针对电力机车主变流器的故障,提出基于小波分析和支持向量机(SVM)的故障诊断方法。首先,运用小波包对特征信号进行分解和重构,然后提取各频带的能量,将得到的能量值构造为特征向量,最后把特征向量输入到支持向量机,进行故障诊断。MATLAB仿真结果表明,该方法能够准确地对故障进行诊断。
Focusing on faults of electric locomotive main converter, this paper proposes the fault-diagnosis method based on wavelet analysis and support vector. Firstly, the feature signals are decomposed and recomposed using wavelet packets. Afterwards, the signal energy values extracted from each frequency band are constructed as feature vectors. Finally, feature vectors are input into the support vector machine for fault diagnosis. The result of MATLAB simulation shows that this method can accurately diagnose the faults.