Fan blade inspection system and method based on unmanned aerial vehicle
By constructing a health scoring model and a nearest neighbor heuristic algorithm, the inspection path of the UAV is dynamically adjusted, which solves the problem of unreasonable resource allocation in the existing technology and realizes efficient, accurate inspection and flexible detection of wind turbine blades.
Patent Information
- Application Number
- CN202511395985.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-09-28
- Publication Date
- 2025-11-04
- Estimated Expiration
- 2045-09-28
AI Technical Summary
Existing drone inspection systems cannot dynamically adjust inspection priorities and routes, resulting in unreasonable resource allocation and difficulty in conducting focused inspections of high-risk wind turbines, thus affecting inspection efficiency and effectiveness.
By constructing a health scoring model, the health status of wind turbine blades is scored based on historical inspection data and real-time working data, a priority queue is generated, the nearest neighbor heuristic algorithm is used to plan the inspection path, and the inspection target is adjusted in real time. The defect type is identified by combining image grayscale values and vibration characteristics, and the inspection strategy is dynamically adjusted.
It significantly improves the targeting and efficiency of inspection tasks, enables accurate identification of blade defects, has environmental adaptability, ensures that critical defective wind turbines are detected and dealt with in a timely manner, and improves resource utilization efficiency and flexibility.
Smart Images

Figure CN120893787A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present application relates to the technical field of fan blade inspection, in particular to a fan blade inspection system and method based on a UAV. BACKGROUND
[0002] As an important component of a fan, the operating condition of a sea fan blade directly affects the power generation efficiency and safety of a wind turbine generator system. Due to long-term exposure to the marine environment, the blade is eroded by sea wind, high humidity, salt spray, ultraviolet rays, and sea waves, and is more prone to various defects than land fans, including blade surface corrosion, stain deposition, cracks, and other structural damage. These defects can lead to a decrease in blade aerodynamic performance, a decrease in fan operating efficiency, and even further development into serious blade rupture and machine shutdown accidents, causing huge economic losses to the wind farm operation.
[0003] Current UAV inspection tasks are usually based on fixed inspection cycles or fan positions, and the health status of fan blades cannot be prioritized by combining historical inspection data and real-time operation data. This method may lead to unreasonable resource allocation and difficulty in focusing on high-risk fan inspection.
[0004] In the prior art, the system and method for inspecting fan blades based on a UAV are disclosed in CN117536797A. The system includes: a collection module for collecting blade data and surrounding environment data of blades to be inspected, determining characteristic inspection points of the UAV according to the blade data and the surrounding environment data, and generating an inspection path; an inspection module for photographing corresponding blades at the characteristic inspection points according to the inspection path to obtain first and second inspection images; and an analysis module for receiving the first and second inspection images, analyzing the first and second inspection images, obtaining the health status of the corresponding blades, and formulating a maintenance plan according to the health status of the blades. However, this system ignores the priority relationship between inspected fans, and cannot adjust the subsequent inspection plan according to the real-time detection results during the inspection task execution. For example, if a blade has a serious defect, it may indicate that the blades of adjacent fans also have similar problems, but this method cannot dynamically adjust the inspection priority and path, thereby affecting the inspection efficiency and effect.
[0005] The above information disclosed in the background section is only used to enhance the understanding of the background of the present disclosure, and therefore it can include information that does not constitute prior art known to those of ordinary skill in the art. SUMMARY
[0006] The present application aims to provide a fan blade inspection system and method based on a UAV to solve the problems raised in the background.
[0007] To achieve the above object, the present application provides the following technical solutions: A wind turbine blade inspection system based on a UAV, specifically comprising: A priority analysis module for collecting historical inspection data of each wind turbine blade in a wind farm and working data of a specified period before shutdown, performing normalization processing on the data, constructing a health score model, scoring the health status of each blade, and generating a wind turbine health priority queue sorted by health priority; An inspection target determination module for selecting inspection wind turbines from the queue to form an inspection target set according to the initial endurance distance of the UAV and the distance between adjacent wind turbines in the health priority queue; An inspection route planning module for planning an inspection path of the UAV based on the inspection target set using a nearest neighbor heuristic algorithm; A blade defect detection module for controlling the UAV to inspect the target wind turbines in turn according to the planned inspection path, collecting image data of the blades during the inspection, identifying target areas according to changes in the gray scale values in the images, extracting geometric morphological parameters of the target areas, and determining the blade defect type in combination with the vibration characteristic data of the corresponding blades; A real-time target adjustment module for analyzing the structural defect degree of the blades with structural defects, determining the associated detection field, adding wind turbines in the associated detection field that have not been inspected to the current inspection target set, and regenerating the inspection path of the remaining inspection wind turbines in the current round to complete the entire inspection task.
[0008] Further, the historical inspection data includes the historical failure frequency and the operating life of each blade, and the working data of the specified period before shutdown includes the blade vibration amplitude difference, the blade speed difference, and the power generation difference; Wherein, the vibration amplitude difference, the blade speed difference, and the power generation difference specifically refer to the absolute difference between the blade vibration amplitude, speed, and power generation in the specified period before shutdown and the reference vibration amplitude, speed, and power generation under the same wind speed; The health score model is constructed to score the health status of each blade, and the formula for calculating the health status score of the blade is: ; In the formula, is the health status score of the i-th blade, is the normalized value of the historical failure frequency of the i-th blade, is the normalized value of the operating life of the i-th blade, is the state coefficient of the i-th blade, and are the historical scaling constant and the actual scaling constant, respectively, and i is the index of the wind turbine blade; The state coefficient of the i th blade The working data of a specified period before shutdown is specifically characterized, and the formula specifically used for calculation is as follows: ; In the formula, is the vibration amplitude difference normalized value of the i th blade, is the speed difference normalized value of the i th blade, is the power generation difference normalized value of the i th blade.
