Intelligent route planning system for fan unmanned aerial vehicle inspection

Abstract

The invention provides an intelligent route planning system for fan unmanned aerial vehicle inspection. The system comprises a data acquisition module, a route planning module, a dynamic adjustment module and an analysis optimization module. The data acquisition module is used for acquiring fan operation state information and environment information in real time; the route planning module is used for generating an inspection route of the unmanned aerial vehicle according to preset task requirements and fan distribution; the dynamic adjustment module is used for dynamically optimizing the flight route of the unmanned aerial vehicle in the unmanned aerial vehicle inspection process; the analysis optimization module is used for optimizing and analyzing a follow-up task planning route of the unmanned aerial vehicle; according to the invention, through real-time data acquisition, dynamic path adjustment and intelligent optimization, high efficiency, self-adaptability and accuracy of the unmanned aerial vehicle routing inspection route are realized, and the routing inspection efficiency and task quality are significantly improved.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned aerial vehicle (UAV) route planning systems, and in particular to an intelligent route planning system for wind turbine UAV inspection. Background Art

[0002] As a clean energy source, wind power generation has been widely used around the world, and the operation and maintenance of wind turbines directly affects the power generation efficiency and equipment safety. Among them, the status monitoring of wind turbine blades is particularly important. Blade damage such as cracks, corrosion or ice accumulation may lead to serious performance degradation or equipment failure. Therefore, regular inspection of wind turbine blades has become an important part of wind farm operation. Traditional wind turbine inspection methods mainly rely on manual or ground equipment. These methods have problems such as long time consumption, low efficiency and high safety hazards, especially when facing wind farms at high altitudes or complex terrains. It is difficult to meet actual needs. The application of drone technology provides a new, efficient and safe way for wind turbine inspections. Drones have the advantages of flexible flight, diverse perspectives, and convenient operation. They can quickly approach wind turbine blades, collect high-definition images and videos, and achieve efficient monitoring of wind turbine status.

[0003] After consulting the relevant disclosed technical solutions, the technology with publication number CN115145314B proposes a wind turbine blade inspection path planning method based on drones, including: calibrating the template wind turbine, and bringing the basic parameters of the template wind turbine into the calculation to obtain the inspection path of the template wind turbine, and the drone can adjust the posture when flying to each planned waypoint to take a more accurate picture, and then save it as an inspection path template; calibrating the wind turbine to be inspected by the drone; bringing the calibration result into the inspection path template for calculation to obtain the inspection path of the wind turbine to be inspected; this solution can be quickly applied to wind turbines of the same model but in different positions, thereby improving the inspection efficiency of drones; but this solution mainly relies on the preset inspection path template for calculation, and cannot respond to changes in the operating status of the wind turbine or the dynamic impact of the environment in real time; and lacks the ability to continuously improve the path planning strategy. Summary of the invention

[0004] The purpose of the present invention is to propose an intelligent route planning system for wind turbine UAV inspection in view of the current shortcomings.

[0005] The present invention adopts the following technical solution:

[0006] An intelligent route planning system for wind turbine drone inspection, characterized in that the system includes a data acquisition module, a route planning module, a dynamic adjustment module and an analysis and optimization module; the data acquisition module is used to obtain wind turbine operating status information and environmental information in real time; the route planning module is used to generate the drone inspection route according to pre-set task requirements and wind turbine distribution; the dynamic adjustment module is used to dynamically optimize the drone's flight route during the drone inspection process; the analysis and optimization module is used to optimize and analyze the drone's subsequent task planning route.

[0007] The data acquisition module includes an environment sensing unit and a fan status acquisition unit; the environment sensing unit is used to obtain the drone's surrounding environment information in real time during the drone inspection process; the fan status acquisition unit is used to obtain the fan operation status information in real time during the drone inspection process.

[0008] The dynamic adjustment module includes a route optimization unit and a route recording unit; the route optimization unit is used to dynamically optimize the flight route of the drone according to environmental changes; the route recording unit is used to record the navigation trajectory of each drone inspection process.

[0009] Furthermore, the route optimization unit includes a UAV status monitoring subunit, a dynamic perception subunit and a path adjustment execution subunit; the UAV status monitoring subunit is used to obtain the flight status information of the UAV itself; the dynamic perception subunit is used to dynamically adjust and generate an optimized flight route for the UAV according to the flight status information and environmental information; the path adjustment execution subunit is used to control the UAV to navigate along the dynamically adjusted and optimized flight route.

