Diagnostics and prognostics of planetary gearbox using CWT, auto regression (AR) and K-means algorithm

Condition monitoring of machine is recognized as effective strategy for undertaking the maintenance in wide variety of industries. Planetary gearbox is a critical component in helicopters, wind turbines, hybrid vehicles and so forth. Planetary gearbox are complex in nature due to its size and meshing components. Condition monitoring and fault diagnosis of planetary gearbox is challenging due to complexity in dependable fault extraction from raw vibration signal. The mechanism of planetary gearbox is complex as there are several gears meshing at the same time. To find out the nature of fault and defective component in planetary gearbox is difficult. In this paper, the fault detection and fault type identification diagnostic approach using auto regression model (AR) and continuous wavelet transforms (CWT) by considering different frequency range is established. The experimental research conducted with different type of fault vibration signals in the gearbox have been diagnosed and identified the fault type using AR Modelling, Impulse and Shape Factor for validation purposes. The unique behaviors and fault characteristics of planetary gearboxes are identified and analyzed. The fault frequency identification and extraction of features from the non-stationary signals in different fault severity level of vibration data demonstrates the reliability of proposed method. The developed algorithm adds efficacy in detecting the nature of fault and defective component without performing a visual inspection.