A method and device for detecting wind turbine operating parameters of wind turbine towers

Abstract

This invention relates to the field of wind turbine testing technology, and more particularly to a method and apparatus for detecting wind turbine operating parameters on wind turbine towers. The method includes: obtaining the centerline equation of the target wind turbine blade closest to the image acquisition device based on wind turbine blade images continuously acquired by an image acquisition device deployed on the wind turbine tower during wind turbine operation; obtaining the hub center coordinates of the wind turbine based on the centerline equation of the target wind turbine blade corresponding to multiple frames of wind turbine blade images; obtaining the maximum and minimum values ​​of the rotation angle of the target wind turbine blade based on the hub center coordinates and the contour equation of the target wind turbine blade; obtaining the yaw angle of the wind turbine based on the maximum and minimum values ​​of the rotation angle; and obtaining the wind turbine rotational speed based on the interval between the occurrence of the maximum rotation angle in multiple frames of wind turbine blade images. This technical solution overcomes the inherent requirement for the completeness of wind turbine blade images, improving the flexibility and accuracy of wind turbine operating parameter detection.

Description

Technical Field

[0001] This invention relates to the field of wind turbine testing technology, and in particular to a method and apparatus for testing wind turbine operating parameters of wind turbine towers. Background Technology

[0002] As the scale of offshore wind energy harvesting continues to expand, the safe and efficient operation of wind turbines is of paramount importance. Therefore, it is necessary to monitor wind turbine operating parameters, including yaw angle and turbine speed, in real time. Traditional monitoring methods, which rely on physical sensors such as accelerometers, gyroscopes, and GPS devices installed in the turbine nacelle or on the tower, are not only difficult to install and maintain, but also lack flexibility in monitoring.

[0003] In existing technologies, mobile inspection robots equipped with image acquisition devices are used to photograph the operating status of wind turbines, and the operating parameters of the turbines are analyzed from the images. However, this method requires that the camera's field of view completely cover the entire rotor (sweeped surface) of the wind turbine, that is, to continuously and clearly capture the trajectory of all blade tips. This is quite difficult for offshore wind turbine towers with large blades, especially when the mobile inspection robot climbs up the wind turbine tower, the field of view of the camera on the mobile inspection robot becomes increasingly narrow, making it difficult to capture the complete outline of the wind turbine blades, thus affecting the accuracy of the wind turbine operating parameters analyzed from the images.

[0004] Therefore, those skilled in the art urgently need to develop a new technical solution to address the above problems. Summary of the Invention

[0005] This invention provides a method and apparatus for detecting wind turbine operating parameters of wind turbine towers, which can break the inherent requirement for the integrity of wind turbine blade images and improve the flexibility and accuracy of wind turbine operating parameter detection.

[0006] In a first aspect, embodiments of the present invention provide a method for detecting wind turbine operating parameters of a wind turbine tower, including:

[0007] Based on the images of the wind turbine blades continuously acquired by the image acquisition equipment deployed on the wind turbine tower during wind turbine operation, the equation of the centerline of the target wind turbine blade closest to the image acquisition equipment is obtained;

[0008] Based on the equation of the central axis of the target wind turbine blade corresponding to multiple frames of wind turbine blade images, the hub center coordinates of the wind turbine are obtained.

[0009] Based on the hub center coordinates and the contour equation of the target wind turbine blade in the multi-frame wind turbine blade images, the maximum and minimum values ​​of the rotation angle of the target wind turbine blade during wind turbine operation are obtained.

[0010] The yaw angle of the wind turbine is obtained based on the maximum and minimum values ​​of the rotation angle.

[0011] The rotational speed of the wind turbine is obtained based on the time interval between the occurrence of the maximum value of the rotation angle in the multi-frame wind turbine blade images.

[0012] Secondly, embodiments of the present invention provide a wind turbine operating parameter detection device for a wind turbine tower, comprising:

[0013] The centerline determination module obtains the centerline equation of the target wind turbine blade closest to the image acquisition device based on the wind turbine blade images continuously acquired by the image acquisition device deployed on the wind turbine tower during wind turbine operation.

[0014] The hub center determination module is connected to the centerline determination module. Based on the centerline equation of the target wind turbine blade corresponding to multiple frames of wind turbine blade images, the hub center coordinates of the wind turbine are obtained.

[0015] The rotation angle determination module is connected to the hub center determination module. Based on the hub center coordinates and the contour equation of the target wind turbine blade in the multi-frame wind turbine blade images, it obtains the maximum and minimum values ​​of the rotation angle of the target wind turbine blade during wind turbine operation.

[0016] The yaw angle determination module is connected to the rotation angle determination module, and obtains the yaw angle of the wind turbine based on the maximum and minimum values ​​of the rotation angle;

[0017] The wind turbine speed determination module is connected to the yaw angle determination module. Based on the interval between the occurrence of the maximum value of the rotation angle in the multi-frame wind turbine blade images, the wind turbine speed is obtained.

