Data processing method and system for wind farm monitoring data
By dividing the acquisition area according to the linear velocity distribution of the wind turbine blades and dynamically adjusting the flight path of the UAV, the problem of blurry images in UAV inspection was solved, the acquisition efficiency and clarity were improved, and efficient blade image acquisition was achieved.
Patent Information
- Application Number
- CN202610761916.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-05-29
- Publication Date
- 2026-08-25
AI Technical Summary
Existing drone inspection solutions do not take into account the differences in the linear velocity distribution of wind turbine blades, which makes image acquisition prone to motion blur and results in low acquisition efficiency.
The drone's acquisition area is divided based on the linear velocity distribution of the wind turbine blades. The flight path is dynamically adjusted. By dividing multiple tracking acquisition areas and configuring corresponding flight parameters, the drone is controlled to acquire images within the target acquisition area until the clarity requirements are met, at which point the flight path is updated.
It reduced image blur, improved acquisition efficiency, reduced the number of times the drone switched between acquisition areas, shortened the total acquisition time, and achieved efficient leaf image acquisition.
Smart Images
Figure CN122632687A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to data processing technology, and more particularly to a data processing method and system for wind farm monitoring data. Background Technology
[0002] As a core component of wind turbines, the surface condition of wind turbine blades directly affects the power generation efficiency and operational safety of the turbine. Regular inspections of wind turbine blades and acquisition of high-quality blade images are indispensable parts of wind farm operation and maintenance management. In recent years, drones have been gradually introduced into the field of wind turbine blade inspection to replace traditional manual visual inspection methods.
[0003] Currently, when using drones to inspect wind turbine blades, the linear velocities at different radial positions of the blades vary greatly due to their rotation. The linear velocity at the blade tip can reach a high level, while the linear velocity at the blade root is relatively low. Existing drone inspection solutions do not consider this difference in linear velocity distribution and use a uniform fixed flight strategy to photograph the entire blade, which makes the acquired images prone to motion blur.
[0004] Therefore, how to achieve zoned data collection based on the differences in the linear velocity distribution of wind turbine blades, and how to dynamically adjust the flight path of the UAV based on the data collection quality to improve data collection efficiency, has become a key issue that urgently needs to be addressed. Summary of the Invention
[0005] This invention provides a data processing method and system for wind farm monitoring data, which can achieve zoned data collection based on the differences in the linear velocity distribution of wind turbine blades, and dynamically adjust the flight path of the UAV according to the collection quality to improve the collection efficiency.
[0006] A first aspect of the present invention provides a data processing method for wind farm monitoring data, comprising: The positioning acquisition area collected by the positioning drone is divided based on the linear velocity distribution of the wind turbine blades, resulting in multiple tracking acquisition areas; To configure a corresponding tracking and acquisition area as the target acquisition area for the follower drone, control the follower drone within the target acquisition area to acquire images of the wind turbine blades within the target acquisition area based on preset tracking flight parameters. When the clarity of the acquired blade image meets the preset clarity, the real-time position of the following drone is retrieved, and the subsequent flight path of the following drone is dynamically updated based on the real-time position.
[0007] Optionally, in one possible implementation of the first aspect, the positioning acquisition area collected by the positioning drone is divided based on the linear velocity distribution of the wind turbine blades to obtain multiple tracking acquisition areas, including: The linear velocity of the wind turbine blade at different radial positions is obtained by multiplying the rotational angular velocity of the wind turbine blade by the length at different radial positions. The wind turbine blades are divided according to the linear velocity to obtain a height division sequence; The real-time data collection area collected by the positioning drone is segmented to obtain the positioning data collection area; The positioning acquisition area is divided sequentially based on the height division sequence to obtain multiple tracking acquisition areas.
[0008] Optionally, in one possible implementation of the first aspect, dividing the wind turbine blades according to the linear velocity to obtain a height division sequence includes: Retrieve the preset high and medium partitioning speeds; On the wind turbine blades, the radial position corresponding to the high speed is selected as the high speed position, and the radial position corresponding to the medium speed is selected as the medium speed position. The high-speed length from the high-speed position to the tip of the wind turbine blade, the medium-speed length from the medium-speed position to the high-speed position, and the low-speed length from the medium-speed position to the root of the wind turbine blade are obtained. The low-speed length, medium-speed length, and high-speed length are sorted sequentially to obtain the height division sequence.
[0009] Optionally, in one possible implementation of the first aspect, the step of segmenting and dividing the real-time acquisition area collected by the positioning drone to obtain a positioning acquisition area includes: Obtain the real-time data collection area from the positioning drone; Based on the extreme coordinate values of the wind turbine blades in the real-time acquisition area, the real-time acquisition area is cropped to obtain the blade acquisition area. The blade acquisition area is divided according to any centerline axis of symmetry in the blade acquisition area to obtain the positioning acquisition area.
