WavCapsNet: An Interpretable Intelligent Compound Fault Diagnosis Method by Backward Tracking
Weihua Li, Hao Lan, Junbin Chen, Ke Feng, Ruyi Huang
Abstract
With significant advantages in feature learning, the deep learning based compound fault diagnosis method has brought many successful applications for industrial equipment. However, few studies focus on the interpretability of intelligent compound fault 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 compound fault diagnosis framework, called wavelet capsule network (WavCapsNet), is proposed for machinery by leveraging the backward tracking technique. First, the WavCapsNet is constructed with a wavelet kernel convolutional 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 compound fault intelligently. Second, the WavCapsNet is trained and optimized with the normal and single fault samples (without compound fault samples). Finally, the interpretable analysis is launched by backward tracking 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 compound fault decoupling accuracy under the scenario of incomplete fault data but also improves the transparency and interpretability in the decision-making process of fault diagnosis.