Intelligent unmanned aerial vehicle electric power inspection method

Abstract

The invention discloses an intelligent unmanned aerial vehicle electric power inspection method, and relates to the technical field of unmanned aerial vehicle electric power inspection, and the method comprises the following steps: 1, planning an inspection path according to the characteristics of an electric power circuit to be inspected; step 2, using an unmanned aerial vehicle and an inspection sensor to collect and process an image of a power line needing inspection; step 3, processing the acquired data in real time; 4, dynamically adjusting the take-off point, the inspection point and the landing point of the unmanned aerial vehicle; 5, performing dynamic planning on the step 4, and adopting a particle filtering algorithm; cloud data can be determined through the unmanned aerial vehicle and the inspection sensor in combination with an electric power line inspection path, then the cloud data is corrected, line image data can be transmitted back in real time through the unmanned aerial vehicle, real-time three-dimensional reconstruction can be supported, effectiveness can be enhanced, the inspection efficiency is greatly improved, and the maintenance cost is reduced. And the data can be wirelessly transmitted and backed up through the wireless transmission system, so that the safety and accuracy of the data are greatly improved.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned aerial vehicle power inspection, and in particular to an intelligent unmanned aerial vehicle power inspection method. Background Art

[0002] Power inspection refers to the regular, planned, and organized inspection, monitoring, evaluation, and maintenance of power systems and equipment, which aims to timely discover and eliminate hidden dangers of power equipment failures and ensure the safe operation and reliable supply of the power system. Power inspection includes inspection, testing, and maintenance of power plants, substations, transmission lines, distribution devices, and various types of power equipment. Inspectors need to conduct a comprehensive inspection of the appearance, operating status, operating parameters, etc. of the equipment and record relevant information. At the same time, it is also necessary to monitor the insulation condition, temperature, vibration, etc. of the equipment, and conduct necessary testing and maintenance work.

[0003] However, in the process of power system inspection, the locations of some power plants and substations are relatively complex, and manual inspection takes a long time and has poor inspection accuracy, which greatly reduces the inspection efficiency of the power system. Therefore, an intelligent UAV power inspection method is provided to solve the problems raised in the above background technology. Summary of the invention

[0004] The purpose of the present invention is to provide an intelligent UAV power inspection method to solve the problems raised in the above background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] An intelligent UAV power inspection method comprises the following steps:

[0007] Step 1: Plan the inspection route according to the characteristics of the power line to be inspected;

[0008] Step 2: Use drones and inspection sensors to collect and process images of power lines that need to be inspected;

[0009] Step 3: Collect data for real-time processing;

[0010] Step 4: Dynamically adjust the drone’s take-off point, inspection point, and landing point;

[0011] Step 5: Perform dynamic planning on step 4, adopt a particle filter algorithm, and obtain the real-time position information of the drone according to the Beidou differential airborne positioning unit in the drone.

[0012] As a further solution of the present invention: wherein, according to the step three, it also includes: cloud grading the power lines, extracting key inspection points of the power lines, and simulating and verifying the power lines according to the particle filtering algorithm.

[0013] As a further solution of the present invention: wherein, the step 4 further includes: taking the take-off point of the drone as the center, selecting four orthogonal directions, obtaining the elevations of the four orthogonal directions at a distance of 0.3-1m from the take-off point, adding the elevation of the take-off point, and calculating the arithmetic mean and variance according to the five elevation data:

[0014] H=(H0+H 0° +H 90° +H 180° +H 270° ) / 5;

[0015] Where: H is the arithmetic mean of the earth's height, H0 represents the earth's height at the center of the circle, and H 0° , H 90° , H 180° H 270 ° represents the geodetic height in the four orthogonal directions respectively.

[0016] As a further solution of the present invention: wherein, the UAV includes a visual odometer and inertial navigation, and the visual odometer includes a sensor device, a control system and a map navigation; the sensor device collects the driving data of the UAV through multiple sensors, and obtains the real-time position information of the UAV through the Beidou differential airborne positioning unit; the control system collects the driving data through the sensors to control the driving direction and speed of the UAV; the map navigation determines the driving direction and driving path of the UAV, sets the track points as the main reference points of the UAV inspection route, automatically calculates the best path points based on the genetic algorithm, and then performs distance detection between the path points and the track points, edits the track points that do not meet the requirements, and obtains the best path for power line inspection.