[0018] Thirdly, the present invention provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, it implements the method described in the first aspect of the present invention.

[0019] Fourthly, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed in a computer, causes the computer to perform the method described in the first aspect of the present invention.

[0020] The present invention provides a method and apparatus for detecting wind turbine operating parameters of a wind turbine tower. By identifying a portion of the wind turbine blade outline in an image, and performing linear fitting on the outline points using the least squares method, the location of the wind turbine blade's central axis is determined. The hub center of the wind turbine is obtained by extracting the central axis equation from multiple consecutive frames of wind turbine blade images, and operating parameters such as yaw angle and rotational speed are analyzed based on this equation. This method does not rely on the complete visibility of the wind turbine blades in the image, breaking the inherent requirement for the integrity of wind turbine blade images. It has lower computational complexity and improves the flexibility and accuracy of wind turbine operating parameter detection. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 This is a flowchart of a method for detecting wind turbine operating parameters of a wind turbine tower according to an embodiment of the present invention;

[0023] Figure 2 This is a hardware architecture diagram of an electronic device provided in an embodiment of the present invention;

[0024] Figure 3 This is a structural diagram of a wind turbine operating parameter detection device for a wind turbine tower according to an embodiment of the present invention;

[0025] Figure 4 This is a schematic diagram of the wind turbine blade image after background subtraction.

[0026] Figure 5 This is a schematic diagram of a wind turbine blade.

[0027] Figure 6 A statistical graph showing the relationship between the rotation angle and slope of wind turbine blades;

[0028] Figure 7 This is a schematic diagram of the wind turbine's yaw angle;

[0029] Figure 8 A schematic diagram of the output screen for the detection results of the wind turbine operating parameters. Detailed Implementation

[0030] 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 some embodiments of the present invention, but not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0031] Please refer to Figure 1 This invention provides a method for detecting wind turbine operating parameters of wind turbine towers, the method comprising:

[0032] Step 100: Based on the images of the wind turbine blades continuously acquired by the image acquisition equipment deployed on the wind turbine tower during the wind turbine operation, obtain the equation of the centerline of the target wind turbine blade closest to the image acquisition equipment;

[0033] Step 102: Based on the equation of the centerline of the target wind turbine blade corresponding to multiple frames of wind turbine blade images, obtain the hub center coordinates of the wind turbine;

[0034] Step 104: Based on the hub center coordinates and the contour equation of the target wind turbine blade in multiple frames of wind turbine blade images, obtain the maximum and minimum values ​​of the rotation angle of the target wind turbine blade during wind turbine operation;

[0035] Step 106: Based on the maximum and minimum values ​​of the rotation angle, obtain the yaw angle of the wind turbine.

[0036] Step 108: Obtain the rotational speed of the wind turbine based on the interval between the maximum values ​​of the rotation angles in the multi-frame wind turbine blade images.

[0037] In this embodiment of the invention, the image acquisition device is typically deployed on a mobile inspection robot. The robot attaches to the wind turbine tower and can move up and down along it to acquire images of the wind turbine blades. Before acquiring images, the robot's position is usually adjusted so that the image acquisition device (camera) can capture images of the wind turbine impeller and that the central axis of the wind turbine tower is centered in the frame. During wind turbine operation, the image acquisition device continuously acquires images of the wind turbine blades and records the timestamp for each frame. Based on the blade images, the target blade closest to the image acquisition device is selected as the object of study at the corresponding timestamp. As acquisition continues, when the target blade rotates away from the image acquisition device, and the next blade becomes the closest target blade, this new target blade is selected as the new object of study. Thus, each blade in the image is continuously analyzed. For each target blade, the central axis equation is obtained by fitting the contour equation from the blade image using the least squares method. Understandably, due to the slender structure of wind turbine blades, even when partially obscured, the visible contour point set in the wind turbine blade image still exhibits a strong linear trend in spatial distribution, with the direction of this trend consistent with the actual pointing height of the blade. By extracting contour points through image processing techniques and using a fitting algorithm to extract the axis that best represents the overall distribution direction from these point cloud data, the reliance on blade integrity is transformed into the perception of its local contour direction trend. This allows the system to accurately track the rotation state of a blade even with only an incomplete blade contour by observing changes in the central axis direction, effectively overcoming interference from partial occlusion. After determining the central axis equation, the central axis equations corresponding to multiple frames of wind turbine blade images are fitted to obtain the hub center of the wind turbine. Based on the hub center, the normal vector of the target wind turbine blade is analyzed to determine the maximum and minimum values ​​of the target wind turbine blade's rotation angle, and the yaw angle and rotational speed of the wind turbine are calculated to complete the detection process of the wind turbine's operating parameters.

