Abstract
Predicting friction at the wheel-rail interface is a key problem in the rail industry. Current forecasts give regional-level predictions, however, it is well known that friction conditions can change dramatically over a few hundred meters. In this study, we aimed to produce a proof-of-concept friction prediction tool which could be used on trains to give an indication of the limiting friction present at a precise location. To this end, field data including temperature, humidity, friction, and images were collected. These were used to fit a statistical model including effects of local environmental conditions, surroundings, and railhead state. The model predicted the friction well with an R2 of 0.97, falling to 0.96 for naive models in cross validation. With images and environmental data collected on a train, a real-time friction measurement would be possible.
References
1.
European Environment Agency
, 2021
, “Rail and Waterborne—Best for Low-Carbon Motorised Transport
,” Publications Office Luxembourg.2.
Lightoller
, A.
, and Purcell
, L.
, 2020
, “Low Adhesion and Sanders
,” PWI
, 138
, pp. 28
–33
.3.
Monsuur
, F.
, Enoch
, M.
, Quddus
, M.
, and Meek
, S.
, 2021
, “Modelling the Impact of Rail Delays on Passenger Satisfaction
,” Transp. Res. Part A Policy Pract.
, 152
, pp. 19
–35
. 4.
Kalker
, J. J.
, 1982
, “A Fast Algorithm for the Simplified Theory of Rolling Contact
,” Veh. Syst. Dyn.
, 11
(1
), pp. 1
–13
. 5.
Bernal
, E.
, Spiryagin
, M.
, Stichel
, S.
, Bosso
, N.
, Lewis
, R.
, Bosomworth
, C.
, Wu
, Q.
, and Cole
, C.
, 2022
, “Friction-Slip Curves—The Pathway From Twin-Disc Tribo Measurements to Full-Scale Locomotive Multibody Simulations
,” 2022 Joint Rail Conference
, p. V001T07A005
.6.
Chevalier
, L.
, Eddhahak-Ouni
, A.
, and Cloupet
, S.
, 2008
, “On a Simplified Model for Numerical Simulation of Wear During Dry Rolling Contacts
,” ASME J. Tribol.
, 131
(1
), p. 011402
. 7.
Kalker
, J. J.
, 1990
, Three-Dimensional Elastic Bodies in Rolling Contact
, Springer, Dordrecht, Netherlands
.8.
de Mul
, J. M.
, Kalker
, J. J.
, and Fredriksson
, B.
, 1986
, “The Contact Between Arbitrarily Curved Bodies of Finite Dimensions
,” ASME J. Tribol.
, 108
(1
), pp. 140
–148
. 9.
Meierhofer
, A.
, 2015
, “A New Wheel-Rail Creep Force Model Based on Elasto-Plastic Third Body Layers
.”10.
Trummer
, G.
, Buckley-Johnstone
, L. E.
, Voltr
, P.
, Meierhofer
, A.
, Lewis
, R.
, and Six
, K.
, 2017
, “Wheel-Rail Creep Force Model for Predicting Water Induced Low Adhesion Phenomena
,” Tribol. Int.
, 109
, pp. 409
–415
. 11.
Buckley-Johnstone
, L.
, Lewis
, R.
, Six
, K.
, Trummer
, G.
, Stow
, J.
, and Alturbeh
, H.
, 2020
, “T1149: Extension of WILAC Low Adhesion Mode
,” RSSB Project Report.12.
El Rashidy
, R.
, Stow
, J.
, Chapman
, V.
, Fawcett
, L.
, and Dyer
, E.
, 2020
, “Feasibility of Integrating Operational Data With Adhesion Forecasts
,” Report No. COF-FCA-03, 29-07-2020. Institute of Railway Research, University of Huddersfield, The Met Office.13.
Bauroth
, S
, 2022
, “AI Holds Key to Improving Biodiversity by Britain’s Railway Tracks
,” https://keen-ai.com/blog/ai-holds-key-to-improving-biodiversity-by-britains-railway-tracks/. Accessed November 15, 2022.14.
OneBigCircle
, 2022
, “Case Study: Network Rail
,” https://onebigcircle.co.uk/case-study-networkrail/, Accessed November 15, 2022.15.
Marian
, M.
, and Tremmel
, S.
, 2021
, “Current Trends and Applications of Machine Learning in Tribology—A Review
,” Lubricants
, 9
(9
), p. 86
. 16.
Chambers
, J. M.
, and Hastie
, T. J.
, 2017
, “Statistical Models,” Statistical Models in S
, Routledge
, UK
, pp. 13
–44
.17.
Bishop
, C. M.
, and Nasrabadi
, N. M.
, 2006
, Pattern Recognition and Machine Learning
, Springer
, New York
.18.
Folorunso
, M. O.
, Lewis
, R.
, and Lanigan
, J. L.
, 2022
, “Effects of Temperature and Humidity on Railhead Friction Levels
,” Proc. Inst. Mech. Eng. Part F J. Rail Rapid Transit
, 0
, p. 09544097221148236
. 19.
RSSB
, 2008
, Guidance on Wheel/Rail Low Adhesion Measurement, London
.20.
Lewis
, R.
, Lewis
, S. R.
, Zhu
, Y.
, Abbasi
, S.
, and Olofsson
, U.
, 2013
, “The Modification of a Slip Resistance Meter for Measurement of Railhead Adhesion
,” Proc. Inst. Mech. Eng. Part F. J. Rail Rapid. Transit.
, 227
(2
), pp. 196
–200
. 21.
White
, B.
, 2018
, “Using Tribo-Chemistry Analysis to Understand Low Adhesion in the Wheel-Rail Contact
,” University of Sheffield
, Sheffield, UK
.22.
George
, A.
, and Vidyapeetham
, A.
, 2012
, “Anomaly Detection Based on Machine Learning: Dimensionality Reduction Using PCA and Classification Using SVM
,” Int. J. Comput. Appl.
, 47
(21
), pp. 5
–8
. 23.
Van der Walt
, S.
, Schönberger
, J. L.
, Nunez-Iglesias
, J.
, Boulogne
, F.
, Warner
, J. D.
, Yager
, N.
, Gouillart
, E.
, and Yu
, T.
, 2014
, “. Scikit-Image: Image Processing in Python
,” PeerJ
, 2
, p. e453
. 24.
Lee
, J.
, Bahri
, Y.
, Novak
, R.
, Schoenholz
, S. S.
, Pennington
, J.
, and Sohl-Dickstein
, J.
, “Deep Neural Networks as Gaussian Processes
,” arXiv preprint arXiv:171100165 2017.25.
Hasan
, M. S.
, Kordijazi
, A.
, Rohatgi
, P. K.
, and Nosonovsky
, M.
, 2022
, “Triboinformatics Approach for Friction and Wear Prediction of Al-Graphite Composites Using Machine Learning Methods
,” ASME J. Tribol.
, 144
(2
), p. 011701
. 26.
Xie
, H.
, Wang
, Z.
, Qin
, N.
, Du
, W.
, and Qian
, L.
, 2020
, “Prediction of Friction Coefficients During Scratch Based on an Integrated Finite Element and Artificial Neural Network Method
,” ASME J. Tribol.
, 142
(2
), p. 021703
. Copyright © 2023 by ASME
You do not currently have access to this content.
