A fan non-stop inspection method, device, equipment and storage medium

Abstract

This invention discloses a method, apparatus, equipment, and storage medium for non-stop wind turbine inspection, relating to the field of wind turbine inspection technology. The method includes: acquiring point cloud data of the wind turbine to be inspected and determining the covariance matrix of the blade point cloud in the point cloud data; determining the eigenvalues ​​and corresponding eigenvectors of the covariance matrix, and determining the rotation axis direction of the wind turbine to be inspected based on the eigenvalues ​​and eigenvectors; determining the yaw angle of the wind turbine to be inspected based on the rotation axis direction, and determining the blade azimuth angle of the wind turbine to be inspected based on the point cloud data; and determining the UAV inspection route of the wind turbine to be inspected based on the yaw angle and blade azimuth angle at different times. The technical solution of this invention achieves non-stop, adaptive, and highly secure intelligent wind turbine inspection.

Description

Technical Field

[0001] This invention relates to the field of wind turbine inspection technology, and in particular to a method, apparatus, equipment and storage medium for wind turbine inspection without shutting down. Background Technology

[0002] Wind turbine generators are the core assets of wind farms, and their safe and stable operation directly affects the power generation efficiency of the entire farm. As a critical component of the unit, wind turbine blades are constantly exposed to harsh environments such as strong winds, salt spray, lightning strikes, and icing, making them highly susceptible to damage such as cracks and corrosion. Therefore, regular and efficient inspections of the blades to promptly detect and address defects are crucial for preventing catastrophic accidents such as blade breakage and turbine collapse, and for ensuring power generation.

[0003] The introduction of drone technology has brought new possibilities to inspection work, but current common drone inspection methods usually require wind turbines to be shut down. Furthermore, due to fixed flight paths and a lack of flexibility, they cannot adapt to the real-time position of the blades, potentially creating blind spots and resulting in a lengthy process and consequently, power generation losses. Summary of the Invention

[0004] This invention provides a method, apparatus, equipment, and storage medium for non-stop wind turbine inspection, in order to solve the problem of inadequate wind turbine inspection methods.

[0005] In a first aspect, the present invention provides a method for continuous inspection of a wind turbine, comprising: Acquire point cloud data of the wind turbine to be inspected, and determine the covariance matrix of the blade point cloud in the point cloud data; Determine the eigenvalues ​​and corresponding eigenvectors of the covariance matrix, and determine the rotation axis direction of the wind turbine to be inspected based on the eigenvalues ​​and eigenvectors. The yaw angle of the wind turbine to be inspected is determined based on the direction of the rotation axis, and the blade azimuth angle of the wind turbine to be inspected is determined based on the point cloud data. The drone inspection route for the wind turbine to be inspected is determined based on the yaw angle and blade azimuth angle at different times.

[0006] Secondly, the present invention provides a wind turbine non-stop inspection device, comprising: The calculation module is used to acquire point cloud data of the wind turbine to be inspected and determine the covariance matrix of the blade point cloud in the point cloud data. The direction determination module is used to determine the eigenvalues ​​and corresponding eigenvectors of the covariance matrix, and to determine the rotation axis direction of the fan to be inspected based on the eigenvalues ​​and eigenvectors. An angle determination module is used to determine the yaw angle of the wind turbine to be inspected based on the direction of the rotation axis, and to determine the blade azimuth angle of the wind turbine to be inspected based on the point cloud data. The cruise route determination module is used to determine the UAV inspection route of the wind turbine to be inspected based on the yaw angle and the blade azimuth angle at different times.

[0007] Thirdly, the present invention provides an electronic device comprising: At least one processor; and memory that is communicatively connected to at least one processor; The memory stores a computer program that can be executed by at least one processor, which enables the at least one processor to perform the wind turbine non-stop inspection method described in the first aspect.

[0008] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions that, when executed by a processor, implement the wind turbine non-stop inspection method of the first aspect described above.

[0009] The wind turbine non-stop inspection solution provided by this invention accurately extracts the wind turbine's rotation axis (yaw direction) and blade instantaneous azimuth angle based on real-time acquired point cloud data. By incorporating these dynamic parameters into the flight path planning algorithm, the UAV can adjust its shooting posture to closely follow the wind turbine's real-time attitude, ensuring that each shot is aimed at the key parts of the blades, achieving full-angle coverage, effectively avoiding blind spots, and automatically planning inspection routes while the wind turbine is generating electricity normally. This enables non-stop, adaptive, and highly safe intelligent wind turbine inspection.

