Wind power plant blade lightning protection detection unmanned aerial vehicle task scheduling and path optimization management method

Abstract

The invention relates to the field of resource allocation, and discloses a wind power plant blade lightning protection detection unmanned aerial vehicle task scheduling and path optimization management method, which is used for improving the efficiency, safety and economy of wind power plant blade lightning protection detection. Comprising the steps of generating a dynamic risk tag and sorting a task queue based on a fan spacing topological relation, a blade grounding resistance annual degradation rate and a real-time lightning early warning level, outputting a detection work order with a time window in combination with the residual electric quantity of the unmanned aerial vehicle and a return distance, and calculating a unit time cost derivative by adopting a fractional order differential equation, and dynamically regulating and controlling the deployment density of the unmanned aerial vehicle cluster, constructing a three-dimensional composite potential field containing the lightning rod safety radius in the digital elevation model, monitoring the deviation between the actual detection cost and the predicted value in real time, and dynamically adjusting the work order priority based on the enterprise risk coefficient. According to the method, dynamic risk assessment, cost optimization, obstacle avoidance planning and intelligent decision making are integrated, and the timeliness, economical efficiency and reliability of wind power plant blade lightning protection detection are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the field of resource allocation, and in particular to a method for task scheduling and path optimization management of unmanned aerial vehicle (UAV) for lightning protection inspection of blades in wind farms. Background Art

[0002] With the transformation of the global energy structure and the large-scale development of renewable energy, wind power, as a key component of clean energy, continues to see rapid growth in installed capacity. Wind farms are typically located in areas with complex geographical environments and variable climatic conditions, such as coastal areas, plateaus, or mountainous areas. While these areas are rich in wind resources, they also face challenges such as frequent lightning activity and rugged terrain. As core components for capturing wind energy, the structural integrity of wind turbine blades is directly related to power generation efficiency and equipment safety. However, lightning strikes on blades can cause material aging, crack propagation, or even fracture, seriously threatening the stable operation of wind farms. Therefore, efficient lightning protection inspection and maintenance of wind turbine blades are critical to ensuring wind farm safety.

[0003] Traditional wind turbine blade lightning protection inspections rely primarily on manual inspections or fixed monitoring equipment. Manual inspections are characterized by low efficiency, high costs, and high risks, making them particularly difficult to implement in complex terrain or inclement weather. While fixed monitoring equipment can achieve real-time monitoring, it has high deployment costs, limited coverage, and difficulty responding flexibly to dynamically changing risk scenarios. In recent years, drone technology has been gradually applied to wind turbine blade inspections due to its advantages, such as high maneuverability, wide coverage, and ability to carry a variety of sensors. However, existing drone inspection solutions still have the following shortcomings: Existing methods are mostly based on static risk assessments, which do not fully consider the impact of dynamic factors such as lightning warnings and equipment degradation on detection priorities. This results in high-risk areas not being covered in a timely manner and resources being wasted in low-risk areas. Traditional path planning algorithms fail to incorporate real-time constraints such as the drone's remaining battery life and return distance, which can easily lead to mission interruptions or failure to return. Furthermore, obstacle avoidance strategies for obstacles such as the lightning rod safety radius and complex terrain are insufficient, posing safety risks. Existing drone swarm scheduling often uses uniform distribution or empirical deployment, without dynamically adjusting drone density based on the complexity of the inspection task. This results in irrational resource allocation and high inspection costs. The deviation between actual cost and predicted value during the detection process is not effectively utilized, and there is a lack of dynamic strategy optimization mechanism based on real-time data, making it difficult to respond to sudden risks or efficiency improvement needs.

[0004] Therefore, we proposed a wind farm blade lightning protection inspection drone task scheduling and path optimization management method to solve the above problems. Summary of the Invention

[0005] The present invention provides a method for dispatching and optimizing the path of wind farm blade lightning protection inspection UAV tasks, which is used to improve the efficiency, safety and economy of wind farm blade lightning protection inspection.

[0006] The first aspect of the present invention provides a method for scheduling and optimizing the path of UAV tasks for lightning protection inspection of blades in a wind farm. The method comprises: calculating the regional connectivity based on the topological relationship of the spacing between wind turbines, superimposing the annual degradation rate of the blade grounding resistance and the real-time lightning warning level, and generating a dynamic risk label for the wind turbine; using the dynamic risk label for the wind turbine, arranging them in descending order of risk value, and outputting an inspection work order instruction with a time window in combination with the remaining power of the UAV and the return distance; parsing the inspection work order instruction, calling the average inspection time of the same type of wind turbines in the past 90 days, calculating the unit time cost derivative using a fractional-order differential equation, and generating a UAV cluster deployment density instruction; based on the UAV cluster deployment density instruction, constructing a repulsive potential field including the lightning rod safety radius in a digital elevation model, and generating an obstacle avoidance track point sequence by gradient descent of the potential field; monitoring the track execution progress of the obstacle avoidance track point sequence, and when the actual inspection cost drops to a preset value compared with the predicted value, calculating the strategy switching probability according to the enterprise risk coefficient, and outputting a work order priority update instruction if the probability is greater than the set value.

[0007] Optionally, in a first implementation method of the first aspect of the present invention, it includes: taking the wind turbine position as a node, establishing connection edges, and forming a wind turbine adjacency graph; analyzing the interconnected unit clusters in the adjacency graph, and marking clusters with more than 3 units as highly connected areas; extracting historical detection values ​​of blade grounding resistance, calculating the annual degradation percentage, and generating an equipment degradation warning label; receiving the lightning warning level signal issued by the meteorological department, and activating the environmental risk sign according to the warning level.

[0008] Optionally, in a second implementation method of the first aspect of the present invention, it includes: placing the wind turbine with a red risk label at the top of the queue, the yellow label next, and the green label at the bottom, and arranging wind turbines of the same color level in descending order according to the ground resistance degradation rate value, and outputting a risk-sorted wind turbine queue; obtaining the real-time remaining power of the drone, multiplying it by the endurance conversion coefficient to obtain the safe flight time, combining it with the average cruising speed of the wind farm, calculating the maximum one-way operating distance, and outputting the safe operating radius of each drone; taking the location of the wind farm charging pile as the center of the circle, matching available drones, establishing a drone-charging pile exclusive mapping relationship table, and outputting a charging pile binding list; for the risk-sorted wind turbine queue, allocating the nearest drone according to the safe operating radius of each drone, superimposing the charging pile binding list to ensure that it can return to the exclusive charging pile after the inspection is completed, and outputting a work order instruction with three elements; when multiple drones are assigned to the same wind turbine, priority is given to the unit with high remaining power, and the replaced drone is automatically reallocated to the inspection task of the next wind turbine in the queue, and an updated work order instruction set is output.

[0009] Optionally, in a third implementation of the first aspect of the present invention, the safe flight time is set to , the maximum one-way operating distance is ,but: ;in, is the percentage of remaining power, is the endurance conversion factor; ;in, is the average cruising speed in km / h, The unit of safe flight time is minutes; the safe operating radius of each drone is R: .

[0010] Optionally, in a fourth implementation method of the first aspect of the present invention, it includes: parsing the target wind turbine model and blade length in the inspection work order instruction, matching the wind turbine technical files in the historical database according to the model, and outputting the identification label of the same type of wind turbine; calling the inspection time records of the same model wind turbine in the past 90 days, eliminating timeout anomalies, and outputting a standard time distribution table; based on the standard time distribution table, combined with the real-time labor rate and drone depreciation parameters, using fractional-order differential equations to describe the memory effect of cost changes with inspection time, and outputting a unit time cost change rate curve; when the unit time cost change rate exceeds the cost change rate threshold, increasing the number of drones per unit area, and outputting the drone / square kilometer density control value; when the density control value fluctuates by >30% compared with the previous instruction, triggering the operation and maintenance expert review process, correcting the density control value according to the review opinion, and outputting the final deployment density instruction.

[0011] Optionally, in the fifth implementation method of the first aspect of the present invention, it includes: reading the drone / square kilometer density control value, converting it into the minimum horizontal spacing standard between drones, and outputting the spacing constraint parameters; obtaining the geographic coordinates of all lightning rods in the wind farm, generating a cylindrical repulsion field with the coordinates as the center, and outputting the lightning rod potential field layer.

