JZUS - Journal of Zhejiang University SCIENCE

Journal of Zhejiang University SCIENCE A

Accepted manuscript available online (unedited version)

Self-attention and convolutional feature fusion for real-time intelligent fault detection of high-speed railway pantographs

Author(s): Xufeng LI¹, Jien MA¹, Ping TAN², Lanfen LIN³, Lin QIU¹, Youtong FANG¹
Affiliation(s): ¹College of Electrical Engineering, Zhejiang University, Hangzhou 310027, China; more
Corresponding email(s): majien@zju.edu.cn, 115011@zust.edu.cn
Key Words: High-speed railway pantograph; self-attention; CNN; real-time; feature fusion; fault detection

Share this article to： More <<< Previous Paper \|Next Paper >>>

Xufeng LI¹, Jien MA¹, Ping TAN², Lanfen LIN³, Lin QIU¹, Youtong FANG¹. Self-attention and convolutional feature fusion for real-time intelligent fault detection of high-speed railway pantographs[J]. Journal of Zhejiang University Science A,in press.Frontiers of Information Technology & Electronic Engineering,in press.https://doi.org/10.1631/jzus.A2400549

@article{title="Self-attention and convolutional feature fusion for real-time intelligent fault detection of high-speed railway pantographs",
author="Xufeng LI¹, Jien MA¹, Ping TAN², Lanfen LIN³, Lin QIU¹, Youtong FANG¹",
journal="Journal of Zhejiang University Science A",
year="in press",
publisher="Zhejiang University Press & Springer",
doi="https://doi.org/10.1631/jzus.A2400549"
}

%0 Journal Article
%T Self-attention and convolutional feature fusion for real-time intelligent fault detection of high-speed railway pantographs
%A Xufeng LI¹
%A Jien MA¹
%A Ping TAN²
%A Lanfen LIN³
%A Lin QIU¹
%A Youtong FANG¹
%J Journal of Zhejiang University SCIENCE A
%P
%@ 1673-565X
%D in press
%I Zhejiang University Press & Springer
doi="https://doi.org/10.1631/jzus.A2400549"

TY - JOUR
T1 - Self-attention and convolutional feature fusion for real-time intelligent fault detection of high-speed railway pantographs
A1 - Xufeng LI¹
A1 - Jien MA¹
A1 - Ping TAN²
A1 - Lanfen LIN³
A1 - Lin QIU¹
A1 - Youtong FANG¹
J0 - Journal of Zhejiang University Science A
SP -
EP -
%@ 1673-565X
Y1 - in press
PB - Zhejiang University Press & Springer
ER -
doi="https://doi.org/10.1631/jzus.A2400549"

Abstract
Chinese Summary
Academic Network
Reviewer Comment

Abstract: Currently, most trains are equipped with dedicated cameras for capturing pantograph videos. Pantographs are core to the high-speed-railway pantograph-catenary system and their failure directly affects the normal operation of high-speed trains. However, given the complex and variable real-world operational conditions of high-speed railways, there is no real-time and robust pantograph fault-detection method capable of handling large volumes of surveillance video. Hence, it is of paramount importance to maintain real-time monitoring and analysis of pantographs. Our study presents a real-time intelligent detection technology for identifying faults in high-speed railway pantographs, utilizing a fusion of self-attention and convolution features. We delved into lightweight multi-scale feature-extraction and fault-detection models based on deep learning to detect pantograph anomalies. Compared with traditional methods, this approach achieves high recall and accuracy in pantograph recognition, accurately pinpointing issues like discharge sparks, pantograph horns, and carbon pantograph-slide malfunctions. After experimentation and validation with actual Electric Multiple Units train-surveillance videos, our algorithmic model demonstrates real-time, high-accuracy performance even under complex operational conditions.

Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article

Reference

Open peer comments: Debate/Discuss/Question/Opinion

<1>

- Go to

Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article

Reference