基于PSO-SVM的柴油机故障诊断研究

Research on fault diagnosis of diesel engine based on PSO-SVM

文章以船舶柴油机表面振动信号作为故障诊断的对象,使用经验模态分解(EMD)结合小波阈值法对振动信号进行分解和降噪,再通过PSO-SVM方法对数据样本进行故障诊断。通过对比原始信号和重构信号在PSO-SVM算法计算之后的结果,经过降噪后的振动信号能很好地保持自身特性,可以很好地去除其中冗余、无效的信号,在提升诊断准确率的同时,还可以提高诊断速度。

This article takes the surface vibration signal of marine diesel engine as the object of fault diagno-sis,uses empirical mode decomposition(EMD)combined with wavelet threshold method to decompose and reduce the noise of the vibration signal,and then uses the PSO-SVM method to perform fault diagnosis on the data sample.By comparing the results of the original signal and the reconstructed signal after the calculation of the PSO-SVM algorithm,the vibration signal after noise reduction can well maintain its own characteristics,and can well remove the redundant and invalid signals,thereby improving the accuracy of diagnosis at the same time;it can also improve the speed of diagnosis.