A method and system for determining the hydrophobicity level of composite insulators

Abstract

A method for determining the hydrophobicity level of a composite insulator relates to the technical field of hydrophobicity level determination. A hydrophobicity detection intelligent device is mounted on a multi-rotor unmanned aerial vehicle platform, and water is sprayed on a composite insulator through the hydrophobicity detection intelligent device to obtain a color image of the composite insulator before the water spraying operation and a water spraying image of the composite insulator after the water spraying operation; a gray image of the composite insulator and a gray image of the composite insulator spraying water are obtained, and a water droplet pixel queue is constructed according to the gray image of the composite insulator and the gray image of the composite insulator spraying water; a color image of the composite insulator spraying water is obtained, a similarity criterion is defined, and a coverage area of ​​each water droplet pixel in the color image of the composite insulator spraying water is obtained according to the similarity criterion; the coverage area ratio and the water drop area of ​​the coverage area of ​​each water droplet pixel are obtained, a fuzzy level judgment model is constructed, and the HC level interval of the composite insulator is obtained according to the fuzzy level judgment model.

Description

Technical Field

[0001] The invention relates to the technical field of hydrophobicity grade determination, and in particular to a method and system for determining the hydrophobicity grade of a composite insulator. Background Art

[0002] Transmission lines are numerous and wide-ranging, and the changing natural environment and sudden natural disasters have a huge impact on the safe and stable operation of the lines. In particular, with the continuous increase in voltage levels, the requirements for the safe and reliable operation of ultra-high voltage lines are getting higher and higher. As an important part of the transmission line, the insulation performance of insulators is a very important performance. There are many factors that affect the insulation performance of insulators, and hydrophobicity is a very important one. The hydrophobicity of insulators is related to the safety level of external insulation of the power system.

[0003] In the power system, insulators are mainly used to support transmission lines and form electrical insulation between lines and towers. The surface dirt of glass insulators and porcelain insulators that have been in operation for a long time is increasingly accumulated. In rainy weather, pollution flashover accidents are very likely to occur. In recent years, a series of large-scale pollution flashover accidents have brought great harm to the safe and stable operation of the power system, thus causing huge national economic losses. Compared with traditional glass and porcelain insulators, composite insulators have good hydrophobicity and hydrophobicity migration characteristics, and excellent pollution flashover resistance.

[0004] Composite insulators are widely used in transmission lines, especially ultra-high voltage transmission lines, due to their high strength, light weight, high wet flashover voltage, and convenient operation and maintenance. Hydrophobicity testing is the main means of judging the performance of composite insulators and an important guarantee for ensuring the safe operation of composite insulators. At present, the commonly used method for testing the hydrophobicity of composite insulators is to manually climb the tower to take samples and use the water spray classification method to determine the hydrophobicity level. This method requires manual climbing of the iron tower to spray water close to the surface of the insulator to observe the distribution of water droplets or water belts on the surface of the insulator, and to determine the hydrophobicity level of the composite insulator by visual identification, so as to determine the insulation performance. In terms of sampling composite insulators, this method not only bears the risk of high-altitude operations, but also has low efficiency; in terms of determining the hydrophobicity level, it only relies on visual judgment by the inspectors. Due to the differences in the understanding of the standards by different personnel, the judgment results are obviously subjective and the detection accuracy is not high. Therefore, line operation and maintenance management units urgently need to study a method for determining the hydrophobicity level of composite insulators that can achieve remote operation, online sampling, and automatic determination under operating conditions. Summary of the invention

[0005] In order to solve the above technical problems, the present invention aims to provide a method for determining the hydrophobicity level of a composite insulator, comprising the following steps:

[0006] Step s1: a hydrophobicity detection intelligent device is mounted on a multi-rotor UAV platform, and a water spraying operation is performed on the composite insulator through the hydrophobicity detection intelligent device to obtain a color image of the composite insulator before the water spraying operation and a water spraying image of the composite insulator after the water spraying operation;

[0007] Step s2: obtaining a composite insulator grayscale image and a composite insulator water spraying grayscale image, and constructing a water drop pixel queue according to the composite insulator grayscale image and the composite insulator water spraying grayscale image;

[0008] Step s3: obtaining a composite insulator water spraying color image, defining a similarity criterion, and obtaining the coverage area of ​​each water droplet pixel point in the composite insulator water spraying color image according to the similarity criterion;

[0009] Step s4: Obtain the coverage area ratio and water drop area of ​​the coverage area of ​​each water drop pixel point, construct a fuzzy grade judgment model, and obtain the HC grade range of the composite insulator according to the fuzzy grade judgment model.

[0010] Furthermore, the process of obtaining the composite insulator grayscale image and the composite insulator water spray grayscale image includes:

[0011] A composite insulator color image before the composite insulator to be inspected undergoes water spraying operation and a composite insulator water spraying color image after the composite insulator to be inspected undergoes water spraying operation are obtained, and the composite insulator color image and the composite insulator water spraying color image are denoised and grayscale preprocessed to obtain a composite insulator grayscale image and a composite insulator water spraying grayscale image.

[0012] Furthermore, the process of constructing a water drop pixel queue according to the composite insulator grayscale image and the composite insulator water spraying grayscale image includes:

[0013] The image alignment technology is used to perform pixel alignment on the composite insulator grayscale image after denoising and grayscale preprocessing and the composite insulator water spraying grayscale image, and the grayscale values ​​of the pixels at corresponding positions of the composite insulator grayscale image and the composite insulator water spraying grayscale image are subtracted to obtain a difference value. A binary image is constructed according to the difference value, and the difference value of each pixel in the binary image is obtained. A difference value threshold is set, and pixels in the binary image whose difference value is greater than or equal to the difference value threshold are screened out, and the pixels are marked as water droplet pixels. The water droplet pixels in the binary image are sorted in positive order according to the difference value. The larger the difference value, the higher the ranking of the water droplet pixel, and a water droplet pixel queue is constructed.

