A Fine-Grained Adversarial Network Method for Cross-Domain Industrial Fault Diagnosis

While machine-learning techniques have been widely used in smart industrial fault diagnosis, there is a major assumption that the source domain data (where the diagnosis model is trained) and the future target data (where the model is applied) must have the same distribution. However, this assumption may not hold in real industrial applications due to the changing operating conditions or mechanical wear. Recent advances have embedded the adversarial-learning mechanism into deep neural networks to reduce the distribution discrepancy between different domains to learn domain-invariant features and perform fault diagnosis. However, they only aligned the distributions of domains and neglected the fault-discriminative structure underlying the target domain, which leads to a decline in the diagnostic performance. In this article, a new method termed the fine-grained adversarial network-based domain adaptation (FANDA) is proposed to address the cross-domain industrial fault diagnosis problem. Different from the existing domain adversarial adaptation methods considering the domain discrepancy only, the features in FANDA are learned by competing against multiple-domain discriminators, which enable both a global alignment for two domains and a fine-grained alignment for each fault class across two domains. Thus, the fault-discriminative structure underlying two domains can be preserved in the adaptation process and the fault classification ability learned on the source domain can remain effective on the target data. Experiments on a mechanical bearing case and an industrial three-phase flow process case demonstrate the effectiveness of the proposed method. Note to Practitioners-The varying industrial conditions (domains) can lead to the degradation of diagnostic performance as the distribution can change from the source domain to the target domain. The focus of this article is to develop a fine-grained adversarial network-based domain adaptation (FANDA) strategy to diagnose different kinds of faults across the domains. The proposed FANDA algorithm can reduce the distribution discrepancy of both the global domains and each fault class across the domains automatically. The training procedure is completed using an adversarial way, driving the learned feature representations to be transferable across two domains. Thus, the fault classifier learned on the source domain can be applied to the target domain directly. It is noted that common deep network architectures can be embedded into the FANDA framework, and thus, this article is suitable for carrying out cross-domain fault diagnosis tasks in diverse advanced manufacturing applications.