A Machine Learning Approach for Real-Time Wheel-Rail Interface Friction Estimation

被引：4

作者：

Folorunso, Morinoye O. O. ^{[1
]}

Watson, Michael ^{[1
]}

Martin, Alan ^{[1
]}

Whittle, Jacob W. W. ^{[1
]}

Sutherland, Graham ^{[2
]}

Lewis, Roger ^{[1
]}

机构：

[1] Univ Sheffield, Dept Mech Engn, Sheffield S3 1JD, England

[2] Consulting Canetia Analyt Inc, San Diego, CA 92007 USA

来源：

JOURNAL OF TRIBOLOGY-TRANSACTIONS OF THE ASME | 2023年 / 145卷 / 09期

基金：

英国工程与自然科学研究理事会;

关键词：

low adhesion; wheel-rail interface; friction prediction; machine learning;

D O I：

10.1115/1.4062373

中图分类号：

TH [机械、仪表工业];

学科分类号：

0802 ;

摘要：

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 R-2 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.

引用

页数：10

共 50 条

[21] Real-time Detection of Human Falls in Progress: Machine Learning Approach
Serpen, Gursel
Khan, Rakibul Hasan
CYBER PHYSICAL SYSTEMS AND DEEP LEARNING, 2018, 140 : 238 - 247
[22] A machine learning approach for accurate and real-time DNA sequence identification
Yiren Wang
Mashari Alangari
Joshua Hihath
Arindam K. Das
M. P. Anantram
BMC Genomics, 22
[23] Influence of ambient humidity on the adhesion and damage behavior of wheel-rail interface under hot weather condition
Rong, Kang-jie
Xiao, Ye-long
Shen, Ming-xue
Zhao, Huo-ping
Wang, Wen-Jian
Xiong, Guang-yao
WEAR, 2021, 486
[24] An unsupervised machine learning approach for real-time damage detection in bridges
Bayane, Imane
Leander, John
Karoumi, Raid
ENGINEERING STRUCTURES, 2024, 308
[25] Development of the wheel-rail interface management model and its applications in heavy haul operations
Wu, H.
Kalay, S.
Tournay, H.
PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART F-JOURNAL OF RAIL AND RAPID TRANSIT, 2011, 225 (F1) : 38 - 47
[26] Towards accurate real-time luminescence thermometry: An automated machine learning approach
Santos, Emanuel P.
Pugina, Roberta S.
Hilario, Eloisa G.
Carvalho, Alyson J. A.
Jacinto, Carlos
Rego-Filho, Francisco A. M. G.
Canabarro, Askery
Gomes, Anderson S. L.
Caiut, Jose Mauricio A.
Moura, Andre L.
SENSORS AND ACTUATORS A-PHYSICAL, 2023, 362
[27] Data-Triggered Approach for Real-Time Machine Learning in IoT Systems
Cheng, Tou
Coulibaly, Falla
Patooghy, Ahmad
Kursun, Olcay
2020 IEEE 63RD INTERNATIONAL MIDWEST SYMPOSIUM ON CIRCUITS AND SYSTEMS (MWSCAS), 2020, : 101 - 104
[28] A novel machine learning based tangent stiffness calculation method for 3D wheel-rail interaction element
Pan, Jinghao
Huang, Caigui
Huang, Surong
Gu, Quan
ADVANCES IN STRUCTURAL ENGINEERING, 2022, 25 (10) : 2043 - 2057
[29] Real-time wind estimation from the internal sensors of an aircraft using machine learning
Motamedi, Ali
Sabzehparvar, Mehdi
Mortazavi, Mahdi
Soft Computing, 2024, 28 (17-18) : 10601 - 10628
[30] Deep Learning Approach for a Machine-Human interface based on optical real-time Gesture Recognition for Automated Guided Vehicles
Krishnakumar, Kiran Raj
Gersmeier, Laura
Harders, Leif Ole
Hussmann, Stephan
REAL-TIME PROCESSING OF IMAGE, DEPTH, AND VIDEO INFORMATION 2024, 2024, 13000

← 1 2 3 4 5 →