An adaptive deep learning framework to classify unknown composite power quality event using known single power quality events

作者：

Highlights：

• Classification of unknown composite PQD variations with high performance using known PQD variations.

• Development of an adaptive CNN architecture that is responsive to different numbers of IMF inputs.

• Flexible architecture is suitable for working with different signal processing methods such as EMD and VMD.

• High classification performance compared to current state-of-the-art methods.

摘要

•Classification of unknown composite PQD variations with high performance using known PQD variations.•Development of an adaptive CNN architecture that is responsive to different numbers of IMF inputs.•Flexible architecture is suitable for working with different signal processing methods such as EMD and VMD.•High classification performance compared to current state-of-the-art methods.

论文关键词：Power quality disturbance (PQD),Deep learning,CNN,Classification,Signal monitoring,Signal disturbance

论文评审过程：Received 16 January 2021, Revised 1 April 2021, Accepted 8 April 2021, Available online 13 April 2021, Version of Record 29 April 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.115023