Method, device, equipment and system for determining tower clearance of wind turbine generator set

The identification of the tip position of the wind turbine blades through image processing technology solves the problems of limited installation of the wind turbine tower clearance measurement device and poor environmental adaptability, achieving high accuracy and flexible tower clearance measurement.

CN115143045BActive Publication Date: 2024-11-22BEIJING GOLDWIND SCI & CREATION WINDPOWER EQUIP CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202110338008.9
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-03-30
Publication Date
2024-11-22
Estimated Expiration
2041-03-30

AI Technical Summary

Technical Problem

The existing wind turbine tower clearance measurement device is limited in installation and poor environmental adaptability, so it cannot accurately measure under extreme weather conditions.

Method used

The image acquisition device is used to obtain multi-frame images of the wind turbine, and the blade area and blade tip position are identified through image processing. The effective blade tip position is filtered based on preset conditions, and the tower clearance is calculated to reduce the limitations on installation location and the impact on extreme weather. .

Benefits of technology

It realizes flexible installation and high accuracy measurement of tower clearance, enhances environmental adaptability and ensures the reliability of calculation results.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN115143045B_ABST
    Figure CN115143045B_ABST
Patent Text Reader

Abstract

The present application provides a method, device, equipment and system for determining the tower clearance of a wind turbine generator set. The method for determining the tower clearance of a wind turbine generator set includes: acquiring multiple frames of images of the wind turbine generator set; determining the blade area of ​​the wind turbine generator set in each frame of the image to obtain N blade areas, where N is a positive integer; performing image retrieval on the N blade areas respectively to determine P blade tip positions, where P is a positive integer; determining the M blade tip positions that meet the preset first valid condition among the P blade tip positions as M first valid blade tip positions, where M is a positive integer; and determining the tower clearance of the wind turbine generator set based on the M first valid blade tip positions. The image acquisition device in the present application is flexible to install, has a high calculation accuracy of the tower clearance, and has strong environmental adaptability.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of wind power technology, and in particular to a method, device, equipment and system for determining the clearance of a tower of a wind turbine generator set. Background Art

[0002] The tower clearance of a wind turbine generator set refers to the distance from the tip of the blade (blade tip) to the tower surface during the rotation of the wind turbine generator set's impeller, which can be used to determine whether the blade has swept the tower during rotation. In the prior art, actual distance measurement is usually used to directly measure the physical distance from the tower point to the blade (tower clearance value), such as laser distance measurement. In this way, a corresponding measuring device needs to be installed. Such measuring devices have high requirements for the installation position. If the installation position is not appropriate, the accurate distance cannot be measured. Generally, it is required to be in the middle of the tower, which is not very convenient to install. In addition, the measurement is easily affected by extreme weather and has poor environmental adaptability. Summary of the invention

[0003] The embodiments of the present application provide a method, device, equipment and system for determining the tower clearance of a wind turbine generator set, which can solve the problems of limited installation and poor environmental adaptability of the measuring device in the prior art.

[0004] In a first aspect, an embodiment of the present application provides a method for determining a tower clearance of a wind turbine generator set, comprising:

[0005] Acquire multiple frames of images of a wind turbine generator set;

[0006] Determine the blade area of ​​the wind turbine generator set in each frame image to obtain N blade areas, where N is a positive integer;

[0007] Perform image retrieval on N leaf regions respectively to determine P leaf tip positions, where P is a positive integer;

[0008] Determine M blade tip positions that meet a preset first effective condition among the P blade tip positions as M first effective blade tip positions, where M is a positive integer;

[0009] The tower clearance of the wind turbine generator set is determined based on the M first effective blade tip positions.

[0010] In a second aspect, an embodiment of the present application provides a device for determining the clearance of a tower of a wind turbine generator set, comprising:

[0011] An image acquisition module, used for acquiring multiple frames of images of a wind turbine generator set;

[0012] The region determination module is used to determine the blade region of the wind turbine in each frame image and obtain N blade regions, where N is a positive integer.

[0013] A position determination module is used to perform image retrieval on N leaf regions respectively to determine P leaf tip positions, where P is a positive integer;

[0014] A position screening module, used for determining M blade tip positions satisfying a preset first validity condition among the P blade tip positions as M first valid blade tip positions, where M is a positive integer;

[0015] The clearance determination module is used to determine the tower clearance of the wind turbine generator set based on the M first effective blade tip positions.

[0016] In a third aspect, an embodiment of the present application provides a device for determining tower clearance of a wind turbine generator set, comprising: a processor and a memory storing computer program instructions;

[0017] When the processor executes the computer program instructions, the method for determining the wind turbine tower clearance provided in the first aspect of the embodiment of the present application is implemented.

[0018] In a fourth aspect, an embodiment of the present application provides a system for determining the clearance of a tower of a wind turbine generator set, comprising: an image acquisition device and a device for determining the clearance of a tower of a wind turbine generator set provided in the third aspect of the embodiment of the present application;

[0019] The image acquisition device is arranged at a specific position and is in communication connection with the determination device; the specific position includes: the bottom of the nacelle of the wind turbine generator set or the side of the wind turbine generator set and the position with a preset distance from the wind turbine generator set;

[0020] The image acquisition device is used to shoot a wind turbine generator set to obtain multiple frames of images.

[0021] In a fourth aspect, an embodiment of the present application provides a computer storage medium storing computer program instructions, which, when executed by a processor, implements the method for determining the tower clearance of a wind turbine generator set provided in the first aspect of the embodiment of the present application.

[0022] The technical solution provided in the embodiments of the present application can at least achieve the following beneficial effects:

[0023] 1) The embodiment of the present application provides a tower clearance determination method based on video monitoring, which can use an image acquisition device to acquire multiple frames of images of a wind turbine generator set, and can identify the blade area based on the multiple frames of images, and then determine the blade tip position. The installation position of the image acquisition device is flexible, and can be installed on or outside the wind turbine generator set;

[0024] 2) The embodiment of the present application may also screen the determined blade tip position based on the first valid condition to ensure the validity and consistency of the blade tip position used to calculate the tower clearance, so as to improve the accuracy of the calculation;

[0025] 3) The technical solution of the embodiment of the present application calculates the tower clearance based on the monitored image rather than the actual distance measurement, which can effectively reduce the impact of extreme weather and has strong environmental adaptability. Compared with the direct data obtained by the existing actual distance measurement method, the image monitored by the embodiment of the present application is used as the original data to verify the accuracy of the calculation results, making the calculation results more secure. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solution of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0027] Figure 1 A schematic flow chart of a method for determining the tower clearance of a wind turbine generator set provided in an embodiment of the present application;

