FAULT DIAGNOSIS OF BALL BEARING BASED ON ELCD PERMUTATION ENTROPY AND RVM

Aiming at the no stationary characteristic of a gear fault vibration signal, it proposes a recognition method based on ELCD（Ensemble local Characteristic-scale decomposition） permutation entropy and RVM. First, the vibration signal was decomposed by ELCD, then a series of intrinsic scale components were obtained; Secondly, according to the kurtosis of ISCs, principal ISCs were selected, then, calculate the permutation entropy of principal ISCs and combined into a feature vector; Finally, the feature vector were input RVM classifier to train and test to identify the type of rolling bearing faults. Experimental results show that this method can effectively diagnosis four kinds of working condition, and the effect is better than local Characteristic-scale decomposition method.