Self-learning transferable neural network for intelligent fault diagnosis of rotating machinery with unlabeled and imbalanced data

作者：

Highlights：

• A novel STNN is proposed for the intelligent fault diagnosis of rotating machinery.

• Three novel loss terms are constructed motivated by learning strategy of human being.

• Proposed method can well adapt to the situation of unlabeled and imbalanced datasets.

• The effectiveness of the proposed method is verified by two experimental cases.

摘要

•A novel STNN is proposed for the intelligent fault diagnosis of rotating machinery.•Three novel loss terms are constructed motivated by learning strategy of human being.•Proposed method can well adapt to the situation of unlabeled and imbalanced datasets.•The effectiveness of the proposed method is verified by two experimental cases.

论文关键词：Intelligent diagnosis,Self-learning,Transfer learning,Imbalanced dataset,Unlabeled dataset

论文评审过程：Received 19 April 2021, Revised 26 June 2021, Accepted 6 August 2021, Available online 9 August 2021, Version of Record 24 August 2021.

论文官网地址：https://doi.org/10.1016/j.knosys.2021.107374