[0028] Figure 2 A schematic diagram of a frame of image of a wind turbine generator set captured by an image acquisition device;

[0029] Figure 3 for Figure 2 A schematic diagram of a frame image preceding the image shown;

[0030] Figure 4 A partial flow chart of another method for determining the tower clearance of a wind turbine generator set provided in an embodiment of the present application;

[0031] Figure 5 For the general Figure 2 The images shown and Figure 3 A schematic diagram of an image obtained after performing difference calculation on the image shown;

[0032] Figure 6 For Figure 5 A schematic diagram of a binarized image after the image shown is subjected to grayscale binarization processing;

[0033] Figure 7 A partial flow chart of another method for determining the tower clearance of a wind turbine generator set provided in an embodiment of the present application;

[0034] Figure 8 The schematic diagram is a principle diagram of determining the position of the blade tip based on the binary image;

[0035] Fig. 9 It is a schematic diagram of the effective area, invalid area and blade tip motion trajectory of the image;

[0036] Fig.10 A partial flow chart of another method for determining the clearance of a wind turbine tower provided in an embodiment of the present application;

[0037] Fig.11 This is a schematic diagram of the principle of determining the tower position in an embodiment of the present application;

[0038] Fig.12 A schematic diagram of a flow chart of an optional implementation of the blade tip identification thread in the embodiment of the present application;

[0039] Fig.13 A schematic diagram of a flow chart of an optional implementation method of blade tip screening sub-threads in an embodiment of the present application;

[0040] Fig.14 A flowchart of an optional implementation of a headroom calculation sub-thread in an embodiment of the present application;

[0041] Fig.15 A schematic diagram of the structural framework of a device for determining the tower clearance of a wind turbine generator set provided in an embodiment of the present application;

[0042] Fig.16 A schematic diagram of the structural framework of a system for determining the tower clearance of a wind turbine generator set provided in an embodiment of the present application. DETAILED DESCRIPTION

[0043] The features and exemplary embodiments of various aspects of the present application will be described in detail below. In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application, rather than to limit the present application. For those skilled in the art, the present application can be implemented without the need for some of these specific details. The following description of the embodiments is only to provide a better understanding of the present application by illustrating the examples of the present application.

[0044] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "include..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0045] In order to solve the problems of the prior art, the embodiments of the present application provide a method, device, equipment and system for determining the tower clearance of a wind turbine generator set.

[0046] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments.

[0047] The present application embodiment provides a method for determining the tower clearance of a wind turbine generator set, such as Figure 1 As shown, the method includes:

[0048] S110, acquiring multiple frames of images of the wind turbine generator set;

[0049] S120, determining a blade region of the wind turbine generator set in each frame of the image, and obtaining N blade regions, where N is a positive integer;

[0050] S130, performing image retrieval on N leaf regions respectively to determine P leaf tip positions, where P is a positive integer;

[0051] S140, determining M blade tip positions that meet a preset first validity condition among the P blade tip positions as M first valid blade tip positions, where M is a positive integer;

[0052] S150: Determine a tower clearance of the wind turbine generator set based on the M first effective blade tip positions.

[0053] The method for determining the tower clearance of a wind turbine generator set provided in the embodiment of the present application can at least achieve the following beneficial effects:

[0054] 1) The embodiment of the present application provides a tower clearance determination method based on video monitoring, which can use an image acquisition device to acquire multiple frames of images of a wind turbine generator set, and can identify the blade area based on the multiple frames of images, and then determine the blade tip position. The installation position of the image acquisition device is flexible, and can be installed on or outside the wind turbine generator set;

[0055] 2) The embodiment of the present application may also screen the determined blade tip position based on the first valid condition to ensure the validity and consistency of the blade tip position used to calculate the tower clearance, so as to improve the accuracy of the calculation;

[0056] 3) The technical solution of the embodiment of the present application calculates the tower clearance based on the monitored image rather than the actual distance measurement, which can effectively reduce the impact of extreme weather and has strong environmental adaptability. Compared with the direct data obtained by the existing actual distance measurement method, the image monitored by the embodiment of the present application is used as the original data to verify the accuracy of the calculation results, making the calculation results more secure.

[0057] In an optional embodiment, the multiple frames of images of the embodiment of the present application may include: images obtained by an image acquisition device set at a specific position to shoot a wind turbine; the specific position includes: the bottom of the nacelle of the wind turbine or the side of the wind turbine and the distance between the wind turbine and the wind turbine is a preset distance.

[0058] The image acquisition device in the embodiment of the present application captures the wind turbine generator set and obtains the image as follows: Figure 2 and Figure 3 shown.

[0059] In an optional embodiment, if Figure 4 As shown, in step S120, when determining the leaf region in each frame of image, each frame of image may be processed by the following steps S121-S122:

[0060] S121, performing difference calculation between pixel values ​​of the current frame image and pixel values ​​of the previous frame image, and determining at least one moving object region in the current frame image according to the difference calculation result.

[0061] In one example, if Figure 2 The image shown is the current frame image. Figure 3 The image shown is Figure 2 The previous frame image of the current frame image shown in FIG. 1 can be used to determine the leaf area. Figure 2 The pixel values ​​of the image shown are Figure 3 Subtract the pixel values ​​of the images shown. Since the time difference between two adjacent frames is usually short, the background objects in the image are usually unchanged, so the subtraction can remove Figure 2 The background objects of the image shown in the figure only retain the moving objects that have changed, and we get the following Figure 5 The image shown. Figure 5 In the image shown, the area with lower brightness is the background object area. Figure 2 It can be seen that Figure 5 The background objects in the image have been removed, leaving only the moving objects with higher brightness. Figure 5 The brightness difference of different areas shown can be used to determine Figure 5 The moving object area in .

[0062] In an optional embodiment, determining at least one moving object region in the current frame image according to the difference calculation result may include: performing a clearing process on the image obtained after the difference calculation, and identifying at least one moving object region in the cleared image.

[0063] by Figure 5 Take the image after difference calculation as an example, Figure 5 To clarify Figure 5The boundary of the moving object area in the image is clearer, and a cleared image is obtained. At least one area with higher brightness is identified in the cleared image, that is, at least one moving object area, that is, each area with higher brightness is a moving object area; when judging whether it is an area with higher brightness, it can be judged according to a preset brightness threshold, and the brightness threshold can be pre-set according to actual needs or experience values.

[0064] In the embodiments of the present application, a variety of methods can be used to achieve image sharpening, such as an image sharpening method based on high-pass filtering or an image sharpening method based on spatial differentiation. In one example, a grayscale binarization method (one of the spatial differentiation methods) can be used to sharpen an image such as Figure 5 The image shown in the figure is sharpened to obtain Figure 6 The binary image shown in Figure 6 The white area identified in the binary image shown is the moving object area.

