A novel symplectic relevance matrix machine method for intelligent fault diagnosis of roller bearing

作者：

Highlights：

• A novel symplectic relevance matrix machine (SRMM) is proposed.

• The problem of model complexity and time-consuming parameter optimization is avoided.

• The prediction results of SRMM have statistical significance.

• SRMM can protect the original structure information of the signal and has robustness.

摘要

•A novel symplectic relevance matrix machine (SRMM) is proposed.•The problem of model complexity and time-consuming parameter optimization is avoided.•The prediction results of SRMM have statistical significance.•SRMM can protect the original structure information of the signal and has robustness.

论文关键词：Symplectic relevance matrix machine,Probability framework,Symplectic geometry similarity transformation,Fault diagnosis

论文评审过程：Received 22 October 2021, Revised 21 November 2021, Accepted 10 December 2021, Available online 17 December 2021, Version of Record 22 December 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.116400