Fan clearance distance detection method, fan and readable storage medium

Abstract

The invention discloses a draught fan clearance distance detection method, a draught fan and a readable storage medium, and relates to the technical field of wind power generation, the draught fan clearance distance detection method comprises the steps that point cloud data of the draught fan in the operation period is collected through a laser radar, the laser radar is arranged at the bottom of a cabin of the draught fan, and the emission direction of the laser radar is vertically downward; projecting the point cloud data to a target plane which is vertical to a transmitting window of the laser radar and is vertical to a blade rotating plane of the fan to obtain a two-dimensional image; converting the two-dimensional image into a grayscale image according to the number of the point cloud data corresponding to each pixel point in the two-dimensional image; and selecting a tower drum reference point and a blade tip reference point in the grayscale image, and determining the clearance distance of the fan based on the coordinates of the tower drum reference point and the blade tip reference point. The technical problem that the precision and stability of the draught fan clearance distance obtained through a traditional clearance detection scheme are poor is solved.

Description

Technical Field

[0001] The present application relates to the technical field of wind power generation, and in particular to a wind turbine clearance distance detection method, a wind turbine, and a computer-readable storage medium. Background Art

[0002] The clearance distance of a wind turbine is the distance from the blade tip to the tower wall at the corresponding tower height. To effectively warn of tower sweep risks and ensure safe operation of wind turbines, clearance distance monitoring is necessary to prevent accidents. Currently, commonly used clearance detection methods based on LiDAR (LiDAR) primarily use multi-laser beam ranging values ​​combined with empirical models to indirectly determine clearance distance. However, the accuracy of clearance distance is affected by the accuracy of the model and the number of laser beams, resulting in poor accuracy and stability in wind turbine clearance distance. Summary of the Invention

[0003] The main purpose of this application is to provide a wind turbine clearance distance detection method, a wind turbine and a computer-readable storage medium, aiming to solve the technical problems of poor accuracy and stability of the wind turbine clearance distance obtained by traditional clearance detection schemes.

[0004] To achieve the above objectives, the present application provides a method for detecting the clearance distance of a wind turbine, the method comprising:

[0005] Collecting point cloud data of the wind turbine during operation by using a laser radar, wherein the laser radar is located at the bottom of the nacelle of the wind turbine and transmits data vertically downward;

[0006] Projecting the point cloud data onto a target plane that is perpendicular to the emission window of the laser radar and perpendicular to the rotation plane of the wind turbine blades to obtain a two-dimensional image;

[0007] Converting the two-dimensional image into a grayscale image according to the amount of point cloud data corresponding to each pixel in the two-dimensional image;

[0008] A tower reference point and a blade tip reference point are selected in the grayscale image, and a clearance distance of the wind turbine is determined based on the coordinates of the tower reference point and the blade tip reference point.

[0009] In one embodiment, after the step of collecting point cloud data of the wind turbine during operation by using a laser radar, the method further comprises:

[0010] Eliminating point cloud data whose laser reflection intensity is less than a preset intensity threshold from the point cloud data to obtain denoised point cloud data;

[0011] Point cloud data within a preset valid range in the denoised point cloud data is filtered to obtain valid point cloud data, wherein the valid range is determined by the ranging range of the laser radar and the blade length of the wind turbine, and the valid point cloud data is used to be projected onto the target plane to obtain a two-dimensional image.

[0012] In one embodiment, the step of projecting the point cloud data onto a target plane perpendicular to the emission window of the laser radar and perpendicular to the rotation plane of the wind turbine blades to obtain a two-dimensional image includes:

[0013] Determining the pixel coordinates of each point on the target plane based on the three-dimensional coordinates of each point in the point cloud data;

[0014] The point cloud data is combined according to the pixel coordinates of each point to obtain a two-dimensional image located on the target plane.

[0015] In one embodiment, the resolution of the two-dimensional image in the horizontal axis direction is a first preset value, and the resolution in the vertical axis direction is a second preset value, and the pixel point coordinates include the pixel point horizontal coordinate and the pixel point vertical coordinate;

[0016] The step of determining the pixel coordinates of each point on the target plane based on the three-dimensional coordinates of each point in the point cloud data comprises:

[0017] Extract the horizontal axis coordinate and the vertical axis coordinate of the three-dimensional coordinates of each point;

[0018] Calculating the ratio of the sum of the horizontal axis coordinate and the horizontal axis offset of each point to the first preset value, and rounding down to obtain the horizontal coordinate of the pixel point corresponding to each point;

[0019] The ratio of the sum of the vertical axis coordinate of each point and the vertical axis offset to the second preset value is calculated, and the ratio is rounded down to obtain the vertical coordinate of the pixel point corresponding to each point.