[0010] Optionally, in one possible implementation of the first aspect, the positioning acquisition area is sequentially divided based on the height division sequence to obtain multiple tracking acquisition areas, including: The boundary line of the area in contact with the leaf root in the positioning and acquisition area is used as the dividing reference line, and the boundary line of the area parallel to the dividing reference line is used as the dividing termination line. Construct a directional positioning line perpendicular to the dividing baseline, and take the direction along the directional positioning line from the dividing baseline to the dividing termination line as the dividing direction; Using the dividing baseline as a reference, the positioning acquisition area is divided by extracting the length of the height division sequence according to the dividing direction, resulting in multiple tracking acquisition areas.
[0011] Optionally, in one possible implementation of the first aspect, dynamically updating the subsequent flight path of the following drone based on the real-time location includes: Obtain the starting position of the drone within the target collection area, and obtain the first distance between the starting position and the real-time position; When the first distance is determined to be less than or equal to a preset update threshold, preset cross-regional flight parameters are configured for the following drone; The cross-regional flight parameters and the tracking flight parameters are combined to obtain a composite movement path; The control drone continuously collects data on the corresponding wind turbine blades based on a composite movement path until the cutoff condition is reached, at which point the data collection stops.
[0012] Optionally, in one possible implementation of the first aspect, the controlled follower drone continuously collects data on the corresponding wind turbine blades based on a composite movement path until a cutoff condition is reached, at which point the current data collection stops, including: The controlled drone continuously collects images of the wind turbine blades based on a composite movement path to obtain extended images; If the acquisition resolution of the extended image is determined to be lower than the preset resolution and / or the real-time position of the following drone is not within the target acquisition area, the cutoff condition is determined to have been reached, and the following drone is controlled to stop the acquisition.
[0013] Optionally, in one possible implementation of the first aspect, it also includes: When the first distance is determined to be greater than the preset update threshold, the following drone is controlled to stop the current collection within the target collection area.
[0014] Optionally, in one possible implementation of the first aspect, it also includes: Store leaf images and extended images that meet the preset resolution; Update the next tracking and acquisition area of the following drone to the target acquisition area.
[0015] A second aspect of the present invention provides a data processing system for wind farm monitoring data, comprising: The segmentation module is used to divide the positioning acquisition area collected by the positioning drone based on the linear velocity distribution of the wind turbine blades, resulting in multiple tracking acquisition areas; The control module is used to configure a corresponding tracking acquisition area as the target acquisition area for the follower drone, and control the follower drone to acquire images of the wind turbine blades in the target acquisition area based on preset tracking flight parameters. The adjustment module is used to determine that when the clarity of the captured image of the blade meets the preset clarity, retrieve the corresponding real-time position of the following drone, and dynamically update the subsequent flight path of the following drone based on the real-time position.
[0016] The beneficial effects of this invention are as follows: 1. This invention obtains the linear velocity of the wind turbine blades at different radial positions by multiplying the rotational angular velocity of the blades by the length at different radial positions. Based on this linear velocity, the wind turbine blades are divided into height division sequences, and the positioning acquisition area is then sequentially divided into multiple tracking acquisition areas based on these height division sequences. This invention, based on linear velocity gradient-based region division, provides a matching standard for determining the flight parameters of the following drone, allowing multiple speed levels to be assigned to the drone. When the following drone enters a certain tracking acquisition area, the corresponding flight speed of that area can be extracted, thereby reducing the relative speed with the wind turbine blades and avoiding image blurring caused by differences in the blade rotational linear velocity.
[0017] 2. This invention retrieves the real-time position of the following drone when the image sharpness of the blade meets a preset sharpness threshold. It then obtains a first distance between the starting position and the real-time position. If this first distance is less than or equal to a preset update threshold, preset cross-regional flight parameters are configured for the following drone. These parameters are combined with the tracking flight parameters to obtain a composite movement path. The following drone is then controlled to continuously collect images of the wind turbine blades based on this composite movement path. This invention first acquires blade images and determines the image sharpness, then dynamically plans the subsequent flight path of the following drone based on the sharpness and real-time position, achieving adaptive dynamic updating of the image acquisition plan.
[0018] 3. When the first distance is determined to be less than or equal to a preset update threshold, this invention controls the following drone to continuously acquire extended images of the wind turbine blades based on a composite movement path. This invention uses a composite movement path to allow the following drone to extend from the current target acquisition area to adjacent tracking acquisition areas during a single tracking process, simultaneously acquiring images of multiple tracking acquisition areas in a single flight. This reduces the number of times the following drone switches back and forth between tracking acquisition areas, shortening the total time required to acquire images of the entire surface of the wind turbine blades. Attached Figure Description
[0019] Figure 1 A flowchart of a data processing method for wind farm monitoring data provided by the present invention; Figure 2 This is a schematic diagram of the positioning and acquisition area in this invention; Figure 3 This is a schematic diagram of the structure of the tracking and acquisition area in this invention; Figure 4This is a structural diagram of the starting position and real-time position in this invention; Figure 5 This is a schematic diagram of the structure of a data processing system for wind farm monitoring data provided by the present invention; Figure 6 This is a schematic diagram of the hardware structure of an electronic device provided by the present invention. Detailed Implementation
[0020] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0021] The terms "first," "second," "third," "fourth," etc. (if present) in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein.
