基于仿生模式识别的GIS局部放电类型辨识  

GIS Partial Discharge Type Recognition Based on the BPR

作　　者：胡凯旋[1] 刘利强[1] 李昌陵 车传强[3] 吕超[1] 

机构地区：[1]内蒙古工业大学电力学院,呼和浩特010080 [2]国网新疆电力公司经济技术研究院,乌鲁木齐830000 [3]内蒙古电力科学研究院,呼和浩特010020

出　　处：《高压电器》2016年第2期35-41,共7页High Voltage Apparatus

基　　金：国家自然科学基金资助项目(61364009);内蒙古自治区自然科学基金项目(2015MS0543)~~

摘　　要：为实现气体绝缘组合电器(GIS)局部放电检测和故障识别,设计了GIS典型缺陷模型,使用超高频法检测放电信号,并提取特征参数。利用主成分分析法对特征参数进行降维处理,引入仿生模式识别算法进行辨识,提出一种改变连通方向的方法,提高了算法的辨识率,分析了连通方向改变前后样本的辨识率,以及未训练样本类型的错分率。结果表明,基于仿生模式识别的GIS局部放电类型辨识率能达到满意的效果。In order to realize detection and fault identification of the GIS partial discharge,the typical defects of GIS model are designed, the discharge signals are detected by UHF method and the feature parameters are extracted. Then principal component analysis（PCA）is used to reduce dimension of feature parameters,the bionic pattern recognition（BPR）is quoted and a method to change the connecting direction is put forward to improve the recognition rate of the algorithmic. The recognition rate before and after changing the connecting direction as well as the misclassification rate of sample types without training are analysized. The results show that the recognition rate of GIS partial discharge type based on BPR is satisfactory.

关 键 词：气体绝缘组合电器 局部放电 主成分分析 仿生模式识别 连通方向 

分 类 号：TM595[电气工程—电器]