[0014] Furthermore, a process of obtaining a composite insulator water spraying color image, defining a similarity criterion, and obtaining a coverage area of ​​each water droplet pixel point in the composite insulator water spraying color image according to the similarity criterion includes:

[0015] Acquire a water spray color image of a composite insulator after denoising preprocessing;

[0016] Obtain the first water drop pixel with the largest difference value in the water drop pixel queue, mark the first water drop pixel as the first water drop pixel, and obtain the brightness, RGB color and texture features of the first water drop pixel and several adjacent pixels adjacent to the first water drop pixel;

[0017] Preset a similarity coefficient threshold, compare the brightness, RGB color and texture features of the first water droplet pixel with the brightness, RGB color and texture features of each adjacent pixel, obtain the similarity coefficient of each adjacent pixel with the first water droplet pixel, and determine whether there are adjacent pixels with a similarity coefficient greater than or equal to the similarity coefficient threshold. If there are adjacent pixels with a similarity coefficient greater than or equal to the similarity coefficient threshold, mark the adjacent pixel as the first water droplet pixel, and continue the regional infection process of the first water droplet pixel;

[0018] If there are no adjacent pixels whose similarity coefficient is greater than or equal to the similarity coefficient threshold, the regional infection process of the first water droplet pixel is terminated.

[0019] Further, the process of continuing the regional infection process of the first water droplet pixel point includes:

[0020] Acquire several adjacent pixel points adjacent to the adjacent pixel point marked as the first water drop pixel point, acquire the brightness, RGB color and texture features of the several adjacent pixel points, perform similarity comparison between the adjacent pixel point marked as the first water drop pixel point and the several adjacent pixel points, acquire the similarity coefficient between each adjacent pixel point and the adjacent pixel point marked as the first water drop pixel point, and determine whether there are adjacent pixel points whose similarity coefficient is greater than or equal to the similarity coefficient threshold. If there are adjacent pixel points whose similarity coefficient is greater than or equal to the similarity coefficient threshold, mark the adjacent pixel point as the first water drop pixel point, and continue the regional infection process of the first pixel point, and so on, until the regional infection process of the first water drop pixel point is terminated, and the coverage area of ​​the first water drop pixel point is acquired.

[0021] Furthermore, the process of obtaining the coverage area of ​​each water droplet pixel includes:

[0022] When the regional infection process of the first water droplet pixel is terminated, the next water droplet pixel in the water droplet pixel queue is obtained, the next water droplet pixel is marked as the second water droplet pixel, and the regional infection process of the second water droplet pixel is performed; when the regional infection process of the second water droplet pixel is terminated, the next-second water droplet pixel in the water droplet pixel queue is obtained, the next-second pixel is marked as the third water droplet pixel, and the regional infection process of the third water droplet pixel is performed, and so on, until the regional infection process of all water droplet pixel points in the water droplet pixel queue is completed, and the coverage area of ​​each water droplet pixel is obtained.

[0023] Furthermore, the process of obtaining the coverage area ratio of the coverage area of ​​each water drop pixel point and the water drop area includes:

[0024] The coverage area ratio of each water drop pixel point and the circularity of the coverage area of ​​each water drop pixel point are obtained, a circularity threshold is preset, and the coverage area of ​​the water drop pixel points whose circularity is greater than or equal to the circularity threshold is marked as a water drop area.

[0025] Furthermore, a fuzzy grade judgment model is constructed, and the process of obtaining the HC grade interval of the composite insulator according to the fuzzy grade judgment model includes:

[0026] Constructing an HC level comparison table, wherein the HC level comparison table includes the coverage areas of different water droplet pixels and the HC level intervals corresponding to the number of water droplet areas;

[0027] A fuzzy grade judgment model is constructed. The input of the fuzzy grade judgment model is the coverage area ratio of the water drop pixel point and the number of water drop areas. The output is the HC grade interval. The membership function and membership threshold of the fuzzy grade judgment model are preset, and the HC grade interval is pre-divided into several fuzzy subsets. The HC grade comparison table is used as the adaptive rule control table of the fuzzy grade judgment model.

[0028] The fuzzy grade judgment model takes the coverage area ratio of the water droplet pixel points corresponding to the composite insulator and the number of water drop areas as evaluation indicators, sets the indicator weights of the evaluation indicators, and obtains the membership matrix of the fuzzy subsets corresponding to different HC grade intervals of the composite insulator through fuzzy comprehensive evaluation;

[0029] The membership of the fuzzy subsets corresponding to different HC level intervals of the composite insulator is obtained according to the membership matrix and the index weight, the HC level interval corresponding to the fuzzy subset with the highest membership is screened out, and the HC level interval is used as the HC level interval of the composite insulator.

[0030] A composite insulator hydrophobicity grade determination system comprises a monitoring center, wherein the monitoring center is communicatively connected with a data acquisition module, a water droplet pixel point queue construction module, a coverage area matching module and an HC grade matching module;

[0031] The data acquisition module is used to carry a hydrophobicity detection intelligent device on a multi-rotor UAV platform, and perform a water spraying operation on the composite insulator through the hydrophobicity detection intelligent device to obtain a color image of the composite insulator before the water spraying operation and a water spraying image of the composite insulator after the water spraying operation;

[0032] The water drop pixel queue construction module is used to obtain the composite insulator grayscale image and the composite insulator water spraying grayscale image, and construct the water drop pixel queue according to the composite insulator grayscale image and the composite insulator water spraying grayscale image;

[0033] The coverage area matching module is used to obtain a composite insulator water spraying color image, define a similarity criterion, and obtain the coverage area of ​​each water droplet pixel point in the composite insulator water spraying color image according to the similarity criterion;

[0034] The HC level matching module is used to obtain the coverage area ratio and the water drop area of ​​the coverage area of ​​each water drop pixel point, build a fuzzy level judgment model, and obtain the HC level interval of the composite insulator according to the fuzzy level judgment model.

[0035] Furthermore, the process of constructing a water drop pixel queue by the water drop pixel queue construction module according to the composite insulator grayscale image and the composite insulator water spraying grayscale image includes:

[0036] The image alignment technology is used to perform pixel alignment on the composite insulator grayscale image after denoising and grayscale preprocessing and the composite insulator water spraying grayscale image, and the grayscale values ​​of the pixels at corresponding positions of the composite insulator grayscale image and the composite insulator water spraying grayscale image are subtracted to obtain a difference value. A binary image is constructed according to the difference value, and the difference value of each pixel in the binary image is obtained. A difference value threshold is set, and pixels in the binary image whose difference value is greater than or equal to the difference value threshold are screened out, and the pixels are marked as water droplet pixels. The water droplet pixels in the binary image are sorted in positive order according to the difference value. The larger the difference value, the higher the ranking of the water droplet pixel, and a water droplet pixel queue is constructed.

