Machine learning-based wear fault diagnosis for marine diesel engine by fusing multiple data-driven models

作者：

Highlights：

• Demerits of single data-driven models can be overcome by fusing their outputs.

• ER rule distinguishes single model reliability and importance weight in model fusion.

• Model accuracy and stability are used to determine the reliability of single model.

摘要

•Demerits of single data-driven models can be overcome by fusing their outputs.•ER rule distinguishes single model reliability and importance weight in model fusion.•Model accuracy and stability are used to determine the reliability of single model.

论文关键词：Wear fault diagnosis,Marine diesel engine,Machine learning-based diagnostic model,Fusion system,ER rule

论文评审过程：Received 28 February 2019, Revised 30 November 2019, Accepted 30 November 2019, Available online 6 December 2019, Version of Record 7 February 2020.

论文官网地址：https://doi.org/10.1016/j.knosys.2019.105324