基于主元分析的柱塞泵故障诊断方法

Investigation on PCA-based Method of Fault Diagnosis for a Piston Pump

在分析了主元分析法的基础上,提出了PCA的故障诊断方法,利用小波变换对原始信号进行了预处理,提取了包含时域和频域特征参数构成的特征向量,应用PCA进行了故障诊断。对液压泵进行故障诊断,试验结果表明,时域和频域特征参数构成的特征向量很好反映了故障特征,该方法对液压泵故障诊断有良好的效果。

A fault diagnosis method is proposed based on principles components analysis（PCA） algorithm,original signal is preprocessed by wavelet analysis,eigenvector is extracted which is comprised time-domain and frequency-domain characteristic parameters,fault is diagnosed by use of PCA.The method is tested on the hydraulic pump,it is shown from the result of the experiment： the eigenvector is reflected better fault features,this method is valid to the fault diagnosis of the hydraulic pump.