Computational Technology Resources - CCC

M. Nabais, J. Torres, J. Pagaimo, S. Vieira, H. Magalhaes, "Data-Driven Models for the Classification and Estimation of Railway Track Irregularities Based on Vehicle Dynamics", in J. Pombo, (Editor), "Proceedings of the Seventh International Conference on Railway Technology: Research, Development and Maintenance ", Civil-Comp Press, Edinburgh, UK, Online volume: CCC 15, Paper 7.7, 2026, doi:10.4203/ccc.15.7.7

Keywords: railway track geometry, condition monitoring, vehicle dynamics, multibody simulation, machine learning, convolutional neural networks.

Abstract

Railway track geometry maintenance is crucial for ensuring the comfort, safety, and efficiency of railway operations. Traditional inspection systems, however, rely on costly specialized vehicles, which limits inspection frequency and delays maintenance interventions. To overcome these limitations, this study presents a data-driven methodology that utilizes vehicle dynamic responses to classify and estimate track irregularities. A high-fidelity multibody (MB) model of the EM120 inspection vehicle is developed to simulate realistic operating conditions and map the correlations between vehicle behavior and track defects. A comprehensive dataset, generated from track segments with known irregularities, is used to train and evaluate various Artificial Intelligence (AI) models. The results demonstrate a strong correlation between track irregularities and bogie frame dynamics, enabling highly accurate classification of track sections. This research confirms the feasibility of continuous track condition monitoring using a simple sensor module mounted on the bogie frame, offering a scalable and cost-effective strategy for predictive railway maintenance.

download the full-text of this paper (PDF, 8 pages, 427 Kb)

go to the previous paper
go to the next paper
return to the table of contents
return to the volume description

	Computational & Technology Resources an online resource for computational, engineering & technology publications
	not logged in - login
Front Page Browse CCC CCP CSETS CTR IJRT Other Authors Search Purchase Guide FAQ Contact us	Civil-Comp Conferences ISSN 2753-3239 CCC: 15 PROCEEDINGS OF THE SEVENTH INTERNATIONAL CONFERENCE ON RAILWAY TECHNOLOGY: RESEARCH, DEVELOPMENT AND MAINTENANCE Edited by: J. Pombo Paper 7.7 Data-Driven Models for the Classification and Estimation of Railway Track Irregularities Based on Vehicle Dynamics M. Nabais, J. Torres, J. Pagaimo, S. Vieira and H. Magalhaes IDMEC, Instituto Superior Técnico, Universidade de Lisboa, Lisbon, Portugal doi:10.4203/ccc.15.7.7 Full Bibliographic Reference for this paper M. Nabais, J. Torres, J. Pagaimo, S. Vieira, H. Magalhaes, "Data-Driven Models for the Classification and Estimation of Railway Track Irregularities Based on Vehicle Dynamics", in J. Pombo, (Editor), "Proceedings of the Seventh International Conference on Railway Technology: Research, Development and Maintenance ", Civil-Comp Press, Edinburgh, UK, Online volume: CCC 15, Paper 7.7, 2026, doi:10.4203/ccc.15.7.7 Keywords: railway track geometry, condition monitoring, vehicle dynamics, multibody simulation, machine learning, convolutional neural networks. Abstract Railway track geometry maintenance is crucial for ensuring the comfort, safety, and efficiency of railway operations. Traditional inspection systems, however, rely on costly specialized vehicles, which limits inspection frequency and delays maintenance interventions. To overcome these limitations, this study presents a data-driven methodology that utilizes vehicle dynamic responses to classify and estimate track irregularities. A high-fidelity multibody (MB) model of the EM120 inspection vehicle is developed to simulate realistic operating conditions and map the correlations between vehicle behavior and track defects. A comprehensive dataset, generated from track segments with known irregularities, is used to train and evaluate various Artificial Intelligence (AI) models. The results demonstrate a strong correlation between track irregularities and bogie frame dynamics, enabling highly accurate classification of track sections. This research confirms the feasibility of continuous track condition monitoring using a simple sensor module mounted on the bogie frame, offering a scalable and cost-effective strategy for predictive railway maintenance. download the full-text of this paper (PDF, 8 pages, 427 Kb) go to the previous paper go to the next paper return to the table of contents return to the volume description
Back to top	©Civil-Comp Limited 2023 - terms & conditions