Wind power plant intelligent inspection method and system based on unmanned aerial vehicle inspection path planning

Abstract

The invention relates to a wind power plant intelligent inspection method and system based on unmanned aerial vehicle inspection path planning, and the method comprises the following steps: S1, constructing an unmanned aerial vehicle inspection system which comprises an unmanned aerial vehicle and a cloud platform data analysis system; s2, unmanned aerial vehicle inspection parameters are set; s3, planning an autonomous inspection and obstacle avoidance route of the unmanned aerial vehicle by adopting an artificial potential field method; and S4, the unmanned aerial vehicle carries out routing inspection according to the set routing inspection parameters and the planned routing inspection route, and transmits a routing inspection result to the cloud platform data analysis system after routing inspection is completed. Compared with the prior art, the method has the advantages that the station daily inspection efficiency is improved, and the accuracy of data processing in unmanned aerial vehicle route planning is improved.

Description

Technical Field

[0001] The present invention relates to a wind farm inspection method, and in particular to an intelligent wind farm inspection method and system based on unmanned aerial vehicle (UAV) inspection path planning. Background Art

[0002] In recent years, drones have become increasingly popular in the commercial sector, and drones equipped with various types of sensors can be used in even more applications. For example, in agriculture, drones equipped with spectral and thermal imaging sensors can monitor crop health and soil moisture. In environmental monitoring, gas sensors and water quality sensors can be used to detect pollutants in water and air. In meteorology, meteorological sensors can be used to collect atmospheric data.

[0003] In the new energy sector, drones are being used in the operation, maintenance, and inspection of photovoltaic and wind farms. Drones equipped with thermal imaging cameras can quickly identify hot spots, damage, or faults in photovoltaic modules. Drones equipped with high-definition cameras can identify surface dirt, cracks, and breakage on photovoltaic modules, as well as external damage and corrosion on wind turbine blades, towers, and nacelles. They can also map and assess the surrounding environment of new energy stations. Deploying drones in the daily operation and maintenance of photovoltaic and wind farms can significantly improve efficiency, reduce safety hazards associated with human operators, and accurately identify and locate faults.

[0004] After searching, Chinese patent publication number CN119645049A discloses a smart inspection system and method for wind and solar power stations using drones. Specifically, it discloses that an intelligent analysis module, including an intelligent fault diagnosis and early warning module, uses AI image recognition technology to intelligently analyze the collected images and videos, automatically identify defects and faults in wind power equipment and photovoltaic components, and eliminate the need for manual inspection of faults. At the same time, the intelligent obstacle avoidance module uses visual avoidance technology to process and analyze images using computer vision technology to extract information about obstacles. By identifying and classifying obstacles, the nature and degree of danger of the obstacles are determined. According to the nature and degree of danger of the obstacles, a suitable avoidance strategy is selected to perfectly avoid obstacles that need to be avoided and reduce the risk of damage to the drone.

[0005] The above-mentioned drones have significant advantages in the inspection of wind and solar power stations, but there are still some defects and shortcomings, including limited endurance and load capacity, complex data processing and analysis, interference with accuracy in complex environments, and standardization and compatibility issues. How to solve these problems and thus promote the wider application of drones in the inspection of new energy stations has become a technical issue that needs to be solved. Summary of the Invention

[0006] The purpose of the present invention is to overcome the defects of the above-mentioned prior art and to provide a wind farm intelligent inspection method and system based on drone inspection path planning.

[0007] The purpose of the present invention can be achieved by the following technical solutions:

[0008] According to one aspect of the present invention, a wind farm intelligent inspection method based on drone inspection path planning is provided, the method comprising the following steps:

[0009] Step S1: Build a drone inspection system, including drones and cloud platform data analysis systems;

[0010] Step S2, setting the drone inspection parameters;

[0011] Step S3, using the artificial potential field method to plan the autonomous inspection and obstacle avoidance route of the UAV;

[0012] In step S4, the drone performs inspections according to the set inspection parameters and planned inspection routes, and transmits the inspection results to the cloud platform data analysis system after the inspection is completed.

[0013] As a preferred technical solution, the inspection parameters in step S2 include flight altitude, flight speed, autonomous obstacle avoidance safety buffer distance, wind resistance level, meteorological threshold and camera parameters.

[0014] As a preferred technical solution, the flight height H mm =H hub +R blade +ΔS;

[0015] Among them H hub is the hub height, R blade is the blade radius, and ΔS is the reserved safety height.

[0016] As an optimal technical solution, the flight speed is the minimum value among the camera shooting speed, the endurance speed, and the safe braking speed.

