基于小波变换和支持向量机的电力电子故障诊断

New Method of Wavelet and Support Vector Machine for Power Electronic Fault Diagnose

采用小波分析与支持向量机(SVM)对电力电子故障进行自动识别和诊断,运用变尺度分辨小波方法对电力电子故障信号进行特征处理,SVM能够对小样本数进行模式识别并且具有良好的分类推广能力。在小波分析特征基础上,采用分布式多SVM分类器识别电力电子故障。实验证明,该方法能准确有效地对电力电子故障进行识别和诊断。

The combination of wavelet and support vector machine was introduced to solve automatic detection of power electronic fault diagnose.Wavelet analysis which holds multi-resolution and multi-scale was introduced to deal with the signal characteristics.Support vector machine could carry through the pattern recognition on the small-samples and had well generalized ability.Based on wavelet analysis for signal characteristics,the distributed multi-SVM classifier was utilized to identify the power electronic fault diagnose,the experimental results also show that this method can efficiently identify and diagnose the power electronic fault diagnose.