Visual inspection of fault type and zone prediction in electrical grids using interpretable spectrogram-based CNN modeling

作者：

Highlights：

• Visual representation of electrical signal by using spectrogram-based CNN modeling.

• Building a visually interpretable fault type and zone classification system.

• A highly accurate system able to provide individual or joint FTC or FZC.

• Comparison with a large number of baselines using DFT or DWT.

摘要

•Visual representation of electrical signal by using spectrogram-based CNN modeling.•Building a visually interpretable fault type and zone classification system.•A highly accurate system able to provide individual or joint FTC or FZC.•Comparison with a large number of baselines using DFT or DWT.

论文关键词：Fault diagnosis,Visual explanation,Smart grids,Interpretability

论文评审过程：Received 22 October 2021, Revised 10 July 2022, Accepted 1 August 2022, Available online 6 August 2022, Version of Record 17 August 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.118368