Blade deformation detection method, device, equipment and medium

Abstract

The invention provides a blade deformation detection method and device, equipment and a medium, and relates to the technical field of wind power generation. Determining current deformation data corresponding to the blade based on the full-surface image data; determining current load data corresponding to the current deformation data based on the calibrated mapping relation among the environment data, the deformation data and the load data; and based on the current load data, the unit yaw angle of the blade is determined, so that the stability and reliability of long-term detection of the blade are improved.

Description

Technical Field

[0001] This invention relates to the field of wind power generation technology, and more specifically, to a method, apparatus, equipment, and medium for detecting blade deformation. Background Technology

[0002] With the development of wind power generation technology, blade size is constantly increasing. Traditional blade load measurement methods, such as installing strain gauges at the blade root, have the following drawbacks: the installation of strain gauges requires damaging the blade structure, and factors such as the placement of the gauges, the coupling between multiple loads, and the aging of the turbine structure can affect the measurement accuracy. In addition, each time the gauges are installed, an independent correction of the strain-load relationship is required, which is complex to operate and difficult to guarantee long-term stability and reliability. Furthermore, it cannot fully reflect the overall deformation of the blade. Summary of the Invention

[0003] In view of this, the purpose of the present invention is to provide a method, apparatus, device and medium for detecting blade deformation, so as to improve the stability and reliability of long-term blade detection.

[0004] Firstly, this application provides a method for detecting blade deformation, including: Acquire full-surface image data of the blade; Based on full-surface image data, determine the current deformation data corresponding to the blade; Based on the mapping relationship between calibrated environmental data, deformation data and load data, determine the current load data corresponding to the current deformation data; Based on the current load data, determine the unit yaw angle of the blades.

[0005] Optionally, acquire full-surface image data of the blade, including: Image data collected by multiple image sensors placed around the wind turbine tower is used as full-surface image data.

[0006] Optionally, the blade deformation detection method provided in this application further includes: Acquire current environmental data around the blades; Based on the current environmental data and the full surface image data, the feature image corresponding to the full surface image data is determined.

[0007] Optionally, acquiring current environmental data around the blades includes: The environmental data collected by environmental sensors installed around the wind turbine tower is used as the current environmental data.

[0008] Optionally, based on full-surface image data, determining the current deformation data corresponding to the blade includes: Based on the full-surface image data, determine the in-plane displacement data of the full-surface image data; Based on in-plane displacement data and full-surface image data, determine the spatial displacement and strain parameters of the full-surface image data; Based on spatial displacement and strain parameters, a full-surface deformation field of the blade is constructed as the current deformation data.

[0009] Optionally, the blade deformation detection method provided in this application further includes: Based on environmental data, determine the corresponding operating condition data and deformation data of the blade; Based on the deformation data, determine the load data corresponding to the blade; Based on operating condition data, deformation data, and load data, the mapping relationship between environmental data, deformation data, and load data is determined.

[0010] Optionally, based on current load data, the turbine yaw angle of the blades is determined, including: Based on the mapping relationship between the calibrated blade stress amplitude, the number of blade load cycles, and the yaw angle, the unit yaw angle corresponding to the current load data is determined.

[0011] Secondly, this application provides a blade deformation detection device, comprising: The data acquisition module is used to acquire full-surface image data of the blade; The data processing module is used to determine the current deformation data of the blade based on the full surface image data; The data detection module is used to determine the current load data corresponding to the current deformation data based on the mapping relationship between the calibrated environmental data, deformation data and load data. The control optimization module is used to determine the unit yaw angle of the blades based on the current load data.

[0012] Thirdly, this application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the blade deformation detection method described above.

[0013] Fourthly, this application provides a computer-readable storage medium storing computer instructions, which, when executed by a processor, implement the blade deformation detection method described above.