[0009] Further, the health state score average value of the blades in each wind turbine is calculated, the wind turbines are sorted according to the health state score average value to form a wind turbine health priority queue, and the formula used for calculating the health state score average value corresponding to each wind turbine is as follows: ; In the formula, is the health state score average value corresponding to the j th wind turbine, is the health state score of the i th blade in the j th wind turbine, is the number of blades of the wind turbine, and j is the index of the wind turbine in the wind farm; The wind turbines in the wind farm are arranged in descending order according to the size of the health state score average value to form a wind turbine health priority queue.
[0010] Further, the logic used for constructing the inspection target set is as follows: the takeoff position and the landing position of the unmanned aerial vehicle are set, the length of the preset flight path is not higher than the initial endurance distance as a constraint condition, the wind turbines are sequentially added according to the wind turbine health priority queue to update the preset flight path, the wind turbines in the final preset flight path are taken as the inspection wind turbines to form the inspection target set, and the wind turbines in the wind farm that are not added to the preset flight path are taken as the candidate inspection wind turbines, the preset flight path is a path that starts from the takeoff position and ends at the landing position and sequentially passes through the inspection wind turbines according to the order of the wind turbine addition, and the initial endurance distance specifically refers to the maximum flight distance of the unmanned aerial vehicle in the state of an undischarged battery.
[0011] Further, the inspection path is the shortest flight route covering the inspection wind turbines in the inspection target set, and the specific logic of using the nearest neighbor heuristic algorithm to plan the inspection path of the unmanned aerial vehicle is as follows: the takeoff position is taken as the task starting point, the landing position is taken as the task ending point, and the inspection wind turbines in the inspection target set are taken as the target points to be passed through, the shortest flight route covering the inspection wind turbines in the inspection target set is determined as the inspection path.
[0012] Further, the blade defect type includes a structural defect and a stain defect. The step of determining the target region comprises: performing background separation processing on the collected blade image data, converting the blade part in the image into a gray-scale image, extracting and analyzing the gray-scale values of each pixel point in the gray-scale image, and determining the target region according to the gradient change of the pixel point gray-scale values. The logic for determining the target region according to the gradient change of the pixel point gray-scale values is: calculating the gradient of each pixel point in the blade part image by using a Sobel operator, setting a gradient change threshold, taking the pixel points with a gradient greater than the gradient change threshold as boundary points, and taking the closed region formed by the boundary points as the target region; the vibration characteristic data specifically refers to the blade vibration amplitude and vibration main frequency values; The logic for determining the blade defect type according to the vibration characteristic data of the corresponding blade in the specified time period before shutdown is: extracting the blade vibration amplitude data from the blade vibration time history data, analyzing the vibration main frequency values, calculating the structural defect coefficient according to the deviation degree of the vibration main frequency values and the difference of the blade vibration amplitudes, and using the structural defect coefficient to determine whether the blade has a structural defect; the formula for calculating the structural defect coefficient is: ; In the formula, is the structural defect coefficient of the i th blade, is the vibration main frequency value of the i th blade, is the vibration reference main frequency value of the i th blade; The logic for determining whether the blade has a structural defect is: If , it is determined that the blade has a structural defect; If , it is determined that the blade does not have a structural defect, and the target region is a stain defect; is a structural defect judgment threshold; The type of the structural defect is determined according to the geometric parameters of the target region, the geometric parameters including the area, length and circularity of the region, and the type of the structural defect including a blade crack and surface corrosion; The specific determination logic is: if the area and circularity of the region are less than the set area threshold and circularity threshold, but the corresponding length is greater than the set length threshold, it is determined that the structural defect is a blade crack; if the area and circularity of the region are greater than the set area threshold and circularity threshold, but the corresponding length is less than the set length threshold, it is determined that the structural defect is surface corrosion.
[0013] Further, the logic for determining the correlation detection field is that: the blade defect type is detected and output in real time, if there is a structural defect in the blade, the correlation detection field is set with the current UAV position as the center, and the radius of the correlation detection field is determined by the defect degree, specifically, the field radius is determined by the crack length combined with the area of surface corrosion, and the formula for calculating the radius of the correlation detection field is: ; In the formula, R is the radius of the correlation detection field, R is the reference radius, L is the total length of the crack of the blade, L is the reference length of the crack, is the length influence constant, is the corrosion area influence constant, A is the total area of corrosion of the blade, A is the reference area of corrosion; The candidate inspection wind turbines in the correlation detection field are added to the inspection target set, the current UAV position is taken as the starting point, and the landing position is taken as the task end point, the wind turbines in the inspection target set except the wind turbines that have completed the inspection are taken as the way target points, the candidate shortest flight route is generated based on the nearest neighbor heuristic algorithm, and the candidate shortest flight route is compared with the current endurance distance of the UAV. If the current endurance distance of the UAV is less than the candidate shortest flight route, the corresponding blade inspection of the wind turbine is completed according to the original inspection path, and the candidate inspection wind turbines in the correlation detection field are taken as the next round of inspection targets. If the current endurance distance of the UAV is not greater than the current shortest flight route, the inspection is performed according to the candidate shortest flight route.