[0012] Optionally, in a sixth implementation of the first aspect of the present invention, areas with slopes greater than 30° are marked as terrain obstacles in the digital elevation model, spacing constraint parameters are superimposed to generate an inter-UAV repulsion field, the lightning rod potential field layer is integrated, and a three-dimensional composite potential field model is output; starting from the target wind turbine tower base coordinates, an iterative search is performed along the negative gradient direction of the composite potential field, and the track point coordinates are output every 10 meters, and an obstacle avoidance track point sequence is output; track points that are less than 10 meters away from the lightning rod are automatically marked, and high-risk points are pushed to the operation and maintenance console for manual confirmation, and the confirmation results are integrated to generate a final track sequence.

[0013] Optionally, in a seventh implementation method of the first aspect of the present invention, it includes: receiving the coordinates of the flown track points transmitted back by the UAV in real time, comparing the planned track point sequence to calculate the completion percentage, and outputting the track execution progress report; synchronously obtaining the UAV power consumption and manual monitoring working hours data, superimposing the equipment depreciation rate to calculate the real-time detection cost, and outputting the actual cost flow record; calling the predicted cost baseline value, activating the judgment flag when the actual cost flow record drops by more than 15%, and outputting a cost reduction trigger signal; reading the risk tolerance coefficient preset by the enterprise management system, mapping the strategy switching probability according to the coefficient value, and outputting the strategy switching probability value; outputting the work order priority update instruction based on the strategy switching probability value.

[0014] Optionally, in the eighth implementation method of the first aspect of the present invention, real-time monitoring of the charging pile status is also included: monitoring the charging pile temperature, output current and fault signal, and outputting a charging pile health status table; receiving the sandstorm level issued by the meteorological station, and outputting a track degradation instruction; parsing the high-definition image of the blade surface taken by the drone, and outputting a blade damage alarm package when lightning damage or cracks are identified.

[0015] The mechanism of the present invention is as follows: by integrating the electrical topology connectivity, ground resistance degradation rate and physical parameters of lightning warning, a dynamic risk label-driven detection priority is constructed, and a closed-loop decision-making system is realized by combining the fractional-order historical cost model and the potential field obstacle avoidance mechanism.

[0016] Beneficial Effects: A dynamic risk assessment model is constructed by integrating the topological relationship of wind turbine spacing, the annual degradation rate of blade grounding resistance, and the real-time lightning warning level. This model enables real-time updating and accurate quantification of risk levels. Task queues are sorted in descending order based on risk values. Combined with the remaining battery power of the drone and the return distance constraints, inspection work orders with time windows are generated to ensure that high-risk areas are inspected first, while also avoiding the risk of mission interruption or drone crashes due to insufficient battery. A fractional-order differential equation is introduced to describe the memory effect of inspection costs over time. Combined with the historical inspection time data of similar wind turbines over the past 90 days, the unit time cost derivative is calculated to dynamically adjust the drone deployment density. When the cost change rate exceeds a threshold, the density control mechanism is automatically triggered. Operation and maintenance experts review the decision to ensure rationality and avoid resource waste or insufficient coverage. A three-dimensional composite potential field model is constructed within the digital elevation model, integrating the lightning rod safety radius repulsion potential field, the inter-UAV repulsion potential field, and the terrain obstacle potential field. A potential field gradient descent algorithm is used to generate an obstacle avoidance track point sequence, automatically marking high-risk points for manual confirmation to ensure path safety and compliance. Real-time monitoring of track execution progress and actual inspection costs. When the cost drops by more than 15% compared to the predicted value, the probability of strategy switching is calculated based on the enterprise risk factor. If the probability is greater than 0.6, the work order priority is automatically updated. External data such as charging pile health status monitoring and sandstorm level warnings are integrated to dynamically adjust the track or suspend the task to avoid damage in extreme environments. The five modules of dynamic risk assessment, task scheduling, path planning, cost optimization, and strategy adjustment are integrated to form a closed-loop management system. The modules can communicate data and make collaborative decisions. The intelligent identification function of blade damage is introduced, and damage alarm packages are automatically generated through drone high-definition image analysis, realizing the integration of "detection-analysis-early warning". BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 This is a schematic diagram of an embodiment of a method for task scheduling and path optimization management of a wind farm blade lightning protection inspection drone in an embodiment of the present invention; Figure 2 This is a schematic diagram of another embodiment of a method for task scheduling and path optimization management of a wind farm blade lightning protection inspection drone in an embodiment of the present invention; Figure 3 This is a schematic diagram of an embodiment of a device for task scheduling and path optimization management of a wind farm blade lightning protection inspection drone in an embodiment of the present invention; Figure 4 This is a schematic diagram of an embodiment of a wind farm blade lightning protection inspection drone task scheduling and path optimization management device in an embodiment of the present invention. DETAILED DESCRIPTION

[0018] Embodiments of the present invention provide a method for scheduling and optimizing the paths of unmanned aerial vehicle (UAV) tasks for lightning protection inspection of wind farm blades, thereby improving the efficiency, safety, and cost-effectiveness of wind farm blade lightning protection inspection. The terms "first," "second," "third," "fourth," and so forth (if any) in the present specification and claims, as well as in the accompanying drawings, are used to distinguish similar objects and are not necessarily used to describe a specific order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate, such that the embodiments described herein can be implemented in an order other than that illustrated or described herein. Furthermore, the terms "including," "comprising," "having," and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, product, or apparatus.

[0019] For ease of understanding, the specific process of the embodiment of the present invention is described below. Figure 1An embodiment of the wind farm blade lightning protection inspection UAV task scheduling and path optimization management method in the embodiment of the present invention includes: 101. Wind turbine cluster risk classification: Calculate regional connectivity based on the topological relationship between wind turbines, superimpose the annual degradation rate (%) of blade grounding resistance and the real-time lightning warning level to generate a wind turbine dynamic risk label (Product 1); It is understandable that the execution subject of the present invention can be a wind farm blade lightning protection inspection drone task scheduling and path optimization management device, or a terminal or server, which is not limited here. The embodiment of the present invention is described by taking the server as the execution subject as an example.

[0020] It should be noted that the dynamic risk labels of 20 wind turbines in a certain wind farm were generated, basic data was prepared, and the topological relationship of the wind turbines was as follows: the wind farm layout was in a 4×5 grid, with a spacing of approximately 150 meters between each turbine.

[0021] Regional connectivity calculation: With each wind turbine as the center, count the number of adjacent wind turbines within a radius of 200 meters. Examples of the number of adjacent wind turbines for some wind turbines: Fan ID F01 F02 F03 F04 F05 Adjacent number 3 4 5 4 3 Connectivity weight: when the number of neighbors is ≥5, the weight is 1.2 (high connectivity); when the number is 3-4, the weight is 1.0 (medium); when the number is ≤2, the weight is 0.8 (low connectivity).

[0022] Annual degradation rate of grounding resistance (%): Measured annual degradation rate (reflects the aging speed of the lightning protection system): F01:8.2% (high) F02: 3.5% (low) F03:6.7% (medium) Real-time lightning warning level: Weather system input data (level 1-3): Current level F01 area = 3 (high risk) F02 area = 1 (low risk) F03 area = 2 (medium risk) Dynamic risk label calculation, risk value formula: Risk value = connectivity weight (Ground resistance degradation rate 0.6+ Lightning Level 0.4); Taking the F01 wind turbine as an example: Connectivity weight = 1.0 (4 adjacent turbines, middle connection); Ground degradation rate = 8.2% → normalized to 8.2 (percentage value); Lightning level = 3 → normalized to 3; ; Risk grading rules: high risk (red): ≥5.0; medium risk (yellow): 3.0-4.9; low risk (green): <3.0; Output product 1 (partial fan label): Fan ID Value at Risk Dynamic risk labels F01 6.12 High risk (red) F02 2.18 Low risk (green) F03 4.35 Medium risk (yellow) 102. Time Constrained Work Order Generation: Use the wind turbine dynamic risk labels from Product 1, sort them in descending order of risk value, and combine them with the remaining battery power and return distance of the drone to output a time-windowed inspection work order instruction (Product 2). It should be noted that the following is a specific implementation example of the "Time Constraint Work Order Generation" step (step 102), based on the dynamic risk labels of five wind turbines in a wind farm and the status data of three drones: Basic data preparation, wind turbine dynamic risk labeling (Product 1); Data example: Fan ID Value at Risk Risk Level F03 8.6 High risk (red) F01 7.2 High risk (red) F05 5.1 Medium risk (yellow) F02 3.8 Medium risk (yellow) F04 2.3 Low risk (green) Drone status: Drone cluster: 3 (UAV1, UAV2, UAV3); Remaining battery: UAV1 (85%), UAV2 (70%), UAV3 (90%); Return distance (distance from each wind turbine to the base station / km): Fan ID UAV1 distance UAV2 distance UAV3 distance F03 1.2 0.8 2.5 F01 0.5 1.5 1.0 Work order generation logic and risk prioritization: The order of wind turbine inspection is arranged from highest to lowest risk: F03 → F01 → F05 → F02 → F04. High-risk wind turbines are inspected first to avoid lightning strikes (F03 has a risk value of 8.6, requiring immediate response).