[0038] In one embodiment of the present invention, based on images of wind turbine blades continuously acquired by an image acquisition device deployed on a wind turbine tower during wind turbine operation, the equation of the centerline of the target wind turbine blade closest to the image acquisition device is obtained, including:

[0039] Based on the image acquisition equipment deployed on the wind turbine tower continuously acquiring wind turbine blade images during wind turbine operation, the connected region formed by the contour points of the wind turbine blade in each frame of the wind turbine blade image is obtained.

[0040] The wind turbine blade corresponding to the connected region with the most contour points is taken as the target wind turbine blade that is closest to the image acquisition device.

[0041] Based on the profile equation of the target wind turbine blade, the equation of the centerline of the target wind turbine blade is obtained by linear fitting using the least squares method.

[0042] In this embodiment, before fitting the central axis equation from the wind turbine blade images, the wind turbine blade images acquired by the image acquisition device need to be preprocessed to eliminate the influence caused by the movement of the image acquisition device itself. A Gaussian mixture model background subtraction algorithm is used to model the historical color value of each pixel as a Gaussian mixture distribution, thereby distinguishing between the stable background and the moving foreground. The separated images are then binarized, and the foreground image undergoes opening and dilation operations to eliminate noise and connect the blade regions in the image. Figure 4 The results of extracting moving targets using a background subtraction algorithm are shown. This method can process video sequences during the rotation of a wind turbine in real time and achieve accurate separation of the moving foreground and background.

[0043] In this embodiment of the invention, the wind turbine blade image contains three blades, i.e., a connected region formed by the contour points of the three blades. The connected region with the largest number of contour points in the binary image is selected as the wind turbine blade closest to the camera. This wind turbine blade is then used as the target wind turbine blade, and further analysis is performed on its contour points. In a mathematical coordinate system, the least squares method is used to fit a straight line to the point set to determine the parameters of the central axis equation. k and b Such that the sum of the squared distances from all points to the line is... S=∑(y mathi -(kx i +b） 2 ) 2 Minimize. By setting the partial derivative and The solution can be derived as follows:

[0044] k=(N×∑(x i ×y mathi )-∑x i ×∑y mathi ) / (N×∑(x i 2 )-(∑x i ) 2 ) ,

[0045] b=(∑y mathi -k×∑xi ) / N ,

[0046] Thus, the equation of the central axis is obtained. y=kx+b .

[0047] In one embodiment of the present invention, the hub center coordinates of the wind turbine are obtained based on the central axis equation of the target wind turbine blade corresponding to multiple frames of wind turbine blade images, including:

[0048] The equation of the centerline of the target wind turbine blade is obtained based on multiple frames of wind turbine blade images. a i x h +b i y h =-c i ，i= 1, 2, 3..., m , m The number of frames in the wind turbine blade image;

[0049] Will m The equations of the central axis are converted into matrix form ( A T A )· X=A T C ,in, A= [ a i ，b i ], X=[ x h , y h ] T C=[ -c 1, -c 2, ..., -c m ] T ;

[0050] like A T A Man Yi, based on X = (A T A） -1 ·(A T ·C) Obtain the coordinates of the hub center of the wind turbine ( x h , y h ).

[0051] In this embodiment, as Figure 5 As shown, since the image acquisition device continuously acquires images of the wind turbine blades, it can obtain the centerline equation corresponding to multiple frames of wind turbine blade images. To further obtain the hub center coordinates of the wind turbine through the centerline equation, the above oblique-intercept form of the centerline equation is converted into a normal form. The normal form of the centerline equation is expressed as:

[0052] a i x+b i y+c i =0，

[0053] in,( a i ,b i () is the unit normal vector of the axis equation in this normal form. , i Indicates the first i Image of a wind turbine blade.

[0054] Based on the rigid kinematic constraint that all wind turbine blades are fixedly connected to the center of the hub, the extension of the central axis extracted from each frame of the wind turbine blade image should intersect the center of the hub in physical space. x h , y h Theoretically, the hub center coordinates should simultaneously satisfy the normal equations of all centerlines in the wind turbine blade image:

[0055] a 1 x h +b 1 y h =-c 1 ，

[0056] a 2 x h +b 2 y h =-c 2 ，

[0057] ……

[0058] a m x h +b m yh =-c m ，

[0059] In practical applications, due to image detection noise, fitting errors, and slight model mismatch, the overdetermined system of equations consisting of the aforementioned central axis equations usually does not have an exact solution. Therefore, this invention employs a least squares optimization method to seek the optimal solution.

[0060] Convert the overdetermined system of equations consisting of the above central axis equations into matrix form. A · X=C .

[0061] in, A= [ a i ，b i ] represents an m×2 coefficient matrix, where each row of the matrix is ​​composed of the normal vector of a central axis. X =[ x h , y h ] T , represents a 2×1 vector to be solved. C =[ -c 1, -c 2, ..., -c m ] T , indicating a m A constant term vector of 1 × 1.