[0014] The application also provides a wind turbine blade inspection method based on a UAV, which is used for controlling the wind turbine blade inspection method based on a UAV, and comprises the following steps: Collecting historical inspection data and working data of each wind turbine blade in a wind farm for a specified period before shutdown, performing normalization processing on the data, constructing a health score model, scoring the health state of each blade, and generating a wind turbine health priority queue sorted by health priority; According to the initial endurance distance of the UAV and the distance between adjacent wind turbines in the health priority queue, the inspection wind turbines are selected from the queue to form an inspection target set; Based on the inspection target set, a nearest neighbor heuristic algorithm is used to plan the inspection path of the UAV; The unmanned aerial vehicle controls the unmanned aerial vehicle to inspect the target wind turbine in turn according to the planned inspection path, and collects image data of the blade in the inspection process, identifies the target area according to the change of the gray value in the image, extracts the geometric shape parameters of the target area, and judges the blade defect type in combination with the vibration characteristic data of the corresponding blade; The structural defect degree of the blade with the structural defect is analyzed, the associated detection field is determined, the wind turbine in the associated detection field which has not been inspected is added to the current inspection target set, the inspection path of the remaining inspection wind turbine in the current inspection is regenerated, and the whole inspection task is completed.
[0015] Compared with the prior art, the beneficial effects of the present application are: The health state of the wind turbine blade is quantitatively evaluated through the health score model, the wind turbine with poor health state is preferentially arranged for inspection, the pertinence and efficiency of the inspection task are significantly improved, the precise identification of the blade defect is realized through the fusion of the image gray value difference, the geometric shape parameter and the blade vibration characteristic, the strong environmental adaptability is achieved, and the complex conditions such as uneven light and salt spray interference in the marine environment can be coped with, in the inspection process, the blade defect data is analyzed in real time, the priority of the wind turbine which has not been inspected is dynamically adjusted, the inspection path is re-planned, the key defect wind turbine is detected and processed in time, and the flexibility and resource utilization efficiency of the inspection task are improved. BRIEF DESCRIPTION OF DRAWINGS
[0016] Figure 1 It is a schematic diagram of the overall device structure of the present application; Figure 2 It is a single blade vibration spectrum diagram; Figure 3 It is a vibration time history diagram of the blade with structural defects; Figure 4 It is a schematic diagram of the overall method flow of the present application. DETAILED DESCRIPTION
[0017] In order to make the purpose, technical scheme and advantages of the present application more clear and obvious, the present application is further described in detail below in combination with specific embodiments.
[0018] It should be noted that the technical terms or scientific terms used in the present application should be understood as the general meaning understood by those skilled in the art unless otherwise defined. The terms "first", "second" and the like used in the present application do not represent any order, number or importance, but are only used to distinguish different components. The terms "include" or "contain" and the like mean that the elements or objects before the terms cover the elements or objects listed after the terms and their equivalents, and do not exclude other elements or objects. The terms "connect" or "connected" and the like are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. The terms "up", "down", "left", "right" and the like are only used to represent relative positional relationships, and when the absolute position of the described object changes, the relative positional relationship may also change accordingly.
[0019] Embodiments: Please refer to Figures 1-3 The present application provides a technical solution: A fan blade inspection system based on a UAV, specifically comprising: A priority analysis module is configured to collect historical inspection data of each fan blade in a wind farm and working data of a specified period before shutdown, normalize the data, build a health score model, score the health status of each blade, and generate a fan health priority queue sorted by health priority.
[0020] The historical inspection data includes the historical failure frequency and the operating life of each blade, and the working data of the specified period before shutdown includes the blade vibration amplitude difference, the blade speed difference and the power generation difference. The wind farm usually records the failure information of each blade through an operation and maintenance management system, such as a SCADA system, i.e., a wind turbine monitoring system, including the time of failure, the type of failure, retrieves the historical failure frequency from the database, and according to the equipment maintenance log and the failure alarm information, the information is counted and stored for subsequent analysis.
[0021] The time information when the fan equipment is installed is usually recorded in the operation and maintenance management system, the installation time of the fan is retrieved from the operation management database, and the difference between the current time and the installation time is calculated, i.e., the operating life of the blade is obtained.
[0022] The vibration amplitude difference, the blade speed difference and the power generation difference specifically refer to the absolute difference between the blade vibration amplitude, the speed and the power generation in the specified period before shutdown and the reference vibration amplitude, the speed and the power generation under the same wind speed. The vibration amplitude of the blades is collected in real time by vibration sensors installed on the wind turbine blades or nacelle. Real-time vibration data of the blades is collected within a specified period, such as 30 minutes before shutdown, and stored through a SCADA system or independent data acquisition equipment. The blade speed can be monitored in real time by the speed sensor in the wind turbine nacelle or the wind turbine control system. Blades with large differences in speed may have wear, deformation or other faults. Power generation is the most critical operating indicator for wind turbines. It can be collected through power sensors or energy metering equipment in the wind turbine nacelle. The power sensors measure the output power of the wind turbine in real time, or through SCADA systems. The monitoring system of a wind farm usually records the power generation information of each wind turbine.