[0065] In an optional implementation, determining at least one moving object region in the current frame image according to the difference calculation result may include: determining at least one moving object region in the target region in the current frame image according to the difference calculation result.

[0066] The target area can be an area in the image that is predetermined based on the usual range of motion of the blade, for example, Figure 6 The area within a certain height of the lower edge of the image shown. In one example, a certain moving object area identified in the current frame image (for example, a moving object area caused by light and shadow of people, flying birds, raindrops, etc. that appear in the shooting range) may not be within the normal movement range of the blade. At this time, it is not accurate to regard the moving object area as the blade area. It is more accurate to regard the moving object area identified in the target area as the blade area, which is conducive to improving the accuracy of subsequent blade tip position recognition, thereby improving the accuracy of tower clearance calculation.

[0067] S122: Determine a leaf region in the current frame image according to at least one moving object region.

[0068] In an optional embodiment, when the moving object region includes one, the moving object region is determined as the leaf region in the current frame image; when the moving object region includes at least two, the moving object regions are merged and the obtained merged region is determined as the leaf region in the current frame image.

[0069] In one example, when at least one moving object region is located in the target region, one moving object region in the target region (the case where there is only one moving object region in the target region) is determined as the leaf region in the current frame image, or the merged region of at least two moving objects in the target region is determined as the leaf region in the current frame image.

[0070] During the image processing process, changes in some pixels may occur, causing the same leaf to appear as two different moving object areas in the image. Therefore, when there are at least two moving object areas in the current frame image or the target area therein, the at least two moving object areas can be merged as the leaf area in the current frame image, that is, the union of the moving object areas is used as the leaf area in the current frame image to ensure the integrity of the leaf area.

[0071] In an optional implementation, merging at least two moving object regions may include:

[0072] determining a region distance between each two moving object regions of at least two moving object regions;

[0073] Determine whether there is at least one regional distance between the regional distances of the moving object regions that is less than a preset regional distance threshold; if so, merge the moving object regions corresponding to the regional distances less than the regional distance threshold; if not, consider all the moving object regions invalid and do not merge them, and stop the current process.

[0074] In one example, suppose that there are three moving object regions in the current frame image or the target region of the current frame image, namely region 1, region 2 and region 3, and the region distance between region 1 and region 2 is L 12 , the area distance between area 2 and area 3 is L 23 , the area distance between area 1 and area 3 is L 13 ; In one case, if only L 12 Less than the preset area distance threshold, L 23 and L 13 are greater than or equal to the regional distance threshold, then only L 12 The corresponding regions 1 and 2 are merged; in another case, if L 12 and L 23 are all less than the regional distance threshold, L 12 If L is greater than or equal to the regional distance threshold, 12 and L 23 The corresponding areas 1, 2, and 3 are merged.

[0075] In another optional implementation, merging at least two moving object regions may include:

[0076] Determine whether the number of moving object regions is greater than a preset region number threshold; if so, consider that the current moving object regions are all invalid regions and reacquire the image; if not, merge the moving object regions. The region number threshold is an integer greater than 1.

[0077] When the number of moving object regions is large, the probability of introducing other moving objects other than leaves is high. By setting the region number threshold, the moving object regions can be further screened and the regions that are more likely to be leaf regions can be selected for merging to improve the accuracy of leaf region recognition.

[0078] The regional distance in the embodiment of the present application can be the distance between the centers of the two moving object areas, or it can be the distance between the edges of the two moving object areas. For example, when area 1 is located on the left side of the image and area 2 is located on the right side of the image, the regional distance between area 1 and area 2 is the distance between the right edge of area 1 and the left edge of area 2.

[0079] The area distance threshold in the embodiment of the present application can be preset according to actual needs or empirical values, for example, it can be a distance of 20 pixels.

[0080] The region quantity threshold in the embodiment of the present application can be pre-set according to actual needs or empirical values, for example, it can be 2, or other values ​​greater than 2.

[0081] In an optional embodiment, if Figure 7 As shown, in step S130, image retrieval is performed on N blade regions respectively to determine P blade tip positions, including the following steps S131-S132:

[0082] S131, determining whether the length of each blade region in the first direction is less than a preset length threshold; if so, executing S132; if not, determining that the blade region is an invalid region.

[0083] P may be a positive integer less than or equal to N. In one example, a blade tip position can be determined in each blade region, and P is equal to N, so N blade tip positions can be obtained; in another example, the blade tip position may not be determined in some blade regions, and P is less than N.

[0084] In one example, the first direction may be as follows Figure 8 In the X direction shown in FIG. 1 , if the length of the leaf region in the X direction is too large, the influence of other moving objects other than the leaf may be introduced. By setting a length threshold, the leaf region can be further screened to improve the accuracy of leaf region recognition.

[0085] S132, determining the extreme value position of the second direction in the blade region as the blade tip position in the blade region.

[0086] In one example, the second direction may be as follows Figure 8 In the Y direction shown, the blade area ( Figure 8 The minimum value of the white area in the Y direction is determined as the tip position of the leaf in the leaf area. Figure 8 From the leaf area, it can be seen that in one case, the minimum value in the Y direction corresponds to multiple points including points D1 and D2. At this time, the point with the minimum value in the Y direction and the maximum value in the X direction can be selected, such as Figure 8 Point D2 is shown.

[0087] In an optional embodiment, in step S140, determining M blade tip positions that meet a preset first validity condition among the P blade tip positions as M first valid blade tip positions includes: determining whether there are M blade tip positions that meet at least one of the following preset conditions among the P blade tip positions:

[0088] 1) The M blade tip positions are all within the effective area;

[0089] 2) M is greater than or equal to a preset threshold value of the number of blade tips;

[0090] 3) The concentration and dispersion of the M blade tip positions meet the preset distribution conditions;

[0091] 4) The pixel distance between the current leaf tip position and the adjacent leaf tip position is not the maximum value or the minimum value in the first pixel distance group; the first pixel distance group includes the pixel distance between every two adjacent leaf tip positions in the P leaf tip positions;

[0092] When it is determined that there are M blade tip positions among the P blade tip positions that satisfy at least one of the above four preset conditions, the M blade tip positions that satisfy at least one of the above preset conditions are determined as the M first valid blade tip positions; when it is determined that there are not M blade tip positions that satisfy at least one of the above preset conditions among the N blade tip positions, the current N blade tip positions are considered invalid, and the image is reacquired.

