A small-sample faulty line detection method based on generative adversarial networks

作者：

Highlights：

• A faulty line detection method based on a lightweight depth separable convolution.

• A data augmentation method based on a generative adversarial networks.

• The proposed method has high accuracy of faulty line detection on small samples.

• The effectiveness of the proposed method is verified by several experiments.

摘要

•A faulty line detection method based on a lightweight depth separable convolution.•A data augmentation method based on a generative adversarial networks.•The proposed method has high accuracy of faulty line detection on small samples.•The effectiveness of the proposed method is verified by several experiments.

论文关键词：Depthwise separable convolutional networks (DSCNs),Faulty line detection,Generative adversarial network with Wasserstein distance (WGAN),Small current grounded system (SCGS),Small sample

论文评审过程：Received 24 September 2020, Revised 29 October 2020, Accepted 24 November 2020, Available online 10 December 2020, Version of Record 11 January 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2020.114378