Deep Domain Generalization Combining A Priori Diagnosis Knowledge Toward Cross-Domain Fault Diagnosis of Rolling Bearing

Recent works suggest that using knowledge transfer strategies to tackle cross-domain diagnosis problems is promising for achieving engineering diagnosis. This article presents a diagnosis scheme for rolling bearing under a challenging domain generalization scenario, in which more potential discrepancies among multiple source domains are eliminated and only normal samples of the target domain are available during the training stage. To achieve sufficient generalization performance, a diagnosis scheme combining some a priori diagnosis knowledge and a deep domain generalization network for fault diagnosis (DDGFD) is elaborated. Through signal preprocessing steps guided by the a priori diagnosis knowledge, the inputs of DDGFD with a primary consistent meaning across domains are constructed from the vibration signal. On this basis, DDGFD would intently release its talent on learning discriminative and domain-invariant fault features from source domains, and then generalize the learned knowledge to identify unseen target samples. On cross-domain tasks organized using broad bearing data sets, the superiority of DDGFD is validated by comparing its performance with various data-driven diagnosis methods.

Automated summary

Recent studies show potential in using knowledge transfer strategies to address cross-domain diagnosis problems. This article introduces a diagnosis scheme for rolling bearings that combines a priori diagnostic knowledge with a deep domain generalization network.