[0014] This application provides a method, apparatus, device, and medium for detecting blade deformation. The method involves acquiring full-surface image data of the blade; determining the current deformation data of the blade based on the full-surface image data; determining the current load data corresponding to the current deformation data based on calibrated environmental data, the mapping relationship between deformation data and load data; and determining the turbine yaw angle of the blade based on the current load data, thereby improving the stability and reliability of long-term blade detection.

[0015] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0016] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 A flowchart of a blade deformation detection method provided by an embodiment of the present invention is shown; Figure 2 A schematic diagram of the structure of a blade deformation detection device provided in an embodiment of the present invention is shown; Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of the present invention is shown. Detailed Implementation

[0018] 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. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0019] To facilitate a better understanding of this application by those skilled in the art, the technical terms used in this application will be briefly introduced below.

[0020] A sensor is a detection device capable of detecting measured information and converting it into an electrical signal or other form of output. In the embodiments of this application, the sensor may be a sensor that simultaneously possesses both image data detection and environmental data detection functions, or it may be a sensor that possesses either image data detection or environmental data detection functions. In this case, the sensor includes, but is not limited to, image sensors and environmental sensors; wherein: An image sensor is a sensor capable of detecting images and converting them into electrical signals or other forms of output. In this embodiment, high-definition cameras can be installed as image sensors at multiple fixed observation stations around the wind turbine tower. The high-definition camera array has 3-4 fixed observation stations set up 150-200 meters from the bottom of the wind turbine tower along its circumference. Each observation station is equipped with 2 high-definition cameras to form a binocular stereo vision system. The height corresponds to the center position of the blade rotation plane. The high-definition cameras have a resolution greater than or equal to 24 million pixels, a frame rate of 50-100fps, a lens focal length of 200-400mm, a sensor size greater than or equal to 1 inch, a dynamic range greater than or equal to 14EV, and support for global shutter. (Fixed observation stations;) An environmental sensor is a sensor capable of detecting environmental data such as wind speed and light intensity and converting this data into electrical signals for output. In this embodiment, an integrated wind speed sensor and a light intensity sensor are installed at a fixed observation station. A synchronous controller controls the image sensor, wind speed sensor, and light intensity sensor to simultaneously acquire image data of the blades at different angles and environmental data. The triggering accuracy of the synchronous controller is less than or equal to 1. The integrated wind speed sensor has a measurement range of 0-40 m / s and an accuracy of ±0.1 m / s; the light intensity sensor has a measurement range of 0-100000 m / s. ; ---Digital Image Correlation (DIC) is a non-contact optical measurement technique with advantages such as full-field measurement, high accuracy, relatively simple optical path, and no special requirements for the measurement environment. By using the natural texture or artificial speckle features of the surface of the object to be measured for correlation matching, it can obtain the two-dimensional or three-dimensional shape and deformation information of the object. ---Triangulation is a classic geometric measurement method that uses two or more observation points at known locations, combined with the angle / direction information when observing the target, to calculate the three-dimensional spatial coordinates of the target.

[0021] It should be noted that the terms "first," "second," etc., used in this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such terms can be used interchangeably where appropriate so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. Furthermore, the term "and / or" used in this application describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. The character " / " generally indicates that the preceding and following related objects have an "or" relationship.

[0022] After introducing the technical terms used in this application, the application scenarios and design concepts of the embodiments of this application will be briefly described below.

[0023] This application provides a method for detecting blade deformation, see embodiments. Figure 1 As shown, the general flow of the blade deformation detection method provided in this application embodiment is as follows: Step 110: Obtain full-surface image data of the blade.

[0024] In this embodiment of the application, the acquisition of full-surface image data of the blade includes, but is not limited to, the following methods: Image data collected by multiple image sensors placed around the wind turbine tower is used as full-surface image data.

[0025] Specifically, 3-4 fixed observation stations are set up 150-200 meters from the bottom of the wind turbine tower along its circumference. Each station is equipped with two high-definition cameras as image sensors, forming a binocular stereo vision system to effectively avoid overlapping and occlusion during blade rotation and ensure full coverage of the blade surface. Furthermore, to ensure the stability of image acquisition, each fixed observation station is also equipped with dual-mode infrared and white light supplementary lighting, an IP66 weatherproof cover, and vibration-damping brackets for mounting the sensors.

