Fault diagnosis of gearbox using EMD and cepstrum method based on LABVIEW

Abstract

Gearbox fault signal has non-stationary and non-linear features, conventional spectral analysis methods all have their own limitations. This paper presents the method of combining empirical mode decomposition (EMD) and cepstrum analysis, and develops a gearbox fault detection system based on LABVIEW. Practical tests show that each signal could be decomposed into a number of intrinsic mode functions(IMFS) adaptive by the EMD, then do cepstrum analysis to the IMF that contains the main frequency components of the signal, you can visually identify the fault feature. The result shows that this system can detect Gearbox faults effectively.