Method, device, equipment and medium for quality detection of fan blade

Abstract

This invention discloses a method, device, equipment, and computer-readable storage medium for quality inspection of wind turbine blades. Belonging to the technical field of wind power generation, it differs from the inefficient and inaccurate methods of determining wind turbine blade quality issues through manual inspection or wind power data. By capturing images of the wind turbine blades and converting them into grayscale images for sharpening, a sharpened result image is obtained. Based on this sharpened result image, the presence of obvious quality problems in the wind turbine blades is determined. This allows for rapid, efficient, and accurate identification of blade damage through image processing, solving the technical problem of accurately determining wind turbine blade quality. It enables timely assessment of the wind turbine blade's operating status and accurate identification of problems. Even minor cracks in the wind turbine blades can be detected and the corresponding quality issues identified.

Description

Technical Field

[0001] This invention relates to the technical field of wind power generation, and in particular to a method for quality inspection of wind turbine blades, a device for quality inspection of wind turbine blades, equipment for quality inspection of wind turbine blades, and a computer-readable storage medium. Background Technology

[0002] Wind turbine blades are one of the key components of wind turbines, and their reliability is a crucial factor in ensuring the safe operation of the unit. In recent years, with the vigorous development of wind power generation, the quality inspection of wind turbine blades has become extremely important. Traditional methods for inspecting wind turbine blades include ground tapping for sound identification, visual inspection with binoculars, and manual inspection by rope descent. These methods are all manual, resulting in low efficiency, high human error, and high risk. In today's digital environment, by collecting and analyzing wind power data to determine the operating status of wind turbine blades, it is impossible to accurately pinpoint the problem. For example, even small cracks in a wind turbine blade cannot be detected solely through wind power data. Summary of the Invention

[0003] The main objective of this invention is to provide a method, device, equipment, and computer-readable storage medium for quality inspection of wind turbine blades, aiming to solve the technical problem of accurately determining the quality of wind turbine blades in the prior art.

[0004] To achieve the above objectives, the present invention provides a method for quality inspection of wind turbine blades, comprising the following steps:

[0005] Convert the captured images of the wind turbine blades into grayscale images of the blades;

[0006] The grayscale image of the blade is sharpened to obtain the sharpened result image;

[0007] Based on the sharpened result image, it is determined whether the wind turbine blades have a primary quality problem.

[0008] Optionally, the step of sharpening the grayscale image of the leaf to obtain a sharpened result image includes:

[0009] An 8-direction mask operator is constructed, and the grayscale image of the blade is sharpened based on the 8-direction mask operator to obtain a sharpened result image.

[0010] Optionally, the step of constructing the 8-direction mask operator includes:

[0011] A two-dimensional differential matrix is ​​constructed based on the GL fractional differential equation, and the 8-direction mask operator is constructed based on the two-dimensional differential matrix.

[0012] Optionally, before the step of constructing a two-dimensional differential matrix based on the GL fractional differential equation, the method further includes:

[0013] Determine the image size of the leaf grayscale image, and determine the fractional order of the GL fractional differential equation based on the image size.

[0014] Optionally, after the step of sharpening the grayscale image of the leaf to obtain the sharpened result image, the method further includes:

[0015] The sharpened result image is then subjected to noise reduction processing to obtain the detection result image;

[0016] Based on the detection results, it is determined whether there is a second quality problem with the wind turbine blades.

[0017] Optionally, the step of performing noise reduction processing on the sharpened result image to obtain the detection result image includes:

[0018] Determine the compensation weights for the pixels in the sharpened result image;

[0019] Obtain the first gradient in the X direction and the second gradient in the Y direction;

[0020] The first and second gradients, both assigned the compensation weights, are merged to obtain the detection result image.

[0021] Optionally, the step of determining the compensation weights of the pixels in the sharpened result image includes:

[0022] Obtain the average grayscale value and the grayscale value variance of each pixel in the sharpened result image;

[0023] The pixel compensation weights of the sharpened result image are determined based on the average gray value and the variance of the gray value.

[0024] Optionally, the step of determining the compensation weights of the pixels in the sharpened result image based on the average gray value and the variance of the gray value includes:

[0025] Based on the probability density function of the normal distribution of gray values ​​of each pixel in the sharpened result image, as well as the average gray value and the variance of the gray value, the compensation weight of the pixels in the sharpened result image is determined.