[0017] As a further solution of the present invention: wherein, the sensor device sensor usually uses multiple sensors to collect data while the drone is traveling, and the data includes GPS and lidar. These sensors can capture real-time environmental information around the drone and integrate it with the navigation data of the drone to determine the driving direction and path of the drone.

[0018] As a further solution of the present invention: wherein, the step one establishes a genetic algorithm model to generate track points, and generates multiple paths for the drone take-off point, the drone inspection point, and the drone landing point based on the track points; the paths are checked and simulated, and when the paths are impassable, the impassable paths are repaired; the fitness of the passable paths is calculated through the genetic algorithm model to determine the optimized path.

[0019] As a further solution of the present invention: wherein, according to the step one, it also includes: 1. detecting the safety height and the climbing rate of the planned inspection path; 2. if the result of the detection does not meet the preset conditions, editing and simulating the positions of the planned inspection path and the track points; 3. repeating steps 1 and 2 until the result of the detection meets the preset conditions.

[0020] As a further solution of the present invention: wherein, the UAV has a data acquisition system, a data storage system, a data processing system, and a wireless transmission system; wherein the data acquisition system can collect power line data, and the data storage system stores, backs up and restores the collected data; the data processing system processes and analyzes the stored data to generate an inspection report; the wireless transmission system adopts wireless communication technology to realize data transmission between the UAV and the ground terminal. The wireless transmission system selects appropriate communication protocols, enhances signal coverage, interference elimination technology and data compression and optimization, and identifies data, so that during the UAV's mission, the sensor data can be compressed and optimized, reducing the data volume and transmission delay and improving the efficiency of signal transmission.

[0021] Compared with the prior art, the present invention has the following beneficial effects:

[0022] Through drones and inspection sensors, we can determine cloud data in combination with the power line inspection route, and then correct and process the cloud data to achieve feature planning for the drone. The drone can also transmit line image data in real time and support real-time three-dimensional reconstruction, enhancing effectiveness and greatly improving inspection efficiency. The data can also be wirelessly transmitted and backed up through a wireless transmission system, greatly improving data security and accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 It is a schematic diagram of the overall method principle of the present invention;

[0024] Figure 2 This is a schematic diagram of the structure of the UAV system in the present invention;

[0025] Figure 3 This is a schematic diagram showing that the climbing rate of the UAV does not meet the conditions in the present invention;

[0026] Figure 4 A schematic diagram showing that the safety height of the drone does not meet the conditions in the present invention;

[0027] Figure 5 It is a schematic diagram showing that the climbing rate and safety altitude of the UAV in the present invention do not meet the conditions;

[0028] Figure 6 It is a schematic diagram of the UAV meeting the flight conditions in the present invention. DETAILED DESCRIPTION

[0029] See also Figures 1 to 6 :An intelligent UAV power inspection method includes the following steps:

[0030] Step 1: Plan the inspection route according to the characteristics of the power line to be inspected;

[0031] Among them, before the inspection, the cloud data is determined in combination with the inspection route of the power lines, and then the cloud data is corrected and processed to realize the feature planning of the UAV.

[0032] Step 2: Use drones and inspection sensors to collect and process images of power lines that need to be inspected;

[0033] Step 3: Collect data for real-time processing;

[0034] Among them, the drone can transmit line image data back in real time and can support real-time three-dimensional reconstruction to enhance effectiveness.

[0035] Step 4: Dynamically adjust the drone’s take-off point, inspection point, and landing point;

[0036] Among them, the positions of the take-off point, inspection point and landing point are edited, the take-off, inspection and landing positions are determined, and the inspection path of the power line is determined.

[0037] Step 5: Perform dynamic planning on step 4 and use the particle filter algorithm to obtain the real-time location information of the drone based on the Beidou differential airborne positioning unit in the drone.

[0038] Among them, the UAV may be affected by wind speed and wind direction during the inspection process. In order to improve the stability and reliability of the UAV flight, the particle filter algorithm is used to reduce the impact of wind speed and wind direction on the UAV. The particle filter algorithm can determine the subsequent flight position of the UAV according to the flight status of the UAV.

