基于图像的换流站用避雷器泄漏电流识别  

A recognition method of leakage current of arrester in converter station based on image

作　　者：何红太 崔家瑞[2] 纪建才 胡广大[2] 张波[3] 刘广一[3] 

机构地区：[1]北京国网富达科技发展有限责任公司,北京丰台区100070 [2]北京科技大学自动化学院,北京海淀区100083 [3]中国电力科学研究院,北京海淀区100192

出　　处：《内蒙古科技大学学报》2015年第4期391-396,共6页Journal of Inner Mongolia University of Science and Technology

基　　金：国家高技术研究发展计划(863资助项目)(2012AA050209);国家电网公司科技资助项目(SGCC-119-2012)

摘　　要：针对电力系统中的换流站用避雷器泄漏电流仪表的特点,提出了一种基于图像的换流站用避雷器泄漏电流的识别方法.首先,采用基于透视变换的方法对采集到的避雷器泄漏电流仪表图像进行畸变矫正,通过图像预处理进行图像增强获得相对比较清晰的表盘信息,并利用减影法获取指针的位置.然后,采用基于Canny(坎尼)算子边缘检测和改进的Hough(霍夫)变换检测出避雷器泄漏电流表中的指针直线,完成了换流站避雷器泄漏电流的识别.最后,采用现场拍摄的型号为3EX5 050的西门子避雷器泄漏电流表对本文所提算法进行了验证.结果表明该算法克服了传统Hough变换的许多缺点,能够快速准确的识别出避雷器泄露电流大小.According to the characteristics of the converter station lightning arrester leakage current meter in the power system,a kind of recognition method of the converter station lightning arrester leakage current meter was put forward based on image. Firstly,a distortion correction was made on the collected arrester leakage current meter image based on the method of perspective transform. Then,relatively clear dial information was obtained according to the image processing for image enhancement. Secondly,the subtraction method was used to get a more precise pointer position. Thirdly,the Canny operator edge detection and the improved Hough transform were used to detect the pointer line of the converter lightning arrester leakage current meter,and the identification of converter station lightning arrester leakage current was completed. Finally,Siemens arrester leakage current meter of the 3EX5 050 were conducted to validate the proposed algorithms. The results shows that the algorithm overcomes many disadvantages of the traditional Hough transform and has the ability to identify size arrester leakage current fast and accuratly

关 键 词：避雷器泄漏电流仪表 图像矫正 图像预处理 改进HOUGH变换 读数识别 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]