Detection of railway wheel and rail diseases based on distributed optical fiber acoustic sensing

Wei Tang; Linyu Peng; Zhaojie Li; Kang Liu; Zhen Pan; Shu Yuan; Lang Xie

doi:10.1117/12.2643822

19 December 2022 Detection of railway wheel and rail diseases based on distributed optical fiber acoustic sensing

Wei Tang, Linyu Peng, Zhaojie Li, Kang Liu, Zhen Pan, Shu Yuan, Lang Xie

Proceedings Volume 12321, Advanced Sensor Systems and Applications XII; 1232115 (2022) https://doi.org/10.1117/12.2643822
Event: SPIE/COS Photonics Asia, 2022, Online Only

Conference Poster

Abstract

This research proposes a real-time detection method for the health status of heavy-haul railways based on distributed fiber optic acoustic sensing (DAS). The DAS system detects the wheel-rail acoustic signals using the communication optical cable along the heavy-haul railway, multiple features are mixed to construct an eigenvector and a classifier to realize the typical disaster identification of the heavy-haul railway. The experimental results show that this system can realize the identification and classification of typical track diseases such as rolling contact fatigue (RCF), corrugation, unsupported sleepers on the railway, the achieved average identification rate of disease events is as high as 97.3%, and the identification time of a single event sample is 1ms. This work can achieve real-time detection of track diseases, which can be used as an important basis for workers to maintain and repair. In addition, the DAS system has also successfully monitored the train's running speed and wheel anomalies status information. This work provides a long-term online monitoring method for rail safety operation and maintenance of railway transportation and monitoring of train running status, and does not require any additional sensor arrangement.

Citation Download Citation

Wei Tang, Linyu Peng, Zhaojie Li, Kang Liu, Zhen Pan, Shu Yuan, and Lang Xie "Detection of railway wheel and rail diseases based on distributed optical fiber acoustic sensing", Proc. SPIE 12321, Advanced Sensor Systems and Applications XII, 1232115 (19 December 2022); https://doi.org/10.1117/12.2643822

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available