基于彩色图像的绝缘子污秽等级检测  

Insulator Pollution Level Detection Based on Color Image

作　　者：崔泽涵 CUI Zehan(College of Electrical Engineering&New Energy,China Three Gorges University,Yichang 443002,China)

机构地区：[1]三峡大学电气与新能源学院,湖北宜昌443002

出　　处：《智能物联技术》2024年第3期68-73,共6页Technology of Io T& AI

摘　　要：绝缘子积污易导致污闪事故,危害电网的稳定运行,因此有必要检测绝缘子的污秽等级,以便安排清理作业。文章提出一种基于彩色图像的绝缘子污秽等级判别方法。通过一种基于小波变换与形态学的前景分割算法及一种基于三颜色空间的污秽分割算法,从原始图像中提取污秽部分,同时利用椭圆检测算法圈出绝缘子盘面,通过计算圈出的各个绝缘子盘面内污秽面积与盘面面积的比值均值大小,判断绝缘子的污秽等级,实现绝缘子污秽等级的识别与检测。经实验与对比可知,文章算法对绝缘子污秽等级的检测准确率为99.5%,优于普通的图像检测方法,表明文章方法是一种在线检测绝缘子污秽等级的可行方法。The accumulation of fouling on insulators can easily lead to the pollution flashover accidents and endanger the stable operation of the power grid,so it is necessary to test the insulator fouling level in order to arrange cleaning operations.This paper proposes an insulator fouling level discrimination method based on color image.Through a foreground segmentation algorithm based on wavelet transform and morphology and a fouling segmentation algorithm based on three color space,the fouling part is extracted from the original image;meanwhile,an ellipse testing algorithm is used to circle the insulator disc surface,and the fouling level of the insulator is judged by calculating the mean value of the ratio of the fouling area to the disc surface area in each circled insulator disc surface,and the identification and detection of insulator fouling level is realized.Through experiments and comparisons,it can be seen that the algorithm proposed in this article has an accuracy rate of 99.5%for detecting insulator pollution levels,which is superior to ordinary image detection methods.This indicates that the proposed method is a feasible method for online detection of insulator pollution levels.

关 键 词：绝缘子 小波变换 形态学处理 颜色空间 图像分割 椭圆检测 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]