[0023] Power and return distance constraints: Time window calculation: Single-machine detection time: High-risk wind turbines require an average of 25 minutes (including flight, detection, and obstacle avoidance), and medium- and low-risk wind turbines require 15 minutes. UAV1 operational time = minute.

[0024] Return time reserved: . minute.

[0025] Task Allocation Rules: Dynamic Binding: When assigning wind turbines to each drone, the following conditions must be met: Detection Time + Return Time ≤ Maximum Operating Time. Nearest Dispatch: Prioritize drones with short return distances (UAV2 is assigned to F03 because its return distance is only 0.8 km).

[0026] Output 2: Inspection work order instructions with time window: Work order number Fan ID Risk Level Execution drone Start time window End time window Priority 1 F03 High risk UAV2 T+0min T+25min urgent 2 F01 High risk UAV1 T+5min T+30min urgent 3 F05 Medium risk UAV3 T+10min T+25min high 4 F02 Medium risk UAV1 T+35min T+50min middle 5 F04 Low risk UAV3 T+30min T+45min Low 103. History-dependent cost control: Analyze the inspection work order instructions of Product 2, call the average inspection time of the same type of wind turbines in the past 90 days, use fractional differential equations to calculate the unit time cost derivative, and generate the drone cluster deployment density instruction (Product 3); It should be noted that based on the inspection work order instructions and historical data of 5 wind turbines in a wind farm: Basic data preparation, inspection work order instructions (Product 2): Contains the sequence of fans to be inspected: F03 (high risk), F01 (high risk), F05 (medium risk), F02 (medium risk), F04 (low risk); Planned inspection time window for each fan (unit: minutes): Fan ID Start time End Time F03 T+0 T+25 F01 T+5 T+30 Historical detection time: The average detection time of the same type of wind turbine (2.0MW model) in the past 90 days is: Fan ID Historical average time (minutes) F03 28.5 F01 26.2 F05 18.7 F02 17.9 F04 15.3 Calculation of unit time cost derivative, cost function definition: Based on the historical average time consumption and the real-time work order time window deviation (the difference between the actual time consumption and the planned time consumption), a time cost function is constructed. ,in =0.8 (real-time bias weight), =0.2 (historical benchmark weight).

[0027] Fractional differential calculation: Use fractional differential equations (order 0.7) to calculate the unit time cost derivative , reflecting the sensitivity of cost changes over time. Taking F03 as an example: The planned time is 25 minutes, the historical average is 28.5 minutes, and the real-time deviation is 3.5 minutes. ; Fractional derivatives (A positive value indicates a significant cost increase trend).

[0028] UAV cluster deployment density instruction generation, derivative and deployment density mapping rules: High-density deployment ( ): The distance between drones needs to be shortened to ≤15m to improve detection efficiency and curb cost increases.

[0029] Medium-density deployment ( ): Maintain a standard distance of 20m.

[0030] Low-density deployment ( ): Relax the spacing to ≥25m and optimize resource allocation.

[0031] Output 3 (deployment density instruction): Fan ID Unit time cost derivative Deployment density directives F03 +1.24 High density (≤15m) F01 +0.92 Medium density (20m) F05 -0.38 Medium density (20m) F02 -0.61 Low density (≥25m) F04 -0.43 Medium density (20m) 104. Safety potential field path planning: Based on the deployment density instruction of product 3, a repulsive potential field containing the lightning rod safety radius (≥5m) is constructed in the digital elevation model (DEM). The obstacle avoidance track point sequence is generated by gradient descent of the potential field (product 4). It should be noted that based on the deployment density instructions and geographical data of 5 wind turbines in a wind farm: Basic data preparation, input data: Deployment density instruction (product 3): output from step 103 (F03 wind turbines require high-density deployment ≤ 15m, F01 requires medium-density deployment 20m); Digital Elevation Model (DEM): contains wind turbine coordinates, altitude, and lightning rod location (F03 lightning rod coordinates (120.5, 38.2), safety radius ≥ 5m); Obstacle data: wind turbine tower, surrounding high-voltage lines (coordinates are marked); Potential field construction and superposition, terrain potential field: generate elevation potential field based on DEM, steep slope area (slope>15 ) Set a high potential energy value (altitude mutation zone potential energy = 8).

[0032] Lightning rod repulsion potential field: A spherical repulsion field is constructed with the lightning rod as the center, and the potential energy increases exponentially within a safe radius of 5m (potential energy = 12 when the distance is 4m from the lightning rod; potential energy ≈ 0 when the distance is 6m).

[0033] Target gravitational potential field: Detect the target point (blade leading edge) and set low potential energy (potential energy = -10) to guide the drone closer.

[0034] Density constraint potential field: A repulsive potential field between drones is added in the high-density area (F03). The potential energy rises sharply when the distance is less than 15m (the potential energy is 5 when the distance is 10m).

[0035] Gradient descent generates track points. Take the F03 blade leading edge detection as an example: Starting point: UAV hovering point (coordinates (120.48, 38.18), altitude 90m); Potential field superposition calculation: Lightning rod (distance 3m) → repulsive potential energy = 15; target point (distance 2m) → gravitational potential energy = -8; terrain slope 8 →potential energy = 3; Direction of resultant force: northeast-east (direction of fastest decrease in potential energy gradient).

[0036] Track point sequence generation: Serial number longitude latitude Altitude (m) Obstacle Avoidance Instructions 1 120.482 38.183 92 Avoid the west side of the lightning rod 2 120.487 38.186 95 Climb along a gentle slope 3 120.491 38.190 98 Cut into the leading edge of the blade The track point spacing is dynamically adjusted according to the density command (F03 point spacing ≤ 15m, F04 point spacing = 20m) to ensure cluster collision avoidance.

[0037] Output 4: obstacle avoidance track point sequence: Fan ID Number of track points Total path length (m) Minimum lightning rod distance F03 18 240 5.2 F01 12 180 6.8 105. Strategy Transition Audit Decision: Monitor the progress of Product 4's trajectory execution. When the actual inspection cost decreases by more than 15% compared to the predicted value, calculate the strategy switching probability based on the enterprise risk factor. If the probability is greater than 0.6, output the work order priority update instruction (Product 5). It should be noted that based on the trajectory execution data of 5 wind turbines in a wind farm and the enterprise risk parameters: Basic data preparation, track execution progress (product 4): Actual detection time (minutes): Fan ID Prediction time Actual time Cost reduction F03 25 22 15.4%↓ F01 25 20 22.1%↓ F05 15 14 8.3%↓ Cost reduction formula: ; Enterprise risk factor: Set according to the wind farm safety level: High wind speed area: risk factor = 0.7 (high risk tolerance is low); low wind speed area: risk factor = 0.4 (low risk tolerance is high). In this example, 0.7 is used (currently it is a high wind speed season). Strategy switching decision process, step 1: Monitor actual cost reduction. Trigger condition: Initiate strategy switching calculation only when the cost reduction exceeds 15%. F03's 15.4% reduction meets the condition, and the calculation process begins. F01's 22.1% reduction, while higher, only requires processing the first turbine that meets the condition.