[0010] Furthermore, the dynamic sensing subunit dynamically generates an optimized flight route during the drone inspection process in the following manner:

[0011] S11: Obtaining flight status information and environmental information during the drone inspection process;

[0012] S12: Analyze the obstacle distribution in the inspection route of the UAV according to the environmental information. If there is an obstacle distribution in the current inspection route of the UAV and the distance between the obstacle and the inspection route is less than a preset safety distance threshold, generate multiple candidate adjustment paths according to the following conditions:

[0013]

[0014] in, is the direction vector of the ith obstacle avoidance path, P obstacle is the current position of the drone, P current,i is the position of the i-th obstacle avoidance point; it satisfies:

[0015]

[0016] Among them, P current is the obstacle center position, r is the obstacle avoidance radius, which is set according to the preset safety distance threshold; R(θ i ) is the rotation angle θ around the obstacle center i The rotation matrix is ​​used to generate obstacle avoidance paths with different offset angles; is the unit direction vector pointing to the center of the obstacle;

[0017] After obtaining the direction vectors of the plurality of obstacle avoidance paths, the paths are extended point by point based on each direction vector to generate candidate adjustment path point sequences as the plurality of candidate adjustment paths;

[0018] S13: Evaluate and select the best candidate adjustment path and use it as the optimized flight route; the specific implementation process is as follows:

[0019] Path optimal =argmin(C total,i );

[0020] Among them, Path optimal is the optimal candidate adjustment path selected, argmin() is the minimization function; C total,i is the comprehensive cost index of the i-th candidate adjustment path;

[0021] C total,i =α1·C distance,i +α2·C deviation,i +α3·C time,i ;

[0022] Among them, C distance,i is the path length cost of the i-th candidate adjustment path, obtained according to the total length of the candidate adjustment path; C deviation,i is the data collection cost of the i-th candidate adjustment path, which is obtained according to the amount of wind turbine operating status information obtained on the candidate adjustment path; C time,i is the time cost of the i-th candidate adjustment path, which is obtained based on the length of the candidate adjustment path and the flight status information of the UAV; α1, α2 and α3 are the weight coefficients of path length cost, data collection cost and time cost, respectively, which are pre-set by the user based on historical experience;

[0023] S14: Convert the optimized flight route into executable flight instructions, and transmit the flight instructions to the path adjustment execution subunit.

[0024] Furthermore, the analysis and optimization module includes a data storage unit, a model evaluation unit and an optimized route output unit; the data storage unit is used to store the flight information of the UAV during each inspection process, and the flight information includes the navigation trajectory of the UAV, the task completion status and the UAV status information; the model evaluation unit is used to train and learn through a machine learning model combined with the flight information during each inspection process of the UAV, so as to optimize and generate a path planning strategy that is adapted to different inspection task requirements and wind turbine distribution; the optimized route output unit is used to output a path planning strategy that matches the subsequent task planning according to the output result of the model evaluation unit.

[0025] Furthermore, the model evaluation unit includes a feature extraction subunit, a machine learning model and an update unit; the feature extraction unit is used to extract key features for model input from the flight information; the machine learning model is used to optimize the path planning strategy through training and learning based on the data information provided by the feature extraction subunit, and generate an optimal route that adapts to different mission requirements and wind turbine distribution; the update unit is used to organize a certain amount of flight information into new training samples after obtaining this part of flight information, and input this part of flight information into the machine learning model for incremental learning, thereby dynamically updating the machine learning model weights.

[0026] Beneficial effects achieved by the present invention:

[0027] The present invention constructs a full-process inspection path planning system by combining the real-time collection and dynamic adjustment of UAV flight information and the optimization of machine learning models; during the UAV inspection process, the obstacle distribution is analyzed in real time, multiple candidate paths are generated, and the optimal path is selected as the optimized flight route based on comprehensive cost evaluation, and finally converted into executable flight instructions to guide the navigation of the UAV during the inspection process; by storing the historical flight information of the UAV and inputting it into the machine learning model, the path planning strategy is continuously optimized through the deep reinforcement learning architecture, so that the path planning capability has adaptability and learning ability, and the optimal path planning solution is output according to user needs, which not only realizes efficient inspection task execution, but also improves the intelligence level of UAV inspection path planning, and provides reliable technical support for wind turbine inspection in complex environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] The present invention can be further understood from the following description in conjunction with the accompanying drawings. The components in the figures are not necessarily drawn to scale, but the emphasis is placed on illustrating the principles of the embodiments. In different views, the same reference numerals designate corresponding parts.

