment from the UAV navigation knowledge graph, and extract information such as the geographical coordinates, important components, three-dimensional structure, and connection status with transmission lines of key facilities and equipment from triples;

[0053] (2) Key facilities and equipment positioning learning modeling: input key facilities and equipment into the UAV navigation knowledge graph to match the corresponding UAV key facilities and equipment shooting procedure triples, extract the shooting order, shooting object, shooting distance, shooting number, shooting angle, shooting longitude and latitude, shooting altitude, shooting type information, according to the key equipment shooting procedure, the UAV operator operates in the order of shooting order, shooting object, shooting distance, shooting number, shooting angle, etc. After the UAV takes off, the learning mode is triggered, and the corresponding UAV model, UAV hovering time, UAV shooting longitude and latitude, shooting altitude, shooting angle and other parameters are automatically recorded;

[0054] (3) After completing the flight and shooting of each facility or equipment object, the memory mode is triggered to update and record the drone key equipment shooting procedure information in the drone navigation knowledge map in real time;

[0055] (4) After completing the flight photography study of one of the key facilities and equipment, continue with step (2) until the search results for key facilities and equipment in the UAV navigation knowledge graph are empty;

[0056] (5) If the inspection uses multiple types of drones (with different flight parameters), repeat step (1) for the newly added types of drones to achieve shooting and learning of different types of drones.

[0057] Preferably, the step S3 includes sub-steps: macro inspection channel planning, detailed inspection planning of key facilities and equipment, and flight instruction generation.

[0058] (1) Macro inspection channel planning: read the associated knowledge representation model in the UAV navigation knowledge graph, generate an undirected graph consisting of nodes such as transmission lines and transmission facilities in the memory, convert the undirected graph into a linear sequence through topological sorting, and generate the UAV macro inspection channel according to the sorting of the linear sequence;

[0059] (2) Detailed inspection planning of key facilities and equipment: According to the linear sequence generated in step (1), the node (facility and equipment) triple information is read. If the facility and equipment is a key inspection facility, the detailed inspection planning of key facilities and equipment is triggered. Based on the key facility and equipment flight shooting learning modeling and key facility and equipment positioning learning modeling in step S2, the corresponding drone key facility and equipment shooting procedure triple is retrieved from the drone navigation knowledge graph, and the triple information is inserted into the linear sequence node.

[0060] (3) Repeat step (2) until there are no more key facilities and equipment in the linear sequence;

[0061] (4) Generate the corresponding flight instruction set based on the linear sequence.

[0062] Compared with the prior art, the present invention has the following beneficial effects:

[0063] (1) The present invention can achieve targeted, high-precision, close-range, multi-directional inspection, positioning, and photography of power grid transmission lines and key facilities and equipment;

[0064] (2) The present invention uses flight learning to achieve high-precision, fine-grained flight and inspection without the need for preliminary 3D scanning and 3D modeling of complex power facility equipment;

[0065] (3) The present invention can be used on a large number of power facilities and equipment distributed on the power grid transmission lines in a lower cost and higher efficiency manner;

[0066] (4) The present invention can be linked with the operation and maintenance data of power equipment to achieve more targeted inspections of power equipment.

Claims

1. A method for planning the navigation route of an unmanned aerial vehicle (UAV) for power grid line facilities and equipment, characterized by: S1,Construction of UAV navigation knowledge graph; S2. Flight photography and modeling of key facilities and equipment; S3. Drone route planning.

