Transportation Engineering最新文献

Fault detection, isolation, identification and recovery methods for perception systems in automated railway transport: A review 铁路运输自动化感知系统的故障检测、隔离、识别和恢复方法综述

Q1 Engineering

Transportation Engineering

Pub Date : 2026-01-14 DOI: 10.1016/j.treng.2026.100421

Kevin Renatus , Marc David Rabe , Bernard Baeker , Thomas Waschulzik , Kai Schories

Significantly motivated by climate protection, not only Germany considers shifting the expanding transport sector towards more railway transport. The growing demand for train drivers stands in contrast to the demographic change, which causes a shortage of skilled workers. As a result, automatic train operation is gaining importance, because it offers perspectives regarding increased efficiency and safety. The publicly funded pilot project ‘AutomatedTrain’ aims to demonstrate unattended train operation during provisioning and stabling. To reach the highest grade of automation (GoA4), an extensive front monitor system for environmental perception is developed. Multiple LiDAR, RADAR, camera and ultrasonic sensors enable object detection, traffic guidance monitoring and distance estimation for continuous train control. Such sensors and related components underlie the risk of degradation and faults, often caused by environmental impacts like adverse weather, as seen in automotive applications. To avoid train control failures, a robust diagnostic system for fault detection, isolation, identification and recovery (FDIIR) is crucial.

This publication first identifies typical perception system design approaches based on existing vehicle applications. Secondly, possible environmental impacts on sensors as well as resulting anomalies, faults and failure modes are determined. Thirdly, we present a systematic review of FDIIR methods with a view to future applications in public transport vehicles. The focus lies on operational reporting, in case of functional limitation, loss of redundancy or demand for maintenance. Unplanned corrective maintenance disrupts train operations, and planned preventive maintenance is inefficient. Thus, we emphasize predictive maintenance strategies towards fail-operational systems with increased availability, reliability and safety.

在气候保护的大力推动下，不仅德国考虑将日益扩大的交通运输部门转向更多的铁路运输。对火车司机日益增长的需求与导致熟练工人短缺的人口变化形成鲜明对比。因此，自动列车操作变得越来越重要，因为它提供了提高效率和安全性的前景。政府资助的试点项目“自动化列车”旨在演示在供应和稳定期间无人值守的列车运行。为了达到最高的自动化等级（GoA4），开发了一个广泛的环境感知前端监测系统。多个激光雷达、雷达、摄像头和超声波传感器可实现目标检测、交通引导监控和距离估计，从而实现连续列车控制。这些传感器和相关部件存在退化和故障的风险，通常是由恶劣天气等环境影响引起的，就像汽车应用中看到的那样。为了避免列车控制故障，一个强大的故障检测、隔离、识别和恢复（FDIIR）诊断系统至关重要。本出版物首先确定了基于现有车辆应用的典型感知系统设计方法。其次，确定可能的环境对传感器的影响以及由此产生的异常、故障和失效模式。第三，我们对FDIIR方法进行了系统的回顾，以期在未来的公共交通工具中的应用。在功能限制、冗余丢失或维护需求的情况下，重点在于操作报告。计划外的纠正性维修会扰乱列车运行，而计划内的预防性维修效率低下。因此，我们强调对故障运行系统的预测性维护策略，以提高可用性、可靠性和安全性。

{"title":"Fault detection, isolation, identification and recovery methods for perception systems in automated railway transport: A review","authors":"Kevin Renatus , Marc David Rabe , Bernard Baeker , Thomas Waschulzik , Kai Schories","doi":"10.1016/j.treng.2026.100421","DOIUrl":"10.1016/j.treng.2026.100421","url":null,"abstract":"<div><div>Significantly motivated by climate protection, not only Germany considers shifting the expanding transport sector towards more railway transport. The growing demand for train drivers stands in contrast to the demographic change, which causes a shortage of skilled workers. As a result, automatic train operation is gaining importance, because it offers perspectives regarding increased efficiency and safety. The publicly funded pilot project ‘AutomatedTrain’ aims to demonstrate unattended train operation during provisioning and stabling. To reach the highest grade of automation (GoA4), an extensive front monitor system for environmental perception is developed. Multiple LiDAR, RADAR, camera and ultrasonic sensors enable object detection, traffic guidance monitoring and distance estimation for continuous train control. Such sensors and related components underlie the risk of degradation and faults, often caused by environmental impacts like adverse weather, as seen in automotive applications. To avoid train control failures, a robust diagnostic system for fault detection, isolation, identification and recovery (FDIIR) is crucial.</div><div>This publication first identifies typical perception system design approaches based on existing vehicle applications. Secondly, possible environmental impacts on sensors as well as resulting anomalies, faults and failure modes are determined. Thirdly, we present a systematic review of FDIIR methods with a view to future applications in public transport vehicles. The focus lies on operational reporting, in case of functional limitation, loss of redundancy or demand for maintenance. Unplanned corrective maintenance disrupts train operations, and planned preventive maintenance is inefficient. Thus, we emphasize predictive maintenance strategies towards fail-operational systems with increased availability, reliability and safety.</div></div>","PeriodicalId":34480,"journal":{"name":"Transportation Engineering","volume":"23 ","pages":"Article 100421"},"PeriodicalIF":0.0,"publicationDate":"2026-01-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146077456","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Resilience of road networks to natural hazards: A systematic literature review 道路网络对自然灾害的恢复力：系统的文献综述

