EEMD与EFICA在单通道复合故障诊断中的应用

针对转子不对中和滚动轴承微弱损伤的复合故障诊断问题，提出了一种基于平均经验算法(Ensemble Empirical Mode Decomposition,EEMD)和高效快速独立分量分析(Efficient Variant of FastICA，EFICA)的盲源分离故障诊断方法。利用EEMD算法将单通路复合故障信号分解成多个不同信号特征的本征模函数(Intrinsic Mode Function,IMF)，解决了盲源分离中的欠定问题。在此基础上利用EFICA算法对各个不同信号特征的IMF进行故障特征分离。通过仿真实验和转子实验台的实验结果，表明该算法可以有效分离出各个不同的故障特征。

Application of composite fault diagnosis with single channel based on EEMD and EFICA

Aimed at composite fault of rotor misalignment and weak bearing fault,a fault diagnosis method based on Ensemble Empirical Mode Decomposition(EEMD) and Efficient Variant of FastICA(EFICA) is proposed.A single channel composite fault diagnosis signal is separated into multiple intrinsic mode functions(IMFs) with different feature by EEMD,which solve underdetermined problem in blind source separation(BSS).On the basis,EFICA can separate fault features that are needed from different IMFs.The results of simulation and rotor test stand experiment indicate that method can effectively separate fault features.