[0023] A health scoring model is constructed to score the health status of each leaf. The formula used to calculate the leaf health status score is as follows: ; In the formula, Score the health status of the i-th leaf. Let be the normalized value of the historical failure count for the i-th blade. Let be the normalized value of the service life of the i-th blade. Let be the state coefficient of the i-th leaf. and These are the historical scaling constant and the actual scaling constant, respectively, where i is the index of the wind turbine blade; It should be noted that the health status score of the i-th leaf This value indicates the health of the leaves; a higher value indicates a worse leaf health condition, and vice versa. The historical failure count and operational years reflect the failure records accumulated by the blade during its life cycle, which are usually related to blade aging and usage. Higher values lead to a higher health score, indicating a decline in blade health. Therefore, the historical failure count and operational years are correlated with the health status score of the i-th blade. Proportional; Among them, historical scaling constant and actual scaling constant and Specific settings can be configured based on expert experience.
[0024] Where the state coefficient of the i-th blade Specifically, it is characterized by the working data of a specified period before shutdown, and the specific formula used for calculation is as follows: ; In the formula, Let be the normalized value of the vibration amplitude difference of the i-th blade. The normalized value of the speed difference of the i th blade, The normalized value of the power generation difference of the i th blade.
[0025] It should be noted that the state coefficient of the i th blade is used to represent the vibration and speed difference of the blade, and the larger the value is, the worse the state of the blade is, so the state coefficient is directly proportional to the vibration amplitude difference, the speed difference and the power generation difference of the blade; the purpose of designing this formula is to represent the current state of the blade through three key working parameters of the blade, vibration, speed and power generation, and comprehensively reflect the health and performance of the blade. The vibration amplitude is a direct manifestation of the stability of the blade operation, and abnormal vibration may be the result of blade structure damage such as cracks, loose connecting parts or decline in surface aerodynamic performance; the speed directly determines the power output performance of the fan, and abnormal speed may be related to uneven blade mass and decline in aerodynamic performance; the power generation is the ultimate goal of fan operation, and the state of the blade has a direct impact on the power generation performance, especially when the blade aerodynamic efficiency declines, the power generation will decrease significantly, so the vibration amplitude difference, the speed difference and the power generation difference are all directly proportional to the state coefficient
[0026] . In order to make the vibration amplitude difference, the speed difference and the power generation difference comparable, the three parameters are normalized.
[0027] The average value of the health state score of the blades in each fan is calculated, and the fans are sorted according to the average value of the health state score to form a fan health priority queue, and the formula for calculating the average value of the health state score corresponding to each fan is: In the formula, is the average value of the health state score corresponding to the j th fan, is the health state score of the i th blade in the j th fan, is the number of blades of the fan, and j is the index of the fan in the wind farm; It should be noted that by calculating the average value of the health state score of all blades in each fan, the overall health condition of the fan can be effectively reflected; evaluating the health state of each blade separately may be affected by some abnormal values, while the average value can balance the influence of these extreme values, and the average value provides a standardized index, making the comparison of the health state between different fans more fair and reasonable. The number of blades of different fans may be different, and the average value can eliminate the influence of such difference.
[0028] The fans in the wind farm are arranged in descending order according to the size of the average value of the health state score to form a fan health priority queue.
[0029] The inspection target determination module is configured to select inspection wind turbines from the queue to form an inspection target set according to the initial endurance distance of the unmanned aerial vehicle and the spacing between adjacent wind turbines in the health priority queue.
[0030] The logic for constructing the inspection target set is as follows: the takeoff position and the landing position of the unmanned aerial vehicle are set, the length of the preset flight path is constrained to be not higher than the initial endurance distance, the wind turbines are sequentially added according to the order of the wind turbine health priority queue to update the preset flight path, the wind turbines in the final preset flight path are taken as the inspection wind turbines to form the inspection target set, and the wind turbines in the wind farm that are not added to the preset flight path are taken as candidate inspection wind turbines, the preset flight path is a path that starts from the takeoff position and ends at the landing position and sequentially passes through the inspection wind turbines in the order of the wind turbine addition, and the initial endurance distance specifically refers to the maximum flight distance of the unmanned aerial vehicle in the state that the battery is not consumed.
[0031] The preset flight path starts from the takeoff position of the unmanned aerial vehicle and ends at the landing position, ensuring that the inspection task is completed within the endurance distance. This approach meets the endurance limit of the unmanned aerial vehicle, avoids path planning beyond the maximum flight distance of the battery, and ensures task safety; the sorting of the wind turbines is based on the priority of the health state score, and the higher the health score, the worse the health condition of the wind turbine that is preferentially included in the inspection path, ensuring reasonable allocation of resources and preferential inspection of wind turbines that need attention, thereby avoiding resource waste. The flight path of the unmanned aerial vehicle is constrained by the initial endurance distance. The inspection path is planned within the endurance range, which ensures task completion and avoids inspection failure due to battery depletion of the unmanned aerial vehicle.
[0032] The inspection route planning module is configured to plan the inspection path of the unmanned aerial vehicle based on the inspection target set using the nearest neighbor heuristic algorithm.