[0022] It should be understood that in the various embodiments of the present invention, the sequence number of each process does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.
[0023] It should be understood that in this invention, "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion, for example, a process, method, system, product, or device that includes a series of steps or units is not necessarily limited to those steps or units that are explicitly listed, but may include other steps or units that are not explicitly listed or that are inherent to such process, method, product, or device.
[0024] It should be understood that in this invention, "multiple" refers to two or more. "And / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "Contains A, B, and C", "Contains A, B, and C" means that all three A, B, and C are contained; "Contains A, B, or C" means that one of A, B, and C is contained; "Contains A, B, and / or C" means that any one, two, or three of A, B, and C are contained.
[0025] It should be understood that in this invention, "B corresponding to A", "B corresponding to A", "A and B correspond", or "B and A correspond" means that B is associated with A, and B can be determined based on A. Determining B based on A does not mean determining B solely based on A; B can also be determined based on A and / or other information. Matching A and B is defined as a similarity between A and B that is greater than or equal to a preset threshold.
[0026] Depending on the context, "if" as used here can be interpreted as "when," "when," "in response to determination," or "in response to detection."
[0027] The technical solution of the present invention will be described in detail below with reference to specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments.
[0028] This invention provides a data processing method for wind farm monitoring data, such as... Figure 1 As shown, it includes: S1. Based on the linear velocity distribution of the wind turbine blades, the positioning acquisition area collected by the positioning drone is divided into multiple tracking acquisition areas.
[0029] It should be noted that wind turbine blades are typically tens of meters long, and the distance between different radial positions on the blade and the center of rotation varies. At the same rotational angular velocity, the linear velocities at different radial positions differ significantly; the linear velocity is higher closer to the blade tip and lower closer to the blade root. This step uses a positioning drone to acquire the corresponding blade acquisition area and divides this area based on the blade's linear velocity, resulting in multiple tracking acquisition areas.
[0030] Among them, the positioning drone refers to a drone that hovers at a long distance to collect images of wind turbines and obtain the range of movement of the wind turbine blades; the tracking acquisition area refers to a strip-shaped area obtained by dividing the positioning acquisition area based on the blade linear velocity distribution.
[0031] In some embodiments, step S1 (dividing the positioning acquisition area collected by the positioning drone based on the linear velocity distribution of the wind turbine blades to obtain multiple tracking acquisition areas) includes S11-S14: S11, based on the product of the rotational angular velocity of the wind turbine blade and the length at different radial positions, the linear velocity of the wind turbine blade at different radial positions is obtained.
[0032] It should be noted that when a wind turbine blade undergoes circular motion, the linear velocity at each radial position on the blade is equal to the rotational angular velocity multiplied by the radial distance from that position to the center of rotation. The blade tip is furthest from the center of rotation and has the highest linear velocity; the blade root is closest to the center of rotation and has the lowest linear velocity.
[0033] Understandably, the current angular velocity of the wind turbine blades is retrieved, multiple radial positions are selected along the radial direction of the blades, and the distance from each radial position to the center of rotation is multiplied by the angular velocity to obtain the linear velocity corresponding to that radial position. Since the three wind turbine blades are of the same length and rotate around the same center, the linear velocity distribution at each radial position applies to all three wind turbine blades.
[0034] Among them, rotational angular velocity refers to the angular velocity of the wind turbine blades when they rotate; radial position refers to the point on the wind turbine blades. Different radial positions are at different distances from the center of rotation, and the farther away from the center of rotation, the higher the linear velocity.
[0035] S12, the wind turbine blades are divided according to the linear velocity to obtain a height division sequence.
[0036] It should be noted that the linear velocity of the wind turbine blades increases from the blade root to the blade tip, and the difference in linear velocity at different locations affects the relative motion speed when following the drone to collect images. This step divides the wind turbine blades into different segments by setting a velocity threshold, forming a height segmentation sequence.
[0037] In some embodiments, step S12 (dividing the wind turbine blades according to the linear velocity to obtain a height division sequence) includes S121-S124: S121, retrieve the preset high and medium division speeds.
[0038] Understandably, two pre-set speed thresholds are retrieved, namely the high division speed and the medium division speed.
[0039] Among them, the high division speed refers to the preset linear velocity threshold used to define the lower limit of the high-speed section; the medium division speed refers to the preset linear velocity threshold used to define the lower limit of the medium-speed section.
[0040] S122, select the radial position on the wind turbine blade corresponding to the high speed as the high speed position, and the radial position corresponding to the medium speed as the medium speed position.
[0041] It is understandable that, based on the linear velocity of each radial position calculated in step S11, the radial position with a linear velocity equal to the high division velocity is selected as the high-speed position, and the radial position with a linear velocity equal to the medium division velocity is selected as the medium-speed position.
[0042] S123, obtain the high-speed length from the high-speed position to the tip of the fan blade, the medium-speed length from the medium-speed position to the high-speed position, and the low-speed length from the medium-speed position to the root of the fan blade.
[0043] It is understandable that the high-speed length is obtained by calculating the distance from the high-speed position to the blade tip, the medium-speed length is obtained by calculating the distance from the medium-speed position to the high-speed position, and the low-speed length is obtained by calculating the distance from the medium-speed position to the blade root.