[0020] In one embodiment, the step of converting the two-dimensional image into a grayscale image according to the amount of point cloud data corresponding to each pixel in the two-dimensional image includes:

[0021] Determine the relationship between the amount of point cloud data corresponding to each pixel and a preset threshold value in turn;

[0022] If the number of point cloud data corresponding to the pixel point is greater than a preset number threshold, the grayscale value of the pixel point is set to a preset grayscale value;

[0023] If the number of point cloud data corresponding to the pixel point is less than or equal to the preset number threshold, the grayscale value of the pixel point is set to 0;

[0024] After the grayscale values ​​of all pixels are determined, a grayscale image corresponding to the two-dimensional image is generated.

[0025] In one embodiment, the step of selecting a tower reference point and a blade tip reference point in the grayscale image includes:

[0026] Determining a plurality of independent original connected regions by performing connected region detection on the grayscale image;

[0027] Eliminate the original connected areas in which the number of pixels in each original connected area is less than the noise point number threshold, to obtain the connected areas to be identified;

[0028] Determine the point cloud farthest from the emission window in each of the connected areas to be identified as a blade tip reference point;

[0029] The connected area to be identified with the smallest average value of the horizontal axis coordinate among the connected areas to be identified is determined as the tower area, and the point cloud farthest from the emission window in the tower area is determined as the tower reference point, wherein the direction of the horizontal axis is perpendicular to the blade rotation plane.

[0030] In one embodiment, the step of determining a plurality of independent original connected regions by performing connected region detection on the grayscale image includes:

[0031] Traversing the adjacent pixels of each valid pixel whose grayscale value is greater than 0 in the grayscale image, if there is a valid pixel among the adjacent pixels, connecting the valid pixel with the valid pixel among the adjacent pixels to form a plurality of original connected regions;

[0032] Alternatively, determine the number of other valid pixel points within a preset range for each valid pixel point in the grayscale image whose grayscale value is greater than 0; if the number of other valid pixel points is greater than a preset threshold, connect the valid pixel point with the corresponding other valid pixel points to form multiple original connected areas.

[0033] In one embodiment, the step of determining the clearance distance of the wind turbine based on the coordinates of the tower reference point and the blade tip reference point includes:

[0034] Obtaining the horizontal axis coordinates corresponding to the tower reference point and the blade tip reference point respectively;

[0035] The absolute value of the difference between the horizontal axis coordinate of the tower reference point and the horizontal axis coordinate of the blade tip reference point is calculated to obtain the clearance distance of the wind turbine.

[0036] In addition, to achieve the above-mentioned purpose, the present application also provides a wind turbine, which includes at least a cabin, a laser radar and a clearance detection unit, the laser radar is arranged at the bottom of the cabin, and the emission direction of the laser radar is vertically downward, the clearance detection unit is communicatively connected to the laser radar, and the clearance detection unit includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the steps of the wind turbine clearance distance detection method as described above.

[0037] In addition, to achieve the above-mentioned purpose, the present application also provides a readable storage medium, which is a computer-readable storage medium, and the computer-readable storage medium stores a program for implementing the wind turbine clearance distance detection method. The program for implementing the wind turbine clearance distance detection method is executed by the processor to implement the steps of the wind turbine clearance distance detection method as described above.

[0038] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, including a computer program, which implements the steps of the above-mentioned wind turbine clearance distance detection method when executed by a processor.

[0039] The present application provides a method for detecting the clearance distance of a wind turbine. First, point cloud data of the wind turbine during operation is collected by a laser radar, wherein the laser radar is located at the bottom of the nacelle of the wind turbine and has a vertical downward transmission direction. The point cloud data is then projected onto a target plane perpendicular to the transmission window of the laser radar and perpendicular to the rotation plane of the wind turbine blades to obtain a two-dimensional image. The two-dimensional image is then converted into a grayscale image based on the number of point cloud data corresponding to each pixel in the two-dimensional image. Finally, a tower reference point and a blade tip reference point are selected from the grayscale image, and the clearance distance of the wind turbine is determined based on the coordinates of the tower reference point and the blade tip reference point. In the technical solution of the present application, the three-dimensional point cloud data collected by the laser radar is converted into a two-dimensional image and a grayscale image including the tower and the blade tip. The tower reference point and the blade tip reference point are then selected from the two-dimensional image to calculate the clearance distance. The method has high actuarial accuracy, low dependence on empirical models, no need for calibration, and strong stability.

[0040] In addition, in the technical solution of this application, the three-dimensional point cloud data is first converted into a two-dimensional image before subsequent processing, which simplifies the process of coordinate calculation and reference point selection. Compared with directly performing clearance detection through three-dimensional point cloud data, it has stronger anti-interference ability and higher real-time performance. It can realize real-time detection of clearance distance when the total amount of collected point cloud data is large, thereby ensuring the safety of fan operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0042] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0043] Figure 1 This is a flow chart of an embodiment of a method for detecting wind turbine clearance distance in an embodiment of the present application;

[0044] Figure 2 The left side view and the front view of the wind turbine equipped with a laser radar in the embodiment of the present application are shown;

[0045] Figure 3 This is an overall flow chart of a wind turbine clearance detection method based on a nacelle lidar in an embodiment of the present application;

[0046] Figure 4 Schematic diagram of adjacent pixels of a valid pixel in a grayscale image in an embodiment of the present application;

[0047] Figure 5 Schematic diagram of the equipment structure of the hardware operating environment involved in the wind turbine clearance distance detection method in the embodiment of the present application.

