Computational Technology Resources - CCC

M.C.A. Viana, P.G. Ramos, A.J.C.R. Tameirao, A.C. Pires, G.F.M. Santos, A.A Santos, "Generation of Realistic Artificial Track Irregularities for Multibody Simulation using Measured Geometric Data - from Mid-Chord to Space-Curve", in J. Pombo, (Editor), "Proceedings of the Fifth International Conference on Railway Technology: Research, Development and Maintenance", Civil-Comp Press, Edinburgh, UK, Online volume: CCC 1, Paper 31.14, 2022, doi:10.4203/ccc.1.31.14

Keywords: heavy haul railway, track irregularities, machine learning, multibody simulation, power spectral density, artificial neural network.

Abstract

The inclusion of geometric irregularities in railway simulations is essential since these track imperfections directly interfere with the vehicle’s dynamics. Since railways are constantly monitored by a control car, responsible for measuring irregularities and collecting information from the track, an option for railway simulations would be to use these measurements as an irregularity input in the software. The factor that makes this alternative impossible is that multibody simulation software only accepts irregularities in space-curve coordinates, while most measurements made track measurement car are using a mid-chord coordinate system. This paper presents a machine learning model to transform the railway irregularities measured from the mid-cord into space-curve. The transformed data is represented as a power spectrum density (PSD) function, to be used in the multibody simulation software SIMPACK. The best model was an Artificial Neural Network (ANN) with a R2 coefficient of 0.9444 for vertical track irregularity and 0.8982 for horizontal track irregularity. For validation of the created PSD, results show the dynamic behaviour of a freight vehicle built in the SIMPACK in a real track fragment. The use of Wavelet Coherence showed a high correlation of around 0.95, confirming the correlation between the signal from simulations that used track irregularities generated by the PSD and the signal generated by simulations performed with the measured irregularities in space-curve.

download the full-text of this paper (PDF, 7 pages, 391 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: 1 PROCEEDINGS OF THE FIFTH INTERNATIONAL CONFERENCE ON RAILWAY TECHNOLOGY: RESEARCH, DEVELOPMENT AND MAINTENANCE Edited by: J. Pombo Paper 31.14 Generation of Realistic Artificial Track Irregularities for Multibody Simulation using Measured Geometric Data - from Mid-Chord to Space-Curve M.C.A. Viana¹, P.G. Ramos², A.J.C.R. Tameirao¹, A.C. Pires², G.F.M. Santos¹ and A.A Santos² ¹Department of Mechanical Engineering, Federal University of Espírito Santo, Vitória, Brazil ² Department of Mechanical Engineering, State University of Campinas, Campinas Brazil doi:10.4203/ccc.1.31.14 Full Bibliographic Reference for this paper M.C.A. Viana, P.G. Ramos, A.J.C.R. Tameirao, A.C. Pires, G.F.M. Santos, A.A Santos, "Generation of Realistic Artificial Track Irregularities for Multibody Simulation using Measured Geometric Data - from Mid-Chord to Space-Curve", in J. Pombo, (Editor), "Proceedings of the Fifth International Conference on Railway Technology: Research, Development and Maintenance", Civil-Comp Press, Edinburgh, UK, Online volume: CCC 1, Paper 31.14, 2022, doi:10.4203/ccc.1.31.14 Keywords: heavy haul railway, track irregularities, machine learning, multibody simulation, power spectral density, artificial neural network. Abstract The inclusion of geometric irregularities in railway simulations is essential since these track imperfections directly interfere with the vehicle’s dynamics. Since railways are constantly monitored by a control car, responsible for measuring irregularities and collecting information from the track, an option for railway simulations would be to use these measurements as an irregularity input in the software. The factor that makes this alternative impossible is that multibody simulation software only accepts irregularities in space-curve coordinates, while most measurements made track measurement car are using a mid-chord coordinate system. This paper presents a machine learning model to transform the railway irregularities measured from the mid-cord into space-curve. The transformed data is represented as a power spectrum density (PSD) function, to be used in the multibody simulation software SIMPACK. The best model was an Artificial Neural Network (ANN) with a R2 coefficient of 0.9444 for vertical track irregularity and 0.8982 for horizontal track irregularity. For validation of the created PSD, results show the dynamic behaviour of a freight vehicle built in the SIMPACK in a real track fragment. The use of Wavelet Coherence showed a high correlation of around 0.95, confirming the correlation between the signal from simulations that used track irregularities generated by the PSD and the signal generated by simulations performed with the measured irregularities in space-curve. download the full-text of this paper (PDF, 7 pages, 391 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