[0044] Among them, high-speed length refers to the blade length from the high-speed position to the blade tip; medium-speed length refers to the blade length from the medium-speed position to the high-speed position; and low-speed length refers to the blade length from the medium-speed position to the blade root.
[0045] S124, sort the low-speed length, medium-speed length and high-speed length in sequence to obtain the height division sequence.
[0046] It is understandable that the lengths are arranged in the order of low speed, medium speed, and high speed to form a height division sequence. The low speed length is placed at the beginning of the sequence because when dividing the positioning and acquisition area laterally, the leaf root is used as the starting position, and the division proceeds sequentially from the leaf root to the leaf tip. The low speed length corresponds to the area near the leaf root, and placing it at the beginning of the sequence facilitates extraction starting from the leaf root.
[0047] Among them, the height division sequence refers to the sequence formed by arranging the lengths in the order of low speed, medium speed, and high speed.
[0048] S13, the real-time acquisition area collected by the positioning drone is segmented and divided to obtain the positioning acquisition area.
[0049] It should be noted that the real-time data collection area of the positioning drone has a large coverage area, including the surrounding sky background and other content. The three wind turbine blades rotate around the same center, forming an active range. This step extracts a rectangular area surrounding the active range of the three wind turbine blades from the real-time data collection area and divides it along any midline axis of symmetry to obtain the positioning data collection area.
[0050] In some embodiments, step S13 (intercepting and dividing the real-time acquisition area collected by the positioning drone to obtain the positioning acquisition area) includes S131-S133: S131, Obtain the real-time collection area collected by the positioning drone.
[0051] Understandably, the positioning drone hovers in a position far from the wind turbine, continuously acquiring real-time images of the wind turbine through its onboard camera, obtaining the real-time acquisition area view at the current moment, and the real-time acquisition area view covers the entire blade movement range of the wind turbine.
[0052] The real-time acquisition area refers to the complete image area of the wind turbine captured by the positioning drone.
[0053] S132, Based on the extreme coordinate values of the wind turbine blades in the real-time acquisition area, the real-time acquisition area is cropped to obtain the blade acquisition area.
[0054] Understandably, the process involves identifying the extreme coordinate values of the wind turbine blades within the real-time acquisition area. Based on these extreme coordinate values, a rectangular region enclosing the movement range of the three wind turbine blades is extracted; this is the blade acquisition area.
[0055] Among them, the coordinate extreme value refers to the boundary coordinate of the wind turbine blade's range of motion in the real-time acquisition area; the blade acquisition area refers to the rectangular area that surrounds the wind turbine blade's range of motion, extracted from the real-time acquisition area based on the coordinate extreme value.
[0056] S133, the blade acquisition area is divided according to any centerline symmetry axis in the blade acquisition area to obtain the positioning acquisition area.
[0057] It is understandable that, such as Figure 2 As shown, the blade acquisition area, as a rectangular region, has two midline axes of symmetry, one vertical and one horizontal. The blade acquisition area is divided into two symmetrical sub-regions along either midline axis of symmetry, and one of these sub-regions is selected as the positioning acquisition area. In a preferred embodiment, the blade acquisition area is divided into an upper and lower half along a horizontal midline axis of symmetry, with the upper half selected as the positioning acquisition area. This results in the subsequent tracking acquisition areas being horizontal strips, allowing the drone to fly and collect data horizontally within each tracking acquisition area.
[0058] The positioning acquisition area refers to the rectangular area obtained by dividing the blade acquisition area along any centerline axis of symmetry. The centerline axis of symmetry is the straight line passing through the midpoint of the opposite side in the blade acquisition area.
[0059] S14, the positioning acquisition area is divided sequentially based on the height division sequence to obtain multiple tracking acquisition areas.
[0060] In some embodiments, step S14 (dividing the positioning acquisition area sequentially based on the height division sequence to obtain multiple tracking acquisition areas) includes S141-S143: S141, obtain the boundary line of the area in contact with the leaf root in the positioning acquisition area as the dividing reference line, and take the boundary line of the area parallel to the dividing reference line as the dividing termination line.
[0061] Understandably, the boundary line of the area in contact with the leaf root within the positioning and acquisition zone is used as the dividing baseline, and the boundary line of the area at the leaf tip within the positioning and acquisition zone, parallel to the dividing baseline, is used as the dividing termination line. For example, when the upper half of the leaf acquisition zone is selected as the positioning and acquisition zone, the dividing baseline is the lower boundary line of the positioning and acquisition zone, and the dividing termination line is the upper boundary line of the positioning and acquisition zone.
[0062] S142, construct a directional positioning line perpendicular to the dividing baseline, and take the direction along the directional positioning line from the dividing baseline to the dividing termination line as the dividing direction.
[0063] Understandably, an auxiliary line perpendicular to the dividing baseline is constructed within the positioning and acquisition area as a directional positioning line. The direction along the directional positioning line from the dividing baseline to the dividing termination line is the direction from the leaf root to the leaf tip, and this is used as the dividing direction. For example, when the upper half of the leaf acquisition area is selected as the positioning and acquisition area, the dividing direction is from bottom to top.
