Drive-by damage detection methodology for high-speed railway bridges using sparse autoencoders

IF 4.4 1区 工程技术 Q2 TRANSPORTATION SCIENCE & TECHNOLOGY Railway Engineering Science Pub Date : 2024-08-29 DOI:10.1007/s40534-024-00347-3
Edson Florentino de Souza, Cássio Bragança, Diogo Ribeiro, Túlio Nogueira Bittencourt, Hermes Carvalho
{"title":"Drive-by damage detection methodology for high-speed railway bridges using sparse autoencoders","authors":"Edson Florentino de Souza, Cássio Bragança, Diogo Ribeiro, Túlio Nogueira Bittencourt, Hermes Carvalho","doi":"10.1007/s40534-024-00347-3","DOIUrl":null,"url":null,"abstract":"<p>High-speed railway bridges are essential components of any railway transportation system that should keep adequate levels of serviceability and safety. In this context, drive-by methodologies have emerged as a feasible and cost-effective monitoring solution for detecting damage on railway bridges while minimizing train operation interruptions. Moreover, integrating advanced sensor technologies and machine learning algorithms has significantly enhanced structural health monitoring (SHM) for bridges. Despite being increasingly used in traditional SHM applications, studies using autoencoders within drive-by methodologies are rare, especially in the railway field. This study presents a novel approach for drive-by damage detection in HSR bridges. The methodology relies on acceleration records collected from multiple bridge crossings by an operational train equipped with onboard sensors. Log-Mel spectrogram features derived from the acceleration records are used together with sparse autoencoders for computing statistical distribution-based damage indexes. Numerical simulations were performed on a 3D vehicle–track–bridge interaction system model implemented in Matlab to evaluate the robustness and effectiveness of the proposed approach, considering several damage scenarios, vehicle speeds, and environmental and operational variations, such as multiple track irregularities and varying measurement noise. The results show that the proposed approach can successfully detect damages, as well as characterize their severity, especially for very early-stage damages. This demonstrates the high potential of applying Mel-frequency damage-sensitive features associated with machine learning algorithms in the drive-by condition assessment of high-speed railway bridges.</p>","PeriodicalId":41270,"journal":{"name":"Railway Engineering Science","volume":"70 1","pages":""},"PeriodicalIF":4.4000,"publicationDate":"2024-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Railway Engineering Science","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.1007/s40534-024-00347-3","RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"TRANSPORTATION SCIENCE & TECHNOLOGY","Score":null,"Total":0}
引用次数: 0

Abstract

High-speed railway bridges are essential components of any railway transportation system that should keep adequate levels of serviceability and safety. In this context, drive-by methodologies have emerged as a feasible and cost-effective monitoring solution for detecting damage on railway bridges while minimizing train operation interruptions. Moreover, integrating advanced sensor technologies and machine learning algorithms has significantly enhanced structural health monitoring (SHM) for bridges. Despite being increasingly used in traditional SHM applications, studies using autoencoders within drive-by methodologies are rare, especially in the railway field. This study presents a novel approach for drive-by damage detection in HSR bridges. The methodology relies on acceleration records collected from multiple bridge crossings by an operational train equipped with onboard sensors. Log-Mel spectrogram features derived from the acceleration records are used together with sparse autoencoders for computing statistical distribution-based damage indexes. Numerical simulations were performed on a 3D vehicle–track–bridge interaction system model implemented in Matlab to evaluate the robustness and effectiveness of the proposed approach, considering several damage scenarios, vehicle speeds, and environmental and operational variations, such as multiple track irregularities and varying measurement noise. The results show that the proposed approach can successfully detect damages, as well as characterize their severity, especially for very early-stage damages. This demonstrates the high potential of applying Mel-frequency damage-sensitive features associated with machine learning algorithms in the drive-by condition assessment of high-speed railway bridges.

Abstract Image

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
使用稀疏自动编码器的高速铁路桥梁驱动损坏检测方法
高速铁路桥梁是铁路运输系统的重要组成部分,应保持足够的适用性和安全性。在这种情况下,逐向监测方法已成为一种可行且经济有效的监测解决方案,可用于检测铁路桥梁的损坏情况,同时最大限度地减少列车运行中断。此外,整合先进的传感器技术和机器学习算法也大大增强了桥梁结构健康监测(SHM)的功能。尽管自动编码器在传统的 SHM 应用中得到了越来越多的使用,但在驱动式方法中使用自动编码器的研究并不多见,尤其是在铁路领域。本研究提出了一种新颖的方法,用于高铁桥梁的逐次损伤检测。该方法依赖于装有车载传感器的运行列车从多个过桥处收集的加速度记录。从加速度记录中提取的 Log-Mel 频谱特征与稀疏自动编码器一起用于计算基于统计分布的损伤指数。在 Matlab 中实现的三维车辆-轨道-桥梁交互系统模型上进行了数值模拟,以评估所提出方法的鲁棒性和有效性,其中考虑了多种损坏情况、车辆速度以及环境和运行变化,如多种轨道不规则情况和不同的测量噪声。结果表明,所提出的方法可以成功地检测出损坏情况,并确定其严重程度,特别是对于非常早期的损坏。这表明,将与机器学习算法相关的梅尔频率损伤敏感特征应用于高速铁路桥梁的行车状态评估具有很大的潜力。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
Railway Engineering Science
Railway Engineering Science TRANSPORTATION SCIENCE & TECHNOLOGY-
CiteScore
10.80
自引率
7.90%
发文量
1061
审稿时长
15 weeks
期刊介绍: Railway Engineering Science is an international, peer-reviewed, and free open-access journal that publishes original research articles and comprehensive reviews related to fundamental engineering science and emerging technologies in rail transit systems, focusing on the cutting-edge research in high-speed railway, heavy-haul railway, urban rail transit, maglev system, hyperloop transportation, etc. The main goal of the journal is to maintain high quality of publications, serving as a medium for railway academia and industry to exchange new ideas and share the latest achievements in scientific research, technical innovation and industrial development in railway science and engineering. The topics include but are not limited to Design theory and construction technology System dynamics and safetyElectrification, signaling and communicationOperation and maintenanceSystem health monitoring and reliability Environmental impact and sustainabilityCutting-edge technologiesThe publication costs for Railway Engineering Science are fully covered by Southwest Jiaotong University so authors do not need to pay any article-processing charges.
期刊最新文献
Shear strength characteristics of mixing slag-stone ballast reinforcement with tire geo-scrap using large-scale direct shear tests Innovative and cost-effective rail track construction using recycled rubber Drive-by damage detection methodology for high-speed railway bridges using sparse autoencoders Carbody sway behaviour of railway vehicles due to track irregularity from rail alternate side wear Advancing high-speed train gearbox durability: enhanced bearing load and contact stress through transition from helical to herringbone gears
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1