Q1 Engineering

Transportation Engineering

Pub Date : 2026-01-08 DOI: 10.1016/j.treng.2026.100420

Yohannes Sisay Zeleke , Maurizio Tira , Chiara Scaini

Road networks are essential to societal functioning yet remain highly vulnerable to natural hazards and cascading disruptions. This study presents a systematic review of road network resilience, synthesizing resilience metrics, assessment methods, and research gaps. Following the PRISMA 2020 guidelines, 109 peer-reviewed studies published between 2010 and 2025 were analyzed from the ScienceDirect, Scopus, and Web of Science databases. The results indicate that resilience assessment is primarily based on topology-based, functional performance-based, and hybrid metrics, with 31% of studies focusing on robustness and 25% emphasizing vulnerability and preparedness, while only 4% adopt fully integrated resilience frameworks. Methodologically, conventional approaches dominate the literature, including network analysis (24%), GIS-based methods (15%), and uncertainty modeling techniques (15%), alongside traffic assignment, traffic simulation, and agent-based modeling. In contrast, emerging approaches such as graph neural networks, deep reinforcement learning, digital twins, and hybrid data-driven frameworks are applied in no >14% of the reviewed studies, indicating limited but increasing adoption. Despite methodological progress, persistent gaps remain, including limited link-level analysis, inadequate modeling of spatial and temporal traffic dynamics, weak predictive and real-time capability, and insufficient consideration of multi-hazard scenarios. The study highlights the need for integrated frameworks combining machine learning with analytical and simulation-based methods to enhance dynamic resilience assessment and support proactive decision-making.

道路网络对社会运作至关重要，但仍然极易受到自然灾害和连锁破坏的影响。本研究对路网弹性、综合弹性指标、评估方法和研究空白进行了系统综述。根据PRISMA 2020指南，我们分析了2010年至2025年间发表的109项同行评议研究，这些研究来自ScienceDirect、Scopus和Web of Science数据库。结果表明，弹性评估主要基于拓扑、功能性能和混合指标，31%的研究侧重于鲁棒性，25%的研究强调脆弱性和准备，而只有4%的研究采用了完全集成的弹性框架。在方法上，传统方法主导着文献，包括网络分析（24%）、基于gis的方法（15%）和不确定性建模技术（15%），以及交通分配、交通模拟和基于代理的建模。相比之下，图神经网络、深度强化学习、数字双胞胎和混合数据驱动框架等新兴方法在审查的研究中应用了不到14%，表明采用有限但正在增加。尽管在方法上取得了进步，但仍然存在持续的差距，包括有限的链路级分析，空间和时间交通动态建模不足，预测和实时能力弱，以及对多灾害情景的考虑不足。该研究强调需要将机器学习与基于分析和模拟的方法相结合的集成框架，以增强动态弹性评估并支持主动决策。