[0026] Optionally, after determining whether the wind turbine blades have a second quality problem based on the detection result image, the method further includes:

[0027] Edge detection is performed on the detection result image, and edge information indicating a second quality problem is output on the detection result image.

[0028] Furthermore, to achieve the above objectives, the present invention also provides a quality inspection device for wind turbine blades, the wind turbine blade quality inspection device comprising:

[0029] The conversion module is used to convert the captured images of the wind turbine blades into grayscale images of the blades.

[0030] The sharpening module is used to sharpen the grayscale image of the blade to obtain a sharpened result image;

[0031] The detection module is used to determine whether the wind turbine blades have a primary quality problem based on the sharpened result image.

[0032] In addition, to achieve the above objectives, the present invention also provides a quality inspection device for wind turbine blades, the wind turbine blade quality inspection device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the wind turbine blade quality inspection method as described above.

[0033] In addition, to achieve the above objectives, the present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the wind turbine blade quality detection method as described above.

[0034] This invention provides a method, device, equipment, and computer-readable storage medium for quality inspection of wind turbine blades. The method involves converting captured images of wind turbine blades into grayscale images; sharpening the grayscale images to obtain a sharpened result image; and determining whether a first quality problem exists in the wind turbine blade based on the sharpened result image.

[0035] Unlike the inefficient and inaccurate methods of manually inspecting or using wind power data to determine wind turbine blade quality issues, this method captures images of wind turbine blades, converts them into grayscale images, and then sharpens them to obtain a sharpened image. Based on this sharpened image, it determines whether there are obvious quality problems with the wind turbine blades. This image processing method quickly, efficiently, and accurately identifies blade damage, solving the technical problem of accurately determining wind turbine blade quality. It can promptly assess the operating status of wind turbine blades and accurately pinpoint the location of problems. Even small cracks in the wind turbine blades can be detected and the corresponding quality issues can be identified. Attached Figure Description

[0036] Figure 1 This is a schematic diagram of the structure of the operating device of the hardware operating environment involved in the embodiments of the present invention;

[0037] Figure 2This is a flowchart illustrating an embodiment of a quality inspection method for wind turbine blades according to the present invention;

[0038] Figure 3 This is a schematic diagram of a sand hole in an embodiment of a quality inspection method for wind turbine blades according to the present invention;

[0039] Figure 4 This is a schematic diagram of edge information of an embodiment of a method for quality inspection of wind turbine blades according to the present invention;

[0040] Figure 5 This is a schematic diagram of an embodiment of a method for quality inspection of wind turbine blades according to the present invention;

[0041] Figure 6 This is a schematic diagram of the GL fractional differential equation of an embodiment of a wind turbine blade quality inspection method of the present invention.

[0042] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0043] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0044] Reference Figure 1 , Figure 1 This is a schematic diagram of the operating device of the hardware operating environment involved in the embodiments of the present invention.

[0045] like Figure 1 As shown, the operating device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to enable communication between these components. The user interface 1003 may include a display screen or an input unit such as a keyboard; optionally, the user interface 1003 may also include a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface). The memory 1005 may be a high-speed random access memory (RAM) or a stable non-volatile memory (NVM), such as a disk drive. The memory 1005 may also optionally be a storage device independent of the aforementioned processor 1001.

[0046] Those skilled in the art will understand that Figure 1 The structure shown does not constitute a limitation on the operating equipment and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0047] like Figure 1 As shown, the memory 1005, which serves as a storage medium, may include an operating system, a data storage module, a network communication module, a user interface module, and computer programs.

[0048] exist Figure 1 In the illustrated operating device, the network interface 1004 is mainly used for data communication with other devices; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and memory 1005 in the operating device of the present invention can be installed in the operating device, and the operating device calls the computer program stored in the memory 1005 through the processor 1001 and performs the following operations:

[0049] Convert the captured images of the wind turbine blades into grayscale images of the blades;

[0050] The grayscale image of the blade is sharpened to obtain the sharpened result image;

[0051] Based on the sharpened result image, it is determined whether the wind turbine blades have a primary quality problem.

[0052] Furthermore, the processor 1001 can call a computer program stored in the memory 1005 and also perform the following operations:

[0053] The step of sharpening the grayscale image of the leaf to obtain the sharpened result image includes:

[0054] An 8-direction mask operator is constructed, and the grayscale image of the blade is sharpened based on the 8-direction mask operator to obtain a sharpened result image.