[0048] The purpose, features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0049] To make the above-mentioned purposes, features, and advantages of the present application more clearly understood, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making any creative work are within the scope of protection of this application.

[0050] It should be understood that the specific embodiments described herein are merely used to explain the technical solutions of the present application and are not intended to limit the present application.

[0051] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0052] The clearance distance of a wind turbine refers to the distance from the tip of the wind turbine blade to the tower wall at the corresponding tower height. With the development of wind power technology and the requirement for lightweight blade design, the length of the blade has increased but the stiffness has decreased, which increases the risk of blade sweeping the tower. In order to effectively warn of the risk of tower sweeping, the clearance distance must be monitored in real time to improve the safety of unit operation. The existing clearance detection method based on lidar indirectly obtains the clearance distance based on the ranging values ​​of multiple laser beams and combined with an empirical model. The accuracy of the clearance distance is affected by the accuracy of the model and the number of laser beams. Another clearance detection method based on video mainly calculates the clearance distance based on the blade tip point identified in the video image. This type of device needs to be equipped with a fill light device or combined with an infrared camera to improve the recognition accuracy at night, which is expensive.

[0053] In order to overcome the technical problems and defects in the above-mentioned prior art, the present invention provides a method for detecting the clearance distance of a wind turbine. Figure 1 , Figure 1 This is a flow chart of an embodiment of a method for detecting the clearance distance of a wind turbine according to the present application. The method for detecting the clearance distance of a wind turbine specifically includes:

[0054] Step S10, collecting point cloud data of the wind turbine during operation by using a laser radar, wherein the laser radar is located at the bottom of the nacelle of the wind turbine and has a vertical downward emission direction;

[0055] In the embodiment of the present application, a laser radar is installed at the bottom of the wind turbine cabin to continuously collect point cloud data in a vertical downward direction during the operation of the wind turbine through the laser radar, wherein the wind turbine refers to a wind turbine. Figure 2 As shown, the laser radar installed in the wind turbine cabin can collect point cloud data including the ground and the tower according to its radar field of view during the process of collecting point cloud data. In addition, a rotating shaft is provided at the front end of the cabin, and the blades (not shown in the figure) rotate around the rotating shaft. When the blades turn into the radar field of view, the laser radar can also collect point cloud data about the blade area.

[0056] Step S20: Projecting the point cloud data onto a target plane that is perpendicular to the emission window of the laser radar and perpendicular to the rotation plane of the wind turbine blades to obtain a two-dimensional image;

[0057] Among them, the point cloud data includes the three-dimensional coordinates corresponding to multiple points within the radar field of view. In order to simplify the calculation process of the clearance distance, the collected point cloud data is projected onto a plane perpendicular to the laser radar's emission window and the blade rotation plane to achieve conversion from three-dimensional to two-dimensional.

[0058] like Figure 2As shown, the target plane refers to the plane containing the Z and Y axes (i.e., the YZ plane), based on a three-dimensional coordinate system with the lidar as the coordinate origin, the Y direction directly below, the direction of the rotation axis as the Z direction, and the X direction perpendicular to the YZ plane. The coordinates of each point in the point cloud data are also the position in this three-dimensional coordinate system. In the YZ plane, the closest distance between the tower and the blade tip in the Z direction can be used to represent the wind turbine's clearance.

[0059] Step S30, converting the two-dimensional image into a grayscale image according to the number of point cloud data corresponding to each pixel in the two-dimensional image;

[0060] To represent the positional relationships of various detected objects (including towers, blades, or other objects on the ground) represented by the point cloud data in a 2D image, the number of point cloud data points is used to represent the location of each object. For example, where an object is located, the point cloud data is denser, so the number of corresponding pixel points is larger and the corresponding grayscale value is higher. Whereas, where the point cloud data is sparser, the number of corresponding pixel points is smaller and the corresponding grayscale value is lower.

[0061] Step S40 : selecting a tower reference point and a blade tip reference point in the grayscale image, and determining the clearance distance of the wind turbine based on the coordinates of the tower reference point and the blade tip reference point.

[0062] Among them, the coordinates of the tower reference point and the blade tip reference point only include the coordinates of the two in the Z-axis direction. The clearance distance refers to the difference between the tower reference point and the blade tip reference point along the Z-axis direction. The tower reference point can be a point in the tower area that is closest to the blade area, and the blade tip reference point can be a point in the blade area that is farthest from the origin of the three-dimensional coordinate system.

[0063] It should be noted that after determining the grayscale image, it is first necessary to select the area where the tower and blades are located based on the positions of the various objects reflected in the grayscale image. The area where the tower and blades are located have certain characteristics. For example, the area where the tower is located is closer to the Y-axis, that is, the absolute value of the coordinate in the Z-axis direction is smaller, while the area where the blades are located is farther from the Y-axis. The blade tip reference point is not only farther from the Y-axis, but also relatively farthest from the origin (i.e., the position of the lidar). Among them, in the process of selecting the tower reference point and the blade tip reference point, the three-dimensional coordinates of the point cloud data corresponding to each pixel point are required.

