Gear Fault Detection Based on Ensemble Empirical Mode Decomposition and Hilbert-Huang Transform

A new approach to fault diagnosis of gear crack based on ensemble empirical mode decomposition (EEMD) and Hilbert-Huang transform (HHT) technique is presented. Firstly, the time-domain vibration signal of the gearbox with gear crack fault is measured. Then the original vibration signal is separated into intrinsic oscillation modes, using the ensemble empirical mode decomposition. Secondly, Hilbert transform tracks the modulation energy of the intrinsic mode functions (IMFs) and estimates the instantaneous amplitude and instantaneous frequency. Then the HHT spectrum of the vibration signal can be obtained. Therefore, the character of the gear crack faults can be recognized according to the HHT spectrum. The experimental results show that EEMD and HHT spectrum can effectively diagnose the faults of the gear crack.