[0062] The least squares solution is obtained by solving the normal equations corresponding to the above overdetermined system of equations:

[0063] ( A T A )· X=A T C ,

[0064] like A T A Man Yi calculated the optimal estimate of the hub center coordinates by solving the normal equation:

[0065] X = (A T A） -1 ·(A T ·C) .

[0066] To ensure the stability of the solution, the matrix is ​​processed before solving. AT A The condition number is used to make a judgment; if the matrix A T A If the dispersion is too high, the current historical data is deemed insufficient to provide a reliable estimate, and the solution result for that frame of the wind turbine blade image is discarded, while data continues to accumulate. By continuously introducing new observation data (data obtained from wind turbine blade images) and discarding old data, the system can dynamically adapt to scene changes and has a good smoothing and suppression effect on random errors, ultimately outputting a stable and accurate hub center coordinate (…). x h , y h ).

[0067] In one embodiment of the present invention, based on the hub center coordinates and the contour equation of the target wind turbine blade in multiple frames of wind turbine blade images, the maximum and minimum values ​​of the rotation angle of the target wind turbine blade during wind turbine operation are obtained, including:

[0068] Based on the profile equation of the target wind turbine blade, the profile point of the target wind turbine blade that is farthest from the hub center coordinates is obtained.

[0069] Based on the line vector connecting the contour points and the hub center coordinates, the line vector corresponding to the wind turbine blade image is connected to... x The included angle between the shafts is taken as the rotation angle of the target wind turbine blades;

[0070] Based on the rotation angles corresponding to multiple frames of wind turbine blade images, the maximum and minimum values ​​of the rotation angles are obtained.

[0071] In this embodiment, the farthest contour point between the hub center and the target wind turbine blade contour points is calculated in a mathematical coordinate system. The hub center and the farthest contour point are connected to obtain the vector from the hub center to this contour point. This vector is then compared with the coordinate system... x The angle θ between the axes (the origin of this coordinate system is the center of the hub) is used as the reference for the time when the target blade is captured in the wind turbine blade image. x The angle between axes. It is understandable that, considering the increased computational complexity and error risk due to occlusion issues when simultaneously identifying three blades, and given that the target wind turbine blade closest to the camera is visually most prominent, has the most complete outline, and is less prone to occlusion, and that the motion state of this target wind turbine blade can completely encompass the rotational speed and yaw information of the entire wind turbine, focusing on tracking the target wind turbine blade can avoid complex multi-target identification and occlusion problems. Therefore, this embodiment of the invention only identifies the target wind turbine blade closest to the image acquisition device and records the angle of the target wind turbine blade during rotation. θ Changes, such as Figure 7As shown, the maximum rotation angle of the target wind turbine blades is obtained. θ max and minimum value θ min .

[0072] Specifically, the yaw angle of the wind turbine is obtained using the following formula:

[0073] Yaw=(θ max +θ min ) / 2-90, Yaw This is the yaw angle of the wind turbine. θ max This represents the maximum value of the rotation angle. θ min This represents the minimum rotation angle.

[0074] In one embodiment of the present invention, it further includes:

[0075] The yaw state of the wind turbine is determined based on the yaw angle. Yaw< 0°, indicating that the center of the wind turbine hub is offset to the right of the image acquisition device;

[0076] like Yaw >0°, indicating that the center of the wind turbine hub is offset to the left of the image acquisition device;

[0077] like Yaw =0°, confirming that the center of the wind turbine hub is located at the center of the image acquisition device.

[0078] In this embodiment, the yaw state of the wind turbine is determined based on the sign and magnitude of the yaw angle: if the yaw angle... Yaw< 0 ° The center of the wheel hub is determined to be offset to the right of the camera; if the yaw angle is... Yaw> 0 ° The center of the wheel hub was determined to be offset to the left of the camera; yaw angle. Yaw= 0 °， If the hub center is directly facing the camera, the actual yaw angle of the wind turbine hub center is 0°.

[0079] When the actual yaw angle of the wind turbine hub center is approximately 0°, the wind turbine impeller is symmetrical left and right in the image. If the wind turbine blades rotate clockwise, at this point, the right wind turbine blade has just entered the image and the left wind turbine blade has just left the image, and the number of connected contour points identified for the two wind turbine blades is almost the same. At this time, the wind turbine blade with the largest identified contour point may switch between the left and right wind turbine blades, meaning that the data identified in the wind turbine blade image at this time is unstable, and the slope of the wind turbine blade's central axis will change. This invention proposes a dynamic peak value verification method based on time interval constraints: by capturing the local maxima of the wind turbine blade rotation angle signal in real time and recording their times, when a subsequent candidate peak value is detected, the time interval between it and the previous valid peak value is calculated. If the interval is less than a preset minimum threshold (0.5 seconds), the current candidate peak value is determined to be a non-true extreme point and suppressed, while the previous valid peak value is retained as the current angle value, and peak value detection continues. By introducing a time dimension constraint mechanism, non-physical extreme values ​​caused by transient jitter can be effectively filtered out, ensuring that the peak value detection result is strictly consistent with the actual blade motion state, thereby significantly improving the system's response accuracy and anti-interference capability.

