Research on fault Q&A system for train-controlled on-board equipment based on knowledge graph

Yingyuan Zhi; Yonggang Chen; Haiyong Wang

doi:10.1117/12.3039734

28 August 2024 Research on fault Q&A system for train-controlled on-board equipment based on knowledge graph

Yingyuan Zhi, Yonggang Chen, Haiyong Wang

Proceedings Volume 13251, Ninth International Conference on Electromechanical Control Technology and Transportation (ICECTT 2024); 1325129 (2024) https://doi.org/10.1117/12.3039734
Event: 9th International Conference on Electromechanical Control Technology and Transportation (ICECTT 2024), 2024, Guilin, China

Abstract

At present, the presentation of the knowledge graph of train-controlled on-board equipment is only one model in most cases, the entity extraction process is more complicated, and there is a lack of Q&A system and other related practical applications. In view of the above problems, the paper proposes to apply the deep learning model to the entity recognition in order to improve the accuracy rate, F₁, and increase the faults of the other four models to make the presentation of the graph more complete, and ultimately combine the knowledge graph, graph database, natural language processing, knowledge quiz and other technologies are combined with this field. This paper adopts entity extraction,relationship extraction, entity alignment and knowledge storage to create a knowledge map of train-controlled on-board equipment faults, and accordingly realises the construction of a Q&A system to provide auxiliary decision-making for railway maintenance personnel.

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

Citation Download Citation

Yingyuan Zhi, Yonggang Chen, and Haiyong Wang "Research on fault Q&A system for train-controlled on-board equipment based on knowledge graph", Proc. SPIE 13251, Ninth International Conference on Electromechanical Control Technology and Transportation (ICECTT 2024), 1325129 (28 August 2024); https://doi.org/10.1117/12.3039734

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