[0055] Furthermore, the processor 1001 can call a computer program stored in the memory 1005 and also perform the following operations:

[0056] The steps for constructing the 8-direction mask operator include:

[0057] A two-dimensional differential matrix is ​​constructed based on the GL fractional differential equation, and the 8-direction mask operator is constructed based on the two-dimensional differential matrix.

[0058] Furthermore, the processor 1001 can call a computer program stored in the memory 1005 and also perform the following operations:

[0059] Before the step of constructing a two-dimensional differential matrix based on the GL fractional differential equation, the method further includes:

[0060] Determine the image size of the leaf grayscale image, and determine the fractional order of the GL fractional differential equation based on the image size.

[0061] Furthermore, the processor 1001 can call a computer program stored in the memory 1005 and also perform the following operations:

[0062] After the step of sharpening the grayscale image of the leaf to obtain the sharpened result image, the method further includes:

[0063] The sharpened result image is then subjected to noise reduction processing to obtain the detection result image;

[0064] Based on the detection results, it is determined whether there is a second quality problem with the wind turbine blades.

[0065] Furthermore, the processor 1001 can call a computer program stored in the memory 1005 and also perform the following operations:

[0066] The step of performing noise reduction processing on the sharpened result image to obtain the detection result image includes:

[0067] Determine the compensation weights for the pixels in the sharpened result image;

[0068] Obtain the first gradient in the X direction and the second gradient in the Y direction;

[0069] The first and second gradients, both assigned the compensation weights, are merged to obtain the detection result image.

[0070] Furthermore, the processor 1001 can call a computer program stored in the memory 1005 and also perform the following operations:

[0071] The step of determining the pixel compensation weights of the sharpened result image includes:

[0072] Obtain the average grayscale value and the grayscale value variance of each pixel in the sharpened result image;

[0073] The pixel compensation weights of the sharpened result image are determined based on the average gray value and the variance of the gray value.

[0074] Furthermore, the processor 1001 can call a computer program stored in the memory 1005 and also perform the following operations:

[0075] The step of determining the pixel compensation weights of the sharpened result image based on the average gray value and the variance of the gray value includes:

[0076] Based on the probability density function of the normal distribution of gray values ​​of each pixel in the sharpened result image, as well as the average gray value and the variance of the gray value, the compensation weight of the pixels in the sharpened result image is determined.

[0077] Furthermore, the processor 1001 can call a computer program stored in the memory 1005 and also perform the following operations:

[0078] After the step of determining whether the wind turbine blades have a second quality problem based on the detection result image, the method further includes:

[0079] Edge detection is performed on the detection result image, and edge information indicating a second quality problem is output on the detection result image.

[0080] Reference Figure 2 , Figure 2 This is a flowchart illustrating an embodiment of a quality inspection method for wind turbine blades according to the present invention. This embodiment of the present invention provides a quality inspection method for wind turbine blades, which includes the following steps:

[0081] Step S10: Convert the captured images of the wind turbine blades into grayscale images of the blades.

[0082] The wind turbines to be inspected include, but are not limited to, centralized wind power, distributed wind power, and offshore wind power scenarios. Manual inspection of wind turbine blades is inefficient and inherently dangerous. Therefore, in this embodiment, images of the wind turbine blades will be captured using imaging equipment such as drones during inspections, under suitable weather conditions. This avoids the disadvantages of low efficiency, high human error, and high risk associated with manual inspection. Furthermore, existing methods or algorithms generally have limited effectiveness in detecting wind turbine blades of different colors (excluding white). Therefore, in this embodiment, the captured images of the wind turbine blades are converted into grayscale images. Subsequent quality inspection of the wind turbine blades is then performed based on these grayscale images. Thus, the wind turbine blade quality inspection method of this embodiment is applicable to wind turbine blades of various colors, including but not limited to red, green, and blue. Further, the grayscale image of the blades is sharpened. Before obtaining the sharpened result image, the grayscale image is filtered, and then the filtered image is sharpened again to obtain the sharpened result image.

[0083] Step S20: Sharpen the grayscale image of the blade to obtain a sharpened result image.