[0093] The effective area in the embodiment of the present application can be determined according to actual needs or empirical data, such as Fig. 9 Area B shown, Fig. 9 Area A is usually the area where the blade begins to enter the shooting area, and area C is the area where the blade moves out of the shooting area. Therefore, the moving object area determined in areas A and C cannot be guaranteed to be a complete leaf area. Therefore, areas A and C are both considered invalid areas.

[0094] In one example, the range of zone B can be determined based on the tower position in the image. For example, with the line in the Y direction where the tower position is located as the center, the specified pixel distance is extended to the left and right ends. The expanded image area is the valid area B, the area to the left of area B is the invalid area A, and the area to the right of area B is the invalid area C.

[0095] The blade tip number threshold in the embodiment of the present application can be pre-set according to actual needs or empirical values, for example, it can be set to 5; if the number of blade tip positions is too small, the amount of fitting data will be too small when fitting is required later, and the fitting accuracy will be low. By setting the blade tip number threshold, the fitting accuracy can be improved when fitting is required.

[0096] In an optional embodiment, the embodiment of the present application can also determine the first effective blade tip position based on the time interval between two blade tip positions that are temporally adjacent among the P blade tip positions. Determine whether there are M blade tip positions that meet the following conditions among the P blade tip positions: the time interval between each two blade tip positions that are temporally adjacent among the M blade tip positions is less than a preset time interval threshold; if so, the M blade tip positions can be determined as the M first effective blade tip positions. This condition can be used in parallel with the aforementioned conditions 1)-4), or can be used successively with the aforementioned conditions 1)-4).

[0097] The time interval threshold in the embodiment of the present application can be set according to actual needs or empirical values, for example, it can be set to 4 seconds.

[0098] In an optional embodiment, when determining whether the concentration and dispersion of the M blade tip positions meet the preset distribution condition, it includes determining whether the M blade tip positions meet the following conditions:

[0099] 1) The M blade tip positions are distributed on both sides of the tower line in the image, not just on one side of the tower line; Fig. 9 , the tower line may be a line in the Y direction where the tower position D3 is located.

[0100] 2) The pixel distance between the first side inner edge blade tip position and the second side inner edge blade tip position is less than or equal to a preset first blade tip distance threshold; wherein the first side inner edge blade tip position is the first side of the tower line (for example, Fig. 9 The blade tip position closest to the tower line among the blade tip positions on the left side of the tower line (based on the perspective), and the blade tip position on the second inner edge is the blade tip position on the second side of the tower line (for example, based on the perspective Figure 7 The blade tip position closest to the tower line among the blade tip positions on the right side of the tower line (based on the viewing angle).

[0101] 3) The pixel distance between the blade tip position of the first side outer edge and the blade tip position of the second side outer edge is less than a preset second blade tip distance threshold; wherein the blade tip position of the first side outer edge is the first side of the tower line (for example, Fig. 9 The blade tip position closest to the image edge (e.g. Fig. 9 The blade tip position of the second side outer edge is the second side of the tower line (for example, Fig. 9 The blade tip position closest to the image edge (for example Fig. 9 The tip position of the blade is the right edge of the blade.

[0102] When it is determined that the M blade tip positions satisfy the above three conditions, it is determined that the concentration and dispersion of the M blade tip positions satisfy the preset distribution condition.

[0103] When fitting is required later, if the tip position distribution is too concentrated or too dispersed, it is not conducive to accurate fitting. By setting the above distribution conditions, the concentration and dispersion of the M tip positions can be appropriate. When condition 1) is met, it can be considered that the M tip positions are not too concentrated, and when conditions 2) and 3) are met, it can be considered that the M tip positions are not too dispersed.

[0104] The embodiment of the present application does not limit the judgment order of the above-mentioned conditions. The specific judgment order can be determined according to actual needs, and the latter condition is judged on the basis of the former condition. For example, when it is determined that there are M blade tip positions among P blade tip positions in the valid area, the subsequent conditions are judged for the M blade tip positions in the valid area.

[0105] In an optional embodiment, if Fig.10 As shown, in step S150, determining the tower clearance of the wind turbine generator set based on the M first effective blade tip positions includes the following steps S151-S153:

[0106] S151, performing linear fitting on the M first effective blade tip positions to obtain a target blade tip motion trajectory.

[0107] In an optional embodiment, linear fitting is performed on M first effective blade tip positions to obtain a first blade tip motion trajectory; based on the first blade tip motion trajectory, T first effective blade tip positions that meet a preset second effective condition among the M first effective blade tip positions are determined as T second effective blade tip positions; linear fitting is performed on the T second effective blade tip positions, and the obtained second blade tip motion trajectory is determined as the target blade tip motion trajectory. T is a positive integer not greater than M.

[0108] In another optional embodiment, the first blade tip point motion trajectory obtained by performing linear fitting on the M first effective blade tip positions may be used as the target blade tip motion trajectory.

[0109] In an optional embodiment, T first effective blade tip positions satisfying a preset second effective condition among the M first effective blade tip positions are determined as T second effective blade tip positions, including:

[0110] Determine whether there are T first effective blade tip positions among the M first effective blade tip positions that meet at least one of the following preset conditions:

[0111] 1) The pixel distance between each of the T first effective blade tip positions and the first blade tip motion trajectory is not greater than a preset pixel distance threshold;

[0112] 2) Each of the T first effective blade tip positions is not at the end point of the first blade tip motion trajectory;

[0113] 3) T is greater than or equal to the preset blade tip number threshold;

[0114] 4) The pixel distance between each of the T first effective blade tip positions and the adjacent first effective blade tip position is not the maximum value or the minimum value in the second pixel distance group; the second pixel distance group includes the pixel distance between each adjacent two first effective blade tip positions in the M first effective blade tip positions;

[0115] When it is determined that there are T first effective blade tip positions that satisfy at least one of the above four preset conditions among the M first effective blade tip positions, the T first effective blade tip positions that satisfy at least one of the above preset conditions are determined as T second effective blade tip positions.

[0116] The endpoint of the first blade tip motion trajectory in the embodiment of the present application represents a designated area centered on the endpoint of the first blade tip motion trajectory, and the range of the designated area can be determined based on empirical data.

[0117] The first effective blade tip position that is too far away from the first blade tip motion trajectory is also far away from other first effective blade tip positions, which increases the overall dispersion of the first effective blade tip position, is not conducive to accurate calculation, and is an invalid blade tip position. Therefore, by setting the pixel distance threshold in the above condition 1), the invalid blade tip position can be removed.