[0037] Furthermore, the coverage area matching module obtains the composite insulator water spraying color image, defines a similarity criterion, and obtains the coverage area of ​​each water droplet pixel point in the composite insulator water spraying color image according to the similarity criterion. The process includes:

[0038] Acquire a water spray color image of a composite insulator after denoising preprocessing;

[0039] Obtain the first water drop pixel with the largest difference value in the water drop pixel queue, mark the first water drop pixel as the first water drop pixel, and obtain the brightness, RGB color and texture features of the first water drop pixel and several adjacent pixels adjacent to the first water drop pixel;

[0040] Preset a similarity coefficient threshold, compare the brightness, RGB color and texture features of the first water droplet pixel with the brightness, RGB color and texture features of each adjacent pixel, obtain the similarity coefficient of each adjacent pixel with the first water droplet pixel, and determine whether there are adjacent pixels with a similarity coefficient greater than or equal to the similarity coefficient threshold. If there are adjacent pixels with a similarity coefficient greater than or equal to the similarity coefficient threshold, mark the adjacent pixel as the first water droplet pixel, and continue the regional infection process of the first water droplet pixel;

[0041] If there are no adjacent pixels whose similarity coefficient is greater than or equal to the similarity coefficient threshold, the regional infection process of the first water droplet pixel is terminated.

[0042] Furthermore, the process in which the coverage area matching module continues the area infection process of the first water droplet pixel point includes:

[0043] Acquire several adjacent pixel points adjacent to the adjacent pixel point marked as the first water drop pixel point, acquire the brightness, RGB color and texture features of the several adjacent pixel points, perform similarity comparison between the adjacent pixel point marked as the first water drop pixel point and the several adjacent pixel points, acquire the similarity coefficient between each adjacent pixel point and the adjacent pixel point marked as the first water drop pixel point, and determine whether there are adjacent pixel points whose similarity coefficient is greater than or equal to the similarity coefficient threshold. If there are adjacent pixel points whose similarity coefficient is greater than or equal to the similarity coefficient threshold, mark the adjacent pixel point as the first water drop pixel point, and continue the regional infection process of the first pixel point, and so on, until the regional infection process of the first water drop pixel point is terminated, and the coverage area of ​​the first water drop pixel point is acquired.

[0044] Furthermore, the process of obtaining the coverage area of ​​each water drop pixel by the coverage area matching module includes:

[0045] When the regional infection process of the first water droplet pixel is terminated, the next water droplet pixel in the water droplet pixel queue is obtained, the next water droplet pixel is marked as the second water droplet pixel, and the regional infection process of the second water droplet pixel is performed; when the regional infection process of the second water droplet pixel is terminated, the next-second water droplet pixel in the water droplet pixel queue is obtained, the next-second pixel is marked as the third water droplet pixel, and the regional infection process of the third water droplet pixel is performed, and so on, until the regional infection process of all water droplet pixel points in the water droplet pixel queue is completed, and the coverage area of ​​each water droplet pixel is obtained.

[0046] Furthermore, the process of the HC level matching module obtaining the coverage area ratio of each water drop pixel point and the water drop area includes:

[0047] The coverage area ratio of each water drop pixel point and the circularity of the coverage area of ​​each water drop pixel point are obtained, a circularity threshold is preset, and the coverage area of ​​the water drop pixel points whose circularity is greater than or equal to the circularity threshold is marked as a water drop area.

[0048] Furthermore, the HC level matching module constructs a fuzzy level judgment model, and the process of obtaining the HC level interval of the composite insulator according to the fuzzy level judgment model includes:

[0049] Constructing an HC level comparison table, wherein the HC level comparison table includes the coverage areas of different water droplet pixels and the HC level intervals corresponding to the number of water droplet areas;

[0050] A fuzzy grade judgment model is constructed. The input of the fuzzy grade judgment model is the coverage area ratio of the water drop pixel point and the number of water drop areas. The output is the HC grade interval. The membership function and membership threshold of the fuzzy grade judgment model are preset, and the HC grade interval is pre-divided into several fuzzy subsets. The HC grade comparison table is used as the adaptive rule control table of the fuzzy grade judgment model.

[0051] The fuzzy grade judgment model takes the coverage area ratio of the water droplet pixel points corresponding to the composite insulator and the number of water drop areas as evaluation indicators, sets the indicator weights of the evaluation indicators, and obtains the membership matrix of the fuzzy subsets corresponding to different HC grade intervals of the composite insulator through fuzzy comprehensive evaluation;

[0052] The membership of the fuzzy subsets corresponding to different HC level intervals of the composite insulator is obtained according to the membership matrix and the index weight, the HC level interval corresponding to the fuzzy subset with the highest membership is screened out, and the HC level interval is used as the HC level interval of the composite insulator.

[0053] Compared with the prior art, the beneficial effects of the present invention are as follows: a multi-rotor UAV platform is equipped with an intelligent hydrophobicity detection device, and water is sprayed on a composite insulator through the intelligent hydrophobicity detection device to obtain a water spraying image of the composite insulator after the water spraying operation; the problem that traditional sampling of composite insulators requires manual tower climbing is solved, and the sampling efficiency is improved to a certain extent. Image processing is performed on the water spraying image of the composite insulator to obtain a feature value characterizing the HC value, and a fuzzy grade judgment model is constructed. According to the fuzzy grade judgment model, the HC grade range of the composite insulator is obtained, which avoids the influence of subjective factors on the traditional reliance on visual judgment of the hydrophobicity grade of the composite insulator by detection personnel, realizes efficient automatic judgment, and greatly reduces the error rate of hydrophobicity grade judgment. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 This is a schematic diagram of a method for determining the hydrophobicity level of a composite insulator according to an embodiment of the present application.

[0055] Figure 2 This is a schematic diagram of a composite insulator hydrophobicity grade determination system according to an embodiment of the present application. DETAILED DESCRIPTION

[0056] The following is a clear and complete description of the technical solutions in the embodiments of the present application in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0057] Embodiment 1:

[0058] like Figure 1 As shown, a method for determining the hydrophobicity level of a composite insulator comprises the following steps

[0059] Step s1: a hydrophobicity detection intelligent device is mounted on a multi-rotor UAV platform, and a water spraying operation is performed on the composite insulator through the hydrophobicity detection intelligent device to obtain a color image of the composite insulator before the water spraying operation and a water spraying image of the composite insulator after the water spraying operation;

[0060] Step s2: obtaining a composite insulator grayscale image and a composite insulator water spraying grayscale image, and constructing a water drop pixel queue according to the composite insulator grayscale image and the composite insulator water spraying grayscale image;

[0061] Step s3: obtaining a composite insulator water spraying color image, defining a similarity criterion, and obtaining the coverage area of ​​each water droplet pixel point in the composite insulator water spraying color image according to the similarity criterion;

[0062] Step s4: Obtain the coverage area ratio and water drop area of ​​the coverage area of ​​each water drop pixel point, construct a fuzzy grade judgment model, and obtain the HC grade range of the composite insulator according to the fuzzy grade judgment model.