[0064] Furthermore, in a feasible embodiment, after the step of collecting point cloud data of the wind turbine during operation by using a laser radar, the method further includes:

[0065] Step S11, removing point cloud data whose laser reflection intensity is less than a preset intensity threshold from the point cloud data to obtain denoised point cloud data;

[0066] Step S12, filtering the point cloud data within a preset effective range in the denoised point cloud data to obtain effective point cloud data, wherein the effective range is determined by the ranging range of the lidar and the blade length of the wind turbine, and the effective point cloud data is used to project onto the target plane to obtain a two-dimensional image.

[0067] It should be noted that the point cloud data includes at least coordinate information (x, y, z), reflection intensity I and distance D. In order to reduce the interference caused by noisy point cloud data in the point cloud data, denoising processing is performed after the point cloud data is acquired. Specifically, the point cloud data with laser reflection intensity I less than the preset intensity threshold is eliminated.

[0068] Furthermore, during wind turbine clearance detection, the distance calculation and determination is primarily performed for the tower and blade areas. Therefore, point cloud data outside the blade area is considered invalid and requires no processing. To further reduce computational complexity, the present embodiment uses the LiDAR's ranging range and blade length to determine the corresponding valid range, and further filters the denoised point cloud data to obtain valid point cloud data.

[0069] For example, the LiDAR range is [Dmin, Dmax], where Dmin is the minimum range detected by the LiDAR and Dmax is the maximum range. The blade length is Db, which can also be understood as the boundary between the blade and tower point cloud data detected in the LiDAR field of view. Based on these parameters, the corresponding valid range is [Dmin, Db].

[0070] The resulting valid point cloud data is used to execute step S20, which projects the point cloud data onto a target plane perpendicular to the laser radar's emission window and the wind turbine's blade rotation plane to generate a two-dimensional image. Compared to directly projecting the raw point cloud data, this embodiment further reduces the impact of noise, filters out useless point cloud data, and reduces the amount of point cloud data processing, effectively improving clearance distance detection efficiency.

[0071] In a feasible embodiment, the step of projecting the point cloud data onto a target plane perpendicular to the emission window of the laser radar and perpendicular to the rotation plane of the wind turbine blades to obtain a two-dimensional image includes:

[0072] Step S21, determining the pixel coordinates of each point on the target plane based on the three-dimensional coordinates of each point in the point cloud data;

[0073] When projecting each point in the point cloud data onto the target plane, the y- and z-axis coordinates of each point in the point cloud data are used. Furthermore, a pre-defined image with a predetermined size and number of pixels must be constructed on the target plane. Each point in the point cloud data is then proportionally mapped onto this pre-defined image based on its y- and z-axis coordinates, resulting in the pixel coordinates of each point in the point cloud data.

[0074] Furthermore, the resolution of the two-dimensional image in the horizontal axis direction is a first preset value, and the resolution in the vertical axis direction is a second preset value, and the pixel coordinates include the horizontal coordinates and the vertical coordinates of the pixel points. Step S21 may specifically include the following steps:

[0075] Step S211, extracting the horizontal axis coordinate and the vertical axis coordinate of the three-dimensional coordinates of each point;

[0076] First, the horizontal axis coordinate and the vertical axis coordinate (y, z) are extracted from the three-dimensional coordinates (x, y, z) of each point, where z is the horizontal axis coordinate and y is the vertical axis coordinate.

[0077] Step S212, calculating the ratio of the sum of the horizontal axis coordinate of each point and the horizontal axis offset to the first preset value, and rounding down to obtain the horizontal coordinate of the pixel point corresponding to each point;

[0078] Step S213 , calculating the ratio of the sum of the vertical axis coordinate of each point and the vertical axis offset to the second preset value, and rounding down to obtain the vertical coordinate of the pixel point corresponding to each point.

[0079] For example, in the YZ plane, a preset image of size Yp×Zp is created, with resolutions Ry (the second preset value) and Rz (the first preset value), respectively. The number of pixels in the horizontal axis is Zp / Rz, and the number of pixels in the vertical axis is Yp / Ry. Based on the horizontal and vertical coordinates (y, z) of each point, the corresponding pixel coordinates (i, j) are determined. The coordinate conversion formula is as follows:

[0080]

[0081] Among them, y offset and z offset They are used to represent the vertical axis offset and the horizontal axis offset respectively. It can be understood that when the point cloud data is projected onto the target plane, its overall position may be biased towards one side of the preset image (upper, lower, left, right, etc.), so it is necessary to adjust the coordinate position of the projected pixel point through the pre-set offset to make it centered.

[0082] For example, when the projected pixel coordinate position is biased to the upper left, the horizontal offset and vertical offset are generally set to half the number of pixels in the horizontal and vertical directions of the two-dimensional image, respectively, so that the projected pixel coordinate is centered.