{"title":"Resilience of road networks to natural hazards: A systematic literature review","authors":"Yohannes Sisay Zeleke , Maurizio Tira , Chiara Scaini","doi":"10.1016/j.treng.2026.100420","DOIUrl":"10.1016/j.treng.2026.100420","url":null,"abstract":"<div><div>Road networks are essential to societal functioning yet remain highly vulnerable to natural hazards and cascading disruptions. This study presents a systematic review of road network resilience, synthesizing resilience metrics, assessment methods, and research gaps. Following the PRISMA 2020 guidelines, 109 peer-reviewed studies published between 2010 and 2025 were analyzed from the ScienceDirect, Scopus, and Web of Science databases. The results indicate that resilience assessment is primarily based on topology-based, functional performance-based, and hybrid metrics, with 31% of studies focusing on robustness and 25% emphasizing vulnerability and preparedness, while only 4% adopt fully integrated resilience frameworks. Methodologically, conventional approaches dominate the literature, including network analysis (24%), GIS-based methods (15%), and uncertainty modeling techniques (15%), alongside traffic assignment, traffic simulation, and agent-based modeling. In contrast, emerging approaches such as graph neural networks, deep reinforcement learning, digital twins, and hybrid data-driven frameworks are applied in no >14% of the reviewed studies, indicating limited but increasing adoption. Despite methodological progress, persistent gaps remain, including limited link-level analysis, inadequate modeling of spatial and temporal traffic dynamics, weak predictive and real-time capability, and insufficient consideration of multi-hazard scenarios. The study highlights the need for integrated frameworks combining machine learning with analytical and simulation-based methods to enhance dynamic resilience assessment and support proactive decision-making.</div></div>","PeriodicalId":34480,"journal":{"name":"Transportation Engineering","volume":"23 ","pages":"Article 100420"},"PeriodicalIF":0.0,"publicationDate":"2026-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145977840","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Energy consequences of separating velocity planning and torque distribution in overactuated electric vehicles 过驱动电动汽车速度规划与扭矩分配分离的能量后果

Q1 Engineering

Transportation Engineering

Pub Date : 2025-12-30 DOI: 10.1016/j.treng.2025.100419

Juliette Torinsson , Mats Jonasson , Derong Yang , Bengt Jacobson , Toheed Ghandriz

This paper investigates the energy consequences of determining the energy-optimal velocity profile and torque distribution sequentially versus jointly in a battery electric vehicle (BEV) with two electric motors, one per axle. Three optimization architectures are evaluated: a centralized architecture (CA), a de-centralized architecture (DCA) and a refined de-centralized architecture (r-DCA). CA jointly optimizes the velocity trajectory and torque distribution for minimal energy consumption in a predictive framework, while DCA solves these subproblems hierarchically: velocity trajectory optimization is performed predictively, and torque distribution is computed instantaneously. The joint optimization in CA leads to a reduction in energy consumption of 3.3% at low velocities and 2.2% in an urban city cycle compared to DCA. To mitigate the energy consequences, the objective function in the predictive layer of DCA is augmented with an aggregated power loss map of the powertrain in r-DCA, which achieves energy savings close to CA.

本文研究了在具有两个电机（每轴一个电机）的纯电动汽车（BEV）中，顺序或联合确定能量最优速度剖面和扭矩分配的能量后果。本文评估了三种优化体系结构：集中式体系结构（CA）、去中心化体系结构（DCA）和改进的去中心化体系结构（r-DCA）。CA在预测框架下共同优化速度轨迹和扭矩分布，以实现能量消耗最小，而DCA则分层次解决这些子问题：预测速度轨迹优化，即时计算扭矩分布。与DCA相比，CA的联合优化导致低速能耗降低3.3%，城市循环能耗降低2.2%。为了减轻能量后果，在r-DCA中，DCA预测层中的目标函数被增强为动力总成的聚合功率损失图，从而实现了接近CA的节能。

引用次数: 0

Low-carbon urban transportation: Optimizing mechanical systems for sustainable electric bus and BRT deployment in Kampala 低碳城市交通：优化坎帕拉可持续电动公交车和快速公交部署的机械系统

Q1 Engineering

Transportation Engineering

Pub Date : 2025-12-13 DOI: 10.1016/j.treng.2025.100417

Ismail Kimuli, John Baptist Kirabira

Kampala faces increasing congestion, air pollution, and dependence on fossil fuels, driven by widespread reliance on diesel minibuses and motorcycle taxis. Existing models—KAMPALA-TIMES, KLAP-TIMES, and GKMA-TIMES–CGE—show strong potential for electrified mass transit to reduce emissions, change commuter behavior, and boost macroeconomic welfare. However, these studies assume electric-bus reliability without examining the mechanical conditions needed to achieve their projected outcomes. This study combines system-level modeling insights with vehicle-level engineering analysis to identify key mechanical factors necessary for the successful deployment of electric Bus Rapid Transit (e-BRT) in Kampala. It considers drivetrain torque for steep gradients, battery thermal management in hot equatorial climates, and regenerative braking efficiency in traffic congestion, alongside policy, infrastructure, and grid readiness. Mechanical performance links modeling to implementation—adequate torque, thermal stability, and regenerative braking efficiency directly affect service reliability, headway adherence, fleet uptime, and lifecycle costs. These operational factors influence commuter mode choices, the realism of bottom-up pathways, and the broader economic benefits predicted in top-down scenarios. Engineering reliability must be a core policy consideration, guiding procurement standards, charging infrastructure design, and multisector coordination among KCCA, MoWT, MEMD, and Uganda’s power utilities. Incorporating mechanical parameters into future bottom-up or hybrid models, combined with digital-twin testing and degradation-aware analytics, will enable Kampala to serve as a living laboratory for low-carbon mobility transitions across Sub-Saharan Africa.

