Open AccessResearch on Transmission Lines Early Warning Technology Based on Deep Learning
Author(s) -
Kelin Yang,
Yongsheng Xu,
Peng Li,
Ning Shao
Publication year - 2019
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/631/4/042040
Subject(s) - electric power transmission , computer science , warning system , real time computing , transmission (telecommunications) , intrusion detection system , deep learning , intrusion , grid , power grid , power transmission , artificial intelligence , fault (geology) , span (engineering) , power (physics) , telecommunications , electrical engineering , engineering , geology , seismology , physics , civil engineering , geochemistry , geodesy , quantum mechanics
At the present stage, high-voltage transmission lines are distributed in long distance chains, with large space span, complicated meteorological and geographical environment. The operating environment of the transmission lines is poor. Hence, manual patrol and maintenance are difficult. Various faults are very likely to affect the safe and stable operation of the power grid system. Therefore, this paper proposes a transmission lines early warning method based on Deep Learning. Through object detection technology of Deep Learning, intrusion objects in the monitoring screen are automatically identified, at same time, their positions and types are marked. The experimental results show that this method has high accuracy and is suitable for the current power grid monitoring system.