[0026] In specific implementation, the blade deformation detection method provided in this application embodiment further includes: acquiring current environmental data around the blade; and determining the feature image corresponding to the full surface image data based on the current environmental data and the full surface image data.

[0027] In this application, the current environmental data around the blades is obtained in ways including but not limited to the following: obtaining environmental data collected by environmental sensors installed around the wind turbine tower as the current environmental data.

[0028] Furthermore, the feature image corresponding to the full surface image data can be determined in the following ways: First, the full surface image is denoised. In this embodiment, the full surface image is denoised by a nonlinear bilateral filtering method with spatial domain weights and gray-level domain weights. The spatial domain weights are determined based on the distance between pixels, and the gray-level weights are determined based on the gray-level differences between pixels. Bilateral filtering can remove noise and impurities from the full surface image data while preserving the natural texture (such as composite material textures) or artificial speckle features (if additional features are required) of the blade surface to the greatest extent, avoiding the texture blurring problem caused by traditional mean filtering and other methods. Then, the denoised full-surface image is subjected to illumination equalization processing based on environmental data. In this embodiment, the denoised full-surface image is subjected to illumination equalization processing by an adaptive histogram equalization method. Specifically, the denoised full-surface image is divided into multiple local regions, and the grayscale histogram of each region is equalized (e.g., stretching the grayscale range to make dark areas brighter and bright areas clearer). Then, the results of each region are fused by interpolation to avoid local overexposure or loss of detail that may be caused by global histogram equalization. This ensures that the texture details of the shadow areas in the denoised full-surface image are revealed, and the textures of the bright areas are not overexposed, thus ensuring the consistency of the identification of the texture features of the entire leaf surface and improving the global accuracy of subsequent DIC matching. Finally, distortion correction processing is performed on the full-surface image after illumination equalization. In this embodiment, the distortion correction processing of the full-surface image after illumination equalization is performed based on the camera intrinsic parameter calibration method of Zhang's calibration method. Specifically, the camera's intrinsic parameter matrix (such as focal length, principal point coordinates, distortion coefficients, etc.) is determined by multiple calibration plate images with known size feature points. Then, according to the distortion coefficients (such as radial distortion and tangential distortion) in the intrinsic parameter matrix, the pixel position of the full-surface image after illumination equalization is corrected so that the geometric shape of the blade in the full-surface image after illumination equalization is consistent with the actual physical shape.

[0029] By employing bilateral filtering to remove noise interference from the full-surface image, a clear image foundation is provided for illumination equalization. Then, adaptive histogram equalization is used to optimize illumination, making texture features in the full-surface image easier to identify. Finally, Zhang's calibration method is used to correct geometric distortion in the full-surface image, ensuring the physical accuracy of texture location.

[0030] Step 120: Based on the full surface image data, determine the current deformation data corresponding to the blade.

[0031] In this application embodiment, the current deformation data corresponding to the blade is determined in ways including but not limited to the following: Based on the full-surface image data, the in-plane displacement data of the full-surface image data is determined; based on the in-plane displacement data and the full-surface image data, the spatial displacement and strain parameters of the full-surface image data are determined; based on the spatial displacement and strain parameters, the blade full-surface deformation field is constructed as the current deformation data.

