Deep learning fault diagnosis method based on global optimization GAN for unbalanced data

作者：

Highlights：

• Design a new generator to generate fault feature rather than the fault data itself.

• Design a two-hierarchical discriminator which can filter unqualified fault samples.

• Generator, discriminator and DNN fault diagnosis model are alternatively optimized.

摘要

•Design a new generator to generate fault feature rather than the fault data itself.•Design a two-hierarchical discriminator which can filter unqualified fault samples.•Generator, discriminator and DNN fault diagnosis model are alternatively optimized.

论文关键词：Fault diagnosis,Unbalance data,Global optimization,GAN,Deep learning

论文评审过程：Received 13 March 2019, Revised 5 July 2019, Accepted 6 July 2019, Available online 9 July 2019, Version of Record 18 November 2019.

论文官网地址：https://doi.org/10.1016/j.knosys.2019.07.008