CN111008967B - A Method for Identifying Defects in RTV Coating of Insulators - Google Patents

Abstract

The application belongs to the technical field of image processing, and particularly relates to an insulator RTV coating defect identification method. The existing insulator RTV coating defect identification method needs to be detected on site, and is complex to operate. The application provides an insulator RTV coating defect identification method, which comprises the following steps: 1) Acquiring an image containing defects of the RTV coating of the insulator; 2) Preprocessing the image containing the insulator RTV coating defects; so as to improve the accuracy of the subsequent segmentation of the insulator image and the calculation of the falling area ratio of the RTV coating. 3) And dividing the preprocessed insulator image into a binarized image, and dividing an insulator region and an RTV coating defect region. According to the insulator RTV coating defect identification method, the insulator image is segmented, and the normal insulator and the RTV coating falling-off area can be obtained.

Description

A Defect Identification Method for Insulator RTV Coating

technical field

The application belongs to the technical field of image processing, and in particular relates to a method for identifying defects in an insulator RTV coating.

Background technique

Room Temperature Silicone Rubber (Room Temperature Silicone Rubber) is referred to as RTV anti-pollution flashover coating. The natural accumulation of pollution on the surface of electric ceramics for outdoor equipment in power systems is inevitable. With the development of my country's national economy, air pollution is becoming more and more serious, and pollution sources in various places are increasing , the range of salt density value increases year by year. On the contrary, the configuration of porcelain insulation is generally low, the number of lines is increasing year by year, and there are few anti-pollution flashover professionals. In addition, considering factors such as overvoltage operation, uneasy climate changes, and bird damage, the possibility of pollution flashover is increasing.

Under severe weather conditions (such as: fog, dew, drizzle, etc.), flashovers will occur along the wet insulator surface, resulting in power system pollution flashover accidents. Pollution flashover threatens the safe and stable operation of the power system. If it is mild, it will affect local power supply. If it is serious, it will affect the power grid, and even cause the entire power grid to crack. The impact of pollution flashover on the power supply system has caused huge losses to the national economy.

By identifying the RTV coating defects of insulators, the severity of RTV coating defects of insulators can be effectively characterized, and a theoretical basis is provided for whether to recoat RTV coatings or replace insulators in the next step. However, the existing insulator RTV coating defect identification method requires on-site detection and operation is relatively complicated.

Contents of the invention

1. Technical problems to be solved

Based on the identification of insulator RTV coating defects, the severity of insulator RTV coating defects can be effectively characterized, and a theoretical basis is provided for whether to recoat RTV coatings or replace insulators in the next step. However, the existing insulator RTV coating defect identification method requires on-site detection and operation is relatively complicated. This application provides a method for insulator RTV coating defect identification.

2. Technical solution

In order to achieve the above purpose, the present application provides a method for identifying defects in an insulator RTV coating, the method comprising the following steps:

1) Obtain images containing insulator RTV coating defects;

2) Preprocessing the image containing insulator RTV coating defects, so as to improve the accuracy of subsequent insulator image segmentation and calculation of the ratio of RTV coating shedding area;

3) Segment the preprocessed insulator image into a binary image, and segment the insulator region and the RTV coating defect region.

Another embodiment of the present application is: the image in the step 1) is from an insulator image of an insulator with RTV coating defect taken by aerial photography at close range on site or an insulator image of an insulator with RTV coating defect taken by a laboratory.

Another embodiment of the present application is: the insulator image includes insulator model information. There is no restriction on the color of the insulator body.

Another embodiment of the present application is: the preprocessing in the step 2) includes image grayscale and image median filtering to remove noise, improve image quality, and improve the accuracy of the insulator image segmentation. Subsequently, the proportion of the insulator RTV coating shedding area can be calculated by counting the number of pixels in the image.

Another embodiment of the present application is: the conversion formula of the image grayscale is:

Y＝0.2989*R+0.5870*G+0.1140*B

RGB is the three components in the color image, R represents the red component, G represents the green component, and B represents the blue component. Y is the gray value of the grayscale image.

Another embodiment of the present application is: in the step 3), the preprocessed insulator image is segmented into a binarized image by using the maximum inter-class variance method, and the insulator region and the RTV coating defect region are segmented.

Another embodiment of the present application is: the maximum inter-class variance method includes traversing the value space of image grayscale, calculating the inter-class variance corresponding to each threshold, and making the inter-class variance the largest, which is the optimal threshold T; The threshold T binarizes the gradient values of the image.

Another embodiment of the present application is: further including counting the number of black and white pixels of the binarized image, and calculating the ratio of the insulator RTV coating shedding area.

