A novel domain generalization network with multidomain specific auxiliary classifiers for machinery fault diagnosis under unseen working conditions

The domain adaptation-based intelligent diagnosis approaches have achieved promising performance on diag-nosis tasks under different working conditions. However, these methods rely on a premise that the target data are available in the model training phase. In real industries, collecting interest data from target machines in advance may be infeasible, which greatly restricts the practicality of intelligent diagnosis approaches in reality. To solve this issue, this study proposes a novel domain generalization network for machinery fault diagnosis where in-terest data are completely unavailable during model training. In the proposed network, multiple domain-specific auxiliary classifiers are firstly designed to effectively learn domain-specific features from each source domain, and then, a convolutional auto-encoder module is further constructed to map raw signals into a new feature space where the learned domain-specific features are removed. Meanwhile, with the features outputted by the convolutional auto-encoder, a domain-invariant classifier with inter-domain alignment strategy is designed to learn generalization diagnostic knowledge among different source domains, thereby performing diagnosis tasks under unseen conditions. Experiments on three practical rotary machinery datasets validate the effectiveness of the proposed network, showing that the proposed network is promising for fault diagnosis tasks in practical scenarios.

Automated summary

This study proposes a novel domain generalization network for machinery fault diagnosis where interest data are completely unavailable during model training. Multiple domain-specific auxiliary classifiers are designed to effectively learn domain-specific features, and a convolutional auto-encoder module is used to remove the learned domain-specific features. A domain-invariant classifier with inter-domain alignment strategy is designed to learn generalization diagnostic knowledge among different source domains. Experiments validate the effectiveness of the proposed network, showing its promising potential for fault diagnosis tasks in practical scenarios.