[0038] Step 2: Calculate the probability of strategy switching, formula logic: ; F03 calculation: ; Decision rule: Output update instruction when probability > 0.6.

[0039] Step 3: Generate a work order priority update instruction (product 5). Update logic: Since the inspection efficiency of F03 has been significantly improved (with a high cost reduction), it is speculated that the wind turbine in the same area (F05) may have similar optimization space. Increase the priority of F05 from "High" to "Urgent" and insert it into F01 for inspection: Fan ID Original priority New Priorities Adjusting the detection order F05 high urgent F01→F05→F03 In an embodiment of the present invention, a dynamic risk label for a wind turbine is generated by comprehensively considering the topological relationship of wind turbine spacing, the annual degradation rate of blade grounding resistance, and the real-time lightning warning level. This multi-factor integrated risk assessment method breaks through the limitations of single-factor assessment and can more accurately reflect the actual risk status of each wind turbine, providing a scientific basis for subsequent task scheduling, helping to prioritize high-risk wind turbines and reduce the possibility of lightning strike accidents. Based on the dynamic risk label of the wind turbine, combined with the remaining power and return distance of the drone, a detection work order instruction with a time window is generated. On the basis of meeting the risk priority ranking, the power and return distance constraints are fully considered to achieve dynamic binding and local scheduling. This innovative task allocation rule ensures that high-risk wind turbines are inspected first while rationally utilizing drone resources, improving inspection efficiency, and avoiding delays in inspection tasks due to insufficient power or long return distances. The average inspection time of wind turbines of the same type over the past 90 days is called, and the unit time cost derivative is calculated using a fractional-order differential equation to generate a drone cluster deployment density instruction. This method innovatively combines historical data with real-time work orders. Using fractional-order differential equations, it accurately calculates cost derivatives, reflecting the time-dependent sensitivity of costs. This allows for appropriate adjustments to the deployment density of drone swarms, effectively controlling costs and optimizing resource allocation while ensuring inspection quality. A repulsive potential field, encompassing the lightning rod safety radius, is constructed within the digital elevation model. Obstacle avoidance trackpoint sequences are generated through gradient descent of the potential field. This method comprehensively considers multiple factors, including terrain, lightning rods, target gravity, and inter-UAV density constraints, to construct a complex and comprehensive potential field model, ensuring effective obstacle avoidance and flight safety. Furthermore, trackpoint spacing is dynamically adjusted based on the deployment density of different wind turbines, further improving the safety and efficiency of swarm flight. Track execution progress is monitored. When the actual inspection cost decreases by more than 15% compared to the predicted value, the probability of a strategy switch is calculated based on the enterprise risk factor. If the probability is greater than 0.6, a work order priority update instruction is output. This step dynamically adjusts work order priorities by monitoring cost changes in real time and incorporating enterprise risk factors, enabling flexible switching of inspection strategies. This innovative decision-making mechanism can promptly seize opportunities for cost reduction, further optimize the inspection process, improve overall inspection efficiency, and adapt to the actual operational needs of different wind farms.

[0040] See also Figure 2 Another embodiment of the method for task scheduling and path optimization management of a wind farm blade lightning protection inspection drone in an embodiment of the present invention includes: 201. Wind turbine cluster risk classification: Calculate regional connectivity based on the topological relationship between wind turbines, superimpose the annual degradation rate (%) of blade grounding resistance and the real-time lightning warning level to generate a wind turbine dynamic risk label (Product 1); Specifically, a wind turbine adjacency network is established: with wind turbine locations as nodes, connection edges are established within a spacing of 500 meters to form a wind turbine adjacency relationship graph; and the adjacency relationship graph is output.

[0041] Identify highly connected regions: Analyze the interconnected clusters of units in the adjacency graph and mark clusters with more than 3 units as highly connected regions; output a table of highly connected region markers.

[0042] Quantifying ground resistance degradation: Extract historical blade ground resistance test values ​​and calculate the annual degradation percentage; generate an equipment degradation warning label when the annual degradation rate exceeds 5%; and output the degradation warning label.

[0043] Integrated lightning warning signal: Receive lightning warning level signals issued by the meteorological department; activate the environmental risk sign when the warning level reaches orange (level 4) or above; output the environmental risk sign.

[0044] Generate dynamic risk labels: Generate red risk labels for wind turbines that meet the following conditions simultaneously: located in a highly connected area, carrying an equipment degradation warning label, and a currently activated environmental risk flag; generate yellow risk labels for wind turbines that meet any two of these conditions; generate green risk labels for the remaining wind turbines; output three-color risk labels.

[0045] It should be noted that the following uses a wind farm (containing 10 2.0MW units) as an example to illustrate the specific implementation of the wind turbine cluster risk classification steps and data flow: Create a wind turbine adjacency network and input the following data: Wind turbine coordinates (unit: meters): Fan 1: (0,0); Fan 2: (300, 100); Fan 3: (700, 400); ... (Coordinates of fans 4-10 are omitted); Connection rule: Create connection edges with a radius of 500 meters. Example connection relationship: Wind turbines 1 and 2 (352 meters apart), wind turbines 3 and 4 (420 meters apart), are connected, and wind turbine 5 is isolated.

[0046] Output adjacency graph (partial): node connections: 1-2, 2-3, 3-4, 6-7, 7-8, 8-9; isolated nodes: 5, 10; Identify highly connected areas and perform cluster analysis: Cluster 1: Wind turbines 1-4 (4 units); Cluster 2: Wind turbines 6-9 (4 units); Wind turbines 5 and 10 are single units. Output a highly connected area marker table: Cluster ID Including fan High connectivity (>3 devices) C1 1,2,3,4 yes C2 6,7,8,9 yes Quantify the ground resistance degradation. Input data: ground resistance value in 2023-2024 (unit: ); Fan 1: ( ); Fan 3: (Degradation rate 1.4%); Warning rule: Generate a label if degradation rate > 5%. Output degradation warning label: Fan ID Deterioration rate Warning Label 1 5.9% yes 3 1.4% no Fusion of lightning warning signals: Input: Meteorological Observatory issues lightning orange warning (level 4). Rule: Orange and above warnings activate environmental risk flag. Output environmental risk flag: Warning level Whether to activate orange color yes Generate dynamic risk labels and apply rules (taking wind turbines 1 and 3 as an example): Fan ID Highly connected areas Deterioration warning Environmental risks Number of conditions met Risk Label 1 Yes (C1) yes yes 3 items red 3 Yes (C1) no yes 2 items yellow 5 no no yes 1 item green Output three-color risk labels: red: wind turbines 1, 4; yellow: wind turbines 2, 3, 6, 7; green: wind turbines 5, 8, 9, 10; In this example, wind turbine 1 is marked as the highest risk (red) and requires priority inspection because it is located in a highly connected cluster, has exceeded the ground resistance degradation threshold, and is experiencing an orange lightning warning. Wind turbine 5, operating in isolation and without degradation, is the lowest risk (green). Dynamic label generation enables a three-dimensional coupled assessment of device status, cluster topology, and meteorological threats.

[0047] 202. Time Constrained Work Order Generation: Use the wind turbine dynamic risk labels from Product 1, sort them in descending order of risk value, and combine them with the remaining battery power and return distance of the drone to output a time-windowed inspection work order instruction (Product 2). Specifically, a risk priority sequence is generated: wind turbines with red risk labels are placed at the top of the queue, followed by yellow labels, and green labels are placed at the bottom; wind turbines with the same color level are arranged in descending order according to the ground resistance degradation rate; and a risk-ranked wind turbine queue is output.

[0048] Calculate the effective operating radius of a drone: Obtain the drone's real-time remaining battery power and multiply it by the endurance conversion factor of 0.8 to obtain the safe flight time. Combined with the wind farm's average cruising speed, calculate the maximum one-way operating distance. Output the safe operating radius of each drone.

[0049] Bind the relationship with the nearest charging pile: with the wind farm charging pile location as the center, match the available drones within 20 kilometers; establish a drone-charging pile exclusive mapping relationship table; and output the charging pile binding list.

[0050] Generate time-constrained work orders: sort the wind turbine queue by risk and assign the nearest drone according to each drone's safe operating radius; overlay the charging pile binding list to ensure that the drone can return to the dedicated charging pile after the inspection is completed; and output a work order instruction with three elements: "target wind turbine ID, executing drone ID, latest start time".

