Deep imbalanced domain adaptation for transfer learning fault diagnosis of bearings under multiple working conditions. (February 2023)

• Record Type: Journal Article
• Authors: Ding, Yifei; Jia, Minping; Zhuang, Jichao; Cao, Yudong; Zhao, Xiaoli; Lee, Chi-Guhn
• Is Part Of: Reliability engineering & system safety. Volume 230(2023)
• Publication Date: 2023-02
• Subjects: Fault diagnosis -- Bearings -- Imbalanced domain adaptation -- Label shift -- Domain shift; Reliability (Engineering) -- Periodicals; System safety -- Periodicals; Industrial safety -- Periodicals; Fiabilité -- Périodiques; Sécurité des systèmes -- Périodiques; Sécurité du travail -- Périodiques; 620.00452
• DOI: 10.1016/j.ress.2022.108890
• Languages: English
• ISSNs: 0951-8320

Abstract

Abstract: The tremendous success of deep learning and transfer learning broadened the scope of fault diagnosis, especially the latter further improved the diagnosis accuracy under multiple working conditions. However, most existing attempts assume that label distribution is domain-invariant despite taking into account the different feature distributions. This does not accommodate the diversity of fault mode distributions under different operating conditions and weakens the generalization to imbalanced domain adaptation (IDA) scenarios. Therefore, this work proposed a novel deep imbalanced domain adaptation (DIDA) framework for fault diagnosis of bearings, aiming at the challenging scenario where feature shift and label shift exist simultaneously under different working conditions. Specifically, DIDA overcomes the class-imbalanced label shift and achieves a fine-grained latent space matching by cost-sensitive learning and categorical alignment. Besides, margin loss regularization is introduced to further optimize classification boundaries and improve cross-domain generalization for IDA fault diagnosis tasks. Finally, we simulated the IDA protocols on experimental datasets and conducted case studies under multiple working conditions, thus validating the effectiveness and superiority of the proposed framework. Highlights: A novel deep imbalanced domain adaptation (DIDA) is proposed. DIDA narrows both feature shift and label shift. DIDA broadens fault diagnosis to IDA scenarios. Experimental case studies verified validity and superiority.