[0063] Embodiment 2:

[0064] In a specific implementation process, the process of obtaining the composite insulator grayscale image and the composite insulator water spray grayscale image includes:

[0065] A composite insulator color image before the composite insulator to be inspected undergoes water spraying operation and a composite insulator water spraying color image after the composite insulator to be inspected undergoes water spraying operation are obtained, and the composite insulator color image and the composite insulator water spraying color image are denoised and grayscale preprocessed to obtain a composite insulator grayscale image and a composite insulator water spraying grayscale image.

[0066] It should be noted that the image data of vehicle parts taken by the camera terminal may have noise problems. Therefore, in one embodiment of the present invention, after obtaining the image data, it is necessary to perform image preprocessing operations on it to improve the quality of the image data so as to obtain image data for subsequent analysis. Improving image quality through image preprocessing operations is an image processing method well known to those skilled in the art. In the embodiment of the invention, the noise in the image is removed by a Gaussian filtering method, and then the image data is equalized to improve the contrast within the image, and the image data is grayed to convert the color image into a grayscale image. The graying process is usually achieved by averaging the weights of the color channels, wherein denoising and equalization processing, semantic segmentation network and graying are technical means well known to those skilled in the art, and the specific steps are not repeated here. Other image preprocessing methods may also be used in other embodiments of the present invention, and are not limited here.

[0067] Embodiment 3:

[0068] In a specific implementation process, the process of constructing a water drop pixel queue according to the composite insulator grayscale image and the composite insulator water spray grayscale image includes:

[0069] The image alignment technology is used to perform pixel alignment on the composite insulator grayscale image after denoising and grayscale preprocessing and the composite insulator water spraying grayscale image, and the grayscale values ​​of the pixels at corresponding positions of the composite insulator grayscale image and the composite insulator water spraying grayscale image are subtracted to obtain a difference value. A binary image is constructed according to the difference value, and the difference value of each pixel in the binary image is obtained. A difference value threshold is set, and pixels in the binary image whose difference value is greater than or equal to the difference value threshold are screened out, and the pixels are marked as water droplet pixels. The water droplet pixels in the binary image are sorted in positive order according to the difference value. The larger the difference value, the higher the ranking of the water droplet pixel, and a water droplet pixel queue is constructed.

[0070] Embodiment 4:

[0071] In a specific implementation process, a composite insulator water spraying color image is obtained, a similarity criterion is defined, and a process of obtaining a coverage area of ​​each water droplet pixel point in the composite insulator water spraying color image according to the similarity criterion includes:

[0072] Acquire a water spray color image of a composite insulator after denoising preprocessing;

[0073] Obtain the first water drop pixel with the largest difference value in the water drop pixel queue, mark the first water drop pixel as the first water drop pixel, and obtain the brightness, RGB color and texture features of the first water drop pixel and several adjacent pixels adjacent to the first water drop pixel;

[0074] It should be further explained that the present invention uses grayscale co-occurrence matrix technology to generate a texture feature set for obtaining a composite insulator water spraying color image. For the collected composite insulator water spraying color image, the surface image data is used to calculate the grayscale co-occurrence matrix around each pixel point in a sliding window manner. The specific details are as follows: the grayscale level of the surface image data is quantized into discrete grayscale levels, and the grayscale value range is divided into several levels. For example, an 8-bit image can be divided into 16, 32, and 64 levels, and the parameters required to define the grayscale co-occurrence matrix, including distance (d) and direction (θ), are determined according to actual application requirements. The specific steps will not be repeated. Subsequently, based on the calculated grayscale co-occurrence matrix, a series of texture feature values ​​are extracted to construct a texture feature set. The texture features in the texture feature set include but are not limited to:

[0075] Contrast: It is a statistical feature that describes the contrast of pixels at different gray levels in an image. It is a feature that measures the roughness of the image texture and reflects the clarity of the image and the depth of the texture grooves. The deeper the texture grooves, the greater the contrast and the clearer the visual effect. On the contrary, when the contrast is small, the grooves are shallow and the effect is blurred.

[0076] Correlation: describes the degree of correlation between pixels of different gray levels in the image. It measures the similarity of the elements of the spatial grayscale co-occurrence matrix in the row or column direction. Therefore, the size of the correlation value reflects the local grayscale correlation in the image. When the values ​​of the matrix elements are uniformly equal, the correlation value is large. On the contrary, if the matrix pixel values ​​differ greatly, the correlation value is small. If there is horizontal texture in the image, the correlation of the horizontal matrix is ​​greater than the correlation of the rest of the matrices.

[0077] Energy: describes the uniformity of the grayscale distribution of pixels in an image, measures the randomness contained in the image, and shows the complexity of the image. When all values ​​of the co-occurrence matrix are equal or the pixel values ​​show the greatest randomness, the entropy is the largest;

[0078] Homogeneity: describes the similarity of the gray levels of adjacent pixels in the image; reflects the homogeneity of the image texture and measures the local changes in the image texture. A large value indicates that there is a lack of changes between different areas of the image texture and the local texture is very uniform.

[0079] Entropy: describes the uncertainty of image texture, measures the randomness contained in the image, and shows the complexity of the image. When all values ​​of the co-occurrence matrix are equal or the pixel values ​​show the greatest randomness, the entropy is the largest;

[0080] Inverse variance: reflects the clarity and regularity of the texture. The texture is clear and has strong regularity.

[0081] Preset a similarity coefficient threshold, compare the brightness, RGB color and texture features of the first water droplet pixel with the brightness, RGB color and texture features of each adjacent pixel, obtain the similarity coefficient of each adjacent pixel with the first water droplet pixel, and determine whether there are adjacent pixels with a similarity coefficient greater than or equal to the similarity coefficient threshold. If there are adjacent pixels with a similarity coefficient greater than or equal to the similarity coefficient threshold, mark the adjacent pixel as the first water droplet pixel, and continue the regional infection process of the first water droplet pixel;

[0082] If there are no adjacent pixels whose similarity coefficient is greater than or equal to the similarity coefficient threshold, the regional infection process of the first water droplet pixel is terminated.