[0064] Among them, the direction positioning line refers to the auxiliary line perpendicular to the dividing baseline, which is used to determine the dividing direction; the dividing direction refers to the direction along the direction positioning line from the dividing baseline to the dividing termination line, that is, the direction from the leaf root to the leaf tip.
[0065] S143, using the dividing baseline as a reference, the positioning acquisition area is divided by extracting the length of the height division sequence according to the dividing direction, resulting in multiple tracking acquisition areas.
[0066] It is understandable that, such as Figure 3 As shown, using the dividing baseline as the starting point, the positioning acquisition area is divided by sequentially extracting the length values from the height division sequence along the division direction. Since the lengths in the height division sequence are arranged in the order of low-speed length, medium-speed length, and high-speed length, when dividing from the leaf root, the low-speed length is extracted first, and the first dividing line is formed at the position where the dividing baseline reaches the low-speed length along the division direction. The area between the dividing baseline and the first dividing line is the tracking acquisition area for the low-speed segment near the leaf root. Next, the medium-speed length is extracted, and the second dividing line is formed at the position where the first dividing line reaches the medium-speed length along the division direction. The area between the two dividing lines is the tracking acquisition area for the corresponding medium-speed segment. Finally, the area between the second dividing line and the division termination line is the tracking acquisition area for the high-speed segment near the leaf tip. For example, when the upper half of the blade sampling area is selected as the positioning sampling area, the resulting multiple tracking sampling areas are arranged in horizontal strips from bottom to top. The bottommost area is the tracking sampling area for the low-speed section near the blade root, the middle area is the tracking sampling area for the corresponding medium-speed section, and the topmost area is the tracking sampling area for the high-speed section near the blade tip. The tracking sampling areas are mapped onto the front of the wind turbine using coordinates, and the three wind turbine blades sweep across each tracking sampling area with each revolution during rotation.
[0067] It's worth noting that the division of the tracking and data collection area provides a matching standard for determining the flight parameters of the follower drone, allowing multiple speed levels to be assigned to it. When the follower drone enters a certain tracking and data collection area, the corresponding flight speed for that area can be extracted, thereby reducing the relative speed with the wind turbine blades.
[0068] Furthermore, the width of each tracking and acquisition zone is not the same, and it is divided according to the difference in linear velocity at different radial positions of the blade. The area near the blade tip with higher linear velocity is narrower, meaning it is less likely to have the opportunity to cross the zone downwards for shooting; while the area near the blade root with lower linear velocity is wider, making it more likely to have the opportunity to cross the zone downwards for shooting. This invention achieves graded shooting difficulty through the division of tracking and acquisition zones.
[0069] S2, Configure a corresponding tracking and acquisition area for the follower drone as the target acquisition area, and control the follower drone to acquire images of the wind turbine blades in the target acquisition area based on preset tracking flight parameters.
[0070] It should be noted that after dividing the tracking and acquisition area, the follower drone needs to enter the tracking and acquisition area to perform the acquisition task. One tracking and acquisition area is selected and assigned to the follower drone as the target acquisition area. The follower drone flies within the target acquisition area with preset tracking flight parameters, tracking and capturing images as the wind turbine blades rotate and sweep across the area. The flight direction of the follower drone is consistent with the movement direction of the wind turbine blades as they pass through the area. Motion blur is reduced by decreasing the relative speed between the follower drone and the wind turbine blades. Different tracking and acquisition areas correspond to different wind turbine blade linear velocities, and the preset tracking flight parameters for each area are also different. The tracking and acquisition area near the blade tip corresponds to the highest wind turbine blade linear velocity, and its flight speed in the tracking flight parameters is set to the highest value. The tracking and acquisition areas in the middle are next, and the tracking and acquisition area near the blade root corresponds to the lowest wind turbine blade linear velocity, and its flight speed in the tracking flight parameters is set to the lowest value.
[0071] Understandably, one tracking acquisition area is selected from multiple tracking acquisition areas and assigned to the follower drone as the target acquisition area. Generally, the acquisition can begin with the tracking acquisition area near the blade tip, then switch to the middle tracking acquisition area, and finally acquire the tracking acquisition area near the blade root. During acquisition, preset tracking flight parameters matching the target acquisition area are configured for the follower drone. These preset tracking flight parameters include the flight direction and speed corresponding to that tracking acquisition area. After entering the target acquisition area, the follower drone cyclically flies back and forth within the target acquisition area according to the tracking flight parameters. Wind turbines typically have three blades. As the three blades rotate, they sequentially sweep across the target acquisition area. While flying within the target acquisition area, the follower drone photographs the corresponding portion of each passing blade, continuously cyclically acquiring images until all three blades within the tracking acquisition area have been acquired, thus obtaining blade images.