[0010] It should be understood that the description in this section is not intended to identify key or essential features of the invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1 This is a flowchart of a method for continuous inspection of a fan according to Embodiment 1 of the present invention; Figure 2 This is a schematic diagram of a wind turbine point cloud according to Embodiment 1 of the present invention; Figure 3 This is a flowchart of a method for continuous inspection of a fan according to Embodiment 2 of the present invention; Figure 4 This is a schematic diagram of target point distribution provided in Embodiment 2 of the present invention; Figure 5 This is a schematic diagram of an initial inspection route for a drone according to Embodiment 2 of the present invention; Figure 6 This is a schematic diagram of a fan inspection device that operates without shutting down, according to Embodiment 3 of the present invention. Figure 7 This is a schematic diagram of the structure of an electronic device provided according to Embodiment 4 of the present invention. Detailed Implementation

[0013] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. 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 should fall within the scope of protection of the present invention.

[0014] It should be noted that the terms "first," "second," etc., 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 the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. In the description of this invention, unless otherwise stated, "a plurality of" means two or more. "And / or" describes 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, and B alone. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. Furthermore, the terms "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 explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices.

[0015] Example 1 Figure 1This is a flowchart of a wind turbine non-stop inspection method provided in Embodiment 1 of the present invention. This embodiment can be applied to the inspection of wind turbines in operation. The method can be executed by a wind turbine non-stop inspection device, which can be implemented in hardware and / or software. The wind turbine non-stop inspection device can be configured in an electronic device, which can be composed of two or more physical entities or a single physical entity.

[0016] like Figure 1 As shown in Embodiment 1 of the present invention, a method for continuous inspection of a wind turbine includes the following steps: S101. Obtain the point cloud data of the wind turbine to be inspected, and determine the covariance matrix of the blade point cloud in the point cloud data.

[0017] In this embodiment, the dimensional information of the wind turbine to be inspected can be obtained in advance, including: the wind turbine's latitude and longitude, altitude, nacelle elevation (the height of the center of the nacelle at the top of the wind turbine from the ground), blade length, and tower diameter. Then, based on this dimensional information, a drone carrying airborne radar is controlled to automatically generate a flight path to the top of the wind turbine and scan the turbine in real time to obtain point cloud data of the wind turbine to be inspected. The blade point cloud can be determined from the dimensional information, and then principal component analysis (PCA) can be performed on the blade point cloud to obtain its covariance matrix.

[0018] S102. Determine the eigenvalues ​​and corresponding eigenvectors of the covariance matrix, and determine the rotation axis direction of the fan to be inspected based on the eigenvalues ​​and eigenvectors.

[0019] In this embodiment, the covariance matrix can be eigenvalued by eigenvalue decomposition to obtain multiple eigenvalues ​​and corresponding eigenvectors. A target value is selected from the eigenvalues, and the eigenvector corresponding to the target value is the direction vector of the rotation axis of the wind turbine to be inspected.

[0020] S103. Determine the yaw angle of the fan to be inspected based on the direction of the rotation axis, and determine the blade azimuth angle of the fan to be inspected based on the point cloud data.

[0021] In this embodiment, the angle between the direction vector of the rotation axis and the unit direction vector is the yaw angle of the wind turbine to be inspected. By analyzing the point cloud data of the wind turbine to be inspected, the blade azimuth angle can be determined. The blade azimuth angle can be understood as the angle that the wind turbine blade rotates in the plane of rotation, starting from a fixed reference direction.

[0022] S104. Determine the UAV inspection route for the wind turbine to be inspected based on the yaw angle and blade azimuth angle at different times.

[0023] Specifically, the yaw rate can be obtained based on the yaw angle and the point cloud acquisition cycle. Based on the size information of the wind turbine to be inspected, the yaw rate, and the real-time blade azimuth angle, a drone inspection route can be planned. This drone inspection route should maintain a safe shooting distance to avoid collisions with the wind turbine's point cloud entities; for example, it can be set to 20 meters. The number of waypoints along the drone inspection route, as well as the drone's position and shooting point positions, can be determined based on the required number of photos to be taken. If the drone gets too close to the wind turbine, the shooting waypoints are dynamically adjusted, and the drone moves along the yaw direction of the wind turbine nacelle to a safe area. Assuming the drone starts from the shooting route above, the closest distance to the point cloud entities is calculated. When it is less than a preset distance threshold, it indicates that the drone blade is currently passing in front of the drone, and the high-speed camera is immediately triggered to take a picture. After taking the picture, the drone moves to the next waypoint to complete the shooting. Due to the symmetry of the blades, the shooting route can be further simplified: three shots are taken at a fixed position each time the blade passes, and then the drone moves to the next preset point. This way, after completing two shooting routes, all three blades can be covered.