[0051] Real-time conflict resolution mechanism: When multiple drones are assigned to the same wind turbine, priority is given to the unit with the highest remaining battery power; the replaced drone is automatically reallocated to the inspection task of the next wind turbine in the queue; and an updated work order instruction set is output.

[0052] It should be noted that the following is a specific example of implementing the "Time Constrained Work Order Generation" step for a wind farm (containing 10 2.0MW units). The data is based on the previous risk classification results (Product 1): Generate risk priority sequence, input product 1 data: Red-labeled fans: ID01 (deterioration rate 7.2%), ID04 (deterioration rate 6.8%), ID02 (deterioration rate 5.9%); Yellow-labeled fans: ID03 (deterioration rate 4.5%), ID06 (deterioration rate 3.9%), ID07 (deterioration rate 3.2%), ID09 (deterioration rate 2.8%); Green-labeled fans: ID05, ID08, ID10 (no degradation warning); Sorting rules: ; ; ; Output queue: [ID01,ID04,ID02,ID03,ID06,ID07,ID09,ID05,ID08,ID10]; Set safe flight time to , the maximum one-way operating distance is ,but: ;in, is the percentage of remaining power, is the endurance conversion factor; ;in, is the average cruising speed in km / h, The unit of safe flight time is minutes; the safe operating radius of each drone is R: ; Calculation of the effective operating radius of drones, drone parameters (3 drones): Remaining battery: UAV1 (85%), UAV2 (70%), UAV3 (90%); Endurance conversion factor: 0.8 → Safe flight time: UAV1 (34 minutes), UAV2 (28 minutes), UAV3 (36 minutes); Average cruising speed: 10 m / s (36 km / h); One-way operating distance: UAV1: km (safety radius 10.2 km); UAV2: km (safety radius 8.4km); UAV3: km (safety radius 10.8km); Charging pile binding relationship, charging pile location: pile A (coordinate X1, Y1), pile B (coordinate X2, Y2); Binding rules: Match drones within 20km: UAV1 is 15km away from stake A → bind to stake A; UAV2 is 18km away from stake B → bind to stake B; UAV3 is 12km away from stake A → bind to stake A; Output binding manifest: Drone ID Bind charging pile UAV1 Pile A UAV2 Pile B UAV3 Pile A Time-constrained work order generation and allocation logic: High-risk wind turbines are assigned to the nearest location: ID01 (coordinate P1) is closest to UAV1 (1.2 km) → UAV1 is assigned; ID04 (coordinate P4) is closest to UAV3 (0.8 km) → UAV3 is assigned; ID02 (coordinate P2) is closest to UAV1 (1.5 km), but UAV1 needs to return to pile A ( ) → Change to assign UAV3 (distance 1.8km, ); Conflict resolution: ID02 is competed for by both UAV1 and UAV3. UAV3 with a higher remaining battery level (90% > 85%) is prioritized. UAV3 executes the task; UAV1 is reassigned to the next task, ID03.

[0053] Output work order instructions: Target wind turbine Execution drone Latest startup time (assuming current time is T0) ID01 UAV1 T0+0min (immediate execution) ID04 UAV3 T0+0min ID02 UAV3 T0+15min (UAV3 must complete ID04 first) ID03 UAV1 T0+20min (UAV1 charges after returning home) The work order ensures that the total distance of each drone mission does not exceed the safe operating radius (UAV3 executes ID04+ID02 , and bind an exclusive charging pile to ensure return.

[0054] 203. History-dependent cost control: Analyze the inspection work order instructions of Product 2, call the average inspection time of the same type of wind turbines in the past 90 days, use fractional differential equations to calculate the unit time cost derivative, and generate the drone cluster deployment density instruction (Product 3); Specifically, the fan type features of the work order are extracted: the target fan model and blade length in the inspection work order instruction are parsed; the fan technical files in the historical database are matched according to the model; and the identification tags of fans of the same type are output.

[0055] Construct a historical time consumption distribution matrix: call the inspection time consumption records of the same model of fans in the past 90 days; eliminate timeout outliers (data points > 2 times the average value); and output a standard time consumption distribution table.

[0056] Calculate fractional cost dynamics: Based on a standard time distribution table, combined with real-time labor rates and drone depreciation parameters; use fractional differential equations to describe the memory effect of cost changes with inspection duration; and output a unit time cost change rate curve.

[0057] Generate deployment density instructions: Set the cost change rate threshold to 5% per hour; when the unit time cost change rate curve exceeds the threshold, increase the number of drones per unit area; output the drone / square kilometer density control value.

[0058] Manual review and correction mechanism: When the density control value fluctuates by more than 30% compared to the previous instruction, the operation and maintenance expert review process is triggered; the density control value is corrected based on the review opinion; and the final deployment density instruction is output.

[0059] It should be noted that the following takes a wind farm (including 10 2.0MW units) as an example: Extract the fan type features of the work order and input product 2 data: the inspection work order instruction contains the target fan ID and model: ID01~ID08: Model A (blade length 60m); ID09~ID10: Model B (blade length 45m); Matching historical technical files: Model A corresponds to the technical file number TECH-A (down conductor type: copper cable; number of air terminals: 6); Model B corresponds to TECH-B (down conductor type: aluminum tape; number of air terminals: 4).

[0060] Output the same type of tags: Model A tags: ID01~ID08; Model B tags: ID09~ID10; Build a historical time consumption distribution matrix and call historical data (detection time consumption in the past 90 days): Model A fan: average time 65 minutes (data point examples: 55min, 70min, 60min, 120min*, 62min; *Note: , retained as it did not exceed the standard); Model B fan: average time 45 minutes (data points: 40min, 48min, 50min, 100min*; excluding ).

[0061] Output standard time distribution table: Fan model Valid data points (minutes) Average time A 55,60,62,70 62±5min B 40,48,50 46±4min Calculate the fractional cost dynamics, cost parameters: labor rate: 200 yuan / hour; drone depreciation: 50 yuan / hour; Cost change rate calculation: Based on the historical time distribution of model A, for every 10 minutes of additional testing time, the unit time cost increases by 3.5 yuan / minute (due to the combined effect of labor and depreciation); when the testing time exceeds 70 minutes, the cost growth rate exceeds the 5% / hour threshold ( Yuan, % / h).

[0062] Generate deployment density instructions, threshold determination: When the detection time of model A fan exceeds 70 minutes, the cost change rate exceeds 5% / h → trigger the density increase mechanism; Density control: The original base density of 5 aircraft / square kilometer has been increased to 7 aircraft / square kilometer (a 40% increase), shortening the inspection range of a single aircraft to control inspection time.

[0063] Manual review and correction mechanism, fluctuation determination: density control value fluctuates by 40% or more than 30% compared to the previous value (5 aircraft / square kilometer) → trigger expert review; Correction process: Based on the real-time wind speed (15m / s) and the structural complexity of Model A blades, the operation and maintenance experts approved the density adjustment to 6 aircraft per square kilometer (final order).

[0064] Output the final deployment density instruction: Model A wind turbine area: 6 aircraft / square kilometer; Model B wind turbine area: maintain 5 aircraft / square kilometer.

[0065] 204. Safety potential field path planning: Based on the deployment density instruction of product 3, a repulsive potential field containing the lightning rod safety radius (≥5m) is constructed in the digital elevation model (DEM). The obstacle avoidance track point sequence is generated by gradient descent of the potential field (product 4). Specifically, the deployment density constraint is analyzed: the drone / square kilometer density control value is read; it is converted into the minimum horizontal spacing standard between drones; and the spacing constraint parameters are output.

[0066] Construct a lightning rod repulsion potential field: Obtain the geographic coordinates of all lightning rods in the wind farm; Generate a cylindrical repulsion field with a radius of 5 meters centered on the coordinates; Output the lightning rod potential field layer.

[0067] Fusion of terrain and density potential fields: Marking areas with slopes greater than 30° as terrain obstacles in the digital elevation model (DEM); Overlaying spacing constraint parameters to generate an inter-UAV repulsion field; Fusion of the lightning rod potential field layer with the lightning rod potential field layer; Outputting a 3D composite potential field model.

