A dependence-based feature vector and its application on planetary gearbox fault classification

To achieve planetary gearbox fault classification, vibration signal analysis has been widely employed with rich information about the health status and easy measurement. It is critical to extract features with enough health status information for fault classification. The self-adaptation of ensemble empirical mode decomposition (EEMD) indicates the dependence between the raw vibration signal and EEMD-decomposed intrinsic mode functions (IMFs). In this study, we develop a novel fault feature vector based on the dependence. To develop the dependence-based feature vector, simulated vibration signals with different sun gear tooth crack levels are analyzed. The dependence between the raw signal and each IMF is investigated by Archimedean copulas. With the goodness-of-fit test, the copula estimation closest to the perfect fit is selected for dependence representation. The parameter of the selected copula is applied to develop the dependence-based feature vector. To test the ability of the dependence-based feature vector in fault classification for a real planetary gearbox, experimental vibration signals with different gear fault levels at different gears are classified by a multi-class support vector machine. The classification accuracy of the developed feature vector is compared with that of a reported indicator. Results show the dependence-based feature vector provides higher classification accuracy than the reported, indicating the developed feature vector contains more health status information. The developed feature vector can serve better for planetary gearbox fault classification.