Another embodiment of the present application is: the ratio of the peeling area of the RTV coating of the insulator is the ratio of the front or back of the insulator to the insulating area of the insulator.

Since there is a steel cap part in the middle area of the insulator, this part does not have insulation performance. The ultimate purpose of this patent is to calculate the proportion of the RTV coating peeling off area of the insulator. This proportion refers to the proportion of the front or back of the insulator to the insulator insulation area, excluding In the area of the steel cap part in the middle of the insulator, this calculation method can effectively characterize the severity of the RTV coating defect of the insulator.

Another embodiment of the present application is: the calculation includes the following steps:

a. Calculate the center coordinates (x, y) of the insulator body in the binary image, x=(max(x)+min(x))/2, y=(max(y)+min(y))/2 ;

b. Calculate the insulator radius R=(max(x)-min(x))/2 in the binarized image;

c. Calculate the steel cap radius R ₁ =R×d;

d. Use the fill function to fill the area of the steel cap with black, count the number of black pixels in the picture, and record it as A;

e. Calculate the area of the steel cap area as S=πR ₁ ² ;

f. Delete the peeling area of the insulator RTV coating in the image through the filter function, so that the entire insulator area is black, count the number of black pixels in the picture, and record it as B;

g. Calculate the proportion of insulator RTV coating shedding area Ratio=(B-A)/(B-S)×100%.

Among them, the coordinates of the center of the insulator body are (x, y), the radius of the insulator is R, and the percentage of the diameter of the steel cap to the diameter of the insulator is d.

3. Beneficial effect

Compared with the prior art, the beneficial effects of a method for identifying defects in an insulator RTV coating provided by this application are:

An insulator RTV coating defect recognition method provided in the present application can segment an insulator image to obtain normal insulators and RTV coating shedding areas.

An insulator RTV coating defect recognition method provided by this application collects images containing insulator RTV coating defects, processes and recognizes the images, and obtains insulator RTV coating defects and their occupied areas. The operation is simple, and there is no need to go to the site The identification of insulator RTV coating defects can be realized, and the severity of insulator RTV coating defects can be represented by the proportion of insulator RTV coating defects.

Description of drawings

Fig. 1 is the principle schematic diagram of a kind of insulator RTV coating defect identification method of the present application;

Fig. 2 is a schematic diagram of the specific implementation results of the present application.

Detailed ways

Hereinafter, specific embodiments of the present application will be described in detail with reference to the accompanying drawings. According to these detailed descriptions, those skilled in the art can clearly understand the present application and can implement the present application. Without departing from the principle of the present application, the features in different embodiments can be combined to obtain new implementations, or some features in certain embodiments can be replaced to obtain other preferred implementations.

The OTSU algorithm is also called the maximum inter-class difference method, sometimes called the Otsu algorithm. It was proposed by Otsu in 1979 and is considered to be the best algorithm for threshold selection in image segmentation. It is simple to calculate and is not affected by image brightness and contrast. Therefore, it has been widely used in digital image processing. It divides the image into two parts, the background and the foreground, according to the grayscale characteristics of the image. Variance is a measure of the uniformity of the gray distribution. The larger the inter-class variance between the background and the foreground, the greater the difference between the two parts that make up the image. When part of the foreground is wrongly divided into background or part of the background is wrongly divided into foreground, it will resulting in a smaller difference between the two parts. Therefore, the split that maximizes the between-class variance means the smallest probability of misclassification.

Referring to Figures 1-2, the present application provides a method for identifying defects in an insulator RTV coating, the method includes the following steps:

1) Obtain images containing insulator RTV coating defects;

2) Preprocessing the image containing the insulator RTV coating defect;

3) Segment the preprocessed insulator image into a binary image, and segment the insulator region and the RTV coating defect region.

Further, the image in the step 1) is from an insulator image containing RTV coating defects captured by aerial photography at close range on site or an insulator image containing RTV coating defects captured in a laboratory.

Further, the insulator image type includes insulator model information.

Further, the preprocessing in step 2) includes image grayscale and image median filtering to remove noise, improve image quality, and improve the accuracy of the insulator image segmentation.

The premise of calculating the proportion of insulator RTV coating defect area is to determine the area where the insulator is located, that is, the original image needs to be segmented to separate the insulator area from the background. Since there may be different degrees of noise or other interference factors in the original image, which will affect the accuracy of subsequent insulator image segmentation and recognition, it is necessary to perform a series of preprocessing operations on the original image before the image segmentation operation. The purpose of image preprocessing is Reduce noise, improve image quality, and preserve RTV coating defect information in the original image as much as possible. The preprocessing methods adopted in this application are divided into image grayscale and image median filtering. These two methods can reduce interference and improve computational efficiency for the later work of insulator image segmentation.