[0032] In specific implementation, this application embodiment uses a graphics processing unit (GPU) accelerated server that can support parallel computing of DIC matching point pairs to process the full surface image data and obtain the current deformation data. First, sub-pixel level matching is performed on the single-station binocular camera images (i.e., binocular camera images obtained through two high-definition cameras at a single station), and the in-plane displacement of the blade surface points (i.e., horizontal displacement in the x-direction and vertical displacement in the y-direction) is calculated. During sub-pixel level matching, fine interpolation calculation is performed on the grayscale information of the blade surface texture (such as natural texture or artificial speckle) to determine the corresponding positions of texture feature points in the left and right camera images before and after deformation, and to determine the displacement of each feature point in the image plane. In this application embodiment, the displacement resolution is less than or equal to 1 pixel. Then, based on the in-plane displacement, the intrinsic parameters of the binocular camera (such as focal length and principal point coordinates, which have been corrected using the Zhang calibration method mentioned above), and the extrinsic parameters (i.e., the relative positions of the two cameras), the three-dimensional spatial displacement of the feature points on the blade surface (i.e., in the x, y, and z directions, with the z direction being the depth displacement perpendicular to the image plane) is determined using the principle of triangulation. Then, by differentiating the three-dimensional coordinates of adjacent feature points, the strain parameters of the blade, i.e., the normal strain, are obtained. (Tensile / compressive deformation in the x-direction), normal strain (Tensile / compressive deformation in the y-direction) and shear strain (Shear deformation in the xy plane); Finally, the Kalman filter algorithm is used to fuse the spatial displacement and strain parameters from multiple fixed observation stations to construct the full-surface deformation field of the blade as the current deformation data. Specifically, the Kalman filter algorithm fuses the spatial displacement and strain parameters from multiple (e.g., 3-4) fixed observation stations through an iterative process of prediction and updating. First, for any point on the blade surface to be calculated, the theoretical deformation value (including spatial displacement and strain parameters) is predicted based on existing reliable deformation data in its surrounding area (e.g., multiple overlapping measurements in an unobstructed area) through interpolation or fitting (e.g., polynomial fitting, Gaussian process regression). Simultaneously, the prediction error covariance matrix of the predicted value is estimated to construct a deformation state prediction model. Then, the deviation between the measured value and the predicted value at each fixed observation station is calculated, and the measurement errors of each observation station are considered. The covariance matrix (pre-determined through calibration experiments, e.g., smaller measurement errors and smaller covariance matrix values ​​at unobstructed stations) is used to assess the reliability of the measured values. For measured values ​​with deviations within a reasonable range, the higher the measurement accuracy, the greater the weight, and the more they are fused with the predicted values ​​to obtain the optimal estimated deformation value for that point. For measured values ​​with deviations exceeding the threshold (e.g., displacement jumps caused by overlapping blades or abnormal strain caused by equipment vibration), they are identified as abnormal data and removed from the fusion calculation. Finally, grid interpolation (e.g., Kriging interpolation, bilinear interpolation) is used to fill the data gaps caused by obstruction from multiple fixed observation stations, outputting a deformation data matrix (i.e., a full-surface deformation field) covering the entire area of ​​the blade root, blade body, and blade tip, containing the spatial displacement and strain parameters of each grid point, and ensuring a smooth transition between adjacent deformation values.

[0033] Step 130: Based on the mapping relationship between the calibrated environmental data, deformation data and load data, determine the current load data corresponding to the current deformation data.

[0034] In this embodiment of the application, the mapping relationship between the calibrated environmental data, deformation data, and load data can be calibrated in the following way: Based on environmental data, determine the corresponding operating condition data and deformation data for the blade; based on the deformation data, determine the corresponding load data for the blade; based on the operating condition data, deformation data, and load data, determine the mapping relationship between the environmental data, deformation data, and load data.

[0035] In practice, firstly, based on environmental data (such as wind speed, wind direction, air density, ambient temperature, etc.), determine the corresponding operating conditions of the blade, such as low wind speed stable operating conditions, high wind speed turbulent operating conditions, or extreme wind direction yaw operating conditions; based on the environmental data, determine the blade deformation data under the current operating conditions using the above-mentioned methods for determining deformation data. Then, based on the blade's material properties (such as elastic modulus and Poisson's ratio) and structural parameters (such as thickness and cross-sectional shape), a finite element model of the blade is established. By inputting deformation data, the stress distribution in the finite element model is solved in reverse, and the stress distribution is converted into corresponding load data. Alternatively, loading and deformation experiments are conducted on the blade in the laboratory or on-site. A known standard load (such as a fixed flapping moment) is applied to the blade through a hydraulic loading device, and the corresponding deformation data is collected at the same time. A sample library of known loads and measured deformations is established, and the inverse mapping relationship (i.e., the mapping relationship between deformation data and load data) is fitted through interpolation or machine learning (such as neural networks). Finally, based on the operating condition data, deformation data, and load data, the mapping relationship between environmental data, deformation data, and load data is determined to ensure that the calibrated mapping relationship can cover the main operating conditions of the blade, and that accurate and reliable load data can be output when any environmental data is input and the corresponding deformation data is given.