[0039] Preferably, step three also includes: cloud grading the power lines, extracting key inspection points of the power lines, extracting the key inspection points of the power lines, and simulating and verifying the power lines according to the particle filtering algorithm.

[0040] Among them, the particle filter algorithm can obtain the three-dimensional spatial position information of the UAV based on the key inspection points, provide a basis for the automatic planning of the subsequent UAV route, and simulate and verify the data sent back by the UAV sensor one by one, so that the UAV inspection route can completely cover the key equipment in the power line.

[0041] Preferably, step 4 further includes: taking the take-off point of the drone as the center, selecting four orthogonal directions, obtaining the elevations of the four orthogonal directions at a distance of 0.3-1m from the take-off point, adding the elevation of the take-off point, and obtaining the arithmetic mean and variance according to the five elevation data:

[0042] H=(H0+H 0° +H 90° +H 180° +H 270° ) / 5;

[0043] Where: H is the arithmetic mean of the earth's height, H0 represents the earth's height at the center of the circle, and H 0° , H 90° , H 180° H 270° Represents the geodetic height in four orthogonal directions.

[0044] Among them, the geoid height is the distance from the ground point to the reference ellipsoid along the normal of the reference ellipsoid, which is part of the elevation position. By determining the arithmetic mean and orthogonal direction of the geoid height, the starting coordinates, travel coordinates and end coordinates of the UAV can be planned and processed, thereby improving the degree of automation and intelligence of the UAV.

[0045] Preferably, the UAV includes a visual odometer and inertial navigation, the visual odometer includes a sensor device, a control system and map navigation; the sensor device collects the driving data of the UAV through multiple sensors, and obtains the real-time position information of the UAV through a Beidou differential airborne positioning unit; the control system collects driving data through sensors to control the driving direction and speed of the UAV; the map navigation determines the driving direction and path of the UAV.

[0046] Among them, the sensor device sensor usually uses multiple sensors to collect data while the drone is traveling. The data includes GPS and lidar. These sensors can capture real-time environmental information around the drone and integrate it with the drone's navigation data to determine the drone's driving direction and path.

[0047] Secondly, the control system includes computers and controllers, which are used to process the data collected by the drone's sensors and control the direction and speed of the drone. The control system usually uses a high-precision control system to ensure the navigation accuracy and stability of the drone.

[0048] Furthermore, maps and navigation are used to help the drone determine its driving direction and path. This function usually includes real-time navigation, path planning and multiple map display functions.

[0049] Preferably, a genetic algorithm model is established according to step one to generate track points, and multiple paths are generated for the drone take-off point, the drone inspection point, and the drone landing point according to the track points; the paths are checked and simulated, and when the paths are impassable, the impassable paths are repaired; the fitness of the passable paths is calculated through the genetic algorithm model to determine the optimal path.

[0050] Among them, the track points are set as the main reference points of the drone inspection route, the optimal path points are automatically calculated based on the genetic algorithm, and then the distance between the path points and the track points is detected, and the track points that do not meet the requirements are edited to obtain the optimal path for power line inspection.

[0051] Preferably, according to step one, it also includes: 1. Testing the safety altitude and climb rate of the planned inspection path; 2. If the test result does not meet the preset conditions, editing and simulating the positions of the planned inspection path and track points; 3. Repeating steps 1 and 2 until the test result meets the preset conditions.

[0052] Among them, the best inspection path also requires safety altitude and climb rate detection. If the detection does not meet the standard conditions, it is necessary to manually edit the path points or track points. After the editing is completed, the safety altitude and climb rate detection are performed again until the results meet the requirements.

[0053] Preferably, the UAV has a data acquisition system, a data storage system, a data processing system, and a wireless transmission system; the data acquisition system can collect power line data, and the data storage system can store, back up and restore the collected data; the data processing system processes and analyzes the stored data to generate an inspection report; the wireless transmission system uses wireless communication technology to realize data transmission between the UAV and the ground terminal.

[0054] Among them, the data acquisition system adopts inspection sensors of lidar and infrared thermal imager to collect images of power lines and power equipment in real time, and uses deep learning target detection algorithm to train on a large number of power inspection scene image data sets to learn the location characteristics of drones in different scenarios.

[0055] Secondly, the data storage system adopts a distributed database system to realize data storage, backup and recovery.

