Gear Tooth Crack Detection Method Using Bayesian Neural Network

Gearbox fault detection plays a crucial role in implementing proactive maintenance strategies and reducing economic losses. Fault detection can be addressed by modeling baseline monitoring data and subsequently detecting faults through deviations between the baseline model and newly acquired monitoring data. In the field of deep learning, long short-term memory (LSTM) have been widely applied to nonlinear time series modeling. This article attempts to combine Bayesian neural networks (BNNs) with LSTM, aiming to fully exploit the ability of LSTM to capture complex long-term dependencies as well as the strong regularization and generalization capabilities of BNN. Specifically, we propose two fault detection methods: the fault detection method based on Bayesian LSTM (BLSTM) and the fault detection method based on traditional LSTM with a Bayesian fully connected layer (LSTM-BFC). Comparative and antinoise experiments were conducted using data collected from a gearbox test rig. Experimental results demonstrate that the proposed BNN-based approaches outperform traditional LSTM models in terms of fault detection performance. Among them, the LSTM-BFC method shows particularly outstanding performance in training time, time series prediction capability, fault detection accuracy, and noise robustness.