[0033] The inspection path is the shortest flight route covering the inspection wind turbines in the inspection target set, and the specific logic for planning the inspection path of the unmanned aerial vehicle using the nearest neighbor heuristic algorithm is as follows: taking the takeoff position as the task starting point and the landing position as the task ending point, taking the inspection wind turbines in the inspection target set as the target points, and determining the shortest flight route covering the inspection wind turbines in the inspection target set as the inspection path.
[0034] The wind turbines in the inspection target set are taken as the passing points to ensure that all wind turbines that need to be inspected are covered. This ensures that the unmanned aerial vehicle does not miss any critical targets during the inspection process. The nearest neighbor heuristic algorithm is an efficient greedy algorithm that gradually constructs the path by selecting the nearest target point at each step, thereby minimizing the flight distance. This method is simple and effective, especially suitable for dynamic inspection task scenarios. The nearest neighbor heuristic algorithm selects the nearest fan at each step, thereby minimizing the inspection path and improving inspection efficiency. In practical operation, reducing flight time can save battery power and increase inspection frequency. The nearest neighbor heuristic algorithm is simple and easy to use. Compared with other more complex path optimization algorithms, it has a faster calculation process and can generate a feasible path in a shorter time, making it suitable for real-time inspection tasks.
[0035] In some cases, the inspection target may change, such as the addition of a temporary fan or a sudden health problem. The nearest neighbor heuristic algorithm can quickly re-plan the path and adapt to new inspection requirements.
[0036] The blade defect detection module is used to control the UAV to inspect the target fan in turn according to the planned inspection path, and to collect image data of the blade during the inspection process. According to the change of the gray value in the image, the target area is identified, the geometric shape parameters of the target area are extracted, and the blade defect type is determined in combination with the vibration characteristic data of the corresponding blade.
[0037] The blade defect type includes structural defects and stain defects. The step of determining the target area is: performing background separation processing on the collected blade image data, converting the blade part in the image into a gray image, extracting and analyzing the gray values of each pixel point in the gray image, and determining the target area according to the gradient change of the pixel point gray value. The logic for determining the target area according to the gradient change of the pixel point gray value is: calculating the gradient of each pixel point in the blade part image using the Sobel operator, setting a gradient change threshold, regarding the pixel points with a gradient greater than the gradient change threshold as boundary points, and regarding the closed area formed by the boundary points as the target area. The gradient change threshold is set according to expert experience. In the gradient image, mark the pixel points with a gradient value greater than the threshold as boundary points. These boundary points can be extracted using binary processing. Perform contour detection using the boundary points to identify all closed areas. Save the coordinates, area, shape, and other information of the determined target area as a data file, such as CSV or JSON format, for subsequent analysis or use.
[0038] The vibration characteristic data specifically refers to the blade vibration amplitude and vibration main frequency value. The logic for determining the type of blade defect based on the vibration characteristic data of the corresponding blade within a specified time period before shutdown is as follows: the vibration amplitude data of the blade is extracted from the vibration time history data, and the vibration main frequency value is analyzed. According to the deviation degree of the vibration main frequency value and the difference in the vibration amplitude of the blade, a structural defect coefficient is calculated to determine whether the blade has a structural defect. The formula for calculating the structural defect coefficient is: ; In the formula, is the structural defect coefficient of the i-th blade, is the vibration main frequency value of the i-th blade, is the vibration reference main frequency value of the i-th blade; It should be noted that the vibration main frequency is a core characteristic of blade vibration, and its reference value represents the natural vibration frequency of the blade in a normal state. When the blade has a structural defect, such as a crack, surface damage, internal material deformation, etc., its vibration characteristics will change, causing the vibration main frequency to deviate from the reference main frequency value , which represents the deviation degree of the main frequency. The larger the value, the more serious the blade structural defect; The vibration amplitude is another important characteristic of blade vibration, reflecting the energy and intensity of vibration. Under normal circumstances, the vibration amplitude of the blade maintains within a relatively stable range. If the blade has a structural defect, such as blade material damage or internal stiffness change, the vibration amplitude will change significantly, defined as the abnormality degree of the vibration amplitude, the larger the value, the more serious the abnormality of the blade vibration amplitude; The main frequency deviation value and the amplitude difference are two complementary indicators. The main frequency deviation value focuses on the change of the blade vibration mode, and the amplitude difference focuses on the abnormality of the vibration intensity. The combination of the two comprehensively reflects the health status of the blade.
[0039] The logic for determining whether the blade has a structural defect is as follows: If , it is determined that the blade has a structural defect; If , it is determined that the blade does not have a structural defect, and the target area is a stain defect; is the structural defect judgment threshold, which is specifically set according to expert experience; The type of structural defect is determined according to the geometric parameters of the target area, including area, length and circularity. The types of structural defects include blade cracks and surface corrosion. Since the blade crack usually presents as an elongated and irregular shape, its area is small, the circularity is low, the length of the crack is relatively long, the surface corrosion usually presents as a certain area, and the shape is relatively smooth, the circularity is high, so the type of structural defect can be determined by the geometric morphology.
[0040] The specific determination logic is that if the area and the circularity are less than the set area threshold and the circularity threshold, but the corresponding length is greater than the set length threshold, it is determined that the structural defect is a blade crack, and if the area and the circularity are greater than the set area threshold and the circularity threshold, but the corresponding length is less than the set length threshold, it is determined that the structural defect is surface corrosion; the area threshold, the circularity threshold and the length threshold can be set according to the actual defect situation combined with expert experience.