Image grayscale

The original image obtained through acquisition is generally a color image, and the process of converting a color image into a grayscale image is called image grayscale processing. The color of each pixel in a color image is determined by three components R, G, and B, and each component ranges from 0 to 255, so it is necessary to convert the color image into a grayscale image first to reduce the amount of subsequent calculations. The description of the chromaticity image can still reflect the distribution and characteristics of the chromaticity and brightness levels of the image, just like the color image.

image median filter

Due to the variability of lighting conditions when collecting images, the collected images will have different degrees of noise. These noises may cause the uniform and continuous distribution of gray values in the image to suddenly increase or decrease at a certain point, causing the algorithm to identify False RTV coating defects. In order to reduce the influence of noise and improve the quality of the image, it is necessary to perform median filtering on the grayscale image. Median filtering is to replace the value of a point in the digital image with the median value of each point in a field of the point, and change the pixel with a relatively large difference in the gray value of the surrounding pixels to a value close to the surrounding pixel value. In this way, isolated noise points can be eliminated, which can not only remove noise but also protect the edge information of the insulator.

Further, the conversion formula of the image grayscale is:

Y＝0.2989*R+0.5870*G+0.1140*B

Among them, R represents the red component, G represents the green component, and B represents the blue component. Y is the gray value of the grayscale image.

Further, in the step 3), the preprocessed insulator image is segmented into a binary image by using the maximum inter-class variance method, and the insulator region and the RTV coating defect region are segmented.

Further, the maximum inter-class variance method includes traversing the value space of image grayscale, calculating the inter-class variance corresponding to each threshold, and making the inter-class variance the largest, which is the optimal threshold T; selecting the gradient value of the threshold T to the image Do binarization.

Further, it also includes counting the number of black and white pixels in the binarized image, and calculating the ratio of the insulator RTV coating shedding area.

Further, the ratio of the peeling area of the RTV coating of the insulator is the ratio of the front or back of the insulator to the insulating area of the insulator.

Further, the calculation includes the following steps:

a. Calculate the center coordinates (x, y) of the insulator body in the binary image, x=(max(x)+min(x))/2, y=(max(y)+min(y))/2 ;

b. Calculate the insulator radius R=(max(x)-min(x))/2 in the binarized image;

c. Calculate the steel cap radius R ₁ =R×d;

d. Use the fill function to fill the area of the steel cap with black, count the number of black pixels in the picture, and record it as A;

e. Calculate the area of the steel cap area as S=πR ₁ ² ;

f. Delete the peeling area of the insulator RTV coating in the image through the filter function, so that the entire insulator area is black, count the number of black pixels in the picture, and record it as B;

g. Calculate the proportion of insulator RTV coating shedding area Ratio=(B-A)/(B-S)×100%.

Among them, the coordinates of the center of the insulator body are (x, y), the radius of the insulator is R, and the percentage of the diameter of the steel cap to the diameter of the insulator is d.

In Figure 2, the original image is a color image.

After the original image has undergone the above preprocessing, the next step is to segment the insulator region from the image. This patent uses the Otsu threshold segmentation algorithm to separate the preprocessed insulator area from the image. It uses the difference in gray level between the insulator and the background, and divides the pixel level into several categories by setting the threshold to judge the image. Whether the gray value of each pixel in the image meets the requirements of the threshold, so as to determine whether the pixel in the image belongs to the target area, that is, to realize the separation of the insulator from the background. When the RTV coating of an insulator falls off, the insulator body will be exposed in the off area, and the color of the insulator body is quite different from the color of the RTV coating. Distinguish between the normal insulator area and the RTV coating peeling area.

The steps of the Otsu threshold segmentation algorithm are as follows:

Let the size of the grayscale image be w*h, that is, the number of pixels in the image is w*h, set the segmentation threshold of the foreground and the background to be T, all pixels whose gray value is less than T are the foreground, and all pixels greater than T are background. Suppose the proportion of foreground pixels in the image is ω0, and its average gray level is μ0; the proportion of background pixels in the image is ω1, and its average gray level is μ1. The overall average gray level of the image is μ, and the variance between classes is g, then:

ω0+ω1＝1               (1)

μ＝ω0×μ0+ω1×μ1 (2)

The available between-class variance is:

g＝ω0×(μ0-μ) ² +ω1×(μ1-μ) ² (3)

Combine the above formulas to get:

g＝ω0×ω1×(μ0-μ1) ² (4)

Traverse the value space of the image grayscale, calculate the variance between classes corresponding to each threshold, and make the variance g between classes the largest, which is the optimal threshold T.

