Year: 2021
Type: article
Abstract: This paper proposes a new Image-to-Image Translation (Pix2Pix) enabled deep learning method for traveling wave-based fault location. Unlike the previous methods that require a high sampling frequency of the PMU, the proposed method can translate the scale 1 detail component image provided by the low frequency PMU data to higher frequency ones via the Pix2Pix. This allows us to significantly improve the fault location accuracy. Test results via the YOLO v3 object recognition algorithm show that the images generated by pix2pix can be accurately identified. This enables to improve the estimation accuracy of the arrival time of the traveling wave head, leading to better fault location outcomes.
Source: Sensors
DOI: 10.3390/s21051633
Authors: Jinxian Zhang, Qingwu Gong, Haojie Zhang, Yubo Wang, Yilin Wang
Institution: Wuhan University
Language: English
Subfield: Control and Systems Engineering
Field: Engineering
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $2,376
OpenAlex ID: W3133069477