基于小波包分析与支持向量机的电力电子整流装置故障诊断

针对当前电力电子整流装置使用的故障诊断方法在应用过程中表现出的缺陷,提出了一种基于小波包分析与支持向量机的电力电子整流装置故障诊断方法：首先使用小波包分析方法对故障信号波形进行分解,提取故障特征向量,然后使用支持向量机理论构造多分类故障分类器对提取的故障特征向量进行分类.仿真实验结果表明,该方法能够有效地完成对电力电子整流装置的故障诊断,具有很好的工程应用价值.

Fault Diagnosis of Power Electronics Rectifying Device Based on Wavelet Packet Analysis and Support Vector Machine

For the defect of fault diagnosis methods used for current power electronics rectifier circuit, a fault diagnosis method based on wavelet packet analysis and Support Vector Machine （ SVM ） is presented. First, to decompose the fault signal waveform and extract fault feature vector by using wavelet packet analysis. Then compose a fault classifier of multi-classifier base on theory of Support Vector Machine and classify the fault characteristic vectors extracted before. The simulation shows that this method can efficiently complete fault diagnosis for power electronics rectifier circuit,and be useful for engineering application.