An approach to fault diagnosis of reciprocating compressor valves using Teager–Kaiser energy operator and deep belief networks

作者：

Highlights：

• A new scheme for fault diagnosis of reciprocating compressor valves is proposed.

• The proposed scheme is evaluated with experimental data.

• A comparative study of diagnosis results is carried out.

• The improvement of classification accuracy is demonstrated.

摘要

•A new scheme for fault diagnosis of reciprocating compressor valves is proposed.•The proposed scheme is evaluated with experimental data.•A comparative study of diagnosis results is carried out.•The improvement of classification accuracy is demonstrated.

论文关键词：Fault diagnosis,Teager–Kaiser energy operator,Deep belief networks,Reciprocating compressor

论文评审过程：Available online 29 December 2013.

论文官网地址：https://doi.org/10.1016/j.eswa.2013.12.026