[0072] Here, "following drone" refers to the drone responsible for tracking and photographing wind turbine blades within the tracking and acquisition area; "target acquisition area" refers to the tracking and acquisition area currently assigned to the following drone for acquisition tasks; "tracking flight parameters" refers to the pre-configured motion parameters that control the following drone's flight within the target acquisition area, including flight direction and flight speed. The tracking flight parameters corresponding to each tracking and acquisition area are configured differently based on the linear velocity of the wind turbine blades in that area; and "blade image" refers to the image obtained by the following drone photographing and acquiring wind turbine blades within the target acquisition area.
[0073] It is worth mentioning that when the leaf image collected by the follower drone after completing a tracking flight in the target collection area does not meet the preset clarity, the follower drone returns to the starting position in the target collection area and re-collects according to the tracking flight parameters until a leaf image that meets the preset clarity is collected.
[0074] S3, when it is determined that the clarity of the acquired blade image meets the preset clarity, retrieve the corresponding real-time position of the following drone, and dynamically update the subsequent flight path of the following drone based on the real-time position.
[0075] It should be noted that, unlike existing technologies that plan the flight path before executing the data acquisition task, this invention first acquires images of the wind turbine blades and determines the image clarity, then dynamically plans the subsequent flight path based on the image clarity result. When the follower drone tracks the target acquisition area, due to the difference between the rotational speed of the wind turbine blades and the flight speed of the follower drone, the follower drone may not be able to catch up with the wind turbine blades and capture clear images near its starting position. Different positions at which the follower drone catches up with the wind turbine blades indicate different remaining flight distances within the current target acquisition area. This step, after confirming that the blade images meet the clarity requirements, obtains the real-time position of the follower drone. The distance between the real-time position and the starting position determines whether to dynamically update the flight path. If the distance between the real-time position and the starting position is short, it indicates a longer remaining flight distance, allowing for cross-area flight while continuing tracking, covering a larger acquisition area. If the distance between the real-time position and the starting position is long, it indicates that the remaining flight distance is insufficient to support cross-area flight, so the current acquisition is stopped, and the process switches to the next tracking acquisition area.
[0076] Understandably, the clarity of the captured image of the blade is compared with the preset clarity. When it is determined that the captured clarity meets the preset clarity, the corresponding real-time position of the following drone is retrieved, and the subsequent flight path of the following drone is dynamically updated based on the real-time position.
[0077] Among them, the acquisition clarity refers to the clarity of the image; the preset clarity refers to the pre-configured clarity threshold used to determine whether the leaf image meets the acquisition requirements; and the real-time position refers to the spatial position of the following drone when the clarity requirements are met.
[0078] In some embodiments, step S3 (dynamically updating the subsequent flight path of the following drone based on the real-time location) includes S31-S34: S31, obtain the starting position of the drone in the target collection area, and obtain the first distance between the starting position and the real-time position.
[0079] It is understandable that, such as Figure 4 As shown, the starting position when the drone enters the target collection area is retrieved, and the real-time position obtained in step S3 is retrieved. The distance between the starting position and the real-time position is calculated as the first distance.
[0080] The starting position refers to the spatial position when following the drone into the target collection area; the first distance refers to the distance between the starting position and the real-time position.
[0081] S32, when it is determined that the first distance is less than or equal to a preset update threshold, preset cross-regional flight parameters are configured for the following drone.
[0082] It should be noted that when the first distance is less than or equal to the preset update threshold, it means that the follower drone has captured a leaf image that meets the clarity requirements in the target acquisition area, and the follower drone has a long remaining flight distance in the target acquisition area. At this time, the preset cross-area flight parameters are configured so that the follower drone can move to the adjacent tracking acquisition area at the same time in subsequent flights, and adjust its own flight speed accordingly when entering the adjacent tracking acquisition area.
[0083] Understandably, the first distance is compared with the preset update threshold. When the first distance is less than or equal to the preset update threshold, cross-regional flight parameters are retrieved from the preset parameter library, and the flight of the follower drone is controlled based on the cross-regional flight parameters.
[0084] Among them, the preset update threshold refers to the pre-set distance threshold, which is used to compare with the first distance to determine whether to update the subsequent flight path of the following drone; the cross-area flight parameters refer to the preset motion parameters that control the following drone to move from the current target collection area to the adjacent tracking collection area.
[0085] S33, combine the cross-regional flight parameters and the tracking flight parameters to obtain a composite movement path.
[0086] Understandably, the tracking flight parameter control keeps the drone within the target acquisition area, while the cross-area flight parameter control moves the drone along the defined direction from the current target acquisition area to the adjacent tracking acquisition area. These two sets of parameters are then superimposed to generate a composite movement path. When the drone flies along this composite movement path, its trajectory is tilted, continuing to track and photograph the wind turbine blades within the target acquisition area while gradually entering the range of the adjacent tracking acquisition area. In a single flight, it simultaneously covers the acquisition tasks of both the current target acquisition area and the adjacent tracking acquisition area.
[0087] Among them, the composite movement path refers to the flight trajectory generated by superimposing the tracking flight parameters and the cross-regional flight parameters.
[0088] S34 controls the follower drone to continuously collect data on the corresponding wind turbine blades based on a composite movement path until the cutoff condition is reached, at which point the data collection stops.