2. The method for planning a UAV navigation route for power grid line facilities and equipment according to claim 1, characterized in that: In step S1, the geographical distribution knowledge representation model of power transmission and transformation lines, the knowledge representation model of power facilities and equipment, the knowledge representation model of drone key equipment shooting procedures, drone knowledge representation model and associated knowledge representation model are modeled. (1) Modeling the knowledge representation of the geographical distribution of power transmission and transformation lines. The node information of the geographical distribution of the power transmission lines is represented by triples, and the connection relationship between the nodes is represented by triples. The represented information includes the length of the line, geographical coordinates, and the direction of the line connection. The triples are mapped to points and edges in the knowledge graph, which are used to represent the inspection power transmission lines in the knowledge graph space, providing a basis for the subsequent automatic planning of drone navigation channels. (2) Modeling of knowledge representation of power facilities and equipment: The power facilities and important components on the transmission lines, as well as the physical structure information of the power equipment, are represented by triples. The represented information includes the geographical coordinates of the equipment and facilities, important components, three-dimensional structure, and connection status with the transmission lines. The triples are mapped to points and edges in the knowledge graph, which are used to represent the facilities and equipment to be inspected in the knowledge graph space, providing a basis for the subsequent automatic planning of multi-method inspections and fixed shooting positions of key facilities and equipment using drones; (3) Modeling the knowledge representation of the procedures for photographing key equipment using drones. The procedures for photographing different types of power facilities and equipment that drones are supposed to photograph are represented by triples. The represented information includes the shooting order, shooting object, shooting distance, number of shots, shooting angle, shooting latitude and longitude, shooting altitude, and shooting type (optical shooting, point cloud shooting, etc.). The triples are mapped to points and edges in the knowledge graph to represent the procedures and requirements for photographing key facilities using drones in the knowledge graph space. (4) Modeling of UAV knowledge representation model, which represents information such as UAV model, aircraft parameters, flight time, battery capacity, and maximum flight altitude through triples. This is used to represent inspection UAVs in the knowledge graph space, providing a basis for the automatic planning of flight routes for different types of UAVs in the future. (5) Modeling of the associated knowledge representation model: associating the transmission line knowledge representation model with the facility equipment knowledge representation model, and representing it as the connection between the transmission line and the facility equipment in the knowledge graph space; associating the drone key equipment shooting procedure knowledge representation model with the drone knowledge representation model, the transmission line knowledge representation model, and the facility equipment knowledge representation model, and representing it as the transmission line and facility equipment that a specific type of drone will inspect in the knowledge graph space.

3. The method for planning a UAV navigation route for power grid line facilities and equipment according to claim 1, characterized in that: In step S2, the drone model is selected, key facilities and equipment are retrieved, key facilities and equipment are photographed and learned by flight, and key facilities and equipment are memorized by flight. (1) UAV parameter retrieval: Retrieve the entity information of the corresponding UAV to be learned in the UAV navigation knowledge graph, and extract the UAV model, aircraft parameters, flight time, battery capacity, maximum flight altitude and other information from the triple; (1) Retrieval of key facilities and equipment: Retrieve entity information of key facilities and equipment from the UAV navigation knowledge graph, and extract information such as the geographical coordinates, important components, three-dimensional structure, and connection status with transmission lines of key facilities and equipment from triples; (2) Key facilities and equipment positioning learning modeling: input key facilities and equipment into the UAV navigation knowledge graph to match the corresponding UAV key facilities and equipment shooting procedure triples, extract the shooting order, shooting object, shooting distance, shooting number, shooting angle, shooting longitude and latitude, shooting altitude, shooting type information, according to the key equipment shooting procedure, the UAV operator operates in the order of shooting order, shooting object, shooting distance, shooting number, shooting angle, etc. After the UAV takes off, the learning mode is triggered, and the corresponding UAV model, UAV hovering time, UAV shooting longitude and latitude, shooting altitude, shooting angle and other parameters are automatically recorded; (3) After completing the flight and shooting of each facility or equipment object, the memory mode is triggered to update and record the drone key equipment shooting procedure information in the drone navigation knowledge map in real time; (4) After completing the flight photography study of one of the key facilities and equipment, continue with step (2) until the search results for key facilities and equipment in the UAV navigation knowledge graph are empty; (5) If the inspection uses multiple types of drones (with different flight parameters), repeat step (1) for the newly added types of drones to achieve shooting and learning of different types of drones.

4. The method for planning a UAV navigation route for power grid line facilities and equipment according to claim 1, characterized in that: In step S2, macro inspection channel planning, detailed inspection planning of key facilities and equipment, and flight instructions are generated. (1) Macro inspection channel planning: read the associated knowledge representation model in the UAV navigation knowledge graph, generate an undirected graph consisting of nodes such as transmission lines and transmission facilities in the memory, convert the undirected graph into a linear sequence through topological sorting, and generate the UAV macro inspection channel according to the sorting of the linear sequence; (2) Detailed inspection planning of key facilities and equipment: According to the linear sequence generated in step (1), the node (facility and equipment) triple information is read. If the facility and equipment is a key inspection facility, the detailed inspection planning of key facilities and equipment is triggered. Based on the key facility and equipment positioning learning modeling in step 2, the key facility and equipment flight shooting learning modeling, the corresponding drone key facility and equipment shooting procedure triple is retrieved from the drone navigation knowledge graph, and the triple information is inserted into the linear sequence node. (3) Repeat step (2) until there are no more key facilities and equipment in the linear sequence; (4) Generate the corresponding flight instruction set based on the linear sequence.

Images