Computational Technology Resources - CCC

K. Nakano¹, K. Yabuuchi¹, S. Kuniyuki², W. Wang¹, K. Iida², T. Tanaka² and T. Miyamoto³

¹Institute of Industrial Science, The University of Tokyo, Japan
², Railway Technical Research Institute, Japan
³, Meisei University, Japan

doi:10.4203/ccc.15.3.8

K. Nakano, K. Yabuuchi, S. Kuniyuki, W. Wang, K. Iida, T. Tanaka, T. Miyamoto, "Machine Learning-Based Estimation of Wheel-Rail Contact Conditions from Instrumented Wheelset Data", 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 3.8, 2026, doi:10.4203/ccc.15.3.8

Keywords: Running safety assessment, instrumented wheelset assessment, wheel–rail contact conditions, angle of attack, friction coefficient, machine learning.

Abstract

This study proposes a machine learning-based method to estimate wheel–rail contact conditions from instrumented wheelset (PQ wheelset) measurements for running safety assessment. A multibody dynamics-based vehicle dynamics simulation is used to generate large training datasets covering various speeds, curve radii, and friction conditions. LightGBM and a one-dimensional convolutional neural network are adopted to estimate the angle of attack, lateral contact position, and friction coefficient. Validation under unseen loading and track irregularity conditions demonstrates sufficient practical estimation accuracy over a wide range of speeds and curve radii, supporting real-time safety evaluation.

download the full-text of this paper (PDF, 12 pages, 1208 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 3.8 Machine Learning-Based Estimation of Wheel-Rail Contact Conditions from Instrumented Wheelset Data K. Nakano¹, K. Yabuuchi¹, S. Kuniyuki², W. Wang¹, K. Iida², T. Tanaka² and T. Miyamoto³ ¹Institute of Industrial Science, The University of Tokyo, Japan ², Railway Technical Research Institute, Japan ³, Meisei University, Japan doi:10.4203/ccc.15.3.8 Full Bibliographic Reference for this paper K. Nakano, K. Yabuuchi, S. Kuniyuki, W. Wang, K. Iida, T. Tanaka, T. Miyamoto, "Machine Learning-Based Estimation of Wheel-Rail Contact Conditions from Instrumented Wheelset Data", 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 3.8, 2026, doi:10.4203/ccc.15.3.8 Keywords: Running safety assessment, instrumented wheelset assessment, wheel–rail contact conditions, angle of attack, friction coefficient, machine learning. Abstract This study proposes a machine learning-based method to estimate wheel–rail contact conditions from instrumented wheelset (PQ wheelset) measurements for running safety assessment. A multibody dynamics-based vehicle dynamics simulation is used to generate large training datasets covering various speeds, curve radii, and friction conditions. LightGBM and a one-dimensional convolutional neural network are adopted to estimate the angle of attack, lateral contact position, and friction coefficient. Validation under unseen loading and track irregularity conditions demonstrates sufficient practical estimation accuracy over a wide range of speeds and curve radii, supporting real-time safety evaluation. download the full-text of this paper (PDF, 12 pages, 1208 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