An expert system for EMI data classification based on complex Bispectrum representation and deep learning methods

作者：

Highlights：

• Novel Deep Learning based approach is proposed for insulation fault classification.

• Real-world measured Electromagnetic Interference signals are analysed.

• Complex Bispectrum is employed to retrieve phase related information from the signals.

• The proposed approach successfully classifies the fault signals.

摘要

•Novel Deep Learning based approach is proposed for insulation fault classification.•Real-world measured Electromagnetic Interference signals are analysed.•Complex Bispectrum is employed to retrieve phase related information from the signals.•The proposed approach successfully classifies the fault signals.

论文关键词：Complex and real-valued Bispectrum,Condition monitoring,Deep learning,EMI diagnostic,Expert system,Insulation faults

论文评审过程：Received 10 November 2019, Revised 6 August 2020, Accepted 1 January 2021, Available online 7 January 2021, Version of Record 29 January 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.114568