A new subset based deep feature learning method for intelligent fault diagnosis of bearing
作者：
Highlights：
• A subset approach for bearing vibration signal is proposed.
• A subset based deep auto-encoder feature learning model is proposed.
• A self-adaptive fine-tuning operation is developed to enhance feature learning.
• Particle swarm algorithm is used to optimize the key parameters.
• Effectiveness of the model is demonstrated in 3 bearing case studies.
摘要
•A subset approach for bearing vibration signal is proposed.•A subset based deep auto-encoder feature learning model is proposed.•A self-adaptive fine-tuning operation is developed to enhance feature learning.•Particle swarm algorithm is used to optimize the key parameters.•Effectiveness of the model is demonstrated in 3 bearing case studies.
论文关键词：Bearing intelligent fault diagnosis,Deep feature learning,Subset approach,Deep auto-encoder,Particle swarm optimization
论文评审过程：Received 8 September 2017, Revised 29 May 2018, Accepted 29 May 2018, Available online 2 June 2018, Version of Record 18 June 2018.
论文官网地址：https://doi.org/10.1016/j.eswa.2018.05.032