[0041] The real-time target adjustment module is used to analyze the structural defect degree of the blade with structural defects, determine the associated detection field, add the wind turbines in the associated detection field which have not been inspected to the current inspection target set, regenerate the inspection path of the remaining wind turbines in the current inspection, and complete the whole inspection task.
[0042] The logic for determining the associated detection field is that the blade defect type is detected and output in real time, and if the blade has a structural defect, the current UAV position is taken as the center to set the associated detection field, and the radius of the associated detection field is determined by the defect degree, specifically, the field radius is determined by the crack length combined with the area of the surface corrosion, and the formula for calculating the radius of the associated detection field is: ; In the formula, R is the radius of the associated detection field, r is the reference radius, L is the total length of the crack of the blade, l is the reference length of the crack, k is the length influence constant, a is the corrosion area influence constant, A is the total area of the corrosion of the blade, a is the reference area of the corrosion; It should be noted that the reference radius provides a reference value representing the detection field in the normal state. This is a basic starting point, and through this value, the size of the associated detection field can be flexibly adjusted. The total length of the crack is directly related to the health status of the blade structure. The longer the crack, the more serious the structural damage, as the reference crack length, is used to compare the difference between the current state and the normal state, and by introducing the length influence constant The change in crack length can be weighted to determine its contribution to the radius of the associated detection area. The setting of this constant can be based on empirical data or experimental results. Total corrosion area This reflects the degree of corrosion on the blade surface. The more severe the corrosion, the lower the blade's load-bearing capacity and durability. The corrosion area influence constant is also relevant. This constant is used to adjust the degree of influence of the corrosion area on the radius of the detection field. The impact of corrosion on the health of the blade may vary under different material and environmental conditions; therefore, this constant can be appropriately adjusted based on the specific application scenario and expert experience.
[0043] Where the reference radius The specific setting can be based on the average spacing between the fans, and is generally set to twice the average spacing between the fans.
[0044] Candidate wind turbines in the correlation detection field are added to the inspection target set. Taking the current position of the UAV as the starting point and the landing position as the mission endpoint, the other wind turbines in the inspection target set except for those that have been inspected are taken as path target points. Candidate shortest flight routes are generated based on the nearest neighbor heuristic algorithm, and the candidate shortest flight routes are compared with the current flight range of the UAV. If the current flight range of the drone is less than the candidate shortest flight path, the corresponding wind turbine blade inspection will be completed according to the initial inspection path, and the candidate wind turbines in the associated inspection field will be used as the inspection targets for the next round. If the drone's current range is not greater than the shortest flight path, then the inspection will be carried out according to the candidate shortest flight path.
[0045] Candidate wind turbines within the associated inspection area are added to the inspection target set to ensure that all potentially defective turbines are included in the inspection scope. This effectively improves the comprehensiveness of the inspection, ensuring that every potential risk point is addressed. The current flight range of the drone is compared with the candidate shortest flight path to ensure that the drone can complete the predetermined inspection targets during the mission, avoiding mission failure due to insufficient flight range. If the flight range is less than the candidate path, the corresponding wind turbine blades are inspected according to the initial inspection path, ensuring safety and controllability within the drone's flight range. By setting the condition judgment, the inspection strategy can be dynamically adjusted according to the actual endurance capability of the unmanned aerial vehicle. When the endurance distance is insufficient, a safer and controllable way is selected to continue the inspection. When the endurance capability is sufficient, the candidate shortest flight route inspection is carried out. The flexibility enhances the adaptability and response capability of the inspection, and by excluding the completed inspection wind turbine from the candidate inspection wind turbine in the associated detection field, unnecessary repeated inspection is reduced, resource use is optimized, and inspection efficiency is improved. At the same time, the candidate inspection wind turbine in the associated detection field is taken as the next round of inspection target, forming a continuous inspection strategy, and ensuring the smoothness of the follow-up work.
[0046] Please refer to Figure 4 The application also provides a wind turbine blade inspection method based on an unmanned aerial vehicle, which is used to control the wind turbine blade inspection method based on an unmanned aerial vehicle, and comprises the following steps: Step 1: Collecting historical inspection data and working data of each wind turbine blade in a wind farm within a specified period before shutdown, normalizing the data, constructing a health score model, scoring the health state of each blade, and generating a wind turbine health priority queue sorted by health priority; Step 2: Selecting inspection wind turbines from the queue to form an inspection target set according to the initial endurance distance of the unmanned aerial vehicle and the distance between adjacent wind turbines in the health priority queue; Step 3: Based on the inspection target set, a nearest neighbor heuristic algorithm is used to plan the inspection path of the unmanned aerial vehicle; Step 4: Controlling the unmanned aerial vehicle to inspect the target wind turbine in turn according to the planned inspection path, and collecting image data of the blade during the inspection process, identifying the target area according to the change of the gray value in the image, extracting the geometric morphological parameters of the target area, and combining the vibration characteristic data of the corresponding blade to determine the blade defect type; Step 5: Analyzing the structural defect degree of the blade with structural defects, determining the associated detection field, adding the wind turbines in the associated detection field that have not been inspected to the inspection target set of this round, regenerating the inspection path of the remaining inspection wind turbines of this round, and completing the entire inspection task.
[0047] The above formulas are dimensionless numerical calculations, and the formulas are obtained by software simulation of a large amount of data to obtain the most recent real situation. The preset parameters in the formula are set by a person skilled in the art according to the actual situation.