[0084] Image sharpening compensates for the contours of an image, enhancing its edges and areas of abrupt grayscale changes to make the image clearer. It is divided into spatial domain processing and frequency domain processing. Image sharpening aims to highlight the edges and contours of ground features or certain linear target elements in an image. In this embodiment, the sharpening method for the leaf grayscale image is not limited. After sharpening the leaf grayscale image as the input original image, the sharpened result image is obtained.

[0085] Step S30: Determine whether the wind turbine blades have a first quality problem based on the sharpened result image.

[0086] Reference Figure 3 , Figure 3 This is a schematic diagram of sand holes from an embodiment of a quality inspection method for wind turbine blades according to the present invention. In this embodiment, the blade grayscale image is sharpened to obtain the following... Figure 3 The sharpening result shown is in Figure 3 It can be determined from this that the wind turbine blades have a primary quality problem, namely... Figure 3 The fan blades contain sand holes. Figure 3 (The black dots in the image). Among the appearance defects of the wind turbine blades detected in this embodiment, there are including but not limited to blade cracks, sand holes, paint peeling damage, surface dirt, and shell hollowness. The first quality problem refers to appearance defects that can be directly identified based on the sharpened result image without further image processing.

[0087] In this embodiment, the captured images of the wind turbine blades are converted into grayscale images; the grayscale images are then sharpened to obtain a sharpened result image; based on the sharpened result image, it is determined whether the wind turbine blades have a primary quality problem. Unlike the inefficient and inaccurate methods of determining wind turbine blade quality problems through manual inspection or wind power data, this method captures images of the wind turbine blades, converts them into grayscale images, and then sharpens them to obtain a sharpened result image. Based on this sharpened result image, it determines whether the wind turbine blades have obvious quality problems. This allows for rapid, efficient, and accurate identification of blade damage through image processing, solving the technical problem of accurately determining wind turbine blade quality. It enables timely assessment of the wind turbine blade's operating status and accurate identification of problems. Even small cracks in the wind turbine blades can be detected and identified as corresponding quality issues.

[0088] In another embodiment of the quality inspection method for wind turbine blades provided by the present invention, the step of sharpening the grayscale image of the blade to obtain a sharpened result image includes:

[0089] An 8-direction mask operator is constructed, and the grayscale image of the blade is sharpened based on the 8-direction mask operator to obtain a sharpened result image.

[0090] In this embodiment, an improvement was made by using a 2-direction or 4-direction mask algorithm to construct an 8-direction mask operator. The mask operator is a mask operator with eight directions, including the top, bottom, left, right, upper left, lower left, upper right, and lower right of the planar image. The improved 8-direction mask operator is then used to sharpen the image to obtain the sharpened result image.

[0091] Optionally, the step of constructing the 8-direction mask operator includes:

[0092] A two-dimensional differential matrix is ​​constructed based on the GL fractional differential equation, and the 8-direction mask operator is constructed based on the two-dimensional differential matrix.

[0093] In this embodiment, a two-dimensional differential matrix is ​​constructed using the Grünwald-Letnikov (GL) fractional differential equation, where G represents the GL fractional order, a is the lower bound of the fractional differential, t is the upper bound of the fractional differential, v is the order of the convertible fractional differential, m is the step size on the x-axis of the image coordinate system, and n is the step size on the y-axis. The 8-directional mask operator constructed based on the two-dimensional differential matrix is:

[0094] -V2(-v+1)2 / 48 -V2(-v+1) / 12 -v(-v+1) / 4 -V2(-v+1) / 12 -V2(-v+1)2 / 48 -V2(-v+1) / 12 -v2 / 2 -v -v2 / 2 -V2(-v+1) / 12 -v(-v+1) / 4 -v 8*1 -v -v(-v+1) / 4 -V2(-v+1) / 12 -v2 / 2 -v -v2 / 2 -V2(-v+1) / 12 -V2(-v+1)2 / 48 -V2(-v+1) / 12 -v(-v+1) / 2 -V2(-v+1) / 12 -V2(-v+1)2 / 48

[0095] Optionally, before the step of constructing a two-dimensional differential matrix based on the GL fractional differential equation, the method further includes:

[0096] Determine the image size of the leaf grayscale image, and determine the fractional order of the GL fractional differential equation based on the image size.