[0024] Through the above steps, drones can achieve one-click takeoff, one-click inspection, and one-click return, reducing reliance on manual inspections and experienced pilots. They can also safely, accurately, and efficiently complete the inspection of wind turbines in wind farms without losing power generation.

[0025] The technical solution of this invention, based on real-time acquired point cloud data, accurately extracts the rotation axis (yaw direction) and instantaneous azimuth angle of the wind turbine. By incorporating these dynamic parameters into the flight path planning algorithm, the UAV can adjust its shooting posture to closely follow the real-time attitude of the wind turbine, ensuring that each shot is aimed at the key parts of the blades, achieving full-angle coverage, effectively avoiding blind spots, and automatically planning inspection routes under normal wind turbine power generation conditions, realizing uninterrupted, adaptive, and highly safe intelligent wind turbine inspection.

[0026] Optionally, determining the blade azimuth angle of the wind turbine to be inspected based on the point cloud data includes: determining the blade tip from the blade point cloud in the point cloud data; determining the angle between the line connecting the centroid of the blade point cloud and the blade tip and a preset reference direction in the sweeping plane; and determining the minimum angle as the blade azimuth angle of the wind turbine to be inspected.

[0027] Specifically, by analyzing the blade point cloud data, the blade tip can be determined. Then, the line connecting the centroid of the blade point cloud to each blade tip is determined, and the angle between this line and a preset reference direction in the sweeping plane is determined. The smallest angle is the blade azimuth angle of the wind turbine to be inspected. These angles are fixed intervals, and these fixed angles are related to the number of blades.

[0028] Optionally, acquiring the point cloud data of the wind turbine to be inspected includes: acquiring the initial three-dimensional point cloud of the wind turbine to be inspected using a radar mounted on a UAV; removing background points from the initial three-dimensional point cloud to obtain the point cloud data of the wind turbine to be inspected.

[0029] Specifically, Figure 2 This is a schematic diagram of a wind turbine point cloud. Irrelevant background points can be removed from the initial 3D point cloud based on the size information of the wind turbine to be inspected, thus segmenting the point cloud data of the wind turbine to be inspected, resulting in a point cloud image of the wind turbine to be inspected, as shown below. Figure 2 As shown.

[0030] Example 2 Figure 3 This is a flowchart of a method for non-stop inspection of a wind turbine provided in Embodiment 2 of the present invention. The technical solution of the present invention is further optimized based on the above optional technical solutions, and provides a specific method for inspecting a wind turbine in operation.

[0031] Optionally, determining the blade tip from the blade point cloud in the point cloud data includes: projecting the blade point cloud in the point cloud data onto the yaw direction corresponding to the yaw angle to obtain a two-dimensional point cloud; dividing the two-dimensional point cloud into regions according to the number of blades of the wind turbine to be inspected to obtain multiple point cloud regions; for each point cloud region, determining the target point in each point cloud region that is farthest from the centroid of the two-dimensional point cloud, and determining the target point as the blade tip; wherein, determining the angle between the line connecting the centroid of the blade point cloud and the blade tip and a preset reference direction in the sweep plane includes: determining the angle between the line connecting the centroid of the two-dimensional point cloud and the blade tip and a preset reference direction in the sweep plane.

[0032] Optionally, determining the rotation axis direction of the fan to be inspected based on the eigenvalue and eigenvector includes: determining the direction corresponding to the eigenvector corresponding to the minimum eigenvalue as the rotation axis direction of the fan to be inspected.

[0033] Optionally, before determining the covariance matrix of the leaf point cloud in the point cloud data, the method further includes: determining the geometric center point of the leaf point cloud in the point cloud data; and performing centering processing on the leaf point cloud based on the geometric center point to obtain an updated centered point cloud; wherein, determining the covariance matrix of the leaf point cloud in the point cloud data includes: determining the covariance matrix of the centered point cloud.

