ITSC 2024 Paper Abstract

Close

Paper ThBT13.4

Kalapati, Devakanth (Alstom), Credoz, Arwan (Alstom), Staino, Andrea (Alstom)

An AI-Based Method for Predictive Maintenance of Railway Radio Communication Systems

Scheduled for presentation during the Poster Session "Railway systems and applications" (ThBT13), Thursday, September 26, 2024, 14:30−16:30, Foyer

2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC), September 24- 27, 2024, Edmonton, Canada

This information is tentative and subject to change. Compiled on December 26, 2024

Keywords Data Mining and Data Analysis, Off-line and Online Data Processing Techniques, Other Theories, Applications, and Technologies

Abstract

An Artificial Intelligence (AI)-based method for detection and classification of issues in railway radiocommunication networks is described in this paper. Healthy condition and consistent operational efficiency of radio-based signalling technologies are critical for reliability, availability and safety of railway operation. Conventional monitoring and troubleshooting activities performed by radio engineers could be complex and tedious. The proposed method enables early detection and localization of degradations affecting the communication system. First, a novel pre-processing strategy is implemented to combine radio measurements and signalling information. This strategy allows to account for the influence of context factors such as the train speed on the raw measurements. Subsequently, an approach based on functional analysis is proposed to learn the operational condition of the radio links. An appropriate health indicator for detection of the state of health of the associated radio equipment is designed accordingly. Once a significant deviation from the initial state is observed, the specific degradation affecting the system is classified by using supervised machine learning algorithms. Further, an expert-based recommendation is sent to the maintainer so that the degradation can be timely corrected before the failure state is reached. Application of the proposed method on field data reveals that, thanks to the AI-based maintenance strategy, the risk of loss of communication can be significantly mitigated.

 

 

All Content © PaperCept, Inc.


This site is protected by copyright and trademark laws under US and International law.
All rights reserved. © 2002-2024 PaperCept, Inc.
Page generated 2024-12-26  06:15:24 PST  Terms of use