坎帕拉面临着日益严重的交通拥堵、空气污染和对化石燃料的依赖，这是由于对柴油面包车和摩托车的广泛依赖。现有的kampala - times、klapa - times和gkma - times - cge模型显示了电气化公共交通在减少排放、改变通勤行为和提高宏观经济福利方面的巨大潜力。然而，这些研究假设了电动巴士的可靠性，而没有检查实现预期结果所需的机械条件。本研究将系统级建模见解与车辆级工程分析相结合，以确定坎帕拉成功部署电动快速公交（e-BRT）所需的关键机械因素。除了政策、基础设施和电网准备情况外，它还考虑了陡峭坡度下的动力传动系统扭矩、炎热赤道气候下的电池热管理、交通拥堵时的再生制动效率。机械性能将建模与实施联系起来——足够的扭矩、热稳定性和再生制动效率直接影响到服务可靠性、车头依存度、车队正常运行时间和生命周期成本。这些操作因素影响通勤模式的选择，自下而上路径的现实性，以及自上而下情景下预测的更广泛的经济效益。工程可靠性必须成为核心政策考虑因素，指导采购标准、充电基础设施设计以及KCCA、MoWT、MEMD和乌干达电力公司之间的多部门协调。将机械参数纳入未来的自下而上或混合模型，结合数字孪生测试和退化感知分析，将使坎帕拉成为撒哈拉以南非洲地区低碳交通转型的活实验室。

{"title":"Low-carbon urban transportation: Optimizing mechanical systems for sustainable electric bus and BRT deployment in Kampala","authors":"Ismail Kimuli, John Baptist Kirabira","doi":"10.1016/j.treng.2025.100417","DOIUrl":"10.1016/j.treng.2025.100417","url":null,"abstract":"<div><div>Kampala faces increasing congestion, air pollution, and dependence on fossil fuels, driven by widespread reliance on diesel minibuses and motorcycle taxis. Existing models—KAMPALA-TIMES, KLAP-TIMES, and GKMA-TIMES–CGE—show strong potential for electrified mass transit to reduce emissions, change commuter behavior, and boost macroeconomic welfare. However, these studies assume electric-bus reliability without examining the mechanical conditions needed to achieve their projected outcomes. This study combines system-level modeling insights with vehicle-level engineering analysis to identify key mechanical factors necessary for the successful deployment of electric Bus Rapid Transit (e-BRT) in Kampala. It considers drivetrain torque for steep gradients, battery thermal management in hot equatorial climates, and regenerative braking efficiency in traffic congestion, alongside policy, infrastructure, and grid readiness. Mechanical performance links modeling to implementation—adequate torque, thermal stability, and regenerative braking efficiency directly affect service reliability, headway adherence, fleet uptime, and lifecycle costs. These operational factors influence commuter mode choices, the realism of bottom-up pathways, and the broader economic benefits predicted in top-down scenarios. Engineering reliability must be a core policy consideration, guiding procurement standards, charging infrastructure design, and multisector coordination among KCCA, MoWT, MEMD, and Uganda’s power utilities. Incorporating mechanical parameters into future bottom-up or hybrid models, combined with digital-twin testing and degradation-aware analytics, will enable Kampala to serve as a living laboratory for low-carbon mobility transitions across Sub-Saharan Africa.</div></div>","PeriodicalId":34480,"journal":{"name":"Transportation Engineering","volume":"23 ","pages":"Article 100417"},"PeriodicalIF":0.0,"publicationDate":"2025-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145792047","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

The use of Ground Penetrating Radar and artificial intelligence for automated railway trackbed stratigraphy and Ballast Fouling assessment 探地雷达和人工智能技术在铁路轨道地层和道砟污垢自动评估中的应用

Q1 Engineering

Transportation Engineering

Pub Date : 2025-12-10 DOI: 10.1016/j.treng.2025.100415

Ernest Mbubia Tchoua , Jérôme Tissier , Antoine Martin , Yannick Fargier , Amine Ihamouten