[0034] like Figure 3 As shown in Embodiment 2 of the present invention, a method for continuous inspection of a wind turbine includes the following steps: S201. Acquire the initial three-dimensional point cloud of the wind turbine to be inspected using radar mounted on the UAV; remove background points from the initial three-dimensional point cloud to obtain point cloud data of the wind turbine to be inspected; determine the geometric center point of the blade point cloud in the point cloud data; and perform centering processing on the blade point cloud based on the geometric center point to obtain an updated centered point cloud.

[0035] Specifically, centering refers to subtracting the geometric center point from each point in the point cloud to obtain the final point.

[0036] S202. Determine the covariance matrix of the centered point cloud, and determine the eigenvalues ​​and corresponding eigenvectors of the covariance matrix.

[0037] S203. Determine the direction of the eigenvector corresponding to the minimum eigenvalue as the rotation axis direction of the fan to be inspected, and determine the yaw angle of the fan to be inspected based on the rotation axis direction.

[0038] Specifically, for point clouds of rotation, their geometric distribution has rotational symmetry, and this symmetry determines that there is a specific relationship between the variances of the point cloud in the three orthogonal directions.

[0039] When performing principal component analysis on a point cloud, the eigenvalues ​​and eigenvectors of the covariance matrix are calculated. The magnitude of the eigenvalues ​​reflects the variance of the point cloud along the direction of the eigenvector. Due to rotational symmetry, two orthogonal directions in a plane perpendicular to the rotation axis must have the same variance (denoted as λ'), while the direction along the rotation axis has another variance (denoted as λ”).

[0040] For slender bodies of revolution (such as long cylinders or needle-like bodies): the point cloud distribution range is large along the rotation axis, and λ” is relatively large; the direction perpendicular to the axis is limited by the radius, and λ’ is relatively small. In this case, the direction of rotation axis corresponds to the maximum variance.

[0041] For flat bodies of revolution (such as disks, coins, and short cylinders): the thickness along the axis of rotation is very small, and λ” is small; the distribution range in the direction perpendicular to the axis (within the plane of the disk) is large, and λ’ is large. In this case, the direction of rotation axis corresponds to the minimum variance.

[0042] Sphere: The variances in the three directions are equal, and any direction can be regarded as an axis of rotation.

[0043] For wind turbines, which are typically flat rotating bodies, the direction of the rotating axis direction can be determined by the direction of the eigenvector corresponding to the minimum eigenvalue, based on the geometric property that the point cloud of the rotating body has the minimum variance in the direction of the rotation axis.

[0044] For example, if the number of blades of the wind turbine to be inspected is 3, three characteristic values ​​can be obtained: λ1, λ2, and λ3, and the corresponding characteristic vectors are v1, v2, and v3. If λ3 is the smallest, then v3 is determined as the rotation axis direction vector.

[0045] S204. Project the blade point cloud in the point cloud data onto the yaw direction corresponding to the yaw angle to obtain a two-dimensional point cloud; divide the two-dimensional point cloud into regions according to the number of blades of the wind turbine to be inspected to obtain multiple point cloud regions; for each point cloud region, determine the target point farthest from the centroid of the two-dimensional point cloud in each point cloud region, and determine the target point as the blade tip.

[0046] Specifically, the number of point cloud regions = 360 / number of blades.

[0047] Furthermore, the step of dividing the two-dimensional point cloud into regions based on the number of blades of the wind turbine to be inspected to obtain multiple point cloud regions includes: if the number of blades of the wind turbine to be inspected is 3, then the two-dimensional point cloud is divided at 120-degree intervals to obtain 3 fan-shaped point cloud regions.

[0048] For example, Figure 4 This is a schematic diagram of the distribution of target points. Figure 4 The pentagram in the diagram represents the target point in each point cloud region that is furthest from the centroid of the two-dimensional point cloud.

[0049] S205. Determine the angle between the line connecting the centroid of the two-dimensional point cloud and the blade tip and the preset reference direction in the sweeping plane; determine the minimum angle as the blade azimuth angle of the fan to be inspected.

[0050] S206. Determine the UAV inspection route for the wind turbine to be inspected based on the yaw angle and blade azimuth angle at different times.