[0083] Step S22 , combining the point cloud data according to the pixel coordinates of each point to obtain a two-dimensional image located on the target plane.

[0084] Finally, after determining the pixel coordinates of each point, each point is mapped to the corresponding position in the preset image to obtain the corresponding two-dimensional image. It should be noted that each pixel in the two-dimensional image may correspond to zero, one or more points in the point cloud data.

[0085] In another feasible embodiment, the step of converting the two-dimensional image into a grayscale image according to the amount of point cloud data corresponding to each pixel in the two-dimensional image includes:

[0086] Step S31, sequentially determining the relationship between the amount of point cloud data corresponding to each pixel and a preset amount threshold;

[0087] Step S32: if the number of point cloud data corresponding to the pixel is greater than a preset number threshold, the grayscale value of the pixel is set to a preset grayscale value;

[0088] Step S33: if the number of point cloud data corresponding to the pixel is less than or equal to the preset number threshold, the grayscale value of the pixel is set to 0;

[0089] Step S34: After the grayscale values ​​of all pixels are determined, a grayscale image corresponding to the two-dimensional image is generated.

[0090] In the process of converting a two-dimensional image into a grayscale image, the corresponding grayscale value is set mainly based on the amount of point cloud data contained in each pixel.

[0091] For example, if the number of point cloud data points contained in a pixel exceeds a preset threshold value M, the grayscale value of the pixel is set to a preset grayscale value N (N>0); otherwise, the grayscale value corresponding to the pixel is set to 0. Thus, the grayscale values ​​of all pixels in the two-dimensional image are set to N or 0, respectively, achieving grayscale processing of the two-dimensional image and obtaining a binary grayscale image. Pixels with non-zero grayscale values ​​can be considered valid pixels, and the corresponding point cloud contains actual objects. Pixels with a grayscale value of 0 are invalid pixels, and the corresponding point cloud does not contain actual objects.

[0092] In a feasible embodiment, the step of selecting a tower reference point and a blade tip reference point in the grayscale image includes:

[0093] Step S41, determining a plurality of independent original connected regions by performing connected region detection on the grayscale image;

[0094] In order to effectively identify multiple objects in a grayscale image, a connected region detection method can be used to divide the original connected regions corresponding to each independent object. The connected region detection algorithm is a method for dividing a grayscale image into connected regions based on the grayscale value of each pixel and the grayscale value of its neighborhood.

[0095] The connected region detection algorithm is used to distinguish the regions corresponding to the tower and blades in the grayscale image. In another feasible embodiment, other classification algorithms can also be used to achieve the distinction between different regions, such as data-driven and clustering algorithms.

[0096] Step S42, removing original connected areas in which the number of pixels is less than a noise point threshold, to obtain connected areas to be identified;

[0097] After obtaining the independent original connected regions, to further achieve denoising, original connected regions with too few pixels can be removed. This is because original connected regions with too few pixels are generally other objects with small volumes or cross-sectional areas, not tower or blade regions. Removing them can effectively avoid interference when selecting blade and tower regions, improving region selection accuracy.

[0098] Step S43, determining the point cloud farthest from the emission window in each connected area to be identified as the blade tip reference point;

[0099] Before selecting the tip reference point, the blade area can be determined first. In the field of view of the laser radar, it mainly includes several main connected areas such as the tower area and the blade area. Among them, the blade area includes the point corresponding to the position of the blade tip. In the point cloud data collected by the laser radar, the tower area is mainly biased near the Y axis, while the blade area is located on the plane where the Z axis and the Y axis are located. Relatively speaking, the distance between the position point of the blade tip and the origin is farther than the distance between the position point of the tower area and the origin. If a connected area includes the point cloud farthest from the emission window (ie, the origin), then the connected area can be determined as the blade area, and the point cloud farthest from the origin is determined as the tip reference point.

[0100] For example, for each point cloud in the connected region to be identified, the coordinates can be expressed as (x, y, z), and the distance between it and the origin can be expressed as It can also be directly determined by the point cloud distance D detected by the lidar.

[0101] In step S44, the connected area to be identified with the smallest average value of the horizontal axis coordinate among all connected areas to be identified is determined as the tower area, and the point cloud farthest from the emission window in the tower area is determined as the tower reference point, wherein the direction of the horizontal axis is perpendicular to the blade rotation plane.

[0102] Since the tower area is mainly located near the Y-axis, the absolute value of the coordinate in the Z-axis direction (i.e., the horizontal axis, perpendicular to the blade rotation plane, the plane where the X-axis and the Y-axis are located) is relatively small. Therefore, when selecting the tower area, the Z-axis coordinate value in each connected area to be identified can be calculated according to the pixel points. The connected area to be identified with the smallest Z-axis average value is then determined as the tower area.