[0068] Generate gradient descent track points: Starting from the target wind turbine tower base coordinates; iteratively search along the negative gradient direction of the composite potential field; output track point coordinates (including altitude) every 10 meters; output obstacle avoidance track point sequence.

[0069] Manual verification of high-risk track segments: automatically mark track points that are less than 10 meters away from the lightning rod; push high-risk points to the operation and maintenance console for manual confirmation; integrate the confirmation results to generate the final track sequence.

[0070] It should be noted that the following takes a wind farm (including 10 2.0MW units) as an example: Input data and parameter initialization, deployment density instruction (product 3): Model A area (ID01-ID08): 6 aircraft / square kilometer; Model B area (ID09-ID10): 5 aircraft / square kilometer; Lightning rod coordinates: Lightning rod P1 (near ID01): (120.5, 38.2, 85.0); Lightning rod P2 (near ID04): (122.1, 39.8, 86.5); Digital Elevation Model (DEM): Slope > 30°: Coordinates (121.3, 40.1) are marked as terrain obstacles (altitude change of 20 m); Potential field construction process, analyzing deployment density constraints: Model A regional density is 6 aircraft / km 2 →Minimum drone spacing 40 meters; Model B area density 5 aircraft / km 2 →Minimum spacing 45 meters Output spacing constraint parameter table: area Minimum spacing Model A 40 meters Model B 45 meters Construct a lightning rod repulsion potential field: Generate a cylindrical repulsion field with a radius of 5 meters centered on P1. The potential energy intensity decreases with distance (potential energy = 0.8 when the distance to P1 is 6 meters; potential energy = 2.5 when the distance to P1 is 3 meters). Output the potential field layer: Mark the repulsion range and intensity gradient of P1 and P2.

[0071] Fusion of three-dimensional composite potential fields: Terrain potential field: Mark (121.3, 40.1) in the DEM as an obstacle (slope 35°), with a potential value of 3.0; Inter-UAV repulsion field: Generate a 40-meter-spaced repulsion grid in the Model A area (potential value = 1.5); Lightning rod potential field overlay: The P1 repulsion field covers the area around the ID01 tower base; Output three-dimensional composite potential field model (part): Coordinates (x, y, z) Potential energy type Potential energy value (120.5，38.2，85) Lightning rod repulsion 5.0 (121.3，40.1，72) Terrain obstacles 3.0 (120.8，38.5，80) Inter-drone repulsion 1.5 Track generation and manual verification, gradient descent track generation (starting from the ID01 tower base): starting point: (120.0, 38.0, 80.0); iterative search: along the negative gradient direction of the potential field (avoiding P1 and terrain obstacles); Output track point sequence (partial): Point 1: (120.0, 38.0, 80.0); Point 2: (120.3, 38.3, 82.0) → Go around the west side of P1; Point 3: (120.6, 38.6, 83.5) → avoid the area with sudden changes in terrain; ...(output every 10 meters); High-risk track segment marking and manual verification: Automatic marking: Point (120.4, 38.3, 81.5) is only 8.2 meters away from P1 (<10-meter threshold) → Pushed to the console; Operation and maintenance confirmation: Passage is allowed (because P1 altitude is lower than the track point) → Keep the track point; Final review track sequence, final review track output (ID01 part): track point sequence: [(120.0,38.0,80.0),(120.3,38.3,82.0),(120.4,38.3,81.5)*,(120.6,38.6,83.5)...] *Note: Points marked with * are manually confirmed high-risk points and the original path will be maintained.

[0072] 205. Strategy Transition Audit Decision: Monitor the progress of Product 4's trajectory execution. When the actual inspection cost decreases by more than 15% compared to the predicted value, calculate the strategy switching probability based on the enterprise risk factor. If the probability is greater than 0.6, output the work order priority update instruction (Product 5). Specifically, the progress of track point completion is monitored: the coordinates of the track points that have been flown back by the drone are received in real time; the completion percentage is calculated by comparing the planned track point sequence; and a track execution progress report is output.

[0073] Dynamic collection of actual costs: Synchronously obtain drone power consumption and manual monitoring working hours data; superimpose equipment depreciation rates to calculate real-time detection costs; and output actual cost flow records.

[0074] Cost deviation threshold determination: call the predicted cost benchmark value; activate the determination flag when the actual cost flow record drops by more than 15% compared with the predicted value; output the cost reduction trigger signal.

[0075] Risk quantification strategy decision: Read the risk tolerance coefficient (0-1.0) preset in the enterprise management system; map the strategy switching probability according to the coefficient value: coefficient ≥ 0.8 → switching probability = 0.9; coefficient 0.5-0.8 → switching probability = 0.7; coefficient < 0.5 → switching probability = 0.4; output the strategy switching probability value.

[0076] Work order priority update execution: When the strategy switching probability value is greater than 0.6: reduce the detection weight of high-risk wind turbines by 20%; increase the detection frequency of medium-risk wind turbines by 30%; and output the work order priority update instruction.

[0077] It should be noted that the following takes a wind farm (including 10 2.0MW units) as an example: Input data and monitoring initialization, trajectory planning data (product 4): Target wind turbines: ID01 (red risk), ID04 (red risk), ID03 (yellow risk); Planned track points: 100 in total (40 points for ID01, 35 points for ID04, and 25 points for ID03); Real-time data transmission (UAV1 in progress): Track points flown over: all 40 points of ID01 + the first 30 points of ID04 (70 points in total); completion progress: ; Cost parameters: Labor rate: 200 yuan / hour; Drone depreciation: 50 yuan / hour; Estimated cost baseline (full process): 3,500 yuan; Actual cost dynamic collection, real-time consumption data (as of 70% progress): Drone power consumption: 8.4kWh (electricity price 0.8 yuan / kWh → 6.72 yuan); manual monitoring hours: 1.2 hours → 240 yuan; equipment depreciation: Actual cost total: Yuan; Output actual cost flow record: timestamp T+35min: actual cost 305.02 yuan ( Yuan); Cost deviation threshold determination and deviation calculation: Decline (far exceeding the 15% threshold); Activate the judgment flag: Output the cost reduction trigger signal (reason: the drone shortens the path by avoiding terrain obstacles, saving 40% of flight time); Risk quantification strategy decision-making, enterprise risk tolerance coefficient: 0.7 (medium risk preference); strategy switching probability mapping: coefficient ; Decision logic: ; Work order priority update execution, update rules: high-risk wind turbine (red label) detection weight 20%: Original weights: ID01 = 40%, ID04 = 35% → Updated: ID01 = 32%, ID04 = 28%; Inspection frequency for medium-risk wind turbines (yellow label) 30%: Original frequency: ID03 = 25% → Updated: ID03 = 32.5% (25% × 1.3); Output work order priority update instructions: Fan ID Original weight Updated weight Adjustment basis ID01 40% 32% High risk weight reduction ID04 35% 28% High risk weight reduction ID03 25% 32.5% The frequency of medium-risk incidents has increased 206. Also includes real-time monitoring of charging pile status: Monitor charging pile temperature, output current, and fault signals; mark charging piles as high-risk when temperature > 60°C or current fluctuation > 15%; and output charging pile health status table.

[0078] Sandstorm stratified response mechanism: Receives sandstorm levels (I-IV) issued by the meteorological station; Level I: Reduces flight altitude to within 5 meters of the blades; Level II: Compresses track point spacing to 5 meters; Level III: Suspends detection and initiates the nearest landing; outputs track degradation instructions.

[0079] Closed-loop feedback of blade damage data: Analyzes high-definition images of the blade surface taken by drones; when lightning damage or cracks (length > 10cm) are identified, a blade damage alarm package is output.

[0080] It should be noted that the following takes a certain wind farm (including 10 2.0MW units) as an example to illustrate the specific implementation and data flow of the charging pile status monitoring, sandstorm response and blade damage feedback step (206): Real-time monitoring of charging pile status, input data (real-time parameters of 2 charging piles): Charging pile A: temperature 58°C, output current 50A (fluctuation rate 8%), fault signal: none; Charging pile B: temperature 63°C (>60°C), output current 48A (fluctuation rate 18%>15%), fault signal: poor contact; Monitoring rules: Temperature > 60°C or current fluctuation > 15% → Mark as high-risk pile.