[0097] Before constructing a two-dimensional differential matrix based on the GL fractional differential equation, the parameters in the GL fractional differential equation can be adaptively adjusted. The fractional order *v* of the GL fractional differential equation is variable, and can be selected as first, second, or third order based on the image size. For smaller images, the first derivative can be calculated; for larger images, the second or third derivative can be calculated, generally not exceeding the third order. In this embodiment, there is no limitation on the image size for selecting first, second, or third order. The specific criterion for determining whether *v* is a first, second, or third order image size is image sharpness, i.e., image memory size.

[0098] In another embodiment of the quality inspection method for wind turbine blades provided by the present invention, after the step of sharpening the grayscale image of the blade to obtain a sharpened result image, the method further includes:

[0099] The sharpened result image is then subjected to noise reduction processing to obtain the detection result image;

[0100] Based on the detection results, it is determined whether there is a second quality problem with the wind turbine blades.

[0101] The method of analyzing wind power data to determine the operating status of wind turbine blades cannot detect some minute blade cracks. Therefore, in this embodiment, after sharpening the blade grayscale image to obtain a sharpened result image, a detection result image is obtained based on the noise reduction processing of the sharpened result image to determine whether the wind turbine blade has a second quality problem. Here, the second quality problem refers to appearance defects that cannot be directly identified based on the sharpened result image and require further image processing, such as the noise reduction processing in this embodiment, for detection.

[0102] Optionally, the step of performing noise reduction processing on the sharpened result image to obtain the detection result image includes:

[0103] Determine the compensation weights for the pixels in the sharpened result image;

[0104] Obtain the first gradient in the X direction and the second gradient in the Y direction;

[0105] The first and second gradients, both assigned the compensation weights, are merged to obtain the detection result image.

[0106] In this embodiment, the sharpened result image is denoised using an improved Scharr algorithm to obtain the detection result image. Further, a template for the Scharr operator is obtained, which is divided into two directions: the x-direction and the y-direction. The template for the x-direction is shown below:

[0107] -3 0 3 -10 0 10 -3 0 3

[0108] Its template in the Y direction is shown below:

[0109]

[0110]

[0111] Next, the gradients in different directions are calculated, selecting nine pixels at a time, specifically the translated pixels. Eight directions corresponding to the module are selected: from left to right, from top to bottom, and two tilting directions. The convolution formula is shown below: where * denotes convolution.

[0112] The X direction is:

[0113]

[0114] Right now,

[0115]

[0116] The Y direction is:

[0117]

[0118] Right now,

[0119]

[0120] Different results are obtained in different directions. By merging the data from the two directions, a new pixel is obtained:

[0121]

[0122] Among them G X Represents: the result of convolution with the same template size as the original image in the X direction;

[0123] Among them G y This indicates the result of convolution with the same template size as the original image in the Y direction.

[0124] The above is the general noise reduction process of the Scharr algorithm. Since the Scharr value is relatively large, although the edge information can obtain a strong edge strength, some details will be lost. Therefore, the Scharr algorithm is improved in this embodiment. The compensation weight of the pixels in the sharpened result image is determined, and the first gradient in the X direction and the second gradient in the Y direction, which are given compensation weights, are merged to obtain the detection result image.

[0125] Optionally, the step of determining the compensation weights of the pixels in the sharpened result image includes:

[0126] Obtain the average grayscale value and the grayscale value variance of each pixel in the sharpened result image;

[0127] The pixel compensation weights of the sharpened result image are determined based on the average gray value and the variance of the gray value.

[0128] In this embodiment, the variance of the grayscale value of each pixel in the sharpened result image is:

[0129]

[0130] The average grayscale value of each pixel in the sharpened result image is:

[0131]

[0132] Among them, P n Represents the value of a pixel, P1 to P2. n This represents all pixels in the sharpened result image.

[0133] Optionally, the step of determining the compensation weights of the pixels in the sharpened result image based on the average grayscale value and the variance of the grayscale value includes:

[0134] Based on the probability density function of the normal distribution of gray values ​​of each pixel in the sharpened result image, as well as the average gray value and the variance of the gray value, the compensation weight of the pixels in the sharpened result image is determined.

[0135] The merged pixels are weighted to compensate for the loss of pixel detail, as shown below:

[0136]

[0137] The merged pixels are:

[0138]

[0139] Optionally, after the step of determining whether the wind turbine blades have a second quality problem based on the detection result image, the method further includes:

[0140] Edge detection is performed on the detection result image, and edge information indicating a second quality problem is output on the detection result image.