[0118] The first effective blade tip position at the endpoint of the first blade tip motion trajectory has only one adjacent point, and there is insufficient comparative data to determine the validity of the first effective blade tip position. To reduce the adverse effects of the first effective blade tip position at the endpoint, the first effective blade tip position can be removed by setting the above condition 2).

[0119] The setting of the blade tip number threshold can be referred to the previous content and will not be repeated here.

[0120] S152, determining the pixel distance from the preset tower position to the target blade tip motion trajectory.

[0121] In one example, the target blade tip motion trajectory is as follows: Fig. 9 As shown in the straight line 1001 in FIG. 1 , the expression of the straight line 1001 is y=kx+b, and the tower position is as follows: Fig. 9 As shown in point D3 in the figure, the distance between point D3 and straight line 1001 (as shown in Fig. 9 The distance indicated by the straight line with the double-headed arrow in the figure is the pixel distance from the tower position to the target blade tip motion trajectory.

[0122] S153, determining the physical distance from the tower position to the target blade tip motion trajectory as the tower clearance value according to the pixel distance from the tower position to the target blade tip motion trajectory and the preset correspondence between the pixel distance and the physical distance.

[0123] In one example, the physical distance corresponding to each unit pixel may be set in advance, and then the tower clearance value may be determined in the following manner:

[0124] D=Dx×Dw

[0125] Among them, D is the tower clearance value, Dx is the pixel distance from the tower position to the target blade tip motion trajectory, and Dw is the physical distance corresponding to the unit pixel.

[0126] The tower position in the embodiment of the present application can be predetermined by the following method:

[0127] Determine the actual position of the tower, in one example, Fig.11 As shown, when the blade 1101 is pointing vertically downward, the projection point from the blade tip to the tower 1102 can be used as the actual position of the tower. The actual position of the tower 1102 is usually fixed. When the position of the image acquisition device 1103 is fixed, the shooting range of the image acquisition device 1103 is also fixed, and the pixel position of the tower in the captured image is also fixed. The pixel position of the tower in the captured image can be determined based on the proportional relationship between the real object and the image, which is used as the tower position in the embodiment of the present application.

[0128] In an optional embodiment, the method for determining the tower clearance of a wind turbine generator set provided in the embodiment of the present application can be executed in two independent threads. For example, the aforementioned steps S110 to S130 can be executed in the blade tip identification thread, and the aforementioned steps S140 to S150 can be executed in the clearance determination thread.

[0129] In an optional embodiment, any one of the aforementioned steps S110 - S130 may be executed in a blade tip identification thread, and any one of the aforementioned steps S140 to S150 may be executed in a clearance determination thread.

[0130] In an optional embodiment, the clearance determination thread may include a blade tip screening sub-thread and a clearance calculation sub-thread. In the blade tip screening sub-thread, relevant operations of screening the first effective blade tip position based on the second effective condition as described above may be performed, and in the clearance calculation sub-thread, relevant operations of linear fitting the first effective blade tip position and determining the tower clearance value based on the fitted target blade tip running trajectory may be performed.

[0131] In the embodiments of the present application, different algorithms can be executed in different threads or sub-threads and can operate independently of each other to avoid mutual interference.

[0132] Refer to the following Fig.12 , an optional operation performed in the leaf tip identification thread is introduced, such as Fig.12 As shown, the following steps S1201-S1209 can be executed in the blade tip identification thread:

[0133] S1201, acquiring multiple frames of images of a wind turbine generator set;

[0134] S1202, performing difference calculation between the pixel value of the current frame image and the pixel value of the previous frame image;

[0135] S1203, performing a clearing process on the image obtained after the difference calculation;

[0136] S1204, identifying at least one moving object region in the target region of the cleared image; when the identified moving object region is one, executing S1205; when the identified moving object region is greater than one, executing S1206;

[0137] S1205, determining the moving object region as the leaf region in the current frame image, and then executing S1208;

[0138] S1206, determining whether the number of moving object regions is greater than a preset region number threshold; if so, executing S1201; if not, executing S1207;

[0139] S1207, merging the moving object regions, and determining the obtained merged region as the leaf region in the current frame image;

[0140] S1208, determining whether the length of each blade region in the first direction is less than a preset length threshold; if so, executing S1209; if not, executing S1201;

[0141] S1209: Determine the extreme value position of the second direction in each blade region as the blade tip position in the blade region.

[0142] After the above steps S1201-S1209, P blade tip positions determined based on multiple frames of images can be obtained, and then the clearance determination thread can be triggered based on the P blade tip positions. In one example, the blade tip screening sub-thread in the clearance determination thread can be triggered.

[0143] In an optional embodiment, triggering a clearance determination thread based on P blade tip positions includes:

[0144] Determine whether there is at least one blade tip position in the P blade tip positions located in the target invalid area; the target invalid area is an invalid area where the blade is about to move out of the shooting range of the image acquisition device, for example Fig. 9 Region C is shown.

[0145] Reference Fig. 9 ,Since the blade usually enters the shooting range of the image acquisition device from area A, and moves out of the shooting range from area C after passing area B, when area C stores at least one blade tip position, it can be ensured that the blade completely passes through area B, and there are a larger number of blade tip positions in area B for subsequent calculations.

[0146] In an optional embodiment, in order to more accurately determine whether the blade has completely passed through B, the number of blade tip positions in the target invalid area can be set in the trigger condition. When this number of blade tip positions exists among the P blade tip positions, the clearance determination thread can be triggered.

[0147] Refer to the following Fig.13 , an optional operation performed in the tip screening subthread in the clearance determination thread is introduced, such as Fig.13 As shown, the following steps S1301-S1309 may be executed in the leaf tip screening subthread:

[0148] S1301, determine whether there is a blade tip position in the effective area among the P blade tip positions; if so, execute S1302; if not, execute S1309;

[0149] S1302, determining whether the blade tip position in the effective area is greater than or equal to a preset blade tip quantity threshold; if so, executing S1303; if not, executing S1309;

[0150] S1303, determining whether the blade tip positions in the effective area are distributed on both sides of the tower line in the image; if so, executing S1304; if not, executing S1309;

[0151] S1304, determining whether the pixel distance between the tip position of the first inner edge and the tip position of the second inner edge is less than or equal to a preset first tip distance threshold; if so, executing S1305; if not, executing S1309;

[0152] S1305, determining whether the pixel distance between the tip position of the first outer edge and the tip position of the second outer edge is less than a preset second tip distance threshold; if so, executing S1306; if not, executing S1309;

[0153] S1306, determining whether the pixel distance between each leaf tip position and the adjacent leaf tip position is the maximum value or the minimum value in the first pixel distance group; if so, executing S1307; if not, executing S1308;

[0154] S1307, removing the blade tip position;

[0155] S1308, triggering the headroom calculation sub-thread;

[0156] S1309, reacquire the image.