[0083] Embodiment 5:

[0084] In a specific implementation process, the process of continuing the regional infection process of the first water droplet pixel point includes:

[0085] Acquire several adjacent pixel points adjacent to the adjacent pixel point marked as the first water drop pixel point, acquire the brightness, RGB color and texture features of the several adjacent pixel points, perform similarity comparison between the adjacent pixel point marked as the first water drop pixel point and the several adjacent pixel points, acquire the similarity coefficient between each adjacent pixel point and the adjacent pixel point marked as the first water drop pixel point, and determine whether there are adjacent pixel points whose similarity coefficient is greater than or equal to the similarity coefficient threshold. If there are adjacent pixel points whose similarity coefficient is greater than or equal to the similarity coefficient threshold, mark the adjacent pixel point as the first water drop pixel point, and continue the regional infection process of the first pixel point, and so on, until the regional infection process of the first water drop pixel point is terminated, and the coverage area of ​​the first water drop pixel point is acquired.

[0086] Embodiment 6:

[0087] In the specific implementation process, the process of obtaining the coverage area of ​​each water drop pixel point includes:

[0088] When the regional infection process of the first water droplet pixel is terminated, the next water droplet pixel in the water droplet pixel queue is obtained, the next water droplet pixel is marked as the second water droplet pixel, and the regional infection process of the second water droplet pixel is performed; when the regional infection process of the second water droplet pixel is terminated, the next-second water droplet pixel in the water droplet pixel queue is obtained, the next-second pixel is marked as the third water droplet pixel, and the regional infection process of the third water droplet pixel is performed, and so on, until the regional infection process of all water droplet pixel points in the water droplet pixel queue is completed, and the coverage area of ​​each water droplet pixel is obtained.

[0089] Embodiment 7:

[0090] In the specific implementation process, the process of obtaining the coverage area ratio of each water drop pixel point and the water drop area includes:

[0091] The coverage area ratio of each water drop pixel point and the circularity of the coverage area of ​​each water drop pixel point are obtained, a circularity threshold is preset, and the coverage area of ​​the water drop pixel points whose circularity is greater than or equal to the circularity threshold is marked as a water drop area.

[0092] Embodiment 8:

[0093] In the specific implementation process, the calculation formula for the circularity of the coverage area of ​​the water droplet pixel point is:

[0094] u=4πs / q 2 ;

[0095] Among them, u represents the circularity, s represents the area of ​​the coverage area of ​​the water drop pixel, q represents the circumference of the coverage area of ​​the water drop pixel, and π represents the pi.

[0096] Embodiment 9:

[0097] In the specific implementation process, a fuzzy grade judgment model is constructed, and the process of obtaining the HC grade interval of the composite insulator according to the fuzzy grade judgment model includes:

[0098] Constructing an HC level comparison table, wherein the HC level comparison table includes the coverage areas of different water droplet pixels and the HC level intervals corresponding to the number of water droplet areas;

[0099] A fuzzy grade judgment model is constructed. The input of the fuzzy grade judgment model is the coverage area ratio of the water drop pixel point and the number of water drop areas. The output is the HC grade interval. The membership function and membership threshold of the fuzzy grade judgment model are preset, and the HC grade interval is pre-divided into several fuzzy subsets. The HC grade comparison table is used as the adaptive rule control table of the fuzzy grade judgment model.

[0100] The fuzzy grade judgment model takes the coverage area ratio of the water droplet pixel points corresponding to the composite insulator and the number of water drop areas as evaluation indicators, sets the indicator weights of the evaluation indicators, and obtains the membership matrix of the fuzzy subsets corresponding to different HC grade intervals of the composite insulator through fuzzy comprehensive evaluation;

[0101] The membership of the fuzzy subsets corresponding to different HC level intervals of the composite insulator is obtained according to the membership matrix and the index weight, the HC level interval corresponding to the fuzzy subset with the highest membership is screened out, and the HC level interval is used as the HC level interval of the composite insulator.

[0102] Embodiment 10:

[0103] A composite insulator hydrophobicity grade determination system comprises a monitoring center, wherein the monitoring center is communicatively connected with a data acquisition module, a water droplet pixel point queue construction module, a coverage area matching module and an HC grade matching module;

[0104] The data acquisition module is used to carry a hydrophobicity detection intelligent device on a multi-rotor UAV platform, and perform a water spraying operation on the composite insulator through the hydrophobicity detection intelligent device to obtain a color image of the composite insulator before the water spraying operation and a water spraying image of the composite insulator after the water spraying operation;

[0105] The water drop pixel queue construction module is used to obtain the composite insulator grayscale image and the composite insulator water spraying grayscale image, and construct the water drop pixel queue according to the composite insulator grayscale image and the composite insulator water spraying grayscale image;

[0106] The coverage area matching module is used to obtain a composite insulator water spraying color image, define a similarity criterion, and obtain the coverage area of ​​each water droplet pixel point in the composite insulator water spraying color image according to the similarity criterion;

[0107] The HC level matching module is used to obtain the coverage area ratio and the water drop area of ​​the coverage area of ​​each water drop pixel point, build a fuzzy level judgment model, and obtain the HC level interval of the composite insulator according to the fuzzy level judgment model.

[0108] Embodiment 11:

[0109] In a specific implementation process, the process of constructing a water drop pixel queue by the water drop pixel queue construction module according to the composite insulator grayscale image and the composite insulator water spraying grayscale image includes:

[0110] The image alignment technology is used to perform pixel alignment on the composite insulator grayscale image after denoising and grayscale preprocessing and the composite insulator water spraying grayscale image, and the grayscale values ​​of the pixels at corresponding positions of the composite insulator grayscale image and the composite insulator water spraying grayscale image are subtracted to obtain a difference value. A binary image is constructed according to the difference value, and the difference value of each pixel in the binary image is obtained. A difference value threshold is set, and pixels in the binary image whose difference value is greater than or equal to the difference value threshold are screened out, and the pixels are marked as water droplet pixels. The water droplet pixels in the binary image are sorted in positive order according to the difference value. The larger the difference value, the higher the ranking of the water droplet pixel, and a water droplet pixel queue is constructed.

