Imbalanced bearing fault diagnosis under variant working conditions using cost-sensitive deep domain adaptation network

作者：

Highlights：

• An imbalanced bearing fault diagnostic model under variant conditions is proposed.

• A joint transfer network with marginal and conditional distribution is developed.

• Pseudo label strategy guarantees a good accuracy and fast convergence.

摘要

•An imbalanced bearing fault diagnostic model under variant conditions is proposed.•A joint transfer network with marginal and conditional distribution is developed.•Pseudo label strategy guarantees a good accuracy and fast convergence.

论文关键词：Transfer learning,Fault diagnosis,Class imbalance,Domain adaptation,Deep learning

论文评审过程：Received 18 February 2021, Revised 23 December 2021, Accepted 23 December 2021, Available online 12 January 2022, Version of Record 17 January 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.116459