[0089] It should be noted that after the drone switches to a composite movement path, its collection range is no longer limited to the current target collection area, but extends to the adjacent tracking collection area. However, the collection stops when the deadline is reached.
[0090] In some embodiments, step S34 (controlling the following drone to continuously collect data on the corresponding wind turbine blades based on the composite movement path until the cutoff condition is reached, then stopping the current data collection) includes S341-S342: S341 controls the follow-up drone to continuously collect data on the wind turbine blades based on a composite movement path, thereby obtaining extended images.
[0091] Understandably, after obtaining the composite movement path, the drone is controlled based on the composite movement path to continuously collect data on the wind turbine blades, and the collected images are used as extended images.
[0092] Among them, extended images refer to images of wind turbine blades collected by following the drone along a complex movement path.
[0093] S342, when it is determined that the acquisition clarity of the extended image is lower than the preset clarity and / or the real-time position of the following drone is not in the target acquisition area, the cutoff condition is reached, and the following drone is controlled to stop the acquisition.
[0094] It should be noted that when following a drone along a complex moving path, the sharpness of the extended image may decrease, and the drone may also fly out of the boundary of the current target acquisition area. This step sets two cutoff conditions to control the termination of acquisition, preventing the drone from continuing to fly when the image quality is substandard or when it has exceeded the effective acquisition range.
[0095] Understandably, when the acquired image resolution is lower than the preset resolution, the cutoff condition is determined; similarly, when the real-time position of the following drone is not within the target acquisition area, the cutoff condition is also determined. If any one of these conditions, or both conditions, is met, the following drone is controlled to stop the current acquisition.
[0096] The cutoff condition refers to the criteria for determining when the drone stops collecting data.
[0097] In some embodiments, S35 is also included: S35, when it is determined that the first distance is greater than the preset update threshold, control the following drone to stop the current collection within the target collection area.
[0098] Understandably, when the first distance is greater than the preset update threshold, the remaining flight distance within the target collection area is short, so the drone will stop collecting data within the target collection area and will no longer update its flight path.
[0099] In some embodiments, S36-S37 are also included: S36, stores a blade image and an extended image that meet a preset resolution.
[0100] Understandably, after each acquisition, leaf images and extended images that meet the preset resolution will be stored.
[0101] S37, update the next tracking and acquisition area of the following drone to the target acquisition area.
[0102] Understandably, after storing images that meet the preset resolution, the next tracking acquisition area of the follower drone is updated to the target acquisition area, and the follower drone is controlled to enter the new target acquisition area to continue the acquisition task. The follower drone will continue to perform the acquisition task on the remaining unacquired tracking acquisition areas one by one until the acquisition task of all tracking acquisition areas is completed. The images acquired in each tracking acquisition area can be stitched together to form a complete image of the wind turbine blade, realizing the acquisition of the complete surface of the wind turbine blade.
[0103] See Figure 5 This is a schematic diagram of a data processing system for wind farm monitoring data provided in an embodiment of the present invention. The system includes: The segmentation module is used to divide the positioning acquisition area collected by the positioning drone based on the linear velocity distribution of the wind turbine blades, resulting in multiple tracking acquisition areas; The control module is used to configure a corresponding tracking acquisition area as the target acquisition area for the follower drone, and control the follower drone to acquire images of the wind turbine blades in the target acquisition area based on preset tracking flight parameters. The adjustment module is used to determine that when the clarity of the captured image of the blade meets the preset clarity, retrieve the corresponding real-time position of the following drone, and dynamically update the subsequent flight path of the following drone based on the real-time position.
[0104] See Figure 6 This is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present invention. The electronic device 60 includes: a processor 61, a memory 62, and a computer program; wherein... The memory 62 is used to store the computer program, and the memory may also be flash memory. The computer program is, for example, an application program or functional module that implements the above method.
[0105] The processor 61 is configured to execute the computer program stored in the memory to implement the various steps performed by the device in the above method. For details, please refer to the relevant descriptions in the preceding method embodiments.
[0106] Alternatively, the memory 62 can be either standalone or integrated with the processor 61.
[0107] When the memory 62 is a device independent of the processor 61, the device may further include: Bus 63 is used to connect the memory 62 and the processor 61.
[0108] The present invention also provides a readable storage medium storing a computer program, which, when executed by a processor, is used to implement the methods provided in the various embodiments described above.
[0109] The readable storage medium can be a computer storage medium or a communication medium. A communication medium includes any medium that facilitates the transfer of computer programs from one location to another. A computer storage medium can be any available medium accessible to a general-purpose or special-purpose computer. For example, a readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application-Specific Integrated Circuit (ASIC). Alternatively, the ASIC can be located in a user equipment. Of course, the processor and the readable storage medium can also exist as discrete components in a communication device. The readable storage medium can be a read-only memory (ROM), random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc.
[0110] The present invention also provides a program product including executable instructions stored in a readable storage medium. At least one processor of the device can read the executable instructions from the readable storage medium, and the at least one processor executes the executable instructions to cause the device to implement the methods provided in the various embodiments described above.