Intrusive trenching and coring remain the reference for railway trackbed diagnosis but lack coverage and repeatability. This paper proposes a hybrid GPR–AI framework that automates the detection of dielectric interfaces and the estimation of ballast permittivity and thickness. Synthetic FDTD simulations are used to evaluate Mask Region-based Convolutional Neural Network (Mask R-CNN) for interface segmentation and XGBoost (gradient-boosted trees)/Support Vector Regression(SVR) for layer-wise regression. Results on controlled data confirm high interface detection accuracy (IoU

\approx

0.81) and robust estimation of shallow dielectric parameters (

R^{2} > 0.9

), while sequential conditioning markedly improves deeper-layer predictions. Validation on field measurements acquired with a broadband (40–3000 MHz) GPR antenna array demonstrates good transferability of the methodology, with reliable stratigraphy reconstruction and dielectric-based material attribution along an operational track section. The framework unifies stratigraphy and fouling assessment in a single automated workflow, offering a scalable and interpretable alternative to invasive methods and paving the way for predictive maintenance at the network scale.

侵入式挖沟取芯仍是铁路轨道诊断的参考，但缺乏覆盖面和可重复性。本文提出了一种混合GPR-AI框架，该框架可自动检测介电界面并估计镇流器介电常数和厚度。合成时域有限差分模拟用于评估基于掩模区域的卷积神经网络（Mask R-CNN）用于界面分割和XGBoost（梯度增强树）/支持向量回归（SVR）用于分层回归。控制数据的结果证实了界面检测精度高（IoU≈0.81）和浅层介电参数估计稳健（R2>0.9），而顺序调节显著提高了深层预测。利用宽带（40-3000 MHz）探地雷达天线阵列获得的现场测量数据验证表明，该方法具有良好的可转移性，具有可靠的地层重建和沿运行轨道段的介电材料属性。该框架将地层和结垢评估统一到一个自动化工作流程中，为侵入式方法提供了可扩展和可解释的替代方案，并为网络规模的预测性维护铺平了道路。

{"title":"The use of Ground Penetrating Radar and artificial intelligence for automated railway trackbed stratigraphy and Ballast Fouling assessment","authors":"Ernest Mbubia Tchoua , Jérôme Tissier , Antoine Martin , Yannick Fargier , Amine Ihamouten","doi":"10.1016/j.treng.2025.100415","DOIUrl":"10.1016/j.treng.2025.100415","url":null,"abstract":"<div><div>Intrusive trenching and coring remain the reference for railway trackbed diagnosis but lack coverage and repeatability. This paper proposes a hybrid GPR–AI framework that automates the detection of dielectric interfaces and the estimation of ballast permittivity and thickness. Synthetic FDTD simulations are used to evaluate Mask Region-based Convolutional Neural Network (Mask R-CNN) for interface segmentation and XGBoost (gradient-boosted trees)/Support Vector Regression(SVR) for layer-wise regression. Results on controlled data confirm high interface detection accuracy (IoU <span><math><mo>≈</mo></math></span> 0.81) and robust estimation of shallow dielectric parameters (<span><math><mrow><msup><mrow><mi>R</mi></mrow><mrow><mn>2</mn></mrow></msup><mo>></mo><mn>0</mn><mo>.</mo><mn>9</mn></mrow></math></span>), while sequential conditioning markedly improves deeper-layer predictions. Validation on field measurements acquired with a broadband (40–3000 MHz) GPR antenna array demonstrates good transferability of the methodology, with reliable stratigraphy reconstruction and dielectric-based material attribution along an operational track section. The framework unifies stratigraphy and fouling assessment in a single automated workflow, offering a scalable and interpretable alternative to invasive methods and paving the way for predictive maintenance at the network scale.</div></div>","PeriodicalId":34480,"journal":{"name":"Transportation Engineering","volume":"23 ","pages":"Article 100415"},"PeriodicalIF":0.0,"publicationDate":"2025-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145711873","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Enhancing railway infrastructure monitoring with AI: A machine learning approach for event detection 用人工智能加强铁路基础设施监测：一种用于事件检测的机器学习方法

Q1 Engineering

Transportation Engineering

Pub Date : 2025-12-07 DOI: 10.1016/j.treng.2025.100414

Mohammad Adoul Amin , Taoufik Najeh , Naveen Venkatesh Sridharan , Abdelhamid Ghoul , Ramin Karim

