基于VMD和KFCM-SVM的高压断路器声振联合故障诊断方法  

Acoustic and Vibration Joint Fault Diagnosis Method of High Voltage Circuit Breaker Based on VMD and KFCM-SVM

作　　者：马莉 霍耀佳 吴杨 常婧 韩利 钱勇 方济中 MA Li;HUO Yaojia;WU Yang;CHANG Jing;HAN Li;QIAN Yong;FANG Jizhong(Ningxia Electric Power Research Institute,State Grid Ningxia Electric Power Company,Yinchuan 750001,China)

机构地区：[1]国网宁夏电力有限公司电力科学研究院,银川750001

出　　处：《高压电器》2024年第8期53-62,共10页High Voltage Apparatus

摘　　要：针对高压断路器机械故障复杂、故障特征提取困难的问题,提出一种变分模态分解(variational mode decomposition,VMD)与KFCM-SVM相结合的高压断路器声振联合故障诊断方法。首先利用VMD对去噪后的振动和声音信号进行分解,得到一系列反映断路器操动过程机械状态信息的本征模态函数(IMF);然后对各IMF分量进行Hilbert变换,构造相应的Hilbert边际谱,求取能量熵作为特征向量;最后采用模糊核C—均值聚类(kernel fuzzy C means,KFCM)对特征进行预分类,再利用支持向量机(SVM)建立训练模型实现机械状态辨识。实验结果表明:声振信号Hilbert边际谱能量熵对高压断路器机械状态变化敏感,KFCM-SVM能够准确识别高压断路器分闸操动过程中的机械故障。In view of such issues as complicated mechanical fault and difficult fault extraction of high voltage circuit breaker,a kind of joint acoustic and vibration fault diagnosis method for circuit breaker based on the combination of VMD and KFCM-SVM is proposed.Firstly,VMD is used to decompose the denoised vibration and acoustical signals,and a series of intrinsic mode functions(IMF)reflecting the mechanical state information during operation of the circuit breaker are obtained.Then,Hilbert transform is performed on each IMF component to construct corresponding Hilbert marginal spectrum,and the energy entropy is obtained as the feature vector.Finally,kernel fuzzy C means(KFCM)is used to presort the features,and then the support vector machine(SVM)is used to set up a training model to achieve mechanical state identification.The experimental results show that the energy entropy of the Hilbert marginal spectrum of the acoustic vibration signal is sensitive to the mechanical state variation of high-voltage circuit breaker,and KFCM-SVM can accurately identify mechanical faults during the opening operation of high-voltage circuit breaker.

关 键 词：高压断路器 VMD Hilbert边际谱 能量熵 KFCM-SVM 

分 类 号：TM561[电气工程—电器] TP18[自动化与计算机技术—控制理论与控制工程]