[0157] Reacquiring the image can be achieved through step S110 or S1201. When executing step S1309, the process can directly jump to step S110 or S201 to re-execute the entire tower clearance determination process.

[0158] After the above steps S1301 - S1309 , M first effective blade tip positions can be screened out from P blade tip positions.

[0159] Refer to the following Fig.14 , an optional operation performed in the headroom calculation subthread in the headroom determination thread is introduced, such as Fig.14 As shown, the following steps S1401-S1409 may be executed in the headroom calculation sub-thread:

[0160] S1401, performing linear fitting on M first effective blade tip positions to obtain a first blade tip motion trajectory;

[0161] S1402, determining whether the pixel distance between each first effective blade tip position and the first blade tip motion trajectory is less than or equal to a preset pixel distance threshold; if so, executing S1403; if not, executing S1405;

[0162] S1403, determining whether each first effective blade tip position is at the end point of the first blade tip motion trajectory; if so, executing S1405; if not, executing S1404;

[0163] S1404, determining whether the pixel distance between each first effective blade tip position and the adjacent first effective blade tip position is the maximum value or the minimum value in the second pixel distance group; if so, executing S1405, if not, executing S1406;

[0164] S1405, removing the first effective blade tip position;

[0165] S1406, determining whether the number T of the current first effective blade tip positions is greater than or equal to a preset blade tip number threshold; if so, executing S1407; if not, executing S1408;

[0166] S1407, performing linear fitting on the T second effective blade tip positions, and determining the obtained second blade tip motion trajectory as the target blade tip motion trajectory;

[0167] S1408, reacquire the image.

[0168] Reacquiring the image may be achieved through step S110 or S1201. When executing step S1408, the process may directly jump to step S110 or S1201 to re-execute the entire tower clearance determination process.

[0169] After the above steps S1401-S1408, T first effective blade tip positions can be screened out from the M blade tip positions, and the tower clearance value is calculated based on the screened T first effective blade tip positions to further improve the calculation accuracy.

[0170] Based on the same inventive concept, the embodiment of the present application provides a device for determining the clearance of a tower of a wind turbine generator set, such as Fig.15 As shown, the device includes: an image acquisition module 1501, a region determination module 1502, a position determination module 1503, a position screening module 1504 and a clearance determination module 1505.

[0171] The image acquisition module 1501 is used to acquire multiple frames of images of the wind turbine generator set.

[0172] The region determination module 1502 is used to determine the blade region of the wind turbine generator set in each frame of image, and obtain N blade regions, where N is a positive integer.

[0173] The position determination module 1503 is used to perform image retrieval on N blade regions respectively to determine P blade tip positions, where P is a positive integer.

[0174] The position screening module 1504 is used to determine M blade tip positions that meet a preset first validity condition among the P blade tip positions as M first valid blade tip positions, where M is a positive integer.

[0175] The clearance determination module 1505 is configured to determine the tower clearance of the wind turbine generator set based on the M first effective blade tip positions.

[0176] In an optional implementation, the region determination module 1502 is specifically configured to perform the following processing on each frame of image:

[0177] The pixel values ​​of the current frame image and the pixel values ​​of the previous frame image are difference calculated, and at least one moving object area in the current frame image is determined according to the difference calculation result; and the leaf area in the current frame image is determined according to the at least one moving object area.

[0178] In an optional embodiment, the region determination module 1502 is specifically used to: when the moving object region includes one, determine the moving object region as the leaf region in the current frame image; when the moving object region includes at least two, merge the moving object regions and determine the obtained merged region as the leaf region in the current frame image.

[0179] In an optional embodiment, the position determination module 1503 is specifically used to: determine whether the length of each blade area in the first direction is less than a preset length value; when it is determined that the length of the blade area in the first direction is less than the preset length value, determine the extreme position of the second direction in the blade area as the tip position in the blade area.

[0180] In an optional implementation, the position screening module 1504 is specifically configured to determine whether there are M blade tip positions among the P blade tip positions that satisfy at least one of the following preset conditions:

[0181] The M blade tip positions are all within the effective area;

[0182] M is greater than or equal to a preset number;

[0183] The concentration and dispersion of the M blade tip positions meet the preset distribution conditions;

[0184] The pixel distance between the current leaf tip position and the adjacent leaf tip position is not the maximum value or the minimum value in the first pixel distance group; the first pixel distance group includes the pixel distance between each two adjacent leaf tip positions in the plurality of leaf tip positions;

[0185] When it is determined that there are M blade tip positions satisfying at least one of the above preset conditions among the P blade tip positions, the M blade tip positions satisfying at least one of the above preset conditions are determined as M first effective blade tip positions.

[0186] In an optional embodiment, the clearance determination module 1505 is specifically used to: perform linear fitting on M first effective blade tip positions to obtain a target blade tip motion trajectory; determine the pixel distance from a preset tower position to the target blade tip motion trajectory; and determine the physical distance from the tower position to the target blade tip motion trajectory as a tower clearance value based on the pixel distance and the correspondence between the preset pixel distance and the physical distance.

[0187] In an optional embodiment, the clearance determination module 1505 is specifically used to: perform linear fitting on M first effective blade tip positions to obtain a first blade tip motion trajectory; based on the first blade tip motion trajectory, determine T first effective blade tip positions among the M first effective blade tip positions that meet a preset second effective condition as T second effective blade tip positions; T is a positive integer not greater than M; perform linear fitting on the T second effective blade tip positions, and determine the obtained second blade tip motion trajectory as the target blade tip motion trajectory.

[0188] In an optional implementation, the clearance determination module 1505 is specifically configured to determine whether there are T first effective blade tip positions among the M first effective blade tip positions that satisfy at least one of the following preset conditions:

[0189] The pixel distance between each first effective blade tip position of the T first effective blade tip positions and the first blade tip motion trajectory is not greater than a preset pixel distance threshold;

[0190] Each of the T first effective blade tip positions is not located at an end point of the first blade tip motion trajectory;

[0191] T is greater than or equal to a preset blade tip number threshold;

[0192] The pixel distance between each of the T first effective blade tip positions and the adjacent first effective blade tip position is not the maximum value or the minimum value in the second pixel distance group; the second pixel distance group includes the pixel distance between each adjacent two first effective blade tip positions in the M first effective blade tip positions;

[0193] When it is determined that there are T first effective blade tip positions satisfying at least one of the above preset conditions among the M first effective blade tip positions, the T first effective blade tip positions satisfying at least one of the above preset conditions are determined as T second effective blade tip positions.

