Meta-learning as a promising approach for few-shot cross-domain fault diagnosis: Algorithms, applications, and prospects

作者：

Highlights：

• Review the advances of meta-learning in fault diagnosis for the first time.

• Demonstrate deep meta-learning in fault diagnosis via algorithms and applications.

• Illuminate meta-learning algorithms by mathematical optimization.

• Stimulate future work with open challenges and prospects.

摘要

•Review the advances of meta-learning in fault diagnosis for the first time.•Demonstrate deep meta-learning in fault diagnosis via algorithms and applications.•Illuminate meta-learning algorithms by mathematical optimization.•Stimulate future work with open challenges and prospects.

论文关键词：Meta-learning,Few-shot learning,Small sample,Cross-domain,Fault diagnosis

论文评审过程：Received 17 June 2021, Revised 6 September 2021, Accepted 30 September 2021, Available online 27 October 2021, Version of Record 2 November 2021.

论文官网地址：https://doi.org/10.1016/j.knosys.2021.107646