A Fault Diagnosis Method for Planetary Gearboxes Based on Signal Decomposition and Density Peaks Clustering

Planetary gearbox is the indispensable part in the production equipment so that fault diagnosis for it can ensure the production safety in practice. For fault diagnosis of planetary gearboxes, this paper proposes a fault diagnosis method combined the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and the refined composite multiscale dispersion entropy (RCMDE). First, the CEEMDAN method is used to decompose the signals to obtain a series of IMF components. Then, select several IMF components with relatively high and concentrated energy as valid IMF components to be quantized by RCMDE and form the feature matrix. Next, the principal component analysis method is employed to reduce the dimension of feature matrix and extract the effective information in signals. Finally, the simplified features are sent into density peak clustering (DPC) to obtain the fault diagnosis results. Compared with different methods, the experimental results show that, the method can more effectively extract the information of the original signals and DPC can accurately diagnose the states of planetary gearboxes faults.