This study presents a machine learning-based framework for detecting critical events in railway infrastructure by analyzing vibration signals from trackside accelerometers. Traditional maintenance is often reactive and labor-intensive, but this approach uses continuous sensing and data analytics to enable proactive, real-time monitoring. The research leverages a comprehensive pipeline that includes data preprocessing, segmentation of time-series data into one-second intervals labeled as "event" or "no-event", and the extraction of statistical, temporal, and spectral features like crest factor and kurtosis. Key contribution of this work is the systematic evaluation of 72 algorithm-feature selection configurations. Twelve diverse classification algorithms were compared, including tree-based, linear, and neural network models. Extensive hyperparameter optimization was performed to benchmark performance using metrics such as accuracy, precision, recall, and F1-score. The Multi-Layer Perceptron (MLPClassifier) achieved a peak cross-validation accuracy of 98.89% with the full feature set. The study also found that comparable accuracy (98.67%) could be achieved with a 47% dimensionality reduction using Recursive Feature Elimination (RFE) with only eight features, demonstrating a balance between efficiency and performance. The findings provide actionable insights for developing scalable, high-performance event detection systems.

本研究提出了一种基于机器学习的框架，通过分析轨道边加速度计的振动信号来检测铁路基础设施中的关键事件。传统的维护通常是被动的和劳动密集型的，但是这种方法使用持续的传感和数据分析来实现主动的、实时的监控。该研究利用了一个全面的管道，包括数据预处理，将时间序列数据分割为一秒间隔，标记为“事件”或“无事件”，以及提取统计，时间和光谱特征，如波峰因子和峰度。这项工作的关键贡献是对72种算法特征选择配置的系统评估。比较了12种不同的分类算法，包括基于树的、线性的和神经网络的模型。使用准确度、精密度、召回率和f1分数等指标对基准性能进行了广泛的超参数优化。多层感知器（MLPClassifier）在完整的特征集上实现了98.89%的峰值交叉验证准确率。该研究还发现，使用递归特征消除（RFE）仅使用8个特征，降低47%的维数，可以达到相当的准确率（98.67%），证明了效率和性能之间的平衡。研究结果为开发可扩展的高性能事件检测系统提供了可行的见解。

{"title":"Enhancing railway infrastructure monitoring with AI: A machine learning approach for event detection","authors":"Mohammad Adoul Amin , Taoufik Najeh , Naveen Venkatesh Sridharan , Abdelhamid Ghoul , Ramin Karim","doi":"10.1016/j.treng.2025.100414","DOIUrl":"10.1016/j.treng.2025.100414","url":null,"abstract":"<div><div>This study presents a machine learning-based framework for detecting critical events in railway infrastructure by analyzing vibration signals from trackside accelerometers. Traditional maintenance is often reactive and labor-intensive, but this approach uses continuous sensing and data analytics to enable proactive, real-time monitoring. The research leverages a comprehensive pipeline that includes data preprocessing, segmentation of time-series data into one-second intervals labeled as \"event\" or \"no-event\", and the extraction of statistical, temporal, and spectral features like crest factor and kurtosis. Key contribution of this work is the systematic evaluation of 72 algorithm-feature selection configurations. Twelve diverse classification algorithms were compared, including tree-based, linear, and neural network models. Extensive hyperparameter optimization was performed to benchmark performance using metrics such as accuracy, precision, recall, and F1-score. The Multi-Layer Perceptron (MLPClassifier) achieved a peak cross-validation accuracy of 98.89% with the full feature set. The study also found that comparable accuracy (98.67%) could be achieved with a 47% dimensionality reduction using Recursive Feature Elimination (RFE) with only eight features, demonstrating a balance between efficiency and performance. The findings provide actionable insights for developing scalable, high-performance event detection systems.</div></div>","PeriodicalId":34480,"journal":{"name":"Transportation Engineering","volume":"23 ","pages":"Article 100414"},"PeriodicalIF":0.0,"publicationDate":"2025-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145739052","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Q1 Engineering

