One-shot learning for acoustic diagnosis of industrial machines
作者：
Highlights：
• A system for automatic acoustic monitoring of machine health is presented.
• We introduce the one-shot learning paradigm into the specific domain.
• The system classifies machine states, detects novel ones, and incorporates online.
• We achieve state of the art results under poor data and evolving environments.
• Obtained predictions are interpretable by examining layer-wise activation maps.
摘要
•A system for automatic acoustic monitoring of machine health is presented.•We introduce the one-shot learning paradigm into the specific domain.•The system classifies machine states, detects novel ones, and incorporates online.•We achieve state of the art results under poor data and evolving environments.•Obtained predictions are interpretable by examining layer-wise activation maps.
论文关键词：Machine acoustics,Machine health condition monitoring,One-shot learning,Fault diagnosis,Deep learning,Online learning
论文评审过程：Received 17 July 2020, Revised 16 February 2021, Accepted 30 March 2021, Available online 6 April 2021, Version of Record 16 April 2021.
论文官网地址：https://doi.org/10.1016/j.eswa.2021.114984