[0029] Figure 1 It is a schematic diagram of the overall module of the present invention.

[0030] Figure 2This is a schematic diagram of the workflow of the dynamic sensing subunit of the present invention.

[0031] Figure 3 Schematic diagram of the training learning process of the machine learning model of the present invention. DETAILED DESCRIPTION

[0032] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with its embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention; for those skilled in the art, other systems, methods and / or features of the present embodiment will become apparent after reviewing the following detailed description; it is intended that all such additional systems, methods, features and advantages are included in this specification; included within the scope of the present invention and protected by the appended claims; additional features of the disclosed embodiments are described in the following detailed description, and these features will be apparent from the following detailed description.

[0033] The same or similar numbers in the drawings of the embodiments of the present invention correspond to the same or similar parts; in the description of the present invention, it should be understood that if the terms "upper", "lower", "left", "right" and the like indicate directions or positional relationships based on the directions or positional relationships shown in the drawings, it is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or component referred to must have a specific direction, be constructed and operated in a specific direction. Therefore, the terms describing the positional relationship in the drawings are only used for illustrative purposes and cannot be understood as limitations on this patent. For ordinary technicians in this field, the specific meanings of the above terms can be understood according to specific circumstances.

[0034] Embodiment 1:

[0035] like Figure 1 As shown, this embodiment provides an intelligent route planning system for wind turbine UAV inspection, the system includes a data acquisition module, a route planning module, a dynamic adjustment module and an analysis and optimization module; the data acquisition module is used to obtain wind turbine operating status information and environmental information in real time; the route planning module is used to generate the inspection route of the UAV according to the preset task requirements and wind turbine distribution; the dynamic adjustment module is used to dynamically optimize the flight route of the UAV during the UAV inspection process; the analysis and optimization module is used to optimize and analyze the route for subsequent task planning of the UAV;

[0036] The data acquisition module includes an environment sensing unit and a fan status acquisition unit; the environment sensing unit is used to obtain the surrounding environment information of the drone in real time during the drone inspection process; the fan status acquisition unit is used to obtain the fan operation status information in real time during the drone inspection process;

[0037] Specifically, the environmental perception unit obtains environmental information through a laser radar, a high-definition camera, a meteorological sensor and an ultrasonic sensor installed on the drone, and the environmental information includes wind speed, wind direction and obstacle distribution information; the fan status acquisition unit obtains fan operation status information through a high-definition camera and an infrared thermal imager installed on the drone, and the fan operation status information includes fan images and fan temperature information;

[0038] The dynamic adjustment module includes a route optimization unit and a route recording unit; the route optimization unit is used to dynamically optimize the flight route of the drone according to environmental changes; the route recording unit is used to record the navigation track of each drone inspection process;

[0039] Furthermore, the route optimization unit includes a drone state monitoring subunit, a dynamic perception subunit and a path adjustment execution subunit; the drone state monitoring subunit is used to obtain the drone's own flight state information; the dynamic perception subunit is used to dynamically adjust and generate the drone's optimized flight route according to the flight state information and environmental information; the path adjustment execution subunit is used to control the drone to navigate along the dynamically adjusted optimized flight route;

[0040] Further, such as Figure 2 As shown, the dynamic perception subunit dynamically generates an optimized flight route during the drone inspection process in the following ways:

[0041] S11: Obtaining flight status information and environmental information during the drone inspection process;

[0042] S12: Analyze the obstacle distribution in the inspection route of the UAV according to the environmental information. If there is an obstacle distribution in the current inspection route of the UAV and the distance between the obstacle and the inspection route is less than a preset safety distance threshold, generate multiple candidate adjustment paths according to the following conditions:

[0043]

[0044] in, is the direction vector of the ith obstacle avoidance path, P obstacle is the current position of the drone, P current,i is the position of the i-th obstacle avoidance point; it satisfies:

[0045]

[0046] Among them, P current is the obstacle center position, r is the obstacle avoidance radius, which is set according to the preset safety distance threshold; R(θ i ) is the rotation angle θ around the obstacle center iThe rotation matrix is ​​used to generate obstacle avoidance paths with different offset angles; is the unit direction vector pointing to the center of the obstacle;

[0047] After obtaining the direction vectors of the plurality of obstacle avoidance paths, the paths are extended point by point based on each direction vector to generate candidate adjustment path point sequences as the plurality of candidate adjustment paths;

[0048] S13: Evaluate and select the best candidate adjustment path and use it as the optimized flight route; the specific implementation process is as follows:

[0049] Path optimal =argmin(C total,i );

[0050] Among them, Path optimal is the optimal candidate adjustment path selected, argmin() is the minimization function; C total,i is the comprehensive cost index of the i-th candidate adjustment path;

[0051] C total,i =α1·C distance,i +α2·C deviation,i +α3·C time,i ;

[0052] Among them, C distance,i is the path length cost of the i-th candidate adjustment path, obtained according to the total length of the candidate adjustment path; C deviation,i is the data collection cost of the i-th candidate adjustment path, which is obtained according to the amount of wind turbine operating status information obtained on the candidate adjustment path; C time,i is the time cost of the i-th candidate adjustment path, which is obtained based on the length of the candidate adjustment path and the flight status information of the UAV; α1, α2 and α3 are the weight coefficients of path length cost, data collection cost and time cost, respectively, which are pre-set by the user based on historical experience;

[0053] S14: converting the optimized flight route into an executable flight instruction, and transmitting the flight instruction to the path adjustment execution subunit;

[0054] Furthermore, some functional implementation codes of the dynamic perception subunit are as follows:

[0055]

[0056]

[0057]

[0058] This solution obtains the UAV's flight status information and environmental information, analyzes the obstacle distribution in real time, generates multiple candidate paths, and selects the optimal path as the optimized flight route based on the comprehensive cost evaluation, and finally converts it into executable flight instructions to guide the UAV's navigation during the inspection process; the comprehensive cost evaluation includes the path length cost, data collection cost and time cost, so as to optimize the UAV's flight efficiency, mission execution quality and inspection data collection integrity while meeting the obstacle avoidance requirements.

[0059] Embodiment 2:

[0060] This embodiment should be understood to include at least all the features of any of the above embodiments, and further improve upon them;

[0061] The present embodiment provides a UAV intelligent identification system for wind turbine blade defects, the system comprising a data acquisition module, a route planning module, a dynamic adjustment module and an analysis and optimization module; the data acquisition module is used to obtain wind turbine operating status information and environmental information in real time; the route planning module is used to generate a UAV inspection route according to pre-set task requirements and wind turbine distribution; the dynamic adjustment module is used to dynamically optimize the flight route of the UAV during the UAV inspection process; the analysis and optimization module is used to optimize and analyze the UAV's subsequent task planning route;

[0062] Furthermore, the analysis and optimization module includes a data storage unit, a model evaluation unit and an optimized route output unit; the data storage unit is used to store the flight information of the drone during each inspection process, and the flight information includes the navigation track of the drone, the task completion status and the drone status information; the model evaluation unit is used to train and learn through a machine learning model combined with the flight information during each inspection process of the drone, so as to optimize and generate a path planning strategy that is adapted to different inspection task requirements and wind turbine distribution; the optimized route output unit is used to output a path planning strategy that matches the subsequent task planning according to the output result of the model evaluation unit;

[0063] Furthermore, the model evaluation unit includes a feature extraction subunit, a machine learning model and an updating unit; the feature extraction unit is used to extract key features for model input from flight information; the machine learning model is used to optimize the path planning strategy through training and learning based on the data information provided by the feature extraction subunit, and generate the optimal route adapted to different mission requirements and wind turbine distribution; the updating unit is used to organize this part of flight information into new training samples after obtaining a certain amount of flight information, and input this part of flight information into the machine learning model for incremental learning, thereby dynamically updating the weight of the machine learning model;

[0064] Furthermore, the key features extracted by the feature extraction unit include task requirement features, flight trajectory features, task completion features and drone status features; the task requirement features include inspection task requirements and wind turbine distribution; the flight trajectory features include flight path length and flight trajectory; the task completion features include wind turbine operation status information collection quality and collection rate; the drone status features include flight energy consumption and obstacle avoidance times;