Select the threshold T to binarize the gradient value of the image:

The image g(x,y) after the image f(x,y) is segmented can be obtained from formula (5).

Since there is a steel cap part in the middle area of the insulator, this part does not have insulation performance. The ultimate purpose of this patent is to calculate the proportion of the insulator RTV coating shedding area. This proportion refers to the proportion of the front or back of the insulator to the insulator insulation area. Including the area of the middle steel cap part of the insulator, this calculation method can effectively characterize the severity of the RTV coating defect of the insulator.

The original image is processed by the above preprocessing method and the Otsu threshold segmentation algorithm to obtain a binary image. In the final binary image, the normal insulator area is represented as black, and the RTV coating shedding area and background are white.

An insulator RTV coating defect recognition method provided in the present application can segment an insulator image to obtain normal insulators and RTV coating shedding areas.

An insulator RTV coating defect recognition method provided by this application collects images containing insulator RTV coating defects, processes and recognizes the images, and obtains insulator RTV coating defects and their occupied areas. The operation is simple, and there is no need to go to the site The identification of insulator RTV coating defects can be realized, and the severity of insulator RTV coating defects can be represented by the proportion of insulator RTV coating defects.

Although the present application has been described above with reference to specific embodiments, those skilled in the art should understand that many modifications can be made to the configurations and details disclosed in the present application within the principles and scope disclosed in the present application. The protection scope of the present application is determined by the appended claims, and the claims are intended to cover all modifications included in the equivalent literal meaning or scope of the technical features in the claims.

Claims (7)

1. an insulator RTV coating defect identification method, is characterized in that: described method comprises the steps: 1) Obtain images containing insulator RTV coating defects; 2) Preprocessing the image containing the insulator RTV coating defect; 3) Segment the preprocessed insulator image into a binary image, segment the insulator region and the RTV coating defect region; in the binary image, the normal insulator region is represented as black, and the RTV coating shedding region and background are White, fill the area of the steel cap with black, calculate the number of black and white pixels of the binary image, and calculate the ratio of the shedding area of the insulator RTV coating; the ratio of the shedding area of the insulator RTV coating is the ratio of the front or back of the insulator The ratio of the insulating area of the insulator; said calculation includes the following steps: a. Calculate the center coordinates (x, y) of the insulator body in the binary image, x=(max(x)+min(x))/2, y=(max(y)+min(y))/2 ; b. Calculate the insulator radius R=(max(x)-min(x))/2 in the binarized image; c. Calculate the steel cap radius R ₁ =R×d; d. Use the fill function to fill the area of the steel cap with black, count the number of black pixels in the picture, and record it as A; e. Calculate the area of the steel cap area as S=πR ₁ ² ; f. Delete the peeling area of the insulator RTV coating in the image through the filter function, so that the entire insulator area is black, count the number of black pixels in the picture, and record it as B; g. Calculate the proportion of insulator RTV coating shedding area Ratio=(B-A)/(B-S)×100%; Among them, the coordinates of the center of the insulator body are (x, y), the radius of the insulator is R, and the percentage of the diameter of the steel cap to the diameter of the insulator is d. 2. The insulator RTV coating defect identification method as claimed in claim 1, characterized in that: the image in the step 1) is from an insulator image of an insulator image containing a RTV coating defect taken by a short-distance aerial photograph on site or taken in a laboratory Image of an insulator containing RTV coating defects. 3. The method for identifying defects in an insulator RTV coating according to claim 2, wherein the insulator image includes insulator model information. 4. the insulator RTV coating defect identification method as claimed in claim 1, is characterized in that: described step 2) described pretreatment comprises image gray scale and image median filter, removes noise, improves image quality, Improve the accuracy of the insulator image segmentation. 5. The insulator RTV coating defect identification method as claimed in claim 4, characterized in that: the conversion formula of the gray scale of the image is: Y＝0.2989*R+0.5870*G+0.1140*B Among them, R represents the red component, G represents the green component, B represents the blue component, and Y represents the gray value of the grayscale image. 6. The insulator RTV coating defect recognition method as claimed in claim 1, characterized in that: in the step 3), the preprocessed insulator image is segmented into a binarized image by using the maximum inter-class variance method, and the segmented Insulator area and RTV coating defect area. 7. the insulator RTV coating defect recognition method as claimed in claim 6, is characterized in that: described maximum class variance method comprises the value space of traversing image grayscale, calculates the class variance corresponding to each threshold value, makes class The maximum variance is the optimal threshold T; select the threshold T to binarize the gradient value of the image.

Images