EEMD分解与多特征结合的地铁一系悬挂故障诊断

Fault Diagnosis of Metro Primary Suspension Based on EEMD and Multiple Features

针对地铁运营过程中各类故障很难及时发现的问题,基于构架垂向振动加速度信号进行分析,将信号时域特征指标与聚合经验模态分解出来的固有模态分量的样本熵组合,构成多维特征向量,使用支持向量机进行故障状态识别。根据仿真实验数据显示,当地铁列车以76 km/h速度运行时,故障识别准确率达到并稳定在94%以上。

To solve the fault diagnosis difficulty in metro operation,the combination of time-domain characteristic index of the signal and the sample entropy of the intrinsic mode components decomposed by the ensemble empirical mode is made,based on the analysis of the vertical vibration acceleration signal of the frame,thus forming a multi-dimensional feature vector,and the support vector machine is used to identify the fault state.The experimental data show that the accuracy of fault identification and its stability can be abtained at more than 94%when the metro train runs at 76 km/h.