[0080] It should be noted that the slope K detection process is based on the hub center coordinates (x... h ,y h ) and the point (x) furthest from the hub identified on the current wind turbine blade profile p ,y p ), calculate the vector (x) pointing from the center of the wheel hub to the farthest point. p -x h ,y p -y h The slope K is obtained through the formula K=(y p -y h ) / (x p -x h The calculated slope K reflects the tilt of the vector in the image coordinate system. The core function of the slope K is to quantify the orientation change of the farthest point of the blade profile relative to the hub center in real time. It can not only be verified against the absolute rotation angle θ through the arctangent function relationship (θ=arctan(K)), but also serve as a key auxiliary criterion to effectively improve the stability of angle measurements when the blade profile is incomplete or the image contains noise interference. Figure 6As shown, when the absolute rotation angle θ of the current blade reaches its maximum value and the detection cycle of that target wind turbine blade ends, and the detection of the next wind turbine blade begins, the value of θ will undergo a step change, jumping from its maximum value to its minimum value. At this time, the value of the slope K also undergoes a significant abrupt change simultaneously. This correspondence can serve as an auxiliary verification basis for the rationality of the angle jump. When the wind turbine blade passes through an approximately vertical orientation of the image coordinate system during rotation (i.e., the corresponding vector is close to parallel to the Y-axis), the theoretical value of its slope K tends to infinity. At this time, the corresponding wind turbine blade rotation angle θ should be 90°. If the monitored K value increases abnormally, the special orientation of the wind turbine blade in that frame of the wind turbine blade image can be identified, and the calculation result of the rotation angle can be boundary corrected, thereby avoiding errors caused by unstable numerical calculations.

[0081] In one embodiment of the present invention, the rotational speed of the wind turbine is obtained based on the time interval between the maximum values ​​of the rotation angles appearing in multiple frames of wind turbine blade images, including:

[0082] In multi-frame images of wind turbine blades, determine the image acquisition time corresponding to when the rotation angle of the wind turbine blades reaches its maximum value;

[0083] Based on the continuous rotation angle of the wind turbine blades n +1 times the image acquisition time corresponding to the maximum value will n +1 The time interval between image acquisitions is taken as the time for the fan to complete one rotation. n This refers to the total number of fan blades.

[0084] The fan speed is obtained based on the time it takes for the fan to rotate one revolution.

[0085] In this embodiment, the rotation angle sequence θ of the wind turbine blades is obtained based on the continuously acquired images of the wind turbine blades. The time when the maximum value of the wind turbine blade rotation angle occurs is determined based on the image acquisition time: t1, t2, ..., t n This allows us to calculate the rotational period T of the wind turbine blades. Based on the rotational period T, the wind turbine's rotational speed is determined. RPM The calculation formula is:

[0086] RPM=60 / T ,

[0087] To improve the accuracy and real-time performance of speed measurement, this embodiment of the invention employs a sliding window-based real-time update mechanism during the calculation process. This mechanism does not calculate a single speed value only after the wind turbine has completed a full rotation; instead, it dynamically recalculates the speed based on the four most recent consecutive peak times whenever a new blade angle peak is detected. This effectively utilizes the timeliness of data in the wind turbine blade images, continuously introducing the latest observation data and discarding old data, allowing the speed output value to smoothly respond to dynamic changes in wind turbine speed. Simultaneously, multi-point averaging suppresses single-point measurement noise, balancing real-time performance and accuracy.

[0088] In this embodiment, the wind turbine operating parameters (yaw angle and speed) calculated based on the above steps are fed back in real time through an integrated visualization interface. For example... Figure 8 As shown, the following real-time analysis results are displayed in the overlay area on the original frame of the wind turbine blade image: the wind turbine hub center position estimated by dynamically tracking the marker points; the central axis passing through the identified target wind turbine blade area by fitting; the yaw angle and wind turbine speed values ​​are updated in real time in the upper right corner of the display screen; at the same time, a time-series waveform diagram of the wind turbine blade slope and rotation angle changing over time is also displayed on one side of the screen, and the maximum value of the rotation angle is marked in real time.

[0089] like Figure 2 , Figure 3 As shown in the figure, this specification provides a wind turbine operating parameter detection device for wind turbine towers. The device embodiment can be implemented by software, hardware, or a combination of both. From a hardware perspective, as... Figure 2 The diagram shown is a hardware architecture diagram of an electronic device for detecting wind turbine operating parameters of a wind turbine tower, as provided in an embodiment of this specification. Except for... Figure 2 In addition to the processor, memory, network interface, and non-volatile memory shown, the electronic device in the embodiment may also include other hardware, such as a forwarding chip responsible for processing packets. Taking software implementation as an example, such as... Figure 3 As shown, a device in a logical sense is formed by the CPU of the electronic device in which it is located reading the corresponding computer program from the non-volatile memory into the memory for execution.