[0111] Embodiment 12:

[0112] In a specific implementation process, the coverage area matching module obtains a composite insulator water spraying color image, defines a similarity criterion, and obtains the coverage area of ​​each water droplet pixel point in the composite insulator water spraying color image according to the similarity criterion. The process includes:

[0113] Acquire a water spray color image of a composite insulator after denoising preprocessing;

[0114] Obtain the first water drop pixel with the largest difference value in the water drop pixel queue, mark the first water drop pixel as the first water drop pixel, and obtain the brightness, RGB color and texture features of the first water drop pixel and several adjacent pixels adjacent to the first water drop pixel;

[0115] Preset a similarity coefficient threshold, compare the brightness, RGB color and texture features of the first water droplet pixel with the brightness, RGB color and texture features of each adjacent pixel, obtain the similarity coefficient of each adjacent pixel with the first water droplet pixel, and determine whether there are adjacent pixels with a similarity coefficient greater than or equal to the similarity coefficient threshold. If there are adjacent pixels with a similarity coefficient greater than or equal to the similarity coefficient threshold, mark the adjacent pixel as the first water droplet pixel, and continue the regional infection process of the first water droplet pixel;

[0116] If there are no adjacent pixels whose similarity coefficient is greater than or equal to the similarity coefficient threshold, the regional infection process of the first water droplet pixel is terminated.

[0117] Embodiment 13:

[0118] In a specific implementation process, the process in which the coverage area matching module continues to perform the area infection process of the first water droplet pixel point includes:

[0119] Acquire several adjacent pixel points adjacent to the adjacent pixel point marked as the first water drop pixel point, acquire the brightness, RGB color and texture features of the several adjacent pixel points, perform similarity comparison between the adjacent pixel point marked as the first water drop pixel point and the several adjacent pixel points, acquire the similarity coefficient between each adjacent pixel point and the adjacent pixel point marked as the first water drop pixel point, and determine whether there are adjacent pixel points whose similarity coefficient is greater than or equal to the similarity coefficient threshold. If there are adjacent pixel points whose similarity coefficient is greater than or equal to the similarity coefficient threshold, mark the adjacent pixel point as the first water drop pixel point, and continue the regional infection process of the first pixel point, and so on, until the regional infection process of the first water drop pixel point is terminated, and the coverage area of ​​the first water drop pixel point is acquired.

[0120] Embodiment 14:

[0121] In a specific implementation process, the process of the coverage area matching module obtaining the coverage area of ​​each water drop pixel point includes:

[0122] When the regional infection process of the first water droplet pixel is terminated, the next water droplet pixel in the water droplet pixel queue is obtained, the next water droplet pixel is marked as the second water droplet pixel, and the regional infection process of the second water droplet pixel is performed; when the regional infection process of the second water droplet pixel is terminated, the next-second water droplet pixel in the water droplet pixel queue is obtained, the next-second pixel is marked as the third water droplet pixel, and the regional infection process of the third water droplet pixel is performed, and so on, until the regional infection process of all water droplet pixel points in the water droplet pixel queue is completed, and the coverage area of ​​each water droplet pixel is obtained.

[0123] Embodiment 15:

[0124] In a specific implementation process, the process of the HC level matching module obtaining the coverage area ratio of each water drop pixel point and the water drop area includes:

[0125] The coverage area ratio of each water drop pixel point and the circularity of the coverage area of ​​each water drop pixel point are obtained, a circularity threshold is preset, and the coverage area of ​​the water drop pixel points whose circularity is greater than or equal to the circularity threshold is marked as a water drop area.

[0126] Embodiment 16:

[0127] In a specific implementation process, the HC level matching module constructs a fuzzy level judgment model, and the process of obtaining the HC level interval of the composite insulator according to the fuzzy level judgment model includes:

[0128] Constructing an HC level comparison table, wherein the HC level comparison table includes the coverage areas of different water droplet pixels and the HC level intervals corresponding to the number of water droplet areas;

[0129] A fuzzy grade judgment model is constructed. The input of the fuzzy grade judgment model is the coverage area ratio of the water drop pixel point and the number of water drop areas. The output is the HC grade interval. The membership function and membership threshold of the fuzzy grade judgment model are preset, and the HC grade interval is pre-divided into several fuzzy subsets. The HC grade comparison table is used as the adaptive rule control table of the fuzzy grade judgment model.

[0130] The fuzzy grade judgment model takes the coverage area ratio of the water droplet pixel points corresponding to the composite insulator and the number of water drop areas as evaluation indicators, sets the indicator weights of the evaluation indicators, and obtains the membership matrix of the fuzzy subsets corresponding to different HC grade intervals of the composite insulator through fuzzy comprehensive evaluation;

[0131] The membership of the fuzzy subsets corresponding to different HC level intervals of the composite insulator is obtained according to the membership matrix and the index weight, the HC level interval corresponding to the fuzzy subset with the highest membership is screened out, and the HC level interval is used as the HC level interval of the composite insulator.

