基于小波变换与SVM的复杂装备故障诊断研究

针对复杂装备故障信号提取困难、故障诊断精度低的现状,根据小波变换对处理非平稳信号的优越性和支持向量机(SVM)对模式分类的良好性能,提出了一种基于小波变换与SVM的故障诊断模型,并选取配电系统进行故障诊断仿真实验。结果表明该模型能利用少量训练样本完成故障诊断,有效提高装备故障诊断精度。

Research on Fault Diagnosis of Complex Equipment Based on Wavelet Transformation and Support Vector Machine

With respect to the difficulty of signal extraction and the low accuracy in fault diagnosis in complex equipment,taking the advantage of the adaption of wavelet transformation in processing non-stationary signal and the advantage of the adaption of Support Vector Machine in mode classification,a fault diagnosis model which is based on wavelet transformation and SVM is put forward. The power distribution system is selected in simulation experiment of fault diagnosis. The results show that the model can complete fault diagnosis with a few training samples and the accuracy of fault diagnosis can be improved effectively.