Wheel flat detection using long short-term memory and transformer models with a 1:10 scale railway test rig

In railway systems, the detection of wheel flats is essential for ensuring safety and reducing maintenance costs. This study compares the performance of Long Short-Term Memory and Transformer models in detecting wheel flats using data from a 1:10 scale railway test rig. The findings indicate that th...

Full description

Saved in:
Bibliographic Details
Main Authors: Yong Cui, Euiyoul Kim, Shizhe Yan, Qing Yu
Format: Article
Language:English
Published: SAGE Publishing 2025-01-01
Series:Advances in Mechanical Engineering
Online Access:https://doi.org/10.1177/16878132251314988
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850173373864214528
author Yong Cui
Euiyoul Kim
Shizhe Yan
Qing Yu
author_facet Yong Cui
Euiyoul Kim
Shizhe Yan
Qing Yu
author_sort Yong Cui
collection DOAJ
description In railway systems, the detection of wheel flats is essential for ensuring safety and reducing maintenance costs. This study compares the performance of Long Short-Term Memory and Transformer models in detecting wheel flats using data from a 1:10 scale railway test rig. The findings indicate that the Transformer model significantly outperforms the Long Short-Term Memory model, especially when feature-level sensor fusion is employed, achieving an average error as low as 0.0069 mm with percentage of error at 5.30%, minimizing the maximum error to 0.0985 mm. The study emphasizes the potential of Transformer models in railway diagnostics, particularly for applications requiring high accuracy and reliability. The insights gained from this research have practical implications for improving the precision of wheel flat detection in real-world railway operations, enhancing both safety and efficiency.
format Article
id doaj-art-ab5e9b73a6b04b82bbff528b1b725c25
institution OA Journals
issn 1687-8140
language English
publishDate 2025-01-01
publisher SAGE Publishing
record_format Article
series Advances in Mechanical Engineering
spelling doaj-art-ab5e9b73a6b04b82bbff528b1b725c252025-08-20T02:19:51ZengSAGE PublishingAdvances in Mechanical Engineering1687-81402025-01-011710.1177/16878132251314988Wheel flat detection using long short-term memory and transformer models with a 1:10 scale railway test rigYong Cui0Euiyoul Kim1Shizhe Yan2Qing Yu3Chinese-German Research and Development Centre for Railway and Transportation Technology Stuttgart (CDFEB e. V.), Stuttgart, GermanyChinese-German Research and Development Centre for Railway and Transportation Technology Stuttgart (CDFEB e. V.), Stuttgart, GermanySchool of Urban Construction and Transportation, Anhui Provincial Key Laboratory of Urban Rail Transit Safety and Emergency Management, Hefei University, Hefei, Anhui, ChinaChinese-German Research and Development Centre for Railway and Transportation Technology Stuttgart (CDFEB e. V.), Stuttgart, GermanyIn railway systems, the detection of wheel flats is essential for ensuring safety and reducing maintenance costs. This study compares the performance of Long Short-Term Memory and Transformer models in detecting wheel flats using data from a 1:10 scale railway test rig. The findings indicate that the Transformer model significantly outperforms the Long Short-Term Memory model, especially when feature-level sensor fusion is employed, achieving an average error as low as 0.0069 mm with percentage of error at 5.30%, minimizing the maximum error to 0.0985 mm. The study emphasizes the potential of Transformer models in railway diagnostics, particularly for applications requiring high accuracy and reliability. The insights gained from this research have practical implications for improving the precision of wheel flat detection in real-world railway operations, enhancing both safety and efficiency.https://doi.org/10.1177/16878132251314988
spellingShingle Yong Cui
Euiyoul Kim
Shizhe Yan
Qing Yu
Wheel flat detection using long short-term memory and transformer models with a 1:10 scale railway test rig
Advances in Mechanical Engineering
title Wheel flat detection using long short-term memory and transformer models with a 1:10 scale railway test rig
title_full Wheel flat detection using long short-term memory and transformer models with a 1:10 scale railway test rig
title_fullStr Wheel flat detection using long short-term memory and transformer models with a 1:10 scale railway test rig
title_full_unstemmed Wheel flat detection using long short-term memory and transformer models with a 1:10 scale railway test rig
title_short Wheel flat detection using long short-term memory and transformer models with a 1:10 scale railway test rig
title_sort wheel flat detection using long short term memory and transformer models with a 1 10 scale railway test rig
url https://doi.org/10.1177/16878132251314988
work_keys_str_mv AT yongcui wheelflatdetectionusinglongshorttermmemoryandtransformermodelswitha110scalerailwaytestrig
AT euiyoulkim wheelflatdetectionusinglongshorttermmemoryandtransformermodelswitha110scalerailwaytestrig
AT shizheyan wheelflatdetectionusinglongshorttermmemoryandtransformermodelswitha110scalerailwaytestrig
AT qingyu wheelflatdetectionusinglongshorttermmemoryandtransformermodelswitha110scalerailwaytestrig