Wind turbine gearbox fault diagnosis based on EEMD and fractal theory

Abstract

This paper proposes a novel fault diagnosis method for planetary gearbox based on ensemble empirical mode decomposition (EEMD) and fractal theory. EEMD is applied to process the non-stationary vibration signals and get the feature space. The vibration signal is decomposed by EEMD into different frequency bands effectively. The fractal dimension (FD) can extract fault characters from input signal, thus FD can be selected as the characteristic parameters to diagnose planetary gearbox fault. So the fractal dimension of specific intrinsic mode functions (IMF) components is able to reflect the operation condition of planetary gearbox sensitively. The result of experiment indicates that the combination of EEMD and fractal dimension is an effective method for planetary gearbox's fault diagnosis.