[0051] Specifically, Figure 5 This is a schematic diagram of the initial inspection route for a type of drone. (Example) Figure 5 As shown, based on the information of the wind turbine to be inspected and the blade tip, an initial inspection route can be determined. A line is drawn connecting the nacelle center and the blade tip, and several shooting points are selected from this line. Each blade can have two inspection routes: one for the windward side and one for the leeward side. The initial inspection route is then adjusted according to the yaw angle and blade azimuth angle at different times to obtain the UAV inspection route for the wind turbine to be inspected. The UAV performs shooting tasks one by one along the predetermined route, and a high-speed camera captures high-definition inspection photos. Throughout the process, a safe distance is checked in real time. If a potential hazard is detected, the UAV's attitude is immediately adjusted to ensure operational safety. This solution effectively reduces reliance on manpower and significantly improves the safety and accuracy of wind farm inspections.

[0052] The wind turbine non-stop inspection method provided in this invention utilizes the geometric characteristic of the rotating body point cloud having the minimum variance along the rotation axis (applicable to flat rotating bodies like wind turbines). It accurately extracts the eigenvector corresponding to the minimum eigenvalue as the rotation axis direction, thereby calculating the real-time yaw angle of the wind turbine and achieving millimeter-level dynamic perception of the wind turbine's attitude. This provides a high-precision data foundation for subsequent accurate flight path planning. From point cloud acquisition and attitude calculation to flight path generation and execution, the entire process requires no manual intervention. Compared to traditional inspection methods that require experienced pilots to manually operate the turbine and rely on it being shut down, this solution achieves a closed loop of "one-click takeoff - autonomous perception - intelligent planning - automatic inspection - safe return," endowing the UAV with the ability to "perceive - understand - make decisions" in complex dynamic environments, realizing fully autonomous, high-precision, and high-safety inspection of wind turbines without shutting down.

[0053] Example 3 Figure 6 This is a schematic diagram of a non-stop inspection device for a wind turbine provided in Embodiment 3 of the present invention. Figure 6 As shown, the device includes: a calculation module 301, a direction determination module 302, an angle determination module 303, and a cruise route determination module 304, wherein: The calculation module is used to acquire point cloud data of the wind turbine to be inspected and determine the covariance matrix of the blade point cloud in the point cloud data. The direction determination module is used to determine the eigenvalues ​​and corresponding eigenvectors of the covariance matrix, and to determine the rotation axis direction of the fan to be inspected based on the eigenvalues ​​and eigenvectors. An angle determination module is used to determine the yaw angle of the wind turbine to be inspected based on the direction of the rotation axis, and to determine the blade azimuth angle of the wind turbine to be inspected based on the point cloud data. The cruise route determination module is used to determine the UAV inspection route of the wind turbine to be inspected based on the yaw angle and the blade azimuth angle at different times.

[0054] The wind turbine non-stop inspection device provided in this invention accurately extracts the wind turbine's rotation axis (yaw direction) and blade instantaneous azimuth angle based on real-time acquired point cloud data. By incorporating these dynamic parameters into the flight path planning algorithm, the UAV can adjust its shooting posture to closely follow the wind turbine's real-time attitude, ensuring that each shot is aimed at the key parts of the blades, achieving full-angle coverage, effectively avoiding blind spots, and automatically planning inspection routes under normal wind turbine power generation conditions. This enables non-stop, adaptive, and highly safe intelligent wind turbine inspection.

[0055] Optional, the angle determination module includes: A leaf tip determination unit is used to determine the leaf tip from the leaf point cloud in the point cloud data; Angle determination unit is used to determine the angle between the line connecting the centroid of the blade point cloud and the blade tip and a preset reference direction in the sweeping plane. An azimuth angle determination unit is used to determine the minimum included angle as the blade azimuth angle of the fan to be inspected.

[0056] Furthermore, determining the blade tip from the blade point cloud in the point cloud data includes: projecting the blade point cloud in the point cloud data onto the yaw direction corresponding to the yaw angle to obtain a two-dimensional point cloud; dividing the two-dimensional point cloud into regions according to the number of blades of the wind turbine to be inspected to obtain multiple point cloud regions; and for each point cloud region, determining the target point in each point cloud region that is farthest from the centroid of the two-dimensional point cloud, and determining the target point as the blade tip. The step of determining the angle between the line connecting the centroid of the blade point cloud and the blade tip and the preset reference direction in the sweeping plane includes: determining the angle between the line connecting the centroid of the two-dimensional point cloud and the blade tip and the preset reference direction in the sweeping plane.

