A neuro-inspired computational model for adaptive fault diagnosis
作者：
Highlights：
• The neural process of conscious attention is emulated for adaptive fault diagnosis.
• The model is based on the theory of dynamic core hypothesis in neurobiology.
• The computational model applies convolutional neural networks and transfer learning.
• The model is applied to NASA C-MAPSS turbofan engine model as a case study.
• Application potentials for adaptive process monitoring and improvement are outlined.
摘要
•The neural process of conscious attention is emulated for adaptive fault diagnosis.•The model is based on the theory of dynamic core hypothesis in neurobiology.•The computational model applies convolutional neural networks and transfer learning.•The model is applied to NASA C-MAPSS turbofan engine model as a case study.•Application potentials for adaptive process monitoring and improvement are outlined.
论文关键词：Machine consciousness,Deep learning,Convolutional neural networks,Transfer learning
论文评审过程：Received 25 March 2019, Revised 28 June 2019, Accepted 16 August 2019, Available online 17 August 2019, Version of Record 23 August 2019.
论文官网地址：https://doi.org/10.1016/j.eswa.2019.112879
