A Machine Learning Approach for Real-Time Wheel-Rail Interface Friction EstimationSource: Journal of Tribology:;2023:;volume( 145 ):;issue: 009::page 91102-1Author:Folorunso, Morinoye O.
,
Watson, Michael
,
Martin, Alan
,
Whittle, Jacob W.
,
Sutherland, Graham
,
Lewis, Roger
DOI: 10.1115/1.4062373Publisher: The American Society of Mechanical Engineers (ASME)
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.
|
Collections
Show full item record
contributor author | Folorunso, Morinoye O. | |
contributor author | Watson, Michael | |
contributor author | Martin, Alan | |
contributor author | Whittle, Jacob W. | |
contributor author | Sutherland, Graham | |
contributor author | Lewis, Roger | |
date accessioned | 2023-08-16T18:05:16Z | |
date available | 2023-08-16T18:05:16Z | |
date copyright | 5/12/2023 12:00:00 AM | |
date issued | 2023 | |
identifier issn | 0742-4787 | |
identifier other | trib_145_9_091102.pdf | |
identifier uri | http://yetl.yabesh.ir/yetl1/handle/yetl/4291381 | |
description 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. | |
publisher | The American Society of Mechanical Engineers (ASME) | |
title | A Machine Learning Approach for Real-Time Wheel-Rail Interface Friction Estimation | |
type | Journal Paper | |
journal volume | 145 | |
journal issue | 9 | |
journal title | Journal of Tribology | |
identifier doi | 10.1115/1.4062373 | |
journal fristpage | 91102-1 | |
journal lastpage | 91102-10 | |
page | 10 | |
tree | Journal of Tribology:;2023:;volume( 145 ):;issue: 009 | |
contenttype | Fulltext |