[0057] Optional, the direction determination module includes: The rotation axis direction determination unit is used to determine the eigenvector corresponding to the minimum eigenvalue as the rotation axis direction of the fan to be inspected.

[0058] Optionally, the device may also include: The geometric center determination module is used to determine the geometric center point of the leaf point cloud in the point cloud data before determining the covariance matrix of the leaf point cloud in the point cloud data. The centralization processing module is used to centralize the leaf point cloud based on the geometric center point to obtain an updated centralized point cloud. The calculation module includes: A matrix determination unit is used to determine the covariance matrix of the centralized point cloud.

[0059] Furthermore, the step of dividing the two-dimensional point cloud into regions based on the number of blades of the wind turbine to be inspected to obtain multiple point cloud regions includes: if the number of blades of the wind turbine to be inspected is 3, then the two-dimensional point cloud is divided at 120-degree intervals to obtain 3 fan-shaped point cloud regions.

[0060] Optionally, the calculation module includes: The point cloud acquisition unit is used to acquire the initial three-dimensional point cloud of the wind turbine to be inspected through the radar carried by the UAV. A filtering unit is used to remove background points from the initial three-dimensional point cloud to obtain the point cloud data of the wind turbine to be inspected.

[0061] The wind turbine non-stop inspection device provided in this embodiment of the invention can execute the wind turbine non-stop inspection method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0062] Example 4 Figure 7 A schematic diagram of an electronic device 40 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0063] like Figure 7 As shown, the electronic device 40 includes at least one processor 41 and a memory, such as a read-only memory (ROM) 42 or a random access memory (RAM) 43, communicatively connected to the at least one processor 41. The memory stores computer programs executable by the at least one processor. The processor 41 can perform various appropriate actions and processes based on the computer program stored in the ROM 42 or loaded from storage unit 48 into the RAM 43. The RAM 43 may also store various programs and data required for the operation of the electronic device 40. The processor 41, ROM 42, and RAM 43 are interconnected via a bus 44. An input / output (I / O) interface 45 is also connected to the bus 44.

[0064] Multiple components in electronic device 40 are connected to I / O interface 45, including: input unit 46, such as keyboard, mouse, etc.; output unit 47, such as various types of monitors, speakers, etc.; storage unit 48, such as disk, optical disk, etc.; and communication unit 49, such as network card, modem, wireless transceiver, etc. Communication unit 49 allows electronic device 40 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0065] Processor 41 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 41 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 41 performs the various methods and processes described above, such as the wind turbine non-stop inspection method.

[0066] In some embodiments, the wind turbine non-stop inspection method can be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 48. In some embodiments, part or all of the computer program can be loaded and / or installed on electronic device 40 via ROM 42 and / or communication unit 49. When the computer program is loaded into RAM 43 and executed by processor 41, one or more steps of the wind turbine non-stop inspection method described above can be performed. Alternatively, in other embodiments, processor 41 can be configured to perform the wind turbine non-stop inspection method by any other suitable means (e.g., by means of firmware).

[0067] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoC) systems, complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0068] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0069] The computer equipment provided above can be used to execute the wind turbine non-stop inspection method provided in any of the above embodiments, and has the corresponding functions and beneficial effects.

[0070] Example 5 In the context of this invention, the computer-readable storage medium may be a tangible medium, and the computer-executable instructions, when executed by a computer processor, are used to perform a method for continuous wind turbine inspection, the method comprising: Acquire point cloud data of the wind turbine to be inspected, and determine the covariance matrix of the blade point cloud in the point cloud data; Determine the eigenvalues ​​and corresponding eigenvectors of the covariance matrix, and determine the rotation axis direction of the wind turbine to be inspected based on the eigenvalues ​​and eigenvectors. The yaw angle of the wind turbine to be inspected is determined based on the direction of the rotation axis, and the blade azimuth angle of the wind turbine to be inspected is determined based on the point cloud data. The drone inspection route for the wind turbine to be inspected is determined based on the yaw angle and blade azimuth angle at different times.

[0071] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by, or in conjunction with, an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0072] The computer equipment provided above can be used to execute the wind turbine non-stop inspection method provided in any of the above embodiments, and has the corresponding functions and beneficial effects.

[0073] It is worth noting that in the embodiments of the above-mentioned wind turbine non-stop inspection device, the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of each functional unit are only for easy differentiation and are not used to limit the scope of protection of the present invention.