[0081] Output health status table: Charging pile ID temperature Current fluctuation rate Fault signal Health status A 58℃ 8% none normal B 63℃ 18% Poor contact high risk Sandstorm layered response mechanism, input signal: the meteorological station issues a sandstorm level II warning (visibility <500 meters).

[0082] Response rules: Level I: The flight altitude is reduced to within 5 meters of the blade; Level II: The distance between track points is compressed to 5 meters (originally 10 meters); Level III: Suspend detection and land nearby; Output track degradation command: Effective range: All drones; Track adjustment: ID01 track point spacing changed from 10 meters to 5 meters (coordinate sequence density doubled); Execution time: Immediately until the warning is lifted; Closed-loop feedback of blade damage data. Input data: High-definition image of blade ID03 taken by UAV1 (resolution 0.5 mm / pixel).

[0083] Damage identification: Lightning damage: Carbon fiber ablation at the blade tip (area 15cm 2 ); Crack characteristics: Longitudinal crack on suction surface 12cm>10cm long (8 meters from blade root).

[0084] Output damage alarm package: Fan ID: ID03; Damage type: crack (suction side); Damage size: length 12 cm × width 0.8 cm; Position coordinates: (121.5, 38.7, 82.0); Risk level: High (repair required within 72 hours).

[0085] In this embodiment of the present invention, wind turbine spacing topology, equipment status (blade grounding resistance degradation rate), and meteorological threats (lightning warning level) are combined to achieve a three-dimensional coupled assessment of equipment status, cluster topology, and meteorological threats, generating dynamic risk labels. This multidimensional risk assessment method can more comprehensively and accurately reflect the actual risk status of wind turbines, providing a scientific basis for subsequent task scheduling and improving the targeted and effective nature of inspections. When generating inspection work orders, not only risk priority is considered, but also the remaining battery power and return distance of the drones are considered to ensure that the task is completed within the time window and the drones can return safely. Furthermore, through history-dependent cost control, fractional-order differential equations are used to describe the memory effect of cost as it varies with inspection duration, generating drone cluster deployment density instructions to achieve cost optimization. This task scheduling method, which comprehensively considers both timeliness and cost, improves resource utilization efficiency and reduces inspection costs. A repulsive potential field, encompassing the lightning rod safety radius, is constructed within the digital elevation model. The terrain and inter-drone repulsive potential fields are integrated to generate an obstacle avoidance track point sequence through potential field gradient descent. This approach fully considers the actual environmental factors of wind farms, effectively avoiding collisions between drones and lightning rods, terrain obstacles, and other drones, ensuring flight safety and improving the reliability of inspection tasks. Through policy transition audit decisions, the system monitors the progress and cost of trajectory execution in real time. When the actual inspection cost drops below a threshold compared to the predicted value, the inspection strategy is dynamically adjusted based on the enterprise's risk factor, and work order priority update instructions are output. Furthermore, auxiliary mechanisms such as real-time monitoring of charging pile status, a sandstorm stratification response mechanism, and closed-loop feedback of blade damage data further enhance the adaptability, safety, and intelligence of the inspection system, forming a complete closed-loop feedback system that can promptly adjust and optimize the inspection process based on actual conditions.

[0086] The above describes the method for dispatching and optimizing the path of a wind farm blade lightning protection inspection drone in accordance with the present invention. The following describes the device for dispatching and optimizing the path of a wind farm blade lightning protection inspection drone in accordance with the present invention. Figure 3In one embodiment of the present invention, an embodiment of the wind farm blade lightning protection detection drone task scheduling and path optimization management device includes: a label module 301, which is used to calculate the regional connectivity based on the topological relationship of the wind turbine spacing, superimpose the blade grounding resistance annual degradation rate and the real-time lightning warning level, and generate a wind turbine dynamic risk label; a scheduling module 302, which is used to use the wind turbine dynamic risk label, sort it in descending order of risk value, combine the drone's remaining power and return distance, and output a detection work order instruction with a time window; an optimization module 303, which is used to parse the detection work order instruction, call the wind turbine dynamic risk label of the same type in the past 90 days, and output the detection work order instruction with a time window; The average detection time of each machine is calculated, and the unit time cost derivative is calculated using a fractional-order differential equation to generate the drone cluster deployment density instruction; the path module 304 is used to construct a repulsive potential field containing the lightning rod safety radius in the digital elevation model based on the drone cluster deployment density instruction, and generate an obstacle avoidance track point sequence by gradient descent of the potential field; the monitoring module 305 is used to monitor the track execution progress of the obstacle avoidance track point sequence. When the actual detection cost decreases by more than 15% compared with the predicted value, the strategy switching probability is calculated according to the enterprise risk coefficient. If the probability is greater than 0.6, the work order priority update instruction is output.

[0087] In the embodiment of the present invention, a dynamic risk label is generated by comprehensively considering multiple factors such as wind turbine spacing topology, blade grounding resistance degradation and lightning warning, which can more accurately assess wind turbine risks, arrange inspection tasks in descending order of risk value, ensure that high-risk wind turbines are inspected first, improve the pertinence and timeliness of lightning protection inspections, and effectively reduce the risk of blade damage caused by lightning strikes in wind farms; the scheduling module outputs inspection work order instructions with a time window based on the remaining power of the drone and the return distance, to avoid the drone being unable to return or complete the inspection task due to insufficient power, thereby improving the efficiency of drone use and the task completion rate, and reducing resource waste; the optimization module calls nearly 90 The average inspection time of the same type of wind turbines in Tiantong is calculated using fractional-order differential equations to calculate the unit time cost derivative, and the drone cluster deployment density instructions are generated scientifically and reasonably, so as to optimize the drone resource allocation, improve the inspection efficiency, and reduce the overall inspection cost; the path module constructs a repulsive potential field containing the lightning rod safety radius in the digital elevation model, and generates a sequence of obstacle avoidance track points through potential field gradient descent to ensure the safe flight of the drone in complex environments, avoid collisions with obstacles, and ensure the smooth progress of the inspection task; the monitoring module monitors the progress of track execution. When the actual inspection cost drops by more than 15% compared with the predicted value, the strategy switching probability is calculated according to the enterprise risk factor and the work order priority is dynamically adjusted to make the inspection task arrangement more flexible, adapt to changes in actual inspection conditions, and further improve the efficiency and benefits of inspection management.

[0088] above Figure 3From the perspective of modular functional entities, the wind farm blade lightning protection detection drone task scheduling and path optimization management device in the embodiment of the present invention is described in detail. The wind farm blade lightning protection detection drone task scheduling and path optimization management equipment in the embodiment of the present invention is described in detail from the perspective of hardware processing.

[0089] Figure 4 This is a schematic diagram of a wind farm blade lightning protection inspection drone task scheduling and path optimization management device provided by an embodiment of the present invention. The wind farm blade lightning protection inspection drone task scheduling and path optimization management device 400 may have relatively large differences due to different configurations or performances. The device 400 includes a transmitter 401, a receiver 402 and a processor 403. The processor 403 can also be a controller. Figure 4 denoted as “controller / processor 403 ”. Optionally, the device 400 may further include a modem processor 405 , wherein the modem processor 405 may include an encoder 406 , a modulator 407 , a decoder 408 , and a demodulator 409 .

[0090] In one example, transmitter 401 conditions (e.g., performs analog-to-analog conversion, filtering, amplification, and frequency upconversion) the output samples and generates an uplink signal, which is transmitted via an antenna to an access network device. On the downlink, the antenna receives the downlink signal transmitted by the access network device. Receiver 402 conditions (e.g., performs filtering, amplification, frequency downconversion, and digitization) the signal received from the antenna and provides input samples. Within modem processor 405, encoder 406 receives traffic data and signaling messages to be transmitted on the uplink and processes them (e.g., formats, encodes, and interleaves them). Modulator 407 further processes (e.g., performs symbol mapping and modulation) the encoded traffic data and signaling messages and provides output samples. Demodulator 409 processes (e.g., demodulates) the input samples and provides symbol estimates. Decoder 408 processes (e.g., deinterleaves and decodes) the symbol estimates and provides decoded data and signaling messages for transmission to device 400. The encoder 406, modulator 407, demodulator 409, and decoder 408 can be implemented by the combined modem processor 405. These units perform processing based on the radio access technology (e.g., LTE and other evolved system access technologies) used by the radio access network. It should be noted that when the device 400 does not include the modem processor 405, the above functions of the modem processor 405 can also be performed by the processor 403.