[0103] In addition, since the top and bottom thickness of the tower may be inconsistent in actual scenes, for example, thin at the top and thick at the bottom, when calculating the clearance distance, the position closest to the blade tip reference point in the tower area needs to be used as the tower reference point (on the same horizontal line). When screening valid point cloud data, the range of the point cloud data is limited by the length of the blade, so the position of the blade tip is at the position with the largest Y-axis coordinate and the position farthest from the origin. Therefore, the position closest to the blade tip reference point in the tower area is also the position with the largest Y-axis coordinate and the position farthest from the origin.

[0104] For ease of understanding, in a feasible embodiment, as Figure 3 As shown, the overall process of the wind turbine clearance detection method based on the cabin lidar in the embodiment of the present application may include: first, filtering the blade and tower point cloud data from the point cloud data collected by the lidar, then downsampling the point cloud data into a two-dimensional image (grayscale image form), and then performing two-dimensional image connected area detection to divide the blade and tower areas, and then filtering the blade tip point and tower reference point, and finally calculating the clearance distance based on the coordinates of the blade tip point and the tower reference point.

[0105] In a feasible embodiment, the step of determining a plurality of independent original connected regions by performing connected region detection on the grayscale image includes:

[0106] Step S441, traversing the adjacent pixels of each valid pixel whose grayscale value is greater than 0 in the grayscale image, if there is a valid pixel among the adjacent pixels, connecting the valid pixel with the valid pixel among the adjacent pixels to form multiple original connected regions;

[0107] The embodiment of the present application provides a method for detecting connected regions in a grayscale image. Specifically, a connected region detection is performed on each pixel in the grayscale image. Figure 4, dark pixels represent valid pixels. For the valid pixel numbered 5, the pixels numbered 1, 2, 3, 4, 6, 7, 8, and 9 are all its neighboring pixels. Among them, there are valid pixels 1 and 3. Then, valid pixels 1 and 3 are connected to pixel 5 respectively. This process is repeated until all pixels are divided into N connected regions.

[0108] Or, step S442, determine the number of other valid pixel points within a preset range for each valid pixel point with a grayscale value greater than 0 in the grayscale image. If the number of other valid pixel points is greater than the preset number threshold, the valid pixel point is connected with the corresponding other valid pixel points to form multiple original connected areas.

[0109] In addition to step S441, a different connected region detection method can also be adopted. In step S442, a preset range can be set in advance, and then the number of other valid pixels within the preset range for each valid pixel is searched. If the number of other valid pixels is greater than a preset number threshold M, the valid pixel is connected to the other valid pixels within the preset range. Otherwise, the valid pixel is not connected to the other valid pixels. This process is repeated until all pixels are divided into N connected regions.

[0110] In a feasible embodiment, the step of determining the clearance distance of the wind turbine based on the coordinates of the tower reference point and the blade tip reference point includes:

[0111] Step S45, obtaining the horizontal axis coordinates corresponding to the tower reference point and the blade tip reference point respectively;

[0112] Step S46 , calculating the absolute value of the difference between the horizontal axis coordinate of the tower reference point and the horizontal axis coordinate of the blade tip reference point to obtain the clearance distance of the wind turbine.

[0113] The horizontal coordinates (Z-axis coordinates) of the tower reference point and blade tip reference point can be obtained from the 3D coordinates of their corresponding point cloud data. The wind turbine's clearance distance is the difference in the Z-axis distance between the tower reference point and the blade tip reference point. Generally, the Z-axis coordinate of the tower reference point is smaller than the Z-axis coordinate of the blade tip reference point.

[0114] For example, assuming that the Z-axis coordinate of the tower reference point is Z T , the Z-axis coordinate of the blade tip reference point is Z B , then the clearance distance of the fan is:

[0115] L=|Z T -Z B |.

[0116] In another possible embodiment, if it is possible to determine Z B Greater than Z T, then the fan clearance distance can also be calculated by L=Z B -Z T Calculated.

[0117] The technical solution of the embodiment of the present application utilizes point cloud data collected by a laser radar to construct a two-dimensional image of the blades and tower and accurately selects blade tip reference points and tower reference points to calculate the clearance distance. This method has high calculation accuracy and does not rely on empirical models, requiring no calibration after installation. Furthermore, the technical solution of the embodiment of the present application pixelates the three-dimensional point cloud data into a two-dimensional grayscale image before subsequent processing, which reduces the complexity of data processing, provides strong anti-interference capabilities, and high real-time performance. Even with a large number of point clouds, real-time clearance distance detection can still be achieved, providing real-time and effective clearance distance values ​​for wind turbine safety warnings.

[0118] It should be noted that this example is only used to assist in understanding the present application and does not constitute a limitation on the wind turbine clearance distance detection method of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0119] The present application also provides a fan, referring to Figure 2 The wind turbine includes at least a nacelle, a laser radar, and a clearance detection unit. The laser radar is arranged at the bottom of the nacelle, and the emission direction of the laser radar is vertically downward. The clearance detection unit is communicatively connected to the laser radar. The clearance detection unit includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the wind turbine clearance distance detection method in the above-mentioned embodiment one.