[0090] like Figure 3 As shown in the figure, this embodiment provides a wind turbine operating parameter detection device for a wind turbine tower, comprising:

[0091] The centerline determination module 300 obtains the centerline equation of the target wind turbine blade closest to the image acquisition device based on the wind turbine blade images continuously acquired by the image acquisition device deployed on the wind turbine tower during wind turbine operation.

[0092] Hub center determination module 302 is connected to the centerline determination module. Based on the centerline equation of the target wind turbine blade corresponding to multiple frames of wind turbine blade images, the hub center coordinates of the wind turbine are obtained.

[0093] The rotation angle determination module 304 is connected to the hub center determination module. Based on the hub center coordinates and the contour equation of the target wind turbine blade in the multi-frame wind turbine blade images, it obtains the maximum and minimum values ​​of the rotation angle of the target wind turbine blade during wind turbine operation.

[0094] The yaw angle determination module 306 is connected to the rotation angle determination module, and obtains the yaw angle of the wind turbine based on the maximum and minimum values ​​of the rotation angle.

[0095] The wind turbine speed determination module 308 is connected to the yaw angle determination module. Based on the interval between the occurrence of the maximum value of the rotation angle in the multi-frame wind turbine blade images, the wind turbine speed is obtained.

[0096] In this embodiment of the specification, the centerline determination module 300 can be used to execute step 100 in the above method embodiment, the hub center determination module 302 can be used to execute step 102 in the above method embodiment, the rotation angle determination module 304 can be used to execute step 104 in the above method embodiment, the yaw angle determination module 306 can be used to execute step 106 in the above method embodiment, and the fan speed determination module 308 can be used to execute step 108 in the above method embodiment.

[0097] In one embodiment of this specification, obtaining the centerline equation of the target wind turbine blade closest to the image acquisition device, based on images of the wind turbine blades continuously acquired by the image acquisition device deployed on the wind turbine tower during wind turbine operation, includes:

[0098] Based on the image acquisition equipment deployed on the wind turbine tower continuously acquiring wind turbine blade images during wind turbine operation, the connected region formed by the contour points of the wind turbine blade in each frame of the wind turbine blade image is obtained.

[0099] The wind turbine blade corresponding to the connected region with the most contour points is taken as the target wind turbine blade that is closest to the image acquisition device.

[0100] Based on the profile equation of the target wind turbine blade, the equation of the centerline of the target wind turbine blade is obtained by performing a straight line fitting using the least squares method.

[0101] In one embodiment of this specification, obtaining the hub center coordinates of the wind turbine based on the centerline equation of the target wind turbine blade corresponding to multiple frames of wind turbine blade images includes:

[0102] The equation of the centerline of the target wind turbine blade is obtained based on multiple frames of wind turbine blade images. a i x h +b i y h =-c i ，i= 1, 2, 3, ..., m, where m is the frame number of the wind turbine blade image;

[0103] Will m The equation of the central axis is converted into matrix form ( A T A )· X=A T C ,in, A= [ a i ，b i ], X=[ x h , y h ] T C=[ -c 1, -c 2, ..., -c m ] T ;

[0104] If A T A. Fully narrated, based on X = (A... T A) -1 ·(A T •C) Obtain the hub center coordinates of the wind turbine ( x h , y h ).

[0105] In one embodiment of this specification, obtaining the maximum and minimum values ​​of the rotation angle of the target wind turbine blade during wind turbine operation based on the hub center coordinates and the contour equation of the target wind turbine blade in the multi-frame wind turbine blade images includes:

[0106] Based on the profile equation of the target wind turbine blade, the profile point of the target wind turbine blade that is furthest from the coordinates of the hub center is obtained.

[0107] Based on the line vector connecting the contour points and the hub center coordinates, the line vector corresponding to the wind turbine blade image is... xThe included angle between the shafts is taken as the rotation angle of the target wind turbine blades;

[0108] Based on the rotation angles corresponding to the multi-frame wind turbine blade images, the maximum and minimum values ​​of the rotation angles are obtained.

[0109] In one embodiment of this specification, the yaw angle of the wind turbine is obtained using the following formula:

[0110] Yaw=(θ max +θ min ) / 2-90, Yaw The yaw angle of the wind turbine is given. θ max This represents the maximum value of the rotation angle. θ min This represents the minimum rotation angle.

[0111] In one embodiment of this specification, it further includes:

[0112] The yaw state of the wind turbine is determined based on the yaw angle. Yaw< 0°, indicating that the hub center of the wind turbine is offset to the right side of the image acquisition device;

[0113] like Yaw> 0°, indicating that the hub center of the wind turbine is offset to the left of the image acquisition device;

[0114] like Yaw =0°, indicating that the hub center of the wind turbine is located at the center of the image acquisition device.