[0036] It should be noted that the load data includes, but is not limited to, aerodynamic loads, blade root bending moments, and torques.

[0037] Step 140: Based on the current load data, determine the unit yaw angle of the blades.

[0038] In this embodiment of the application, the unit yaw angle of the blade can be determined in the following way: based on the mapping relationship between the calibrated stress amplitude of the blade, the number of load cycles of the blade and the yaw angle, the unit yaw angle corresponding to the current load data is determined.

[0039] In practical implementation, firstly, based on the linear relationship between blade root bending moment and stress, the current stress amplitude corresponding to the current load data is determined; then, based on the mapping relationship between the calibrated blade stress amplitude, the number of load cycles of the blade, and the yaw angle, the current load cycle number corresponding to the current stress amplitude is determined; finally, based on the mapping relationship between stress amplitude, the number of load cycles, and the yaw angle, the current yaw angle of the current stress amplitude and the current load cycle number is determined, and the current yaw angle is used as the unit yaw angle of the blade. That is, the unit yaw angle is the control command that the unit needs to execute, which is transmitted to the yaw drive system (such as the yaw motor) to adjust the nacelle direction so that the blade gradually faces the incoming airflow, reduces non-design loads, and prevents the blade from prematurely fatigued due to long-term high-stress operation.

[0040] This application provides a method for detecting blade deformation, which improves the accuracy of deformation measurement and displacement resolution by using a high-definition camera array combined with a sub-pixel-level DIC matching algorithm, and can capture subtle bending, torsion and strain changes of the blade. A synchronous controller ensures the time alignment of multiple sensors, laying a precise foundation for 3D point cloud reconstruction and multi-station data fusion, and avoiding deformation calculation deviations caused by time differences. Bilateral filtering noise reduction and adaptive histogram equalization optimize image quality, and Zhang's calibration method is used to complete camera intrinsic parameter correction, eliminating measurement errors caused by equipment distortion and illumination fluctuations. The binocular stereo vision layout of multiple circumferential fixed observation stations effectively avoids the problem of blade overlap and occlusion, and overcomes the limitations of local monitoring and partial information of traditional single-point sensors (such as strain gauges).

[0041] This application provides a blade deformation detection device, see below. Figure 2 As shown, the blade deformation detection device provided in this application embodiment includes: The data acquisition module 210 is used to acquire full-surface image data of the blade; Data processing module 220 is used to determine the current deformation data of the blade based on the full surface image data; The data detection module 230 is used to determine the current load data corresponding to the current deformation data based on the mapping relationship between the calibrated environmental data, deformation data and load data. The control optimization module 240 is used to determine the unit yaw angle of the blades based on the current load data.

[0042] In an optional embodiment, the data acquisition module 210 is used to: Image data collected by multiple image sensors placed around the wind turbine tower is used as full-surface image data.

[0043] In an optional embodiment, the data acquisition module 210 is used to: Acquire the current environmental data around the blade; based on the current environmental data and the full surface image data, determine the feature image corresponding to the full surface image data.

[0044] In an optional embodiment, the data acquisition module 210 is used to: The environmental data collected by environmental sensors installed around the wind turbine tower is used as the current environmental data.

[0045] In an optional embodiment, the data processing module 220 is used to: Based on the full-surface image data, the in-plane displacement data of the full-surface image data is determined; based on the in-plane displacement data and the full-surface image data, the spatial displacement and strain parameters of the full-surface image data are determined; based on the spatial displacement and strain parameters, the blade full-surface deformation field is constructed as the current deformation data.