[0132] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A method for determining the hydrophobicity level of a composite insulator, characterized in that: The following steps are included Step s1: a hydrophobicity detection intelligent device is mounted on a multi-rotor UAV platform, and a water spraying operation is performed on the composite insulator through the hydrophobicity detection intelligent device to obtain a color image of the composite insulator before the water spraying operation and a water spraying image of the composite insulator after the water spraying operation; Step s2: obtaining a composite insulator grayscale image and a composite insulator water spraying grayscale image, and constructing a water drop pixel queue according to the composite insulator grayscale image and the composite insulator water spraying grayscale image; Step s3: obtaining a composite insulator water spraying color image, defining a similarity criterion, and obtaining the coverage area of ​​each water droplet pixel point in the composite insulator water spraying color image according to the similarity criterion; Step s4: obtaining the coverage area ratio and the water drop area of ​​the coverage area of ​​each water drop pixel point, constructing a fuzzy grade judgment model, and obtaining the HC grade interval of the composite insulator according to the fuzzy grade judgment model; The process of constructing a water drop pixel queue based on the composite insulator grayscale image and the composite insulator water spray grayscale image includes: Use image alignment technology to perform pixel alignment on the composite insulator grayscale image after denoising and grayscale preprocessing and the composite insulator water spray grayscale image, subtract the grayscale values ​​of the pixels at corresponding positions of the composite insulator grayscale image and the composite insulator water spray grayscale image to obtain a difference value, construct a binary image according to the difference value, obtain the difference value of each pixel in the binary image, set a difference value threshold, filter out the pixels in the binary image whose difference value is greater than or equal to the difference value threshold, mark the pixels as water droplet pixels, and sort the water droplet pixels in the binary image in positive order according to the difference value, the larger the difference value, the higher the ranking of the water droplet pixel, and construct a water droplet pixel queue; The process of obtaining a composite insulator water spraying color image, defining a similarity criterion, and obtaining the coverage area of ​​each water droplet pixel point in the composite insulator water spraying color image according to the similarity criterion includes: Acquire a water spray color image of a composite insulator after denoising preprocessing; Obtain the first water drop pixel with the largest difference value in the water drop pixel queue, mark the first water drop pixel as the first water drop pixel, and obtain the brightness, RGB color and texture features of the first water drop pixel and several adjacent pixels adjacent to the first water drop pixel; Preset a similarity coefficient threshold, compare the brightness, RGB color and texture features of the first water droplet pixel with the brightness, RGB color and texture features of each adjacent pixel, obtain the similarity coefficient of each adjacent pixel with the first water droplet pixel, and determine whether there are adjacent pixels with a similarity coefficient greater than or equal to the similarity coefficient threshold. If there are adjacent pixels with a similarity coefficient greater than or equal to the similarity coefficient threshold, mark the adjacent pixel as the first water droplet pixel, and continue the regional infection process of the first water droplet pixel; If there are no adjacent pixels whose similarity coefficient is greater than or equal to the similarity coefficient threshold, the regional infection process of the first water droplet pixel is terminated; The process of continuing the regional infection process of the first water droplet pixel point includes: Acquire several adjacent pixel points adjacent to the adjacent pixel point marked as the first water drop pixel point, acquire the brightness, RGB color and texture features of the several adjacent pixel points, perform similarity comparison between the adjacent pixel point marked as the first water drop pixel point and the several adjacent pixel points, acquire the similarity coefficient between each adjacent pixel point and the adjacent pixel point marked as the first water drop pixel point, determine whether there are adjacent pixel points whose similarity coefficient is greater than or equal to the similarity coefficient threshold, if there are adjacent pixel points whose similarity coefficient is greater than or equal to the similarity coefficient threshold, mark the adjacent pixel point as the first water drop pixel point, and continue the regional infection process of the first pixel point, and so on, until the regional infection process of the first water drop pixel point is terminated, and acquire the coverage area of ​​the first water drop pixel point; The process of obtaining the coverage area of ​​each water droplet pixel includes: When the regional infection process of the first water droplet pixel is terminated, the next water droplet pixel in the water droplet pixel queue is obtained, the next water droplet pixel is marked as the second water droplet pixel, and the regional infection process of the second water droplet pixel is performed; when the regional infection process of the second water droplet pixel is terminated, the next-second water droplet pixel in the water droplet pixel queue is obtained, the next-second pixel is marked as the third water droplet pixel, and the regional infection process of the third water droplet pixel is performed, and so on, until the regional infection process of all water droplet pixel points in the water droplet pixel queue is completed, and the coverage area of ​​each water droplet pixel is obtained.

2. A method for determining the hydrophobicity level of a composite insulator according to claim 1, characterized in that: The process of obtaining the composite insulator grayscale image and the composite insulator water spray grayscale image includes: A composite insulator color image before the composite insulator to be inspected undergoes water spraying operation and a composite insulator water spraying color image after the composite insulator to be inspected undergoes water spraying operation are obtained, and the composite insulator color image and the composite insulator water spraying color image are denoised and grayscale preprocessed to obtain a composite insulator grayscale image and a composite insulator water spraying grayscale image.

3. A method for determining the hydrophobicity level of a composite insulator according to claim 2, characterized in that: The process of obtaining the coverage area ratio of each water drop pixel point and the water drop area includes: The coverage area ratio of each water drop pixel point and the circularity of the coverage area of ​​each water drop pixel point are obtained, a circularity threshold is preset, and the coverage area of ​​the water drop pixel points whose circularity is greater than or equal to the circularity threshold is marked as a water drop area.

4. A method for determining the hydrophobicity level of a composite insulator according to claim 3, characterized in that: The process of constructing a fuzzy grade judgment model and obtaining the HC grade interval of the composite insulator according to the fuzzy grade judgment model includes: An HC level comparison table is constructed, wherein the HC level comparison table includes the coverage areas of different water droplet pixels and the HC level intervals corresponding to the number of water droplet areas.

5. A method for determining the hydrophobicity level of a composite insulator according to claim 4, characterized in that: Also includes: A fuzzy grade judgment model is constructed. The input of the fuzzy grade judgment model is the coverage area ratio of the water droplet pixel points and the number of water droplet areas. The output is the HC grade interval. The membership function and membership threshold of the fuzzy grade judgment model are preset, and the HC grade interval is pre-divided into several fuzzy subsets. The HC grade comparison table is used as the adaptive rule control table of the fuzzy grade judgment model.

6. A method for determining the hydrophobicity level of a composite insulator according to claim 5, characterized in that: Also includes: The fuzzy grade judgment model takes the coverage area ratio of the water droplet pixel points corresponding to the composite insulator and the number of water drop areas as evaluation indicators, sets the indicator weights of the evaluation indicators, and obtains the membership matrix of the fuzzy subsets corresponding to the composite insulator for different HC grade intervals through fuzzy comprehensive evaluation.

7. A method for determining the hydrophobicity level of a composite insulator according to claim 5, characterized in that: Also includes: The membership of the fuzzy subsets corresponding to different HC level intervals of the composite insulator is obtained according to the membership matrix and the index weight, the HC level interval corresponding to the fuzzy subset with the highest membership is screened out, and the HC level interval is used as the HC level interval of the composite insulator.

