TY - JOUR
T1 - Mitigating Catastrophic Forgetting in Cross-Domain Fault Diagnosis
T2 - An Unsupervised Class Incremental Learning Network Approach
AU - Zhan, Yifan
AU - Yang, Rui
AU - Zhang, Yong
AU - Wang, Zidong
N1 - Publisher Copyright:
© 1963-2012 IEEE.
PY - 2025
Y1 - 2025
N2 - While deep learning has found widespread application in fault diagnosis, it continues to face three primary challenges. First, it assumes that training and test datasets adhere to the same distribution, which is often not the case in industries with varying conditions. Second, it relies heavily on the availability of abundant labeled data for training, overlooking the reality that newly collected data are frequently unlabeled. Third, neural networks frequently encounter catastrophic forgetting, a critical concern in dynamic industrial settings with emerging faults. Therefore, this article proposes an unsupervised class incremental learning network (UCILN), to mitigate catastrophic forgetting in cross-domain fault diagnosis, particularly in situations where the target domain lacks labeled data. A memory module and a semifrozen and semiupdated incremental strategy are designed to balance the retention of old knowledge with the acquisition of new information. Test results obtained from the Case Western Reserve University (CWRU) and Paderborn University (PU) datasets demonstrate the exceptional performance of UCILN.
AB - While deep learning has found widespread application in fault diagnosis, it continues to face three primary challenges. First, it assumes that training and test datasets adhere to the same distribution, which is often not the case in industries with varying conditions. Second, it relies heavily on the availability of abundant labeled data for training, overlooking the reality that newly collected data are frequently unlabeled. Third, neural networks frequently encounter catastrophic forgetting, a critical concern in dynamic industrial settings with emerging faults. Therefore, this article proposes an unsupervised class incremental learning network (UCILN), to mitigate catastrophic forgetting in cross-domain fault diagnosis, particularly in situations where the target domain lacks labeled data. A memory module and a semifrozen and semiupdated incremental strategy are designed to balance the retention of old knowledge with the acquisition of new information. Test results obtained from the Case Western Reserve University (CWRU) and Paderborn University (PU) datasets demonstrate the exceptional performance of UCILN.
KW - Catastrophic forgetting
KW - class incremental learning
KW - fault diagnosis
KW - unsupervised domain adaptation
KW - unsupervised transfer learning
UR - http://www.scopus.com/inward/record.url?scp=86000384298&partnerID=8YFLogxK
U2 - 10.1109/TIM.2024.3500047
DO - 10.1109/TIM.2024.3500047
M3 - Article
AN - SCOPUS:86000384298
SN - 0018-9456
VL - 74
JO - IEEE Transactions on Instrumentation and Measurement
JF - IEEE Transactions on Instrumentation and Measurement
M1 - 3500614
ER -