[0048] The above-described embodiments can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented by software, the above-described embodiments can be implemented in whole or in part in the form of a computer program product. A person of ordinary skill in the art can be aware that units and algorithm steps of the examples described in connection with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether the functions are performed by hardware or software depends on the specific application and design constraints of the technical solutions.
[0049] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, and can be located in one place or distributed on multiple network units. Part or all of the units can be selected to achieve the purpose of the embodiments according to actual needs.
[0050] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto, and any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered within the protection scope of the present application.
Claims
1. A wind turbine blade inspection system based on unmanned aerial vehicles (UAVs), characterized in that, Specifically, it includes: The priority analysis module is used to collect historical inspection data of each wind turbine blade in the wind farm and working data for a specified period before shutdown. After normalizing the data, a health scoring model is constructed to score the health status of each blade and generate a wind turbine health priority queue sorted by health priority. The inspection target determination module is used to select inspection wind turbines from the queue to form an inspection target set based on the initial flight range of the UAV and the spacing between adjacent wind turbines in the health priority queue. The inspection route planning module is used to plan the inspection path of the UAV based on the inspection target set and using the nearest neighbor heuristic algorithm. The blade defect detection module is used to control the drone to inspect the target wind turbine sequentially according to the planned inspection path, and to collect image data of the blades during the inspection process. Based on the changes in grayscale values in the image, the module identifies the target area, extracts the geometric morphology parameters of the target area, and determines the type of blade defect by combining the vibration characteristic data of the corresponding blade. The real-time target adjustment module is used to analyze the degree of structural defects in blades with structural defects, determine the associated detection areas, add the uninspected wind turbines in the associated detection areas to the target set of this round of inspection, and regenerate the inspection path for the remaining wind turbines to be inspected in this round of inspection in order to complete all inspection tasks.
2. The wind turbine blade inspection system based on unmanned aerial vehicles (UAVs) according to claim 1, characterized in that: The historical inspection data includes the number of historical faults and the number of years of operation for each blade, and the working data for the specified period before shutdown includes differences in blade vibration amplitude, differences in blade rotation speed, and differences in power generation. Specifically, the differences in vibration amplitude, blade rotation speed, and power generation refer to the absolute differences between the blade vibration amplitude, rotation speed, and power generation within a specified time period before shutdown and the reference vibration amplitude, rotation speed, and power generation at the same wind speed. A health scoring model is constructed to score the health status of each leaf. The formula used to calculate the leaf health status score is as follows: ; In the formula, Score the health status of the i-th leaf. Let be the normalized value of the historical failure count for the i-th blade. Let be the normalized value of the service life of the i-th blade. Let be the state coefficient of the i-th leaf. and These are the historical scaling constant and the actual scaling constant, respectively, where i is the index of the wind turbine blade; Where the state coefficient of the i-th blade Specifically, it is characterized by the working data of a specified period before shutdown, and the specific formula used for calculation is as follows: ; In the formula, Let be the normalized value of the vibration amplitude difference of the i-th blade. Let be the normalized value of the rotational speed difference for the i-th blade. Let be the normalized value of the power generation difference of the i-th blade.
3. The wind turbine blade inspection system based on unmanned aerial vehicles (UAVs) according to claim 2, characterized in that: Calculate the average health status score of the blades in each wind turbine, and rank the wind turbines according to the average health status score to form a wind turbine health priority queue. The formula used to calculate the average health status score of each wind turbine is as follows: ; In the formula, Let be the average health status score corresponding to the j-th wind turbine. For the j-th wind turbine, the health status score of the i-th blade is given. denoted by , where is the number of blades in the wind turbine, and j is the index of the wind turbine within the wind farm; Based on the average health status score, the wind turbines in the wind farm are ranked in descending order to form a wind turbine health priority queue.
4. The wind turbine blade inspection system based on unmanned aerial vehicles (UAVs) according to claim 2, characterized in that: The logic for constructing the inspection target set is as follows: set the take-off and landing positions of the UAV, with the constraint that the length of the preset flight path is not higher than the initial endurance distance, add wind turbines in sequence according to the wind turbine health priority queue to update the preset flight path, and take each wind turbine in the final preset flight path as the inspection wind turbine to form the inspection target set, and take the wind turbines in the wind farm that have not been added to the preset flight path as candidate inspection wind turbines. The preset flight path is the path that starts from the take-off position and ends at the landing position, and passes through each inspection wind turbine in the order of wind turbine addition. The initial endurance distance specifically refers to the maximum flight distance of the UAV when the battery is not consumed.
5. The wind turbine blade inspection system based on unmanned aerial vehicles (UAVs) according to claim 4, characterized in that: The inspection path is the shortest flight route covering each wind turbine in the inspection target set. The specific logic of using the nearest neighbor heuristic algorithm to plan the inspection path of the UAV is as follows: take the take-off position as the mission start point and the landing position as the mission end point, take each wind turbine in the inspection target set as the path target point, and determine the shortest flight route covering each wind turbine in the inspection target set as the inspection path.
