A fault feature extraction method based on the combination of Fast Independent Classification Analysis(FastiCA)and empirical mode decomposition(EMD)is proposed to solve the problem that the vibration signals of rolling bearings are affected by noise.The vibration signal is decomposed into several modal components by empirical mode decomposition.Then,according to the Correlation Coefficient,the effective modal components are selected to construct the noise channel.Finally,the source signal is sep-arated from the noise signal by fast independent classification analysis.The simulation and experimental results of bearing data in Xchu University show that this method can effectively suppress noise interference,clearly see the fault frequency of bearing,and realize the fault diagnosis of bearing.
NETL
NSTL
万方数据