[0046] In an optional embodiment, the data detection module 230 is used to: Based on environmental data, determine the corresponding operating condition data and deformation data of the blade; Based on the deformation data, determine the load data corresponding to the blade; Based on operating condition data, deformation data, and load data, the mapping relationship between environmental data, deformation data, and load data is determined.

[0047] In an optional embodiment, the control optimization module 240 is used to: Based on the mapping relationship between the calibrated blade stress amplitude, the number of blade load cycles, and the yaw angle, the unit yaw angle corresponding to the current load data is determined.

[0048] It should be noted that the principle of the blade deformation detection device provided in this application embodiment to solve the technical problem is similar to that of the blade deformation detection method provided in this application embodiment. Therefore, the implementation of the blade deformation detection device provided in this application embodiment can refer to the implementation of the blade deformation detection method provided in this application embodiment, and the repeated parts will not be described again.

[0049] After introducing the blade deformation detection method and apparatus provided in the embodiments of this application, the electronic equipment provided in the embodiments of this application will be briefly introduced next.

[0050] See Figure 3 As shown, the electronic device 500 provided in this application embodiment includes at least a processor 501, a memory 502, and a computer program stored in the memory 502 and executable on the processor 501. When the processor 501 executes the computer program, it implements the blade deformation detection method provided in this application embodiment.

[0051] The electronic device 500 provided in this application embodiment may further include a bus 503 connecting different components (including processor 501 and memory 502). The bus 503 represents one or more types of bus structures, including memory bus, peripheral bus, local area bus, etc.

[0052] Memory 502 may include a readable storage medium in the form of volatile memory, such as random access memory (RAM) 5021 and / or cache memory 5022, and may further include read-only memory (ROM) 5023. Memory 502 may also include a program tool 5025 having a set (at least one) of program modules 5024, including but not limited to an operating subsystem, one or more application programs, other program modules, and program data, each or some combination of these examples may include an implementation of a network environment.

[0053] Processor 501 can be a single processing element or a collective term for multiple processing elements. For example, processor 501 can be a central processing unit (CPU) or one or more integrated circuits configured to implement the blade deformation detection method provided in the embodiments of this application. Specifically, processor 501 can be a general-purpose processor, including but not limited to CPUs, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.

[0054] Electronic device 500 can communicate with one or more external devices 504 (e.g., keyboard, remote control, etc.), and also with one or more devices that enable a user to interact with electronic device 500 (e.g., mobile phone, computer, etc.), and / or with devices that enable electronic device 500 to communicate with one or more other electronic devices 500 (e.g., router, modem, etc.). This communication can be performed through input / output (I / O) interface 505. Furthermore, electronic device 500 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) through network adapter 506. Figure 3 As shown, network adapter 506 communicates with other modules of electronic device 500 via bus 503. It should be understood that, although... Figure 3As not shown, other hardware and / or software modules may be used in conjunction with the electronic device 500, including but not limited to microcode, device drivers, redundant processors, external disk drive arrays, Redundant Arrays of Independent Disks (RAID) subsystems, tape drives, and data backup storage subsystems.

[0055] It should be noted that, Figure 3 The electronic device 500 shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0056] The following describes the computer-readable storage medium provided in the embodiments of this application. The computer-readable storage medium provided in the embodiments of this application stores computer instructions, which, when executed by a processor, implement the blade deformation detection method provided in the embodiments of this application. Specifically, the computer instructions can be built into or installed in a processor, so that the processor can implement the blade deformation detection method provided in the embodiments of this application by executing the built-in or installed computer instructions.

[0057] In addition, the blade deformation detection method provided in this application embodiment can also be implemented as a computer program product, which includes program code. The program code implements the blade deformation detection method provided in this application embodiment when it is run on a processor.

