Explainable Deep Ensemble Model for Bearing Fault Diagnosis Under Variable Conditions

Deep learning-based intelligent diagnostic methods have been widely used in aerospace, rail transportation, automotive, rail vehicles, and other fields. However, deep neural networks are composed of multilayer nonlinear transformation to learn the feature maps of input, leading to the black-box characteristic. It is usually criticized to be nontransparent and less interpretable in predictions and maintenance decision-making. Meanwhile, due to the variability of machine working conditions in the manufacturing process, there is still a gap between traditional deep learning diagnosis methods and the practical application. To address such problems, an explainable deep ensemble model is proposed for fault diagnosis of bearings, which both leverages feature learning ability and improves model interpretability. First, a residual network integrated with bidirectional long short-term memory (BiLSTM) is designed as the backbone learning framework to perform associative feature extraction from the original 1-D time-series signals. Then, a multibranch model with a multiscale ensemble learning strategy is constructed for feature fusion and final fault diagnosis. After the model is trained, an enhanced gradient-weighted class activation mapping technique, named 1-D Grad-CAM++, is embedded to visualize the region of interest in the convolutional layer, where the prior knowledge gained from the bearing fault mechanism model is effectively combined to provide a better understanding of the learned features and decision-making of model. Finally, three fault diagnosis cases of rolling bearings under different operation conditions are used for algorithm verification. The results demonstrate that the proposed approach shows superior explainable capability and diagnosis performance in comparison with other methods.