[0115] In one embodiment of this specification, obtaining the wind turbine's rotational speed based on the interval between the occurrence of the maximum value of the rotation angle in the multi-frame wind turbine blade images includes:

[0116] In the multi-frame wind turbine blade images, determine the image acquisition time corresponding to when the rotation angle of the wind turbine blade reaches its maximum value;

[0117] Based on the continuous rotation angle of the wind turbine blades n+ The image acquisition time corresponding to the first time the maximum value is reached will be... n + The time interval between each image acquisition is taken as the time for the fan to complete one rotation. n This refers to the total number of fan blades in the aforementioned fan.

[0118] The rotational speed of the fan is obtained based on the time it takes for the fan to complete one revolution.

[0119] It is understood that the structures illustrated in the embodiments of this specification do not constitute a specific limitation on a health status assessment device for spacecraft electromechanical components. In other embodiments of this specification, a health status assessment device for spacecraft electromechanical components may include more or fewer components than illustrated, or combine certain components, or split certain components, or have different component arrangements. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0120] The information interaction and execution process between the modules in the above-mentioned device are based on the same concept as the method embodiments in this specification, and the specific details can be found in the descriptions in the method embodiments in this specification, so they will not be repeated here.

[0121] This specification also provides an electronic device, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, it implements a method for assessing the health status of a spacecraft electromechanical component according to any embodiment of this specification.

[0122] This specification also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, causes the processor to perform a health status assessment method for a spacecraft electromechanical component according to any embodiment of this specification.

[0123] In summary, the wind turbine operating parameter detection method and apparatus for wind turbine towers provided by this invention determines the location of the wind turbine blade's central axis by identifying a portion of the wind turbine blade outline in an image and performing linear fitting on the outline points based on the least squares method. By extracting the central axis equation from multiple consecutive frames of wind turbine blade images, the hub center of the wind turbine is obtained, and operating parameters such as yaw angle and rotational speed are analyzed based on this. This method does not rely on the complete visibility of the wind turbine blades in the image, reducing the requirements for outline integrity and image quality, and lowering computational complexity. Only about 1 / 3 of the rotation cycle of data is needed for the determination, significantly improving real-time performance. This allows wind turbine condition monitoring methods to be effectively extended from traditional fixed observation conditions to local and dynamic observation scenarios under mobile robot platforms. This transformation not only overcomes the dependence on a global field of view but also significantly enhances the system's adaptability and reliability in complex industrial environments, thereby greatly expanding the application scope and applicability of this technology in industrial scenarios such as intelligent operation and maintenance of wind farms and real-time performance diagnosis of wind turbines.

[0124] Specifically, a system or apparatus equipped with a storage medium may be provided, on which software program code implementing the functions of any of the embodiments described above is stored, and the computer (or CPU or MPU) of the system or apparatus may read and execute the program code stored in the storage medium.

[0125] In this case, the program code read from the storage medium can itself implement the function of any of the above embodiments, and therefore the program code and the storage medium storing the program code constitute a part of this specification.

[0126] Storage media embodiments for providing program code include floppy disks, hard disks, magneto-optical disks, optical disks (such as CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RAM, DVD-RW, DVD+RW), magnetic tapes, non-volatile memory cards, and ROMs. Alternatively, program code can be downloaded from a server computer via a communication network.

[0127] Furthermore, it should be clear that not only can the program code read by the computer be executed, but also the operating system or other components operating on the computer can be instructed based on the program code to perform some or all of the actual operations, thereby realizing the function of any of the embodiments described above.

[0128] Furthermore, it is understood that the program code read from the storage medium is written to the memory set in the expansion board inserted into the computer or to the memory set in the expansion module connected to the computer. Then, based on the instructions of the program code, the CPU or other components installed on the expansion board or expansion module execute some and all of the actual operations, thereby realizing the function of any of the above embodiments.

[0129] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus.

[0130] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media that can store program code, such as ROM, RAM, magnetic disk, or optical disk.

[0131] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this specification, and are not intended to limit them. Although this specification 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 of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this specification.

Claims

1. A method for detecting wind turbine operating parameters of a wind turbine tower, characterized in that, include: Based on the images of the wind turbine blades continuously acquired by the image acquisition equipment deployed on the wind turbine tower during wind turbine operation, the equation of the centerline of the target wind turbine blade closest to the image acquisition equipment is obtained; Based on the equation of the central axis of the target wind turbine blade corresponding to multiple frames of wind turbine blade images, the hub center coordinates of the wind turbine are obtained. Based on the hub center coordinates and the contour equation of the target wind turbine blade in the multi-frame wind turbine blade images, the maximum and minimum values ​​of the rotation angle of the target wind turbine blade during wind turbine operation are obtained. The yaw angle of the wind turbine is obtained based on the maximum and minimum values ​​of the rotation angle. The rotational speed of the wind turbine is obtained based on the time interval between the occurrence of the maximum value of the rotation angle in the multi-frame wind turbine blade images.

