Multiscale cascading deep belief network for fault identification of rotating machinery under various working conditions

作者：

Highlights：

• Multiscale coarse-grained procedure is combined with DBN to develop a MCDBN.

• A MCDBN-based end-to-end fault diagnosis scheme is proposed.

• The proposed algorithm is validated using experimental data.

• Compared with DBN and some shallow learning, MCDBN can achieve higher accuracy.

摘要

•Multiscale coarse-grained procedure is combined with DBN to develop a MCDBN.•A MCDBN-based end-to-end fault diagnosis scheme is proposed.•The proposed algorithm is validated using experimental data.•Compared with DBN and some shallow learning, MCDBN can achieve higher accuracy.

论文关键词：Deep belief network,Multiscale feature learning,Rotating machinery,Fault identification

论文评审过程：Received 8 June 2019, Revised 9 November 2019, Accepted 6 January 2020, Available online 9 January 2020, Version of Record 7 March 2020.

论文官网地址：https://doi.org/10.1016/j.knosys.2020.105484