6. The wind turbine blade inspection system based on unmanned aerial vehicles (UAVs) according to claim 5, characterized in that: The types of blade defects include structural defects and stain defects; The steps to determine the target area are as follows: perform background separation processing on the collected leaf image data, convert the leaf part in the image into a grayscale image, extract and analyze the grayscale value of each pixel in the grayscale image, and determine the target area based on the gradient change of the grayscale value of the pixel. The logic for determining the target region based on the gradient change of pixel grayscale values is as follows: the gradient of each pixel in the blade image is calculated using the Sobel operator, a gradient change threshold is set, pixels with gradients greater than the gradient change threshold are taken as boundary points, and the closed region formed by the boundary points is taken as the target region; the vibration feature data specifically refers to the blade vibration amplitude and vibration dominant frequency value. The logic behind determining the type of blade defect by combining vibration characteristic data of the corresponding blade within a specified time period before shutdown is as follows: The blade vibration amplitude data is extracted from the blade's vibration time history data, and the dominant vibration frequency is analyzed. Based on the degree of deviation of the dominant vibration frequency and the difference in blade vibration amplitude, a structural defect coefficient is calculated to determine whether a structural defect exists on the blade. The specific formula for calculating the structural defect coefficient is as follows: ; In the formula, Let be the structural defect coefficient of the i-th blade. Let be the dominant vibration frequency of the i-th blade. This is the vibration reference dominant frequency value for the i-th blade; The logic used to determine whether a blade has structural defects is as follows: like At that time, it was determined that the blade had a structural defect; like At that time, it was determined that the blade did not have structural defects, and the target area was a stain defect; The threshold for judging structural defects; The type of structural defect is determined based on the geometric parameters of the target area, including the area, length and circularity of the area, and the type of structural defect includes blade cracks and surface corrosion. The specific judgment logic is as follows: if the area and roundness of the region are less than the set area threshold and roundness threshold, but the corresponding length is greater than the set length threshold, the structural defect is judged to be a blade crack; if the area and roundness of the region are greater than the set area threshold and roundness threshold, but the corresponding length is less than the set length threshold, the structural defect is judged to be surface corrosion.
7. A wind turbine blade inspection system based on unmanned aerial vehicles (UAVs) according to claim 6, characterized in that: The logic for determining the specific associated detection area is as follows: Real-time detection and output of blade defect types. If a structural defect is detected in the blade, an associated detection area is defined with the current UAV position as the center. The radius of the associated detection area is determined by the defect severity, specifically by combining the crack length with the area of surface corrosion. The formula for calculating the radius of the associated detection area is as follows: ; In the formula, The radius of the correlation detection domain, As a reference radius, This represents the total length of the blade's slits. The reference length of the crack. For length influence constant, The constant is the influence of corrosion area. This represents the total corrosion area of the blade. Corrosion reference area; Candidate wind turbines in the correlation detection field are added to the inspection target set. Taking the current position of the UAV as the starting point and the landing position as the mission endpoint, the other wind turbines in the inspection target set except for those that have been inspected are taken as path target points. Candidate shortest flight routes are generated based on the nearest neighbor heuristic algorithm, and the candidate shortest flight routes are compared with the current flight range of the UAV. If the current flight range of the drone is less than the candidate shortest flight path, the corresponding wind turbine blade inspection will be completed according to the initial inspection path, and the candidate wind turbines in the associated inspection field will be used as the inspection targets for the next round. If the drone's current range is not greater than the shortest flight path, then the inspection will be carried out according to the candidate shortest flight path.
8. A method for inspecting wind turbine blades based on unmanned aerial vehicles (UAVs), characterized in that: The method for inspecting wind turbine blades based on unmanned aerial vehicles (UAVs) is used to control the UAV-based wind turbine blade inspection system according to any one of claims 1-7, comprising: Historical inspection data and working data for a specified period before shutdown of each wind turbine blade in the wind farm are collected. After normalizing the data, a health scoring model is constructed to score the health status of each blade and generate a wind turbine health priority queue sorted by health priority. Based on the initial flight range of the drone and the spacing between adjacent wind turbines in the health priority queue, wind turbines to be inspected are selected from the queue to form an inspection target set; Based on the set of inspection targets, the nearest neighbor heuristic algorithm is used to plan the inspection path of the UAV. The drone is controlled to inspect the target wind turbines sequentially according to the planned inspection path, and image data of the blades is collected during the inspection. Based on the changes in grayscale values in the images, the target area is identified, the geometric morphology parameters of the target area are extracted, and the blade defect type is determined by combining the vibration characteristic data of the corresponding blade. Analyze the degree of structural defects in the blades with defects, determine the associated detection areas, add the uninspected wind turbines in the associated detection areas to the target set of this round of inspection, and regenerate the inspection path for the remaining wind turbines in this round of inspection to complete all inspection tasks.
Citation Information
Patent Citations
Autonomous unmanned aerial vehicle fan blade polling system and method
CN105717934A
Wind turbine blade state monitoring system and method based on reverberation noise
CN115855465A
Fan blade inspection system and method based on unmanned aerial vehicle
CN117536797A
Fan blade shooting method and device, ship, storage medium and program product
CN118175426A
Intelligent unmanned marine monitoring network system and operation method
CN118550259A
Cited By
Fan inspection route planning method and system for intelligent sensor carried by unmanned aerial vehicle
CN121300443A
Unmanned aerial vehicle carries intelligent sensor fan inspection route planning method and system
CN121300443B
Intelligent wind power station inspection management method, device and equipment and storage medium
CN121304139A