[0194] In an optional embodiment, the image acquisition module 1501, the region determination module 1502 and the position determination module 1503 are used to perform corresponding operations in the blade tip identification thread, and the position screening module 1504 and the clearance determination module 1505 are used to perform corresponding operations in the clearance determination thread.

[0195] In an optional embodiment, the multiple frames of images acquired by the image acquisition module 1501 include: images obtained by an image acquisition device set at a specific position to shoot the wind turbine; the specific position includes: the bottom of the cabin of the wind turbine or the side of the wind turbine and the distance between the wind turbine and the wind turbine is a preset distance.

[0196] Each module in the device for determining the tower clearance of a wind turbine generator set provided in the embodiment of the present application has the function of implementing each step in the method for determining the tower clearance of a wind turbine generator set provided in the embodiment of the present application, and can achieve its corresponding technical effect. For the sake of concise description, it will not be repeated here.

[0197] Based on the same inventive concept, the embodiment of the present application provides a system for determining the clearance of a wind turbine tower, such as Fig.16 As shown, the determination system includes: an image acquisition device 1610 and a wind turbine tower clearance determination device 1620.

[0198] The image acquisition device 1610 is set at a specific position and is in communication connection with the determination device 1620; the specific position includes: the bottom of the cabin of the wind turbine or the side of the wind turbine and the distance between the wind turbine and the wind turbine is a preset distance; the image acquisition device 1610 is used to: shoot the wind turbine to obtain multiple frames of images.

[0199] In such Fig.11 In the example shown, the image acquisition device 1103 is arranged at the bottom of the nacelle 1104. In another example, the position on the side of the wind turbine generator set and at a preset distance from the wind turbine generator set can be multiple external positions, and the blades (including the blade tips) and the tower can be photographed.

[0200] Reference Fig.16 The wind turbine tower clearance determination device 1620 provided in the embodiment of the present application may include: a processor 1621 and a memory 1622 storing computer program instructions.

[0201] Specifically, the processor 1621 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0202] The memory 1622 may include a large capacity memory for data or instructions. By way of example and not limitation, the memory 1622 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. In one example, the memory 1622 may include a removable or non-removable (or fixed) medium, or the memory 1622 is a non-volatile solid-state memory. The memory 1622 may be inside or outside the integrated gateway disaster recovery device.

[0203] In one example, the memory 1622 may include a read-only memory (ROM), a random access memory (RAM), a magnetic disk storage medium device, an optical storage medium device, a flash memory device, an electrical, optical or other physical / tangible memory storage device. Thus, typically, the memory 1622 includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the method according to one aspect of the present application.

[0204] The processor 1621 reads and executes the computer program instructions stored in the memory 1622 to implement any one of the methods for determining the tower clearance of a wind turbine generator set provided in the embodiments of the present application and achieve the corresponding technical effect of the method, which will not be repeated here for the sake of brevity.

[0205] In one example, if Fig.16 As shown, the wind turbine tower clearance determination device 1620 may further include a communication interface 1623 and a bus 1624 , and the processor 1621 , the memory 1622 , and the communication interface 1623 are connected via the bus 1624 and communicate with each other.

[0206] The communication interface 1623 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.

[0207] The bus 1624 includes hardware, software, or both, coupling the components of the wind turbine tower clearance determination device 1620 to each other. For example, but not limitation, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a MicroChannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local (VLB) bus, or other suitable buses or a combination of two or more of these. Where appropriate, the bus 1624 may include one or more buses. Although embodiments of the present application describe and illustrate a particular bus, the present application contemplates any suitable bus or interconnect.

[0208] The determination device 1620 can execute any one of the wind turbine tower clearance determination methods provided in the embodiments of the present application and achieve the corresponding technical effects of the method, which will not be repeated here for the sake of brevity.

[0209] Based on the same inventive concept, an embodiment of the present application further provides a computer storage medium on which computer program instructions are stored; when the computer program instructions are executed by a processor, any one of the methods for determining the wind turbine tower clearance in the above embodiments is implemented.

[0210] It should be clear that the present application is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present application is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present application.

[0211] The functional blocks shown in the above-described block diagram can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), appropriate firmware, plug-in, function card, etc. When implemented in software, the elements of the present application are programs or code segments used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or communication link by a data signal carried in a carrier. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, read-only optical disks, optical disks, hard disks, optical fiber media, radio frequency (Radio Frequency, RF) links, etc. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.

[0212] It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, this application is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the embodiment, or in a different order from the embodiment, or several steps can be performed simultaneously.

[0213] The above reference is according to the method of the embodiment of the present application, the flow chart of the device (system) and the computer program product and / or the block diagram described various aspects of the present application.It should be understood that each square box in the flow chart and / or the block diagram and the combination of each square box in the flow chart and / or the block diagram can be realized by computer program instructions.These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer or other programmable data processing device to produce a machine so that these instructions executed by the processor of the computer or other programmable data processing device enable the realization of the function / action specified in one or more square boxes of the flow chart and / or the block diagram.Such a processor can be but is not limited to a general-purpose processor, a special-purpose processor, a special application processor or a field programmable logic circuit.It can also be understood that each square box in the block diagram and / or the flow chart and the combination of the square boxes in the block diagram and / or the flow chart can also be realized by the dedicated hardware that performs the specified function or action, or can be realized by the combination of dedicated hardware and computer instructions.

[0214] The above is only a specific implementation of the present application. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. It should be understood that the protection scope of the present application is not limited to this. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in this application, and these modifications or replacements should be included in the protection scope of this application.

Claims

1. A method for determining the tower clearance of a wind turbine generator set, characterized in that: include: Acquire multiple frames of images of a wind turbine generator set; Determine the blade region of the wind turbine generator set in each frame of the image to obtain N blade regions, where N is a positive integer; Perform image retrieval on the N leaf regions respectively to determine P leaf tip positions, where P is a positive integer; Determine M blade tip positions that meet a preset first validity condition among the P blade tip positions as M first valid blade tip positions, where M is a positive integer; Determining the tower clearance of the wind turbine generator set based on the M first effective blade tip positions; The determining the tower clearance of the wind turbine generator set based on the M first effective blade tip positions comprises: Performing linear fitting on the M first effective blade tip positions to obtain a target blade tip motion trajectory; Determine the pixel distance from the preset tower position to the target blade tip motion trajectory; According to the pixel distance and the correspondence between the preset pixel distance and the physical distance, the physical distance from the tower position to the target blade tip motion trajectory is determined as the tower clearance value.

