Research on fault identification method of railroad fastener based on center point prediction network

Zihao Chen; Zhen Han

doi:10.1117/12.3037448

27 September 2024 Research on fault identification method of railroad fastener based on center point prediction network

Zihao Chen, Zhen Han

Author Affiliations +

Proceedings Volume 13275, Sixth International Conference on Information Science, Electrical, and Automation Engineering (ISEAE 2024); 132751R (2024) https://doi.org/10.1117/12.3037448
Event: 6th International Conference on Information Science, Electrical, and Automation Engineering (ISEAE 2024), 2024, Wuhan, China

Abstract

Currently, image detection based on deep learning has a good application prospect for railroad fault diagnosis. However, the existing methods of applying deep learning to fastener fault detection more or less have some drawbacks, such as computational complexity, slow detection speed, low detection accuracy, poor robustness, etc. To address these issues, this paper introduces a fastener fault identification method for railroad lines based on CenterNet. By introducing the Convolutional Block Attention Module and the jump connection mechanism, and conducting comparative experiments on different networks, it is proved that the network proposed in this paper has a better speed and accuracy for fastener detection.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Zihao Chen and Zhen Han "Research on fault identification method of railroad fastener based on center point prediction network", Proc. SPIE 13275, Sixth International Conference on Information Science, Electrical, and Automation Engineering (ISEAE 2024), 132751R (27 September 2024); https://doi.org/10.1117/12.3037448

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