[0017] As a preferred technical solution, the inspection parameters in step S2 are calibrated in real time according to on-site working conditions during the actual flight process.

[0018] As a preferred technical solution, step S3 specifically includes:

[0019] Step S301, constructing a virtual force field of attraction and repulsion to move the drone in the direction of the resultant force, where the attraction is the target point and the repulsion is the obstacle;

[0020] Step S302: If the UAV encounters a new obstacle during flight, the obstacle sequence is updated and the path planning is re-performed.

[0021] As a preferred technical solution, step S301 specifically includes:

[0022] Step S3011, gravitational field U att (q) is calculated as follows:

[0023]

[0024] where k att is the gravitational coefficient, d(q,q goal ) is the distance from the current position of the UAV to the target point, q is the current position of the UAV, q goal Inspect target locations for drones;

[0025] Step S3012, repulsive field U att (q) is calculated as follows:

[0026]

[0027] where k rep is the repulsion coefficient, d(q,q obs ) is the distance from the UAV to the obstacle, q obs is the obstacle position, d safe For a safe distance

[0028] Step S3013: The combined force F total for:

[0029]

[0030] The drone moves a distance q along the direction of the resultant force next for:

[0031]

[0032] Where η is the step size.

[0033] As a preferred technical solution, due to the rotation of the fan blades, the repulsive field is updated in real time:

[0034]

[0035] in is the repulsive field at the current position and time, k rep is the repulsion coefficient, q blade (t) is the position of the blade at time t, σ is the attenuation coefficient;

[0036] Added wind field correction, increasing virtual resistance when flying against the wind and reducing it when flying with the wind:

[0037] F wind =-k wind (vdrone -v wind )

[0038] Among them F wind is the wind force vector, v drone is the UAV velocity vector, k wind is the drag coefficient, v wind is the wind speed vector.

[0039] According to another aspect of the present invention, a system for the wind farm intelligent inspection method based on drone inspection path planning is provided, the system comprising:

[0040] The equipment layer includes drone equipment and drone nests. The drone pods are equipped with at least a 20-megapixel visible light camera and an infrared thermal imaging device. The drone nests detect the status of the drone equipment and itself.

[0041] The application service layer, including the cloud platform data analysis system, is used to issue task instructions to the device layer and receive drone status data;

[0042] The communication layer uses 4G or 5G networks for communication between the application service layer and the device layer for quality inspection.

[0043] As a preferred technical solution, the cloud platform data analysis system includes:

[0044] A visualization module for UAV inspection and wind turbine blade fault analysis, used to display UAV equipment information;

[0045] The drone lifecycle management module is used to manage the drone's body status, usage time, and battery usage;

[0046] The inspection report generation module automatically identifies the fault type and generates an inspection report.

[0047] Compared with the prior art, the present invention has the following advantages:

[0048] 1) This invention improves the efficiency of daily inspections at stations and increases the accuracy of data processing in drone route planning;

[0049] 2) When planning an inspection route, the present invention updates the obstacle sequence and replans the path when the drone encounters a new obstacle during flight. By optimizing the route, inspection efficiency can be improved and ineffective flights can be reduced.

[0050] 3) The present invention can ensure flight safety and avoid the hidden danger of equipment damage caused by the rotation of fan blades;

[0051] 4) The present invention can support preventive maintenance, timely detect safety hazards such as blade cracks, and avoid major failures. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 Detailed flow chart of the method of the present invention;

[0053] Figure 2 This is a flow chart of the drone path planning of the present invention;

[0054] Figure 3 Schematic diagram of the structure of the system of the present invention. DETAILED DESCRIPTION

[0055] 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 part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0056] like Figure 1 As shown, the present invention provides a wind farm intelligent inspection method based on drone inspection path planning, the method comprising the following steps:

[0057] Step S1: Build a drone inspection system. The intelligent drone inspection system consists of a device layer, a communication layer, and an application service layer. The device layer comprises drones and drone nests. Drones are equipped with pods, high-definition cameras, and other equipment. They will subsequently complete autonomous flights along a prescribed path to acquire characteristic information about the wind farm route. The drone nests contain charging stations, a weather station, and data transmission modules to control drone takeoff and landing, charging, status monitoring, and data transmission. The communication layer architecture utilizes 4G / 5G networks to enable remote, real-time communication and control between the drone, nest, and data platform. The application service layer monitors drone / nest status in real time and sends remote, real-time commands.

