Ensemble transfer CNNs driven by multi-channel signals for fault diagnosis of rotating machinery cross working conditions

作者：

Highlights：

• CNN is modified with stochastic pooling and Leaky rectified linear unit.

• Multi-channel signals are used to pre-train a series of CNNs.

• Transfer CNN is constructed with parameter transfer strategy.

• A new decision fusion strategy is designed based on flexible weight assignment.

摘要

•CNN is modified with stochastic pooling and Leaky rectified linear unit.•Multi-channel signals are used to pre-train a series of CNNs.•Transfer CNN is constructed with parameter transfer strategy.•A new decision fusion strategy is designed based on flexible weight assignment.

论文关键词：Fault diagnosis,Rotating machinery,Ensemble transfer CNN,Multi-channel signals,Decision fusion

论文评审过程：Received 14 January 2020, Revised 7 August 2020, Accepted 8 August 2020, Available online 17 August 2020, Version of Record 21 August 2020.

论文官网地址：https://doi.org/10.1016/j.knosys.2020.106396