[0091] Processor 403 controls and manages the actions of device 400, and is configured to execute the processing performed by device 400 in the above-described embodiments of the present disclosure. For example, processor 403 is also configured to execute the various steps of the sending device or receiving device in the above-described method embodiments, and / or other steps of the technical solutions described in the embodiments of the present disclosure.

[0092] Furthermore, the device 400 may further include a memory 404 , and the memory 404 is used to store program codes and data for the device 400 .

[0093] It is understandable that Figure 4 Only a simplified design of the device 400 is shown. In actual applications, the device 400 may include any number of transmitters, receivers, processors, modem processors, memories, etc., and all devices that can implement the embodiments of the present disclosure are within the scope of protection of the embodiments of the present disclosure.

[0094] The present invention also provides a wind farm blade lightning protection detection drone task scheduling and path optimization management device. The wind farm blade lightning protection detection drone task scheduling and path optimization management device includes a memory and a processor. The memory stores computer-readable instructions. When the computer-readable instructions are executed by the processor, the processor executes the steps of the wind farm blade lightning protection detection drone task scheduling and path optimization management method in the above-mentioned embodiments.

[0095] The present invention also provides a computer-readable storage medium, which can be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium. The computer-readable storage medium stores instructions. When the instructions are run on a computer, the computer executes the steps of the wind farm blade lightning protection detection drone task scheduling and path optimization management method.

[0096] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0097] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes various media that can store program code, such as a USB flash drive, a mobile hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0098] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that the technical solutions described in the above embodiments can still be modified, or some of the technical features thereof can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for task scheduling and path optimization management of UAVs for lightning protection inspection of wind farm blades, characterized in that: The wind farm blade lightning protection inspection UAV task scheduling and path optimization management method includes: The regional connectivity is calculated based on the topological relationship between wind turbine spacing, and the annual degradation rate of blade grounding resistance and the real-time lightning warning level are superimposed to generate a dynamic risk label for the wind turbine. Using the wind turbine's dynamic risk tags, sorting them in descending order of risk value, and combining the drone's remaining battery power and return distance, outputs inspection work order instructions with a time window. Parse inspection work order instructions, call the average inspection time of the same type of wind turbines in the past 90 days, use fractional differential equations to calculate the unit time cost derivative, and generate drone swarm deployment density instructions; According to the UAV swarm deployment density instruction, a repulsive potential field containing the lightning rod safety radius is constructed in the digital elevation model, and an obstacle avoidance track point sequence is generated through potential field gradient descent. Monitor the progress of the trajectory execution of the obstacle avoidance track point sequence. When the actual detection cost drops to the preset value compared with the predicted value, calculate the strategy switching probability based on the enterprise risk coefficient. If the probability is greater than the set value, output the work order priority update instruction.

2. The method for task scheduling and path optimization management of wind farm blade lightning protection detection drones according to claim 1 is characterized in that: include: Taking the wind turbine locations as nodes, establish connecting edges to form a wind turbine adjacency graph; Analyze the interconnected clusters of units in the adjacency graph and mark clusters with more than 3 units as highly connected areas; Extract historical blade ground resistance test values, calculate annual degradation percentage, and generate equipment degradation warning labels; Receive lightning warning level signals issued by the meteorological department and activate environmental risk signs according to the warning level.

3. The method for task scheduling and path optimization management of wind farm blade lightning protection detection drones according to claim 2 is characterized in that: include: Place the wind turbine with a red risk label at the top of the queue, followed by the yellow label, and the green label at the bottom. Arrange wind turbines of the same color level in descending order of ground resistance degradation rate, and output the risk-ranked wind turbine queue. Obtain the drone's real-time remaining battery power, multiply it by the endurance conversion coefficient to obtain the safe flight time. Combined with the wind farm's average cruising speed, calculate the maximum one-way operating distance and output the safe operating radius for each drone. With the wind farm charging pile location as the center, match available drones, establish a drone-charging pile exclusive mapping relationship table, and output a charging pile binding list; The wind turbine queue is ranked by risk, and the nearest drone is assigned according to each drone's safe operating radius. A list of charging pile bindings is superimposed to ensure that the drone can return to the dedicated charging pile after inspection is completed, and a work order instruction with three elements is output; When multiple drones are assigned to the same wind turbine, priority is given to the unit with higher remaining power. The replaced drone is automatically reallocated to the inspection task of the next wind turbine in the queue and outputs the updated work order instruction set.

4. The method for task scheduling and path optimization management of wind farm blade lightning protection inspection drones according to claim 3 is characterized in that: Set safe flight time to , the maximum one-way operating distance is ,but: ； in, is the percentage of remaining power, is the endurance conversion factor; ； in, is the average cruising speed in km / h, The unit of safe flight time is minutes; The safe operating radius of each drone is R: 。 5. The method for task scheduling and path optimization management of wind farm blade lightning protection inspection drones according to claim 4 is characterized in that: include: Parse the target wind turbine model and blade length in the inspection work order instruction, match the model with the wind turbine technical files in the historical database, and output the identification tag of the same type of wind turbine; Call the inspection time records of the same model of fans in the past 90 days, remove the overtime abnormal values, and output the standard time distribution table; Based on the standard time distribution table, combined with real-time labor rates and drone depreciation parameters, a fractional-order differential equation is used to describe the memory effect of cost changes with inspection time, and a unit time cost change rate curve is output; When the cost change rate per unit time exceeds the cost change rate threshold, the number of drones per unit area is increased, and the drone / square kilometer density control value is output; When the density control value fluctuates by more than 30% compared with the previous instruction, the operation and maintenance expert review process is triggered, the density control value is revised based on the review opinion, and the final deployment density instruction is output.

6. The method for task scheduling and path optimization management of wind farm blade lightning protection inspection drones according to claim 5 is characterized in that: include: Read the drone / square kilometer density control value, convert it into the minimum horizontal spacing standard between drones, and output the spacing constraint parameters; Obtain the geographic coordinates of all lightning rods in the wind farm, generate a cylindrical repulsion field with the coordinates as the center, and output the lightning rod potential field layer.

7. The method for task scheduling and path optimization management of wind farm blade lightning protection inspection drones according to claim 6 is characterized in that: In the digital elevation model, areas with slopes greater than 30° are marked as terrain obstacles. Spacing constraint parameters are superimposed to generate an inter-UAV repulsion field. The lightning rod potential field layer is then integrated to output a three-dimensional composite potential field model. Starting from the target wind turbine tower base coordinates, iteratively search along the negative gradient direction of the composite potential field, output track point coordinates every 10 meters, and output obstacle avoidance track point sequence; Automatically mark track points that are less than 10 meters away from the lightning rod, push high-risk points to the operation and maintenance console for manual confirmation, and integrate the confirmation results to generate the final track sequence.

8. The method for task scheduling and path optimization management of wind farm blade lightning protection inspection drones according to claim 7 is characterized in that: include: Receive the coordinates of the flown track points sent back by the drone in real time, compare them with the planned track point sequence to calculate the completion percentage, and output the track execution progress report; Synchronously obtain drone power consumption and manual monitoring working hours data, superimpose equipment depreciation rate to calculate real-time detection costs, and output actual cost flow records; Call the predicted cost benchmark value, and when the actual cost flow record drops by more than 15%, activate the judgment flag and output the cost reduction trigger signal; Read the risk tolerance coefficient preset by the enterprise management system, map the strategy switching probability according to the coefficient value, and output the strategy switching probability value; Output a work order priority update instruction based on the strategy switching probability value.

9. The method for task scheduling and path optimization management of wind farm blade lightning protection inspection drones according to claim 8 is characterized in that: Also includes real-time monitoring of charging pile status: Monitor charging pile temperature, output current and fault signals, and output charging pile health status table; Receive the sandstorm level issued by the meteorological station and output the track degradation instruction; Analyze high-definition images of blade surfaces taken by drones, and output a blade damage alarm package when lightning damage or cracks are identified.

Images