WavCapsNet: An Interpretable Intelligent Compound Fault Diagnosis Method by Backward Tracking

With significant advantages in feature learning, the deep learning-based compound fault (CF) diagnosis method has brought many successful applications for industrial equipment; however, few studies focus on the interpretability of intelligent CF diagnosis methods, and the diagnosis results are hard to interpret, which prevents the wide application of these methods in practical industrial scenarios. To solve the above challenging problems, an intelligent and interpretable CF diagnosis framework, called wavelet capsule network (WavCapsNet), is proposed for machinery by leveraging the backward tracking (BT) technique. First, the WavCapsNet is constructed with a wavelet kernel convolutional layer (WavConv Layer), which is employed to learn the features with interpretable meaning from vibration signals, and two capsule layers, which endow the diagnosis model with the ability to decouple the CF intelligently. Second, the WavCapsNet is trained and optimized with normal and single fault samples (without CF samples). Finally, the interpretable analysis is launched by BT, the coupling matrices in capsule layers, which is focused on the relationship between the learned features and different health conditions. The experimental results on a five-speed transmission dataset show that the proposed method, compared to other methods, not only achieves higher CF decoupling accuracy under the scenario of incomplete fault data but also improves the transparency and interpretability in the decision-making process of fault diagnosis.