Transportation Engineering

Pub Date : 2025-12-01 DOI: 10.1016/j.treng.2025.100412

Mohei Menul Islam, Quazi Sazzad Hossain

Superpave hot mix asphalt (HMA), a superior-performing mixture compacted by a Superpave gyratory compactor (SGC) at high temperatures, provides better field performance than the Marshall Mix. Concerning economy and environment, reclaimed asphalt pavement (RAP), from old bituminous pavement can be utilized in the Superpave HMA. RAP carries oxidized bitumen, which has a negative impact on the cracking resistance. Polyethylene terephthalate (PET) from waste bottles can make HMA more resistant to cracking, whereas waste oils used as rejuvenators can make RAP less stiff. The opposite phenomenon of RAP and PET in the cracking resistance cannot be properly addressed by using only one cracking resistance evaluation method. Furthermore, to ensure long-term durability of asphalt pavement, age-related cracking resistance is important. Therefore, in this study, the age-related cracking resistance of PET-modified Superpave HMA containing rejuvenated RAP was evaluated by three methods: Illinois Flexibility Index (I-FIT), Louisiana Semi-Circular Bending (SCB), and Cantabro Abrasion test. To manufacture PET-modified and RAP-added Superpave HMA, 2 % and 4 % PET of two sizes, RAP of 0 %, 20 %, and 40 % rejuvenated by waste oil, and SGC for compaction were used. From the results for the I-FIT and SCB method, 4 % finer PET provided more age-related cracking resistance ability of Superpave HMA without RAP. This value was decreased after adding more rejuvenated RAP. The load-displacement diagram showed that 40 % rejuvenated RAP-added HMA had the stiffest slope and maximum peak load, which indicates the brittleness. However, in Cantabro Abrasion loss, the percentage of material loss was increased with PET and rejuvenated RAP.

Superpave热拌沥青（HMA）是一种由Superpave旋转压实机（SGC）在高温下压实的高性能混合物，比Marshall mix具有更好的现场性能。从经济和环境两方面考虑，旧沥青路面的再生沥青路面（RAP）可用于Superpave HMA。RAP携带氧化沥青，对抗裂性能有负面影响。从废瓶中提取的聚对苯二甲酸乙二醇酯（PET）可以使HMA更耐开裂，而用作恢复剂的废油可以使RAP不那么僵硬。RAP和PET在抗裂性上的对立现象，仅用一种抗裂性评价方法无法很好地解决。此外，为了保证沥青路面的长期耐久性，与年龄相关的抗开裂性是很重要的。因此，本研究通过伊利诺伊柔韧性指数（I-FIT）、路易斯安那半圆弯曲（SCB）和Cantabro磨损试验三种方法，对含有回弹RAP的pet改性Superpave HMA的年龄相关抗裂性能进行了评价。制备PET改性和添加RAP的Superpave HMA，采用2%和4%的PET， 0%、20%和40%的RAP进行废油再生，SGC进行压实。从I-FIT和SCB方法的结果来看，4%的细PET在没有RAP的情况下可以提高Superpave HMA的抗年龄相关开裂能力。在加入更多的活化RAP后，这个值降低了。荷载-位移图显示，回复率为40%的添加rap的HMA具有最硬的斜率和最大的峰值荷载，表明其具有脆性。然而，在Cantabro磨损损失中，PET和再生RAP增加了材料损失的百分比。

{"title":"Age-related cracking resistance of waste PET plastic-modified Superpave hot mix asphalt containing rejuvenated RAP","authors":"Mohei Menul Islam, Quazi Sazzad Hossain","doi":"10.1016/j.treng.2025.100412","DOIUrl":"10.1016/j.treng.2025.100412","url":null,"abstract":"<div><div>Superpave hot mix asphalt (HMA), a superior-performing mixture compacted by a Superpave gyratory compactor (SGC) at high temperatures, provides better field performance than the Marshall Mix. Concerning economy and environment, reclaimed asphalt pavement (RAP), from old bituminous pavement can be utilized in the Superpave HMA. RAP carries oxidized bitumen, which has a negative impact on the cracking resistance. Polyethylene terephthalate (PET) from waste bottles can make HMA more resistant to cracking, whereas waste oils used as rejuvenators can make RAP less stiff. The opposite phenomenon of RAP and PET in the cracking resistance cannot be properly addressed by using only one cracking resistance evaluation method. Furthermore, to ensure long-term durability of asphalt pavement, age-related cracking resistance is important. Therefore, in this study, the age-related cracking resistance of PET-modified Superpave HMA containing rejuvenated RAP was evaluated by three methods: Illinois Flexibility Index (I-FIT), Louisiana Semi-Circular Bending (SCB), and Cantabro Abrasion test. To manufacture PET-modified and RAP-added Superpave HMA, 2 % and 4 % PET of two sizes, RAP of 0 %, 20 %, and 40 % rejuvenated by waste oil, and SGC for compaction were used. From the results for the I-FIT and SCB method, 4 % finer PET provided more age-related cracking resistance ability of Superpave HMA without RAP. This value was decreased after adding more rejuvenated RAP. The load-displacement diagram showed that 40 % rejuvenated RAP-added HMA had the stiffest slope and maximum peak load, which indicates the brittleness. However, in Cantabro Abrasion loss, the percentage of material loss was increased with PET and rejuvenated RAP.</div></div>","PeriodicalId":34480,"journal":{"name":"Transportation Engineering","volume":"22 ","pages":"Article 100412"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145680792","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Thermal behavior of permeable pavements under freeze–thaw conditions 冻融条件下透水路面的热特性