[0141] Reference Figure 4 , Figure 4 This is a schematic diagram of edge information from an embodiment of a wind turbine blade quality inspection method according to the present invention. After determining whether a second quality problem exists in the wind turbine blade based on the inspection result image, edge detection is performed on the inspection result image, and the result is output as shown below. Figure 4 The image shows edge information indicating a second quality problem. Therefore, image sharpening is performed based on an improved GL differential algorithm, and edge detection is performed on the sharpened image based on an improved Scharr algorithm. The combination of these two improved algorithms enhances detail information while ensuring edge information enhancement, thus enabling a clearer diagnosis of quality problems in the wind turbine blades.

[0142] In another embodiment of the wind turbine blade quality inspection method provided by the present invention, in this embodiment, S1: convert the captured image of the wind turbine blade into a blade grayscale image; S2: utilize as... Figure 6The GL fractional differential equation shown is used to construct a two-dimensional differential matrix; S3: Construct an 8-direction mask operator and sharpen the grayscale image; S4: Obtain the templates of the Scharr operator in the x and y directions, calculate the gradients in different directions, obtain the results in different directions, and then merge the data in the two directions to obtain new pixels; Since the Scharr value is relatively large, although the edge information can obtain strong edge strength, some details will be lost. Therefore, the merged pixels are weighted to compensate for the loss of pixel details; S5: Output as shown Figure 3 and Figure 4 The image shown illustrates this. Therefore, image sharpening is performed based on an improved GL differential algorithm, and edge detection is performed on the sharpened image based on an improved Scharr algorithm. The combination of these two improved algorithms enhances detail information while ensuring edge information enhancement, thus enabling a clearer diagnosis of quality problems in the wind turbine blades.

[0143] In addition, refer to Figure 6 This invention also provides a quality inspection device for wind turbine blades, the wind turbine blade quality inspection device comprising:

[0144] The conversion module M1 is used to convert the captured images of the wind turbine blades into grayscale images of the blades.

[0145] The sharpening module M2 is used to sharpen the grayscale image of the blade to obtain a sharpened result image;

[0146] The detection module M3 is used to determine whether the wind turbine blades have a first quality problem based on the sharpened result image.

[0147] Optionally, the sharpening module is also used to construct an 8-direction mask operator and perform sharpening processing on the blade grayscale image based on the 8-direction mask operator to obtain a sharpened result image.

[0148] Optionally, the sharpening module is also used to construct a two-dimensional differential matrix based on the GL fractional differential equation, and to construct the 8-direction mask operator based on the two-dimensional differential matrix.

[0149] Optionally, the sharpening module is also used to determine the image size of the leaf grayscale image before the step of constructing a two-dimensional differential matrix based on the GL fractional differential equation, and to determine the fractional order of the GL fractional differential equation based on the image size.

[0150] Optionally, the wind turbine blade quality inspection device further includes a noise reduction module, used after the step of sharpening the grayscale image of the blade to obtain a sharpened result image.

[0151] The sharpened result image is then subjected to noise reduction processing to obtain the detection result image;

[0152] Based on the detection results, it is determined whether there is a second quality problem with the wind turbine blades.

[0153] Optionally, the noise reduction module is also used to determine the compensation weights of the pixels in the sharpened result image;

[0154] Obtain the first gradient in the X direction and the second gradient in the Y direction;

[0155] The first and second gradients, both assigned the compensation weights, are merged to obtain the detection result image.

[0156] Optionally, the noise reduction module is also used to obtain the average gray value and the gray value variance of each pixel in the sharpened result image;

[0157] The pixel compensation weights of the sharpened result image are determined based on the average gray value and the variance of the gray value.

[0158] Optionally, the noise reduction module is further configured to determine the compensation weight of the pixels in the sharpened result image based on the probability density function of the normal distribution of the gray values ​​of each pixel in the sharpened result image, as well as the average gray value and the variance of the gray value.

[0159] Optionally, the noise reduction module is also used to perform edge detection on the detection result image and output edge information indicating a second quality problem on the detection result image.