2. The method according to claim 1, characterized in that, The method of obtaining the equation of the centerline of the target wind turbine blade closest to the image acquisition device by continuously acquiring wind turbine blade images from the image acquisition device deployed on the wind turbine tower during wind turbine operation includes: Based on the image acquisition equipment deployed on the wind turbine tower continuously acquiring wind turbine blade images during wind turbine operation, the connected region formed by the contour points of the wind turbine blade in each frame of the wind turbine blade image is obtained. The wind turbine blade corresponding to the connected region with the most contour points is taken as the target wind turbine blade that is closest to the image acquisition device. Based on the profile equation of the target wind turbine blade, the equation of the centerline of the target wind turbine blade is obtained by performing a straight line fitting using the least squares method.

3. The method according to claim 1, characterized in that, The method of obtaining the hub center coordinates of the wind turbine based on the central axis equation of the target wind turbine blade corresponding to multiple frames of wind turbine blade images includes: The equation of the centerline of the target wind turbine blade is obtained based on multiple frames of wind turbine blade images. a i x h +b i y h =-c i ，i= 1, 2, 3..., m , m The number of frames in the wind turbine blade image; Will m The equation of the central axis is converted into matrix form ( A T A )· X=A T C ,in, A= [ a i ，b i ], X=[ x h , y h ] T , C =[ - c 1, -c 2, ..., -c m ] T ; like A T A Man Yi, based on X = (A T A） -1 ·(A T ·C) Obtain the hub center coordinates of the wind turbine. （x h ，y h ） .

4. The method according to claim 1, characterized in that, The method of obtaining the maximum and minimum values ​​of the rotation angle of the target wind turbine blade during wind turbine operation based on the hub center coordinates and the contour equation of the target wind turbine blade in the multi-frame wind turbine blade images includes: Based on the profile equation of the target wind turbine blade, the profile point of the target wind turbine blade that is furthest from the coordinates of the hub center is obtained. Based on the line vector connecting the contour points and the hub center coordinates, the line vector corresponding to the wind turbine blade image is... x The included angle between the shafts is taken as the rotation angle of the target wind turbine blades; Based on the rotation angles corresponding to the multi-frame wind turbine blade images, the maximum and minimum values ​​of the rotation angles are obtained.

5. The method according to claim 1, characterized in that, The yaw angle of the wind turbine can be obtained using the following formula: Yaw=(θ max +θ min ) / 2-90, Yaw The yaw angle of the wind turbine is given. θ max This represents the maximum value of the rotation angle. θ min This is the minimum value of the rotation angle.

6. The method according to claim 5, characterized in that, Also includes: The yaw state of the wind turbine is determined based on the yaw angle. Yaw< 0°, indicating that the hub center of the wind turbine is offset to the right side of the image acquisition device; like Yaw> 0°, indicating that the hub center of the wind turbine is offset to the left of the image acquisition device; like Yaw =0°, indicating that the hub center of the wind turbine is located at the center of the image acquisition device.

7. The method according to claim 1, characterized in that, The method of obtaining the wind turbine's rotational speed based on the interval between the occurrence of the maximum value of the rotation angle in the multi-frame wind turbine blade images includes: In the multi-frame wind turbine blade images, determine the image acquisition time corresponding to when the rotation angle of the wind turbine blade reaches its maximum value; Based on the continuous rotation angle of the wind turbine blades n+ The image acquisition time corresponding to the first time the maximum value is reached will be... n+ The time interval between each image acquisition is taken as the time for the fan to complete one rotation. n This refers to the total number of fan blades in the aforementioned fan. The rotational speed of the fan is obtained based on the time it takes for the fan to complete one revolution.

8. A wind turbine operating parameter detection device for a wind turbine tower, characterized in that, include: The centerline determination module obtains the centerline equation of the target wind turbine blade closest to the image acquisition device based on the wind turbine blade images continuously acquired by the image acquisition device deployed on the wind turbine tower during wind turbine operation. The hub center determination module is connected to the centerline determination module. Based on the centerline equation of the target wind turbine blade corresponding to multiple frames of wind turbine blade images, the hub center coordinates of the wind turbine are obtained. The rotation angle determination module is connected to the hub center determination module. Based on the hub center coordinates and the contour equation of the target wind turbine blade in the multi-frame wind turbine blade images, it obtains the maximum and minimum values ​​of the rotation angle of the target wind turbine blade during wind turbine operation. The yaw angle determination module is connected to the rotation angle determination module, and obtains the yaw angle of the wind turbine based on the maximum and minimum values ​​of the rotation angle; The wind turbine speed determination module is connected to the yaw angle determination module. Based on the interval between the occurrence of the maximum value of the rotation angle in the multi-frame wind turbine blade images, the wind turbine speed is obtained.

9. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, and the processor, when executing the computer program, implements the method as described in any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, which, when executed in a computer, causes the computer to perform the method of any one of claims 1-7.

Images