[0058] Step S2: Set the drone inspection parameters. The parameters required for intelligent drone inspections at wind farms include: flight altitude (a high altitude affects image clarity, while a low altitude increases collision risk); flight speed (to ensure both flight stability and inspection efficiency); autonomous obstacle avoidance safety buffer distance; wind resistance level and meteorological thresholds (to automatically return home and terminate inspections when environmental conditions exceed thresholds (such as wind speed, precipitation, and temperature); camera resolution and frame rate; and data analysis parameters, such as image overlap, data format, and photo format. These parameters should be calibrated in real time based on on-site operating conditions during actual flight.

[0059] Step S3 uses the artificial potential field method to plan the drone's autonomous inspection and obstacle avoidance route. Autonomous inspections by drones require consideration of multiple factors, including the inspection area environment, obstacles, and the inspection mission. This ensures the safety of the drone's inspection path and effectively avoids obstacles. Therefore, to ensure the drone can perform its mission safely, stably, and efficiently, it is necessary to plan the drone's inspection trajectory and autonomously avoid obstacles.

[0060] In step S4, the drone conducts an inspection based on the configured inspection parameters and planned inspection route. Upon completion, the inspection results are transmitted to the cloud platform data analysis system, displaying the drone's data and image transmission information, flight altitude and speed, and latitude and longitude information. This enables the drone's lifecycle management, primarily including its status, usage time, and battery life. The inspection results are summarized to prepare for the next round of inspections.

[0061] The specific implementation process of the method of the present invention is as follows:

[0062] Step 1: Build the UAV inspection system framework, such as Figure 3 As shown, the hardware framework of the automated inspection system primarily consists of a drone and a drone nest. The drone's pod must be equipped with a visible light camera with at least 20 megapixels to better capture defects such as blade surface cracks and paint peeling. The pod should also have infrared thermal imaging capabilities with a temperature measurement accuracy within ±2°C to detect defects such as abnormal electrical connector temperatures and gearbox temperature rise. The drop-off stabilization gimbal must ensure stable viewing in wind gusts of 15 m / s. The drone must have a minimum IP54 protection rating. The drone nest must provide millimeter-level positioning guidance, achieving a landing accuracy of ±2 cm. Furthermore, the nest must be able to detect the drone's equipment and its own status and faults. The drone's flight endurance depends on the specific area of ​​the station, but should be at least one hour. The cloud platform must undergo a three-way handshake (cloud platform-dock nest-drone) when issuing mission commands and receiving drone status data to ensure high data reliability.

[0063] Step 2: Set inspection parameters. Flight altitude H mm =H hub +R bllade +ΔS, where H hub is the hub height, R bllade is the blade radius, and ΔS is the reserved safety height.

[0064] The speed setting needs to take into account the camera shooting speed, endurance speed, and safe braking speed. Where GSD is the ground resolution. The endurance speed is usually 60%-70% of the maximum speed of the drone. The safe specified speed is The flight speed should be the minimum of the three.

[0065] The wind resistance level is set based on the weather data of the day. During actual flight, the parameters should be calibrated in real time according to the actual operating conditions.

[0066] Step 3: Planning the inspection route. This invention uses the artificial potential field method to plan the autonomous inspection and obstacle avoidance route of the UAV. It is necessary to construct a virtual force field of attraction (target point) and repulsion (obstacle) to make the UAV move along the direction of the resultant force.

[0067] The gravitational field is calculated as follows:

[0068]

[0069] where k att is the gravitational coefficient, d(q,q goal ) is the distance from the current position of the UAV to the target point.

[0070] The repulsive field is calculated as follows:

[0071]

[0072] where k rep is the repulsion coefficient, d(q,q obs ) is the distance from the UAV to the obstacle, d safe It is a safe distance (for example, the safe distance between a drone and a wind turbine blade is 15m).

[0073] The combined force of the two is:

[0074]

[0075] The distance the UAV moves in the direction of the resultant force is:

[0076]

[0077] Where η is the step size.

[0078] Due to the rotation of the fan blades, the repulsive field needs to be updated in real time:

[0079]

[0080] where q blade (t) is the position of the blade at time t, and σ is the attenuation coefficient.

[0081] Added wind field correction, increasing virtual resistance when flying against the wind and reducing it when flying with the wind:

[0082] F wind =-k wind (v drone -v wind )

[0083] where k windis the drag coefficient, v wind is the wind speed vector.

[0084] Due to the long wind farm lines and complex environment, the UAV will encounter multiple obstacles when inspecting the wind farm lines. When the UAV encounters a new obstacle during flight, it will update the obstacle sequence and re-plan the path. The specific obstacle avoidance path planning steps are as follows: Figure 2 shown.

