基于核主成分分析-SoftMax的高压断路器机械故障诊断技术研究  

Mechanical Fault Diagnosis Research of High Voltage Circuit Breaker Based on Kernel Principal Component Analysis and SoftMax

作　　者：王昱皓 武建文[1] 马速良[1] 杨景刚 赵科 Wang Yuhao;Wu Jianwen;Ma Suliang;Yang Jinggang;Zhao Ke(School of Automation Science and Electrical Engineering Beihang University,Beijing,100191,China;Jiangsu Electric Power Company Research Institute of State Grid,Nanjing,211103,China)

机构地区：[1]北京航空航天大学自动化科学与电气工程学院,北京100191 [2]江苏省电力公司电力科学研究院,南京211103

出　　处：《电工技术学报》2020年第S01期267-276,共10页Transactions of China Electrotechnical Society

基　　金：国家自然科学基金（51677002）;国博士后科学基金（2018M631307）资助项目

摘　　要：高压断路器是保证电力系统安全、可靠运行的重要设备,对于高压断路器机械故障定位和诊断成为近年来重要的研究课题。本文针对高压断路器典型工况的振动信号,提出了一种基于核主成分分析(KPCA)的SoftMax故障诊断模型。首先,通过小波包分解计算振动信息的时频能量比,定义高压断路器六种典型机械工况下的特征描述。然后,利用KPCA对原始特征空间进行压缩,重构低维、高识别度的特征空间,采用SoftMax分类算法对高压断路器典型工况进行诊断定位。最后,对比原始特征空间下、主成分分析特征空间下和KPCA特征空间下的SoftMax分类结果以及KPCA特征下多种典型分类诊断算法,诊断结果表明结合KPCA特征空间重构的SoftMax诊断模型的优越性,为高压断路器机械故障诊断与定位提供新思路。The high voltage circuit breaker(HVCB)is a crucial equipment to ensure the security and reliability of power system,consequently the mechanical fault diagnosis research of HVCB has become a key issue.In this paper,a SoftMax classifier model based on Kernel principal component analysis(KPCA)was developed,which was located to identify the vibration signal of typical working conditions.Firstly,the wavelet packet time-frequency energy rate was adopted as the characteristic description of six typical mechanical conditions.Secondly,KPCA was used for dimensionality reduction to obtain a feature space with lower latitude and high-recognition.Then,SoftMax was adopted to diagnose the typical working conditions.To prove the superiority of the SoftMax diagnostic model combined with KPCA feature space,the comparative experiment of SoftMax classifier results in the origin feature space,the principal component analysis(PCA)feature space,the KPCA feature space was carried out,the comparison for accuracy of various methods in the KPCA feature space was proceed as assist.The result indicates that the proposed method provides a new thought for HVCB mechanical fault diagnosis.

关 键 词：高压断路器 故障诊断 振动信号 核主成分分析 SoftMax 

分 类 号：TM561[电气工程—电器]