Cross-Domain Open-Set Fault Diagnosis for Rotating Machinery Based on Frequency-Aware Model With Neighborhood Invariance

Yu Gao, Jin Qi, Ying Sun, Xingjian Zhu, Genxin Chen, Zhenjiang Dong, Yanfei Sun

Abstract: Domain adaptation (DA) is a frequently used technique in intelligent fault diagnosis. However, existing DA methods presume that the source and target domains have the same label space. Due to the complexity of industrial operation conditions, new fault types will inevitably occur. Thus, the above assumption is only sometimes satisfied. To overcome this issue, we propose a novel frequency-aware model with neighborhood invariance (FAN) for cross-domain open-set fault diagnosis. First, we comprehensively consider the domain shift phenomenon in time and frequency features and construct an encoder based on the Fourier neural operator (FNO) to extract potential invariant information efficiently. Second, we expect known class samples to be mapped to an invariant neighborhood to separate unknown classes. Based on this, we adopt neighborhood invariance learning to reduce the intradomain variations in the target domain and form robust discriminative boundaries. Extensive experiments on public and real-world datasets demonstrate that FAN outperforms the comparison methods and has flexibility.