[0074] Note that the above description is merely a preferred embodiment of the present invention and the technical principles employed. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions can be made without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments, and may include many other equivalent embodiments without departing from the concept of the present invention, the scope of which is determined by the scope of the appended claims.

Claims

1. A method for performing a non-stop fan inspection, the method comprising: include: Acquire point cloud data of the wind turbine to be inspected, and determine the covariance matrix of the blade point cloud in the point cloud data; Determine the eigenvalues ​​and corresponding eigenvectors of the covariance matrix, and determine the rotation axis direction of the wind turbine to be inspected based on the eigenvalues ​​and eigenvectors. The yaw angle of the wind turbine to be inspected is determined based on the direction of the rotation axis, and the blade azimuth angle of the wind turbine to be inspected is determined based on the point cloud data. The drone inspection route for the wind turbine to be inspected is determined based on the yaw angle and blade azimuth angle at different times.

2. The method of claim 1, wherein, Determining the blade azimuth angle of the wind turbine to be inspected based on the point cloud data includes: Determine the leaf tip from the leaf point cloud in the point cloud data; Determine the angle between the line connecting the centroid of the blade point cloud and the blade tip and a preset reference direction in the sweeping plane; The minimum included angle is determined as the blade azimuth angle of the fan to be inspected.

3. The method according to claim 2, characterized in that, Determining the leaf tip point from the leaf point cloud in the point cloud data includes: Project the blade point cloud in the point cloud data onto the yaw direction corresponding to the yaw angle to obtain a two-dimensional point cloud; Based on the number of blades of the wind turbine to be inspected, the two-dimensional point cloud is divided into regions to obtain multiple point cloud regions. For each point cloud region, the target point farthest from the centroid of the two-dimensional point cloud is determined in each point cloud region, and the target point is defined as the leaf tip point; The step of determining the angle between the line connecting the centroid of the blade point cloud and the blade tip and a preset reference direction in the sweeping plane includes: Determine the angle between the line connecting the centroid of the two-dimensional point cloud and the tip of the leaf and the preset reference direction in the sweeping plane.

4. The method according to any one of claims 1-3, characterized in that, Determining the rotation axis direction of the wind turbine to be inspected based on the eigenvalues ​​and eigenvectors includes: The direction of the eigenvector corresponding to the minimum eigenvalue is determined as the rotation axis direction of the fan to be inspected.

5. The method according to claim 1, characterized in that, Before determining the covariance matrix of the leaf point cloud in the point cloud data, the method further includes: Determine the geometric center point of the leaf point cloud in the point cloud data; Based on the geometric center point, the leaf point cloud is centered to obtain an updated centered point cloud. The determination of the covariance matrix of the leaf point cloud in the point cloud data includes: Determine the covariance matrix of the centered point cloud.

6. The method according to claim 3, characterized in that, The step involves dividing the two-dimensional point cloud into regions based on the number of blades of the wind turbine to be inspected, resulting in multiple point cloud regions, including: If the number of blades of the wind turbine to be inspected is 3, then the two-dimensional point cloud is divided at 120-degree intervals to obtain 3 fan-shaped point cloud regions.

7. The method according to claim 1, characterized in that, The acquisition of point cloud data of the wind turbine to be inspected includes: The initial three-dimensional point cloud of the wind turbine to be inspected is obtained by the radar carried by the drone; Background points are removed from the initial 3D point cloud to obtain the point cloud data of the wind turbine to be inspected.

8. A fan inspection device that operates without shutting down, characterized in that, include: The calculation module is used to acquire point cloud data of the wind turbine to be inspected and determine the covariance matrix of the blade point cloud in the point cloud data. The direction determination module is used to determine the eigenvalues ​​and corresponding eigenvectors of the covariance matrix, and to determine the rotation axis direction of the fan to be inspected based on the eigenvalues ​​and eigenvectors. An angle determination module is used to determine the yaw angle of the wind turbine to be inspected based on the direction of the rotation axis, and to determine the blade azimuth angle of the wind turbine to be inspected based on the point cloud data. The cruise route determination module is used to determine the UAV inspection route of the wind turbine to be inspected based on the yaw angle and the blade azimuth angle at different times.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the wind turbine non-stop inspection method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that are used to cause a processor to execute the wind turbine non-stop inspection method according to any one of claims 1-7.

Images