[0160] The wind turbine blade quality inspection device provided by this invention adopts the wind turbine blade quality inspection method in the above embodiments, solving the technical problem of difficulty in accurately determining the quality of wind turbine blades in the prior art. Compared with the prior art, the beneficial effects of the wind turbine blade quality inspection device provided by this invention are the same as the beneficial effects of the wind turbine blade quality inspection method provided in the above embodiments, and other technical features in this wind turbine blade quality inspection device are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0161] Furthermore, this embodiment of the invention also provides a quality inspection device for wind turbine blades. The quality inspection device for wind turbine blades 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 quality inspection method for wind turbine blades as described above.

[0162] Furthermore, embodiments of the present invention also provide a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the wind turbine blade quality detection method described above.

[0163] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0164] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0165] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0166] The above are merely preferred embodiments of the present invention and do not limit the scope of the patent. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of the present invention.

Claims

1. A method for quality inspection of wind turbine blades, characterized in that, The method for quality inspection of wind turbine blades includes the following steps: Convert the captured images of the wind turbine blades into grayscale images of the blades; The grayscale image of the blade is sharpened to obtain the sharpened result image; Based on the sharpened result image, determine whether the wind turbine blades have a primary quality problem; Obtain the average grayscale value and the grayscale value variance of each pixel in the sharpened result image; Based on the probability density function of the normal distribution of gray values ​​of each pixel in the sharpened result image, and the average and variance of the gray values, the compensation weights of the pixels in the sharpened result image are determined, wherein the calculation formula for the compensation weights is as follows: , This represents the average value of the grayscale values. This represents the variance of the grayscale values; Obtain the first gradient in the X direction and the second gradient in the Y direction; The first and second gradients, both assigned the compensation weights, are merged to obtain the detection result image, wherein the merged pixels in the detection result image are: , This represents the first gradient. This represents the second gradient; Based on the detection results, it is determined whether there is a second quality problem with the wind turbine blades.

2. The method for quality inspection of wind turbine blades as described in claim 1, characterized in that, The step of sharpening the grayscale image of the leaf to obtain the sharpened result image includes: An 8-direction mask operator is constructed, and the grayscale image of the blade is sharpened based on the 8-direction mask operator to obtain a sharpened result image.

3. The method for quality inspection of wind turbine blades as described in claim 2, characterized in that, The steps for constructing the 8-direction mask operator include: A two-dimensional differential matrix is ​​constructed based on the GL fractional differential equation, and the 8-direction mask operator is constructed based on the two-dimensional differential matrix.

4. The method for quality inspection of wind turbine blades as described in claim 3, characterized in that, Before the step of constructing a two-dimensional differential matrix based on the GL fractional differential equation, the method further includes: Determine the image size of the leaf grayscale image, and determine the fractional order of the GL fractional differential equation based on the image size.

5. The method for quality inspection of wind turbine blades as described in claim 1, characterized in that, After the step of determining whether the wind turbine blades have a second quality problem based on the detection result image, the method further includes: Edge detection is performed on the detection result image, and edge information indicating a second quality problem is output on the detection result image.

6. A quality inspection device for wind turbine blades, characterized in that, The quality inspection device for the wind turbine blades includes: The conversion module is used to convert the captured images of the wind turbine blades into grayscale images of the blades. The sharpening module is used to sharpen the grayscale image of the blade to obtain a sharpened result image; The detection module is used to determine whether the wind turbine blades have a first quality problem based on the sharpened result image; it is also used to obtain the average gray value and the variance of gray values ​​of each pixel in the sharpened result image; based on the probability density function that the gray values ​​of each pixel in the sharpened result image follow a normal distribution, and the average gray value and the variance of gray values, it determines the compensation weight of the pixels in the sharpened result image, wherein the calculation formula of the compensation weight is: , This represents the average value of the grayscale values. The variance of the grayscale value is represented; the first gradient in the X direction and the second gradient in the Y direction are obtained; the first gradient and the second gradient, both assigned the compensation weight, are merged to obtain the detection result image, wherein the merged pixels in the detection result image are: , This represents the first gradient. The second gradient is indicated; based on the detection result image, it is determined whether there is a second quality problem with the wind turbine blades.

7. A quality inspection device for wind turbine blades, characterized in that, The quality inspection device for wind turbine blades includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the quality inspection method for wind turbine blades as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the wind turbine blade quality inspection method as described in any one of claims 1 to 5.

Images