[0065] Further, such as Figure 3 As shown, the training and learning process of the machine learning model is as follows:

[0066] S21: Data preparation and feature input: obtaining key features extracted by the feature extraction unit corresponding to each piece of flight information as training data;

[0067] S22: Use the Actor-Critic architecture in deep reinforcement learning to build a machine learning model. The Actor network in the architecture is used to generate a path planning strategy, and the Critic network is used to evaluate the comprehensive value of the current path planning strategy. The Critic network's evaluation of the current path planning strategy satisfies:

[0068] U task =β1·U distance +β2·U quality +β3·U energy +β4·U disturbance ;

[0069] Among them, U task is the comprehensive value coefficient of the current path planning strategy, U distance is the path value coefficient of the current path planning strategy, which is proportional to the path length of the current path planning strategy; U quality is the task completion value coefficient of the current path planning strategy, which is inversely proportional to the quality and rate of wind turbine operation status information collected by the current path planning strategy; U energy is the energy consumption value coefficient of the current path planning strategy, which is proportional to the flight energy consumption of the current path planning strategy; β1, β2, β3 and β4 are the influence weights of the path value coefficient, task completion value coefficient, energy consumption value coefficient and disturbance value coefficient, respectively, which can be set by the user according to their own needs; U disturbance is the disturbance value coefficient of the current path planning strategy, satisfying:

[0070] U disturbance =k·exp(ρ·N obstacle );

[0071] Among them, k is the initial disturbance value coefficient, which is set by the user according to the actual mission scenario; ρ is the disturbance impact intensity, which is set by the user according to the obstacle avoidance requirements and mission requirements of the drone; N obstacle The number of obstacle avoidances in the current path planning strategy;

[0072] S23: Input the training data obtained in step S21 into the machine learning model model for training and updating the model parameters; wherein the Critic network optimizes the loss function through the time difference error in combination with the comprehensive value coefficient, thereby improving the path evaluation capability; the Actor network optimizes the path generation strategy through the policy gradient method based on the feedback information of the Critic network, so that it gradually generates a path planning strategy with better comprehensive value; the model training is completed through multiple rounds of iterations, so that the model can achieve the simultaneous improvement of the path planning capability and the policy evaluation capability;

[0073] Furthermore, when the user has a demand for an inspection task in the future, the optimized route output unit inputs the task requirements and wind turbine distribution provided by the user into the feature extraction unit to complete the feature extraction and then inputs it into the machine learning model, thereby outputting the path planning strategy of the current user task requirements, and inputting the output path planning strategy into the route planning module so that the UAV executes a specific inspection route, thereby realizing efficient inspection operations;

[0074] This solution combines the storage, dynamic learning and path optimization of UAV flight information, integrates historical flight information and real-time task requirements into the machine learning model, and realizes the intelligence and adaptability of UAV inspection route planning; in the deep learning model, multi-dimensional factors such as path length, task completion quality, energy consumption and route obstacle avoidance are integrated to dynamically generate the optimal path planning strategy, thereby effectively improving the execution efficiency and resource utilization of inspection tasks, while meeting the diverse inspection needs in complex environments.

[0075] The contents disclosed above are only preferred feasible embodiments of the present invention, and do not limit the protection scope of the present invention. Therefore, all equivalent technical changes made using the contents of the present invention specification and drawings are included in the protection scope of the present invention. In addition, the elements therein can be updated as technology develops.

Claims

1. An intelligent route planning system for wind turbine drone inspection, characterized in that: The system includes a data acquisition module, a route planning module, a dynamic adjustment module and an analysis and optimization module; the data acquisition module is used to obtain wind turbine operating status information and environmental information in real time; the route planning module is used to generate an inspection route for the drone according to pre-set task requirements and wind turbine distribution; The dynamic adjustment module is used to dynamically optimize the flight route of the drone during the drone inspection process; the analysis and optimization module is used to optimize and analyze the flight route of the drone's subsequent mission planning; The data acquisition module includes an environment sensing unit and a fan status acquisition unit; the environment sensing unit is used to obtain the surrounding environment information of the drone in real time during the drone inspection process; the fan status acquisition unit is used to obtain the fan operation status information in real time during the drone inspection process; The dynamic adjustment module includes a route optimization unit and a route recording unit; the route optimization unit is used to dynamically optimize the flight route of the drone according to environmental changes; the route recording unit is used to record the navigation trajectory of each drone inspection process.