[0085] Step 4: Data transmission and analysis of inspection results. A visualization system for analyzing wind turbine blade faults during drone inspections is constructed, displaying the drone's data and image transmission information, flight altitude and speed, and latitude and longitude. This system also provides comprehensive drone lifecycle management, including information on aircraft status, usage time, and battery life. This system provides information on the drone's battery life, number of charge and discharge cycles, cumulative flight time, and notifications for overtime. Historical flight videos collected by the drone are analyzed using an artificial intelligence algorithm, which transmits and plays back the data, and can archive and store live video streams. This system automatically identifies fault types and generates inspection reports, providing comprehensive information to management personnel.

[0086] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present invention, and such modifications or substitutions are intended to be within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be subject to the scope of protection of the claims.

Claims

1. A wind farm intelligent inspection method based on drone inspection path planning, characterized in that: The method comprises the following steps: Step S1: Build a drone inspection system, including drones and cloud platform data analysis systems; Step S2, setting the drone inspection parameters; Step S3, using the artificial potential field method to plan the autonomous inspection and obstacle avoidance route of the UAV; In step S4, the drone performs inspections according to the set inspection parameters and planned inspection routes, and transmits the inspection results to the cloud platform data analysis system after the inspection is completed.

2. The wind farm intelligent inspection method based on drone inspection path planning according to claim 1 is characterized in that: The inspection parameters in step S2 include flight altitude, flight speed, autonomous obstacle avoidance safety buffer distance, wind resistance level, weather threshold and camera parameters.

3. The wind farm intelligent inspection method based on drone inspection path planning according to claim 2 is characterized in that: The flying height H mm =H hub +R blade +ΔS; Among them H hub is the hub height, R blade is the blade radius, and ΔS is the reserved safety height.

4. The wind farm intelligent inspection method based on drone inspection path planning according to claim 2 is characterized in that: The flight speed is the minimum value among the camera shooting speed, the endurance speed, and the safe braking speed.

5. The wind farm intelligent inspection method based on drone inspection path planning according to claim 2 is characterized in that: The inspection parameters in step S2 are calibrated in real time according to the on-site working conditions during the actual flight process.

6. The wind farm intelligent inspection method based on drone inspection path planning according to claim 1 is characterized in that: The step S3 specifically includes: Step S301, constructing a virtual force field of attraction and repulsion to move the drone in the direction of the resultant force, where the attraction is the target point and the repulsion is the obstacle; Step S302: If the UAV encounters a new obstacle during flight, the obstacle sequence is updated and the path planning is re-performed.

7. The wind farm intelligent inspection method based on drone inspection path planning according to claim 6 is characterized in that: The step S301 specifically includes: Step S3011, gravitational field U att (q) is calculated as follows: where k att is the gravitational coefficient, d(q,q goal ) is the distance from the current position of the UAV to the target point, q is the current position of the UAV, q goal For drones to inspect target locations; Step S3012, repulsive field U att (q) is calculated as follows: where k rep is the repulsion coefficient, d(q,q obs ) is the distance from the UAV to the obstacle, q obs is the obstacle position, d safe For a safe distance Step S3013: The combined force F total for: The drone moves a distance q along the direction of the resultant force next for: Where η is the step size.

8. The wind farm intelligent inspection method based on drone inspection path planning according to claim 7 is characterized in that: Due to the rotation of the fan blades, the repulsive field is updated in real time: in is the repulsive field at the current position and time, k rep is the repulsion coefficient, q blade (t) is the position of the blade at time t, σ is the attenuation coefficient; Added wind field correction, increasing virtual resistance when flying against the wind and reducing it when flying with the wind: F wind =-k wind (v drone -v wind ) Among them F wind is the wind force vector, v drone is the UAV velocity vector, k wind is the drag coefficient, v wind is the wind speed vector.

9. A system for the wind farm intelligent inspection method based on drone inspection path planning as described in any one of claims 1 to 8, characterized in that: The system includes: The equipment layer includes drone equipment and drone nests. The drone pods are equipped with at least a 20-megapixel visible light camera and an infrared thermal imaging device. The drone nests detect the status of the drone equipment and itself. The application service layer, including the cloud platform data analysis system, is used to issue task instructions to the device layer and receive drone status data; The communication layer uses 4G or 5G networks for communication between the application service layer and the device layer for quality inspection.

10. The system according to claim 9, characterized in that The cloud platform data analysis system includes: A visualization module for UAV inspection and wind turbine blade fault analysis, used to display UAV equipment information; The drone lifecycle management module is used to manage the drone's body status, usage time, and battery usage; The inspection report generation module automatically identifies the fault type and generates an inspection report.

Images