[0058] The computer program product provided in this application embodiment may employ one or more computer-readable storage media, which may be, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination thereof. Specifically, more specific examples (a non-exhaustive list) of computer-readable storage media include electrical connections with one or more wires, portable disks, hard disks, RAM, ROM, erasable programmable read-only memory (EPROM), optical fibers, portable compact disc read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0059] The computer program product provided in this application embodiment can be a CD-ROM and include program code, and can also run on electronic devices such as computers. However, the computer program product provided in this application embodiment is not limited thereto. In this application embodiment, the computer-readable storage medium can be any tangible medium that contains or stores program code, which can be used by or in conjunction with an instruction execution system, device, or apparatus.

[0060] It should be noted that although several units or sub-units of the device have been mentioned in the detailed description above, this division is merely exemplary and not mandatory. In fact, according to embodiments of this application, the features and functions of two or more units described above can be embodied in one unit. Conversely, the features and functions of one unit described above can be further divided and embodied by multiple units.

[0061] Furthermore, although the operations of the method of this application are described in a specific order in the accompanying drawings, this does not require or imply that these operations must be performed in that specific order, or that all the operations shown must be performed to achieve the desired result. Additionally or alternatively, certain steps may be omitted, multiple steps may be combined into one step, and / or one step may be broken down into multiple steps.

[0062] Although preferred embodiments of this application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this application.

[0063] Obviously, those skilled in the art can make various modifications and variations to the embodiments of this application without departing from the spirit and scope of the embodiments of this application. Therefore, if these modifications and variations to the embodiments of this application fall within the scope of the claims of this application and their equivalents, this application also intends to include these modifications and variations.

Claims

1. A method of detecting blade deformation, characterized by, The method comprises: obtaining full-surface image data of a blade; determining current deformation data corresponding to the blade based on the full-surface image data; determining current load data corresponding to the current deformation data based on a mapping relationship between calibrated environmental data, deformation data and load data; determining a unit yaw angle of the blade based on the current load data.

2. The method of claim 1, wherein The method of obtaining full-surface image data of a blade comprises: obtaining image data collected by a plurality of image sensors arranged around a fan tower drum as the full-surface image data.

3. The method of claim 1, wherein The method further comprises: obtaining current environmental data around the blade; determining feature images corresponding to the full-surface image data based on the current environmental data and the full-surface image data.

4. The method of claim 3, wherein The method of obtaining current environmental data around the blade comprises: obtaining environmental data collected by an environmental sensor arranged around the fan tower drum as the current environmental data.

5. The method of claim 1, wherein The method of determining current deformation data corresponding to the blade based on the full-surface image data comprises: determining in-plane displacement data of the full-surface image data based on the full-surface image data; determining spatial displacement and strain parameters of the full-surface image data based on the in-plane displacement data and the full-surface image data; constructing a full-surface deformation field of the blade as the current deformation data based on the spatial displacement and the strain parameters.

6. The method of claim 1, wherein The method further comprises: determining working condition data corresponding to the blade based on the environmental data and the deformation data; determining the load data corresponding to the blade based on the deformation data; determining a mapping relationship between the environmental data, deformation data and load data based on the working condition data, the deformation data and the load data.

7. The method of claim 6, wherein The method of determining a unit yaw angle of the blade based on the current load data comprises: determining the unit yaw angle corresponding to the current load data based on a mapping relationship between a stress amplitude of the calibrated blade, a load cycle number of the blade and the yaw angle.

8. A device for detecting a deformation of a blade, characterized by The method comprises: a data acquisition module for obtaining full-surface image data of a blade; a data processing module for determining current deformation data corresponding to the blade based on the full-surface image data; a data detection module for determining current load data corresponding to the current deformation data based on a mapping relationship between calibrated environmental data, deformation data and load data; a control optimization module for determining a unit yaw angle of the blade based on the current load data.

9. An electronic device, comprising: The computer program stored in the memory and executable on the processor implements the blade deformation detection method of any one of claims 1 to 7 when the processor executes the computer program.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer instructions, which, when executed by a processor, implement the blade deformation detection method of any one of claims 1 to 7.

Images