2. The intelligent route planning system for wind turbine drone inspection according to claim 1 is characterized in that: The route optimization unit includes a UAV status monitoring subunit, a dynamic perception subunit and a path adjustment execution subunit; the UAV status monitoring subunit is used to obtain the flight status information of the UAV itself; the dynamic perception subunit is used to dynamically adjust and generate the optimized flight route of the UAV according to the flight status information and environmental information; the path adjustment execution subunit is used to control the UAV to navigate along the flight route optimized after dynamic adjustment.

3. The intelligent route planning system for wind turbine drone inspection according to claim 2 is characterized in that: The dynamic perception subunit dynamically generates an optimized flight path during the drone inspection process in the following ways: S11: Obtaining flight status information and environmental information during the drone inspection process; S12: Analyze the obstacle distribution in the inspection route of the UAV according to the environmental information. If there is an obstacle distribution in the current inspection route of the UAV and the distance between the obstacle and the inspection route is less than a preset safety distance threshold, generate multiple candidate adjustment paths according to the following conditions: in, is the direction vector of the ith obstacle avoidance path, P obstacle is the current position of the drone, P current,i is the position of the i-th obstacle avoidance point; it satisfies: Among them, P current is the obstacle center position, r is the obstacle avoidance radius, which is set according to the preset safety distance threshold; R(θ i ) is the rotation angle θ around the obstacle center i The rotation matrix is ​​used to generate obstacle avoidance paths with different offset angles; is the unit direction vector pointing to the center of the obstacle; After obtaining the direction vectors of the plurality of obstacle avoidance paths, the paths are extended point by point based on each direction vector to generate candidate adjustment path point sequences as the plurality of candidate adjustment paths; S13: Evaluate and select the best candidate adjustment path and use it as the optimized flight route; the specific implementation process is as follows: Path optimal =argmin(C total,i ); Among them, Path optimal is the optimal candidate adjustment path selected, argmin() is the minimization function; C total,i is the comprehensive cost index of the i-th candidate adjustment path; C total,i =α1·C distance,i +α2·C deviation,i +α3·C time,i ; Among them, C distance,i is the path length cost of the i-th candidate adjustment path, obtained according to the total length of the candidate adjustment path; C deviation,i is the data collection cost of the i-th candidate adjustment path, which is obtained according to the amount of wind turbine operating status information obtained on the candidate adjustment path; C time,i is the time cost of the i-th candidate adjustment path, which is obtained based on the length of the candidate adjustment path and the flight status information of the UAV; α1, α2 and α3 are the weight coefficients of path length cost, data collection cost and time cost, respectively, which are pre-set by the user based on historical experience; S14: Convert the optimized flight route into executable flight instructions, and transmit the flight instructions to the path adjustment execution subunit.

4. The intelligent route planning system for wind turbine drone inspection according to claim 3 is characterized in that: The analysis and optimization module includes a data storage unit, a model evaluation unit and an optimized route output unit; the data storage unit is used to store the flight information of the drone during each inspection, and the flight information includes the navigation track of the drone, the task completion status and the drone status information; the model evaluation unit is used to train and learn through a machine learning model combined with the flight information during each inspection of the drone, so as to optimize and generate a path planning strategy that is adapted to different inspection task requirements and wind turbine distribution; The optimized route output unit is used to output a path planning strategy that matches the subsequent task planning according to the output result of the model evaluation unit.

5. The intelligent route planning system for wind turbine drone inspection according to claim 1 is characterized in that: The model evaluation unit includes a feature extraction subunit, a machine learning model and an update unit; the feature extraction unit is used to extract key features for model input from flight information; The machine learning model is used to optimize the path planning strategy through training and learning based on the data information provided by the feature extraction subunit, and generate the optimal route that adapts to different task requirements and wind turbine distribution; the update unit is used to organize a certain amount of flight information into new training samples after obtaining this part of flight information, and input this part of flight information into the machine learning model for incremental learning, thereby dynamically updating the machine learning model weights.

Images