Multi-perspective deep transfer learning model: A promising tool for bearing intelligent fault diagnosis under varying working conditions
作者：
Highlights：
• Multi-perspective DTL model is presented for bearing intelligent fault diagnosis.
• High-level discriminative features are extracted by the proposed MPDTL model.
• Spatial and channel attention mechanisms are considered into the proposed model.
• Our model well adapts to transfer diagnosis tasks under varying working conditions.
• Three types of REBs experiments are conducted to validate the proposed method.
摘要
•Multi-perspective DTL model is presented for bearing intelligent fault diagnosis.•High-level discriminative features are extracted by the proposed MPDTL model.•Spatial and channel attention mechanisms are considered into the proposed model.•Our model well adapts to transfer diagnosis tasks under varying working conditions.•Three types of REBs experiments are conducted to validate the proposed method.
论文关键词：Intelligent diagnosis,Deep transfer model,Multi-perspective,Attention mechanism,Discriminative features
论文评审过程：Received 21 December 2021, Revised 26 January 2022, Accepted 10 February 2022, Available online 17 February 2022, Version of Record 2 March 2022.
论文官网地址：https://doi.org/10.1016/j.knosys.2022.108443