8. A composite insulator hydrophobicity grade determination system, characterized in that: It includes a monitoring center, which is communicatively connected with a data acquisition module, a water droplet pixel point queue construction module, a coverage area matching module and an HC level matching module; The data acquisition module is used to carry a hydrophobicity detection intelligent device on a multi-rotor UAV platform, and perform a water spraying operation on the composite insulator through the hydrophobicity detection intelligent device to obtain a color image of the composite insulator before the water spraying operation and a water spraying image of the composite insulator after the water spraying operation; The water drop pixel queue construction module is used to obtain the composite insulator grayscale image and the composite insulator water spraying grayscale image, and construct the water drop pixel queue according to the composite insulator grayscale image and the composite insulator water spraying grayscale image; The coverage area matching module is used to obtain a composite insulator water spraying color image, define a similarity criterion, and obtain the coverage area of ​​each water droplet pixel point in the composite insulator water spraying color image according to the similarity criterion; The HC level matching module is used to obtain the coverage area ratio and the water drop area of ​​the coverage area of ​​each water drop pixel point, build a fuzzy level judgment model, and obtain the HC level interval of the composite insulator according to the fuzzy level judgment model; The process of constructing a water drop pixel queue by the water drop pixel queue construction module according to the composite insulator grayscale image and the composite insulator water spraying grayscale image comprises: Use image alignment technology to perform pixel alignment on the composite insulator grayscale image after denoising and grayscale preprocessing and the composite insulator water spray grayscale image, subtract the grayscale values ​​of the pixels at corresponding positions of the composite insulator grayscale image and the composite insulator water spray grayscale image to obtain a difference value, construct a binary image according to the difference value, obtain the difference value of each pixel in the binary image, set a difference value threshold, filter out the pixels in the binary image whose difference value is greater than or equal to the difference value threshold, mark the pixels as water droplet pixels, and sort the water droplet pixels in the binary image in positive order according to the difference value, the larger the difference value, the higher the ranking of the water droplet pixel, and construct a water droplet pixel queue; The coverage area matching module obtains the composite insulator water spraying color image, defines a similarity criterion, and obtains the coverage area of ​​each water droplet pixel point in the composite insulator water spraying color image according to the similarity criterion. The process includes: Acquire a water spray color image of a composite insulator after denoising preprocessing; Obtain the first water drop pixel with the largest difference value in the water drop pixel queue, mark the first water drop pixel as the first water drop pixel, and obtain the brightness, RGB color and texture features of the first water drop pixel and several adjacent pixels adjacent to the first water drop pixel; Preset a similarity coefficient threshold, compare the brightness, RGB color and texture features of the first water droplet pixel with the brightness, RGB color and texture features of each adjacent pixel, obtain the similarity coefficient of each adjacent pixel with the first water droplet pixel, and determine whether there are adjacent pixels with a similarity coefficient greater than or equal to the similarity coefficient threshold. If there are adjacent pixels with a similarity coefficient greater than or equal to the similarity coefficient threshold, mark the adjacent pixel as the first water droplet pixel, and continue the regional infection process of the first water droplet pixel; If there are no adjacent pixels whose similarity coefficient is greater than or equal to the similarity coefficient threshold, the regional infection process of the first water droplet pixel is terminated; The process in which the coverage area matching module continues to perform the area infection process of the first water droplet pixel point includes: Acquire several adjacent pixel points adjacent to the adjacent pixel point marked as the first water drop pixel point, acquire the brightness, RGB color and texture features of the several adjacent pixel points, perform similarity comparison between the adjacent pixel point marked as the first water drop pixel point and the several adjacent pixel points, acquire the similarity coefficient between each adjacent pixel point and the adjacent pixel point marked as the first water drop pixel point, determine whether there are adjacent pixel points whose similarity coefficient is greater than or equal to the similarity coefficient threshold, if there are adjacent pixel points whose similarity coefficient is greater than or equal to the similarity coefficient threshold, mark the adjacent pixel point as the first water drop pixel point, and continue the regional infection process of the first pixel point, and so on, until the regional infection process of the first water drop pixel point is terminated, and acquire the coverage area of ​​the first water drop pixel point; The process of obtaining the coverage area of ​​each water drop pixel by the coverage area matching module includes: When the regional infection process of the first water droplet pixel is terminated, the next water droplet pixel in the water droplet pixel queue is obtained, the next water droplet pixel is marked as the second water droplet pixel, and the regional infection process of the second water droplet pixel is performed; when the regional infection process of the second water droplet pixel is terminated, the next-second water droplet pixel in the water droplet pixel queue is obtained, the next-second pixel is marked as the third water droplet pixel, and the regional infection process of the third water droplet pixel is performed, and so on, until the regional infection process of all water droplet pixel points in the water droplet pixel queue is completed, and the coverage area of ​​each water droplet pixel is obtained.

9. A method for determining the hydrophobicity level of a composite insulator according to claim 8, characterized in that: The process of obtaining the composite insulator grayscale image and the composite insulator water spray grayscale image includes: A composite insulator color image before the composite insulator to be inspected undergoes water spraying operation and a composite insulator water spraying color image after the composite insulator to be inspected undergoes water spraying operation are obtained, and the composite insulator color image and the composite insulator water spraying color image are denoised and grayscale preprocessed to obtain a composite insulator grayscale image and a composite insulator water spraying grayscale image.

10. A composite insulator hydrophobicity grade determination system according to claim 9, characterized in that: The process of the HC level matching module obtaining the coverage area ratio of each water drop pixel point and the water drop area includes: The coverage area ratio of each water drop pixel point and the circularity of the coverage area of ​​each water drop pixel point are obtained, a circularity threshold is preset, and the coverage area of ​​the water drop pixel points whose circularity is greater than or equal to the circularity threshold is marked as a water drop area.

11. A composite insulator hydrophobicity grade determination system according to claim 10, characterized in that: The HC level matching module constructs a fuzzy level judgment model, and the process of obtaining the HC level interval of the composite insulator according to the fuzzy level judgment model includes: An HC level comparison table is constructed, wherein the HC level comparison table includes the coverage areas of different water droplet pixels and the HC level intervals corresponding to the number of water droplet areas.

12. A composite insulator hydrophobicity grade determination system according to claim 11, characterized in that: Also includes: A fuzzy grade judgment model is constructed. The input of the fuzzy grade judgment model is the coverage area ratio of the water droplet pixel points and the number of water droplet areas. The output is the HC grade interval. The membership function and membership threshold of the fuzzy grade judgment model are preset, and the HC grade interval is pre-divided into several fuzzy subsets. The HC grade comparison table is used as the adaptive rule control table of the fuzzy grade judgment model.

13. A composite insulator hydrophobicity grade determination system according to claim 12, characterized in that: Also includes: The fuzzy grade judgment model takes the coverage area ratio of the water droplet pixel points corresponding to the composite insulator and the number of water drop areas as evaluation indicators, sets the indicator weights of the evaluation indicators, and obtains the membership matrix of the fuzzy subsets corresponding to the composite insulator for different HC grade intervals through fuzzy comprehensive evaluation.

14. A composite insulator hydrophobicity grade determination system according to claim 13, characterized in that: Also includes: The membership of the fuzzy subsets corresponding to different HC level intervals of the composite insulator is obtained according to the membership matrix and the index weight, the HC level interval corresponding to the fuzzy subset with the highest membership is screened out, and the HC level interval is used as the HC level interval of the composite insulator.

Images