2. The method for determining the tower clearance of a wind turbine generator set according to claim 1, characterized in that: Determining the blade region of the wind turbine generator set in each frame of the image to obtain N blade regions includes performing the following processing on each frame of the image: Performing difference calculation on pixel values ​​of a current frame image and pixel values ​​of a previous frame image, and determining at least one moving object region in the current frame image according to the difference calculation result; A leaf region in the current frame image is determined according to the at least one moving object region.

3. The method for determining the tower clearance of a wind turbine generator set according to claim 2, characterized in that: The determining of the leaf region in the current frame image according to the at least one moving object region comprises: When the moving object region includes one, determining the moving object region as a leaf region in the current frame image; When the moving object regions include at least two, the moving object regions are merged, and the obtained merged region is determined as the leaf region in the current frame image.

4. The method for determining the tower clearance of a wind turbine generator set according to claim 1, characterized in that: The performing image retrieval on the N leaf regions respectively to determine the P leaf tip positions includes: Determine whether the length of each of the blade regions in the first direction is less than a preset length threshold; When it is determined that the length of the blade region in the first direction is less than the length threshold, the extreme value position of the second direction in the blade region is determined as the blade tip position in the blade region.

5. The method for determining the tower clearance of a wind turbine generator set according to claim 1, characterized in that: The step of determining M blade tip positions satisfying the preset first validity condition among the P blade tip positions as M first valid blade tip positions includes: Determine whether there are m blade tip point positions among the P blade tip point positions that meet at least one of the following preset conditions: The M blade tip positions are all within the effective area; The M is greater than or equal to a preset blade tip number threshold; The concentration and dispersion of the M blade tip positions meet preset distribution conditions; The pixel distance between the current blade tip position and the adjacent blade tip position is not the maximum value or the minimum value in the first pixel distance group; the first pixel distance group includes the pixel distance between each two adjacent blade tip positions in the plurality of blade tip positions; When it is determined that there are M blade tip positions satisfying at least one of the above preset conditions among the P blade tip positions, the M blade tip positions satisfying at least one of the above preset conditions are determined as the M first effective blade tip positions.

6. The method for determining the tower clearance of a wind turbine generator set according to claim 1, characterized in that: The linear fitting of the M first effective blade tip positions to obtain a target blade tip motion trajectory includes: Perform linear fitting on the M first effective blade tip positions to obtain the first blade tip motion trajectory; According to the first blade tip motion trajectory, T first effective blade tip positions satisfying a preset second effective condition among the M first effective blade tip positions are determined as T second effective blade tip positions, where T is a positive integer not greater than M; Linear fitting is performed on the T second effective blade tip positions, and the obtained second blade tip motion trajectory is determined as the target blade tip motion trajectory.

7. The method for determining the tower clearance of a wind turbine generator set according to claim 6, characterized in that: The step of determining T first effective blade tip positions satisfying a preset second effective condition among the M first effective blade tip positions as T second effective blade tip positions comprises: Determine whether there are T first effective blade tip positions among the M first effective blade tip positions that meet at least one of the following preset conditions: The pixel distance between each of the T first effective blade tip positions and the first blade tip motion trajectory is not greater than a preset pixel distance threshold; Each of the T first effective blade tip positions is not located at an end point of the first blade tip motion trajectory; The T is greater than or equal to a preset blade tip quantity threshold; The pixel distance between each of the T first effective blade tip positions and the adjacent first effective blade tip position is not the maximum value or the minimum value in the second pixel distance group; the second pixel distance group includes the pixel distance between each adjacent two first effective blade tip positions in the M first effective blade tip positions; When it is determined that there are T first effective blade tip positions satisfying at least one of the above preset conditions among the M first effective blade tip positions, the T first effective blade tip positions satisfying at least one of the above preset conditions are determined as T second effective blade tip positions.

8. The method for determining the tower clearance of a wind turbine generator set according to any one of claims 1 to 7, characterized in that: include: The following operations are performed in the blade tip recognition thread: acquiring multiple frame images of the wind turbine generator set; Determine the blade region of the wind turbine generator set in each frame of the image to obtain N blade regions; Performing image retrieval on each of the N leaf regions to determine P leaf tip positions; The following operations are performed in the clearance determination thread: M blade tip positions among the P blade tip positions that meet a preset first validity condition are determined as M first valid blade tip positions; and the tower clearance of the wind turbine generator set is determined based on the M first valid blade tip positions.

9. The method for determining the tower clearance of a wind turbine generator set according to any one of claims 1 to 7, characterized in that: The multiple frames of images include: images obtained by an image acquisition device arranged at a specific position shooting the wind turbine generator set; The specific position includes: a position at the bottom of the nacelle of the wind turbine generator set or at the side of the wind turbine generator set and the distance between the position and the wind turbine generator set is a preset distance.

10. A device for determining the tower clearance of a wind turbine generator set, characterized in that: include: An image acquisition module, used for acquiring multiple frames of images of a wind turbine generator set; A region determination module is used to determine the blade region of the wind turbine generator set in each frame of the image to obtain N blade regions, where N is a positive integer. A position determination module, used for performing image retrieval on the N blade regions respectively to determine P blade tip positions, where P is a positive integer; A position screening module, used for determining M blade tip positions satisfying a preset first validity condition among the P blade tip positions as M first valid blade tip positions, where M is a positive integer; A clearance determination module, configured to determine a tower clearance of the wind turbine generator set based on the M first effective blade tip positions; Among them, the clearance determination module is used to perform linear fitting on the M first effective blade tip positions to obtain a target blade tip motion trajectory; determine the pixel distance from a preset tower position to the target blade tip motion trajectory; and determine the physical distance from the tower position to the target blade tip motion trajectory as the tower clearance value based on the pixel distance and the correspondence between the preset pixel distance and the physical distance.

11. A device for determining the clearance of a wind turbine tower, characterized in that: include: a processor and a memory storing computer program instructions; When the processor executes the computer program instructions, the method for determining the tower clearance of a wind turbine generator set as described in any one of claims 1-9 is implemented.

12. A system for determining the tower clearance of a wind turbine generator set, characterized in that: include: An image acquisition device and a wind turbine tower clearance determination device as claimed in claim 11; The image acquisition device is disposed at a specific position and is in communication connection with the determination device; the specific position includes: a position at the bottom of the nacelle of the wind turbine generator set or a position at the side of the wind turbine generator set and a distance from the wind turbine generator set being a preset distance; The image acquisition device is used to shoot the wind turbine generator set to obtain multiple frames of images.

13. A computer storage medium, characterized in that: Computer program instructions are stored, and when the computer program instructions are executed by a processor, the method for determining the tower clearance of a wind turbine generator set according to any one of claims 1 to 9 is implemented.