[0120] Reference below Figure 5 , which shows a structural schematic diagram of a clearance detection unit suitable for implementing the embodiment of the present disclosure. Figure 5 The clearance detection unit shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0121] like Figure 5As shown, the clearance detection unit may include a processing device 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes based on programs stored in a read-only memory (ROM) 1002 or programs loaded from a storage device 1003 into a random access memory (RAM) 1004. RAM 1004 also stores various programs and data required for the clearance detection unit's operation. Processing device 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems may be connected to I / O interface 1006: input devices 1007 including, for example, a touchscreen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage device 1003 including, for example, a magnetic tape, hard disk, etc.; and communication device 1009. The communication device 1009 can allow the clearance detection unit to communicate with other devices wirelessly or wired to exchange data. Although the figure shows a clearance detection unit with various systems, it should be understood that it is not required to implement or have all of the systems shown. More or fewer systems can be implemented or have instead.

[0122] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment of the present disclosure are performed.

[0123] The fan provided in this application utilizes the fan clearance distance detection method of the above-described embodiment, which can resolve the technical issues of poor accuracy and stability of the fan clearance distance obtained by traditional clearance detection solutions. Compared with the prior art, the fan provided in this embodiment of the application has the same beneficial effects as the fan clearance distance detection method provided in the above-described embodiment, and the other technical features of this fan are the same as those disclosed in the above-described embodiment, and are not further described here.

[0124] It should be understood that various parts of the present disclosure can be implemented with hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in an appropriate manner.

[0125] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0126] An embodiment of the present application further provides a computer-readable storage medium having computer-readable program instructions stored thereon, the computer-readable program instructions being used to execute the wind turbine clearance distance detection method in the above-mentioned embodiment 1.

[0127] The computer-readable storage medium provided in the embodiments of the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0128] The computer-readable storage medium may be included in the clearance detection unit, or may exist independently without being assembled into the clearance detection unit.

[0129] The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by the clearance detection unit, the clearance detection unit executes: collecting point cloud data of the wind turbine during operation through a laser radar, wherein the laser radar is arranged at the bottom of the nacelle of the wind turbine and the emission direction is vertically downward; projecting the point cloud data onto a target plane perpendicular to the emission window of the laser radar and perpendicular to the rotation plane of the blades of the wind turbine to obtain a two-dimensional image; converting the two-dimensional image into a grayscale image according to the number of point cloud data corresponding to each pixel point in the two-dimensional image; selecting a tower reference point and a blade tip reference point in the grayscale image, and determining the clearance distance of the wind turbine based on the coordinates of the tower reference point and the blade tip reference point.

[0130] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on the remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0131] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, program segment or a part of code, and the module, program segment or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented by a dedicated hardware-based system that performs the specified function or operation, or can be implemented by a combination of dedicated hardware and computer instructions.

[0132] The modules involved in the embodiments described in this disclosure may be implemented in software or hardware, wherein the name of a module does not necessarily limit the unit itself.

[0133] The computer-readable storage medium provided in this application is a computer-readable storage medium storing computer-readable program instructions for executing the aforementioned wind turbine clearance distance detection method. This computer-readable storage medium can address the technical issues of poor accuracy and stability in wind turbine clearance distance detection obtained with conventional clearance detection schemes. Compared to the prior art, the beneficial effects of the computer-readable storage medium provided in this embodiment of the application are the same as those of the wind turbine clearance distance detection method provided in the first embodiment above, and are not further elaborated here.

[0134] An embodiment of the present application further provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the above-mentioned wind turbine clearance distance detection method.

[0135] The computer program product provided in this application can address the technical issues of poor accuracy and stability in wind turbine clearance distances obtained by conventional clearance detection solutions. Compared to the prior art, the beneficial effects of the computer program product provided in this embodiment of the application are the same as those of the wind turbine clearance distance detection method provided in Example 1 above, and are not further elaborated here.

[0136] The above are only preferred embodiments of the present application and do not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent processing scope of the present application.

Claims

1. A method for detecting the clearance distance of a fan, characterized in that: The wind turbine clearance distance detection method comprises: The point cloud data of the wind turbine during operation is collected by a laser radar, wherein the laser radar is arranged at the bottom of the nacelle of the wind turbine and the emission direction is vertically downward; Projecting the point cloud data onto a target plane that is perpendicular to the emission window of the laser radar and perpendicular to the blade rotation plane of the wind turbine to obtain a two-dimensional image; Converting the two-dimensional image into a grayscale image according to the number of point cloud data corresponding to each pixel in the two-dimensional image; A tower reference point and a blade tip reference point are selected in the grayscale image, and the clearance distance of the wind turbine is determined based on the coordinates of the tower reference point and the blade tip reference point.