[0056] Furthermore, the data processing system uses computer vision and machine learning techniques to process and analyze the inspection data. The data processing system converts and transforms the raw data so that it can be better processed by the computer vision algorithm.

[0057] Specifically, the wireless transmission system selects appropriate communication protocols, enhances signal coverage, and uses interference elimination technology and data compression and optimization to process and identify data, so that during the drone's mission, the sensor data can be compressed and optimized, reducing the amount of data and transmission delay and improving the efficiency of signal transmission.

[0058] Working principle: Through drones and inspection sensors, cloud data can be determined in combination with the power line inspection route, and then the cloud data can be corrected and processed to realize the feature planning of the drone. The drone can transmit line image data in real time and support real-time three-dimensional reconstruction, which enhances effectiveness and greatly improves the inspection efficiency. The data can be wirelessly transmitted and backed up through the wireless transmission system, which greatly improves the security and accuracy of the data. Multiple paths can be generated for the drone take-off point, drone inspection point and drone landing point based on the track points; the path is checked and simulated, and when the path is impassable, the impassable path is repaired; the fitness of the passable path is calculated through the genetic algorithm model to determine the optimal path, thereby reducing the inspection time and greatly improving the inspection efficiency.

[0059] What is described above is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. An intelligent UAV power inspection method, characterized in that: The following steps are involved: Step 1: Plan the inspection route according to the characteristics of the power line to be inspected; Step 2: Use drones and inspection sensors to collect and process images of power lines that need to be inspected; Step 3: Collect data for real-time processing; Step 4: Dynamically adjust the drone’s take-off point, inspection point, and landing point; Step 5: Perform dynamic planning on step 4, adopt a particle filter algorithm, and obtain the real-time position information of the drone according to the Beidou differential airborne positioning unit in the drone.

2. The intelligent UAV power inspection method according to claim 1 is characterized in that: According to the step three, it also includes: cloud grading the power lines, extracting key inspection points of the power lines, and simulating and verifying the power lines according to the particle filtering algorithm.

3. The intelligent UAV power inspection method according to claim 1 is characterized in that: The step 4 also includes: taking the take-off point of the drone as the center, selecting four orthogonal directions, obtaining the elevations of the four orthogonal directions at a distance of 0.3-1m from the take-off point, adding the elevation of the take-off point, and calculating the arithmetic mean and variance based on the five elevation data: H=(H0+H 0° +H 90° +H 180° +H 270° ) / 5; Where: H is the arithmetic mean of the earth's height, H0 represents the earth's height at the center of the circle, and H 0° , H 90° , H 180° H 270° Respectively represent the geoid heights in the four orthogonal directions.

4. The intelligent UAV power inspection method according to claim 1 is characterized in that: The UAV includes a visual odometer and an inertial navigation system, wherein the visual odometer includes a sensor device, a control system, and a map navigation system; the sensor device collects the driving data of the UAV through a plurality of sensors, and obtains the real-time position information of the UAV through the Beidou differential airborne positioning unit; The control system collects driving data through the sensor to control the driving direction and speed of the drone; the map navigation determines the driving direction and path of the drone.

5. The intelligent UAV power inspection method according to claim 1 is characterized in that: The step 1 establishes a genetic algorithm model to generate track points, and generates multiple paths for the drone take-off point, the drone inspection point, and the drone landing point based on the track points; performs inspection simulation on the path, and when the path is impassable, repairs the impassable path; calculates the fitness of the passable path through the genetic algorithm model to determine the optimal path.

6. The intelligent UAV power inspection method according to claim 5 is characterized in that: According to the step one, it also includes:

1. Testing the safety altitude and climbing rate of the planned inspection path; 2. If the test result does not meet the preset conditions, editing and simulating the positions of the planned inspection path and the track points; 3. Repeating steps 1 and 2 until the test result meets the preset conditions.

7. The intelligent UAV power inspection method according to claim 1 is characterized in that: The drone has a data acquisition system, a data storage system, a data processing system, and a wireless transmission system; wherein the data acquisition system can collect power line data, and the data storage system stores, backs up, and restores the collected data; the data processing system processes and analyzes the stored data to generate an inspection report; The wireless transmission system adopts wireless communication technology to realize data transmission between the UAV and the ground terminal.

Images