Effective Prediction of Bearing Fault Degradation under Different Crack Sizes Using a Deep Neural Network

Abstract

Exact evaluation of the degradation levels in bearing defects is one of the most essential works in bearing condition monitoring. This paper proposed an efficient evaluation method using a deep neural network (DNN) for correct prediction of degradation levels of bearings under different crack size conditions. An envelope technique was first used to capture the characteristic fault frequencies from acoustic emission (AE) signals of bearing defects. Accordingly, a health-related indicator (HI) calculation was performed on the collected envelope power spectrum (EPS) signals using a Gaussian window method to estimate the fault severities of bearings that served as an appropriate dataset for DNN training. The proposed DNN was then trained for effective prediction of bearing degradation using the Adam optimization-based backpropagation algorithm, in which the synaptic weights were optimally initialized by the Xavier initialization method. The effectiveness of the proposed degradation prediction approach was evaluated through different crack size experiments (3, 6, and 12 mm) of bearing faults.