2. The wind turbine clearance distance detection method according to claim 1, characterized in that: After the step of collecting point cloud data of the wind turbine during operation by using a laser radar, the method further includes: Eliminate point cloud data whose laser reflection intensity is less than a preset intensity threshold in the point cloud data to obtain denoised point cloud data; Point cloud data within a preset effective range in the denoised point cloud data is screened to obtain effective point cloud data, wherein the effective range is determined by the ranging range of the laser radar and the blade length of the wind turbine, and the effective point cloud data is used to project onto the target plane to obtain a two-dimensional image.

3. The wind turbine clearance distance detection method according to claim 1, characterized in that: The step of projecting the point cloud data onto a target plane that is perpendicular to the emission window of the laser radar and perpendicular to the blade rotation plane of the wind turbine to obtain a two-dimensional image includes: Determine the pixel coordinates of each point on the target plane according to the three-dimensional coordinates of each point in the point cloud data; The point cloud data is combined according to the pixel coordinates of each point to obtain a two-dimensional image located on the target plane.

4. The wind turbine clearance distance detection method according to claim 3, characterized in that: The resolution of the two-dimensional image in the horizontal axis direction is a first preset value, and the resolution in the vertical axis direction is a second preset value, and the pixel point coordinates include the pixel point horizontal coordinate and the pixel point vertical coordinate; The step of determining the pixel coordinates of each point on the target plane according to the three-dimensional coordinates of each point in the point cloud data comprises: Extract the horizontal axis coordinate and the vertical axis coordinate of the three-dimensional coordinates of each point; Calculate the ratio of the sum of the horizontal axis coordinate of each point and the horizontal axis offset to the first preset value, and round down to obtain the horizontal coordinate of the pixel point corresponding to each point; The ratio of the sum of the longitudinal coordinate of each point and the longitudinal offset to the second preset value is calculated, and rounded down to obtain the longitudinal coordinate of the pixel point corresponding to each point.

5. The wind turbine clearance distance detection method according to claim 1, characterized in that: The step of converting the two-dimensional image into a grayscale image according to the number of point cloud data corresponding to each pixel point in the two-dimensional image comprises: Determine in sequence the relationship between the quantity of point cloud data corresponding to each pixel and a preset quantity threshold; If the number of point cloud data corresponding to the pixel point is greater than a preset number threshold, the grayscale value of the pixel point is set to a preset grayscale value; If the number of point cloud data corresponding to the pixel point is less than or equal to the preset number threshold, the gray value of the pixel point is set to 0; After the grayscale values ​​of all pixels are determined, a grayscale image corresponding to the two-dimensional image is generated.

6. The wind turbine clearance distance detection method according to claim 1, characterized in that: The step of selecting a tower reference point and a blade tip reference point in the grayscale image comprises: Determine a plurality of independent original connected regions by performing connected region detection on the grayscale image; Eliminate the original connected areas in which the number of pixel points is less than the noise point number threshold in each of the original connected areas to obtain the connected areas to be identified; Determine the point cloud farthest from the emission window in each of the connected areas to be identified as a blade tip reference point; The connected area to be identified with the smallest average value of the horizontal axis coordinates among the connected areas to be identified is determined as the tower area, and the point cloud farthest from the emission window in the tower area is determined as the tower reference point, wherein the direction of the horizontal axis is perpendicular to the blade rotation plane.

7. The wind turbine clearance distance detection method according to claim 6, characterized in that: The step of determining a plurality of independent original connected regions by performing connected region detection on the grayscale image comprises: Traversing the adjacent pixels of each valid pixel whose gray value is greater than 0 in the grayscale image, if there is a valid pixel among the adjacent pixels, connecting the valid pixel with the valid pixel among the adjacent pixels to form a plurality of original connected regions; Alternatively, determine the number of other valid pixel points within a preset range for each valid pixel point with a grayscale value greater than 0 in the grayscale image; if the number of other valid pixel points is greater than a preset number threshold, connect the valid pixel point with the corresponding other valid pixel points to form multiple original connected areas.

8. The wind turbine clearance distance detection method according to claim 6, characterized in that: The step of determining the clearance distance of the wind turbine based on the coordinates of the tower reference point and the blade tip reference point comprises: Obtaining the horizontal axis coordinates corresponding to the tower reference point and the blade tip reference point respectively; The absolute value of the difference between the horizontal axis coordinate of the tower reference point and the horizontal axis coordinate of the blade tip reference point is calculated to obtain the clearance distance of the wind turbine.

9. A fan, characterized in that: The wind turbine at least includes a cabin, a laser radar and a clearance detection unit, the laser radar is arranged at the bottom of the cabin, and the emission direction of the laser radar is vertically downward, the clearance detection unit is communicatively connected with the laser radar, and the clearance detection unit includes: a memory, a processor and a computer program stored in the memory and executable on the processor, the computer program is configured to implement the steps of the wind turbine clearance distance detection method as described in any one of claims 1 to 8.

10. A readable storage medium, characterized in that: The readable storage medium is a computer-readable storage medium, on which is stored a program for implementing a wind turbine clearance distance detection method. The program for implementing a wind turbine clearance distance detection method is executed by a processor to implement the steps of the wind turbine clearance distance detection method as described in any one of claims 1 to 8.

Images