[0111] In the embodiments of the above-described device, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly manifested as execution by a hardware processor, or execution by a combination of hardware and software modules within the processor.
[0112] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.
Claims
1. A data processing method for wind farm monitoring data, characterized in that, include: The positioning acquisition area collected by the positioning drone is divided based on the linear velocity distribution of the wind turbine blades, resulting in multiple tracking acquisition areas; To configure a corresponding tracking and acquisition area as the target acquisition area for the follower drone, control the follower drone within the target acquisition area to acquire images of the wind turbine blades within the target acquisition area based on preset tracking flight parameters. When the clarity of the acquired blade image meets the preset clarity, the real-time position of the following drone is retrieved, and the subsequent flight path of the following drone is dynamically updated based on the real-time position.
2. The method according to claim 1, characterized in that, The linear velocity distribution based on the wind turbine blades is used to divide the positioning acquisition area collected by the positioning drone, resulting in multiple tracking acquisition areas, including: The linear velocity of the wind turbine blade at different radial positions is obtained by multiplying the rotational angular velocity of the wind turbine blade by the length at different radial positions. The wind turbine blades are divided according to the linear velocity to obtain a height division sequence; The real-time data collection area collected by the positioning drone is segmented to obtain the positioning data collection area; The positioning acquisition area is divided sequentially based on the height division sequence to obtain multiple tracking acquisition areas.
3. The method according to claim 2, characterized in that, The step of dividing the wind turbine blades according to the linear velocity to obtain a height division sequence includes: Retrieve the preset high and medium partitioning speeds; On the wind turbine blades, the radial position corresponding to the high speed is selected as the high speed position, and the radial position corresponding to the medium speed is selected as the medium speed position. The high-speed length from the high-speed position to the tip of the wind turbine blade, the medium-speed length from the medium-speed position to the high-speed position, and the low-speed length from the medium-speed position to the root of the wind turbine blade are obtained. The low-speed length, medium-speed length, and high-speed length are sorted sequentially to obtain the height division sequence.
4. The method according to claim 2, characterized in that, The real-time acquisition area collected by the positioning drone is segmented and divided to obtain the positioning acquisition area, including: Obtain the real-time data collection area from the positioning drone; Based on the extreme coordinate values of the wind turbine blades in the real-time acquisition area, the real-time acquisition area is cropped to obtain the blade acquisition area. The blade acquisition area is divided according to any centerline axis of symmetry in the blade acquisition area to obtain the positioning acquisition area.
5. The method according to claim 3, characterized in that, The positioning acquisition area is sequentially divided based on the height division sequence to obtain multiple tracking acquisition areas, including: The boundary line of the area in contact with the leaf root in the positioning and acquisition area is used as the dividing reference line, and the boundary line of the area parallel to the dividing reference line is used as the dividing termination line. Construct a directional positioning line perpendicular to the dividing baseline, and take the direction along the directional positioning line from the dividing baseline to the dividing termination line as the dividing direction; Using the dividing baseline as a reference, the positioning acquisition area is divided by extracting the length of the height division sequence according to the dividing direction, resulting in multiple tracking acquisition areas.
6. The method according to claim 1, characterized in that, The step of dynamically updating the subsequent flight path of the following drone based on the real-time location includes: Obtain the starting position of the drone within the target collection area, and obtain the first distance between the starting position and the real-time position; When the first distance is determined to be less than or equal to a preset update threshold, preset cross-regional flight parameters are configured for the following drone; The cross-regional flight parameters and the tracking flight parameters are combined to obtain a composite movement path; The control drone continuously collects data on the corresponding wind turbine blades based on a composite movement path until the cutoff condition is reached, at which point the data collection stops.
7. The method according to claim 6, characterized in that, The controlled follow-up drone continuously collects data on the corresponding wind turbine blades based on a composite movement path until a cutoff condition is reached, at which point the data collection stops, including: The controlled drone continuously collects images of the wind turbine blades based on a composite movement path to obtain extended images; If the acquisition resolution of the extended image is determined to be lower than the preset resolution and / or the real-time position of the following drone is not within the target acquisition area, the cutoff condition is determined to have been reached, and the following drone is controlled to stop the acquisition.
8. The method according to claim 6, characterized in that, Also includes: When the first distance is determined to be greater than the preset update threshold, the following drone is controlled to stop the current collection within the target collection area.
9. The method according to claim 7, characterized in that, Also includes: Store leaf images and extended images that meet the preset resolution; Update the next tracking and acquisition area of the following drone to the target acquisition area.
10. A data processing system for wind farm monitoring data, characterized in that, include: The segmentation module is used to divide the positioning acquisition area collected by the positioning drone based on the linear velocity distribution of the wind turbine blades, resulting in multiple tracking acquisition areas; The control module is used to configure a corresponding tracking acquisition area as the target acquisition area for the follower drone, and control the follower drone to acquire images of the wind turbine blades in the target acquisition area based on preset tracking flight parameters. The adjustment module is used to determine that when the clarity of the captured image of the blade meets the preset clarity, retrieve the corresponding real-time position of the following drone, and dynamically update the subsequent flight path of the following drone based on the real-time position.