Q1 Engineering

Transportation Engineering

Pub Date : 2025-12-01 DOI: 10.1016/j.treng.2025.100400

Dansani Vasanthan Muttuvelu , Lasse Hedegaard Hansen , Ahmad Jan Khattak , Jes Vollertsen

This study develops and validates a one-dimensional (1D) physics-based model for simulating freeze–thaw dynamics in permeable pavements, using field data from a test site in Aalborg, Denmark (2022-2024) that includes continuous temperature measurements at 3, 6, and 30 cm depths and water table observations. The model, adapted from the NOAA framework, incorporates laboratory-measured thermal properties for the engineered pavement layers and uses a custom soil moisture profile to integrate the observed water table data. The calibrated model demonstrated excellent performance, particularly in the permeable subbase layer (30 cm depth), which serves as a rigorous test of the model’s physical realism. At this depth, the model achieved high Nash–Sutcliffe Efficiency (NSE) values of 0.995 for the entire period and 0.990 for the second winter period. Results highlight the critical importance of calibrating global thermal conductivity factors to accurately simulate pavement temperatures, particularly during winter freeze–thaw cycles. Sensitivity analyses confirmed that adjustments to these thermal properties led to substantial improvements in model accuracy in the overlying permeable subbase. While variations in subgrade porosity had minimal impact at shallow depths, they significantly influenced thermal behavior in the subbase. Accurate thermal dynamics predictions are critical for assessing freeze–thaw induced damage mechanisms such as frost heave and thaw settlement, which impact pavement durability. Future research should build upon this thermal foundation by integrating more complex moisture and ice content models to enable physical damage prediction. The developed approach represents an important step towards supporting the long-term resilience of permeable pavement systems in cold climates.

本研究开发并验证了一个一维（1D）物理模型，用于模拟透水路面的冻融动力学，该模型使用了丹麦奥尔堡一个试验场（2022-2024）的现场数据，包括3、6和30厘米深度的连续温度测量和地下水位观测。该模型改编自NOAA框架，结合了实验室测量的工程路面层的热特性，并使用定制的土壤湿度剖面来整合观测到的地下水位数据。校准后的模型表现出优异的性能，特别是在可渗透的亚基层（30厘米深）中，这是对模型物理真实性的严格测试。在该深度，模型在整个冬季和第二个冬季均获得了较高的NSE值，分别为0.995和0.990。结果强调了校准全球导热系数以准确模拟路面温度的重要性，特别是在冬季冻融循环期间。敏感性分析证实，对这些热特性的调整可以显著提高上覆渗透基的模型精度。虽然路基孔隙度的变化对浅深度的影响很小，但它们对底层的热行为有显著影响。准确的热动力学预测对于评估冻融引起的损伤机制（如冻胀和融化沉降）至关重要，这些机制会影响路面的耐久性。未来的研究应该建立在这个热基础上，通过整合更复杂的水分和冰含量模型来实现物理损伤预测。开发的方法代表了在寒冷气候下支持透水路面系统长期弹性的重要一步。

{"title":"Thermal behavior of permeable pavements under freeze–thaw conditions","authors":"Dansani Vasanthan Muttuvelu , Lasse Hedegaard Hansen , Ahmad Jan Khattak , Jes Vollertsen","doi":"10.1016/j.treng.2025.100400","DOIUrl":"10.1016/j.treng.2025.100400","url":null,"abstract":"<div><div>This study develops and validates a one-dimensional (1D) physics-based model for simulating freeze–thaw dynamics in permeable pavements, using field data from a test site in Aalborg, Denmark (2022-2024) that includes continuous temperature measurements at 3, 6, and 30 cm depths and water table observations. The model, adapted from the NOAA framework, incorporates laboratory-measured thermal properties for the engineered pavement layers and uses a custom soil moisture profile to integrate the observed water table data. The calibrated model demonstrated excellent performance, particularly in the permeable subbase layer (30 cm depth), which serves as a rigorous test of the model’s physical realism. At this depth, the model achieved high Nash–Sutcliffe Efficiency (NSE) values of 0.995 for the entire period and 0.990 for the second winter period. Results highlight the critical importance of calibrating global thermal conductivity factors to accurately simulate pavement temperatures, particularly during winter freeze–thaw cycles. Sensitivity analyses confirmed that adjustments to these thermal properties led to substantial improvements in model accuracy in the overlying permeable subbase. While variations in subgrade porosity had minimal impact at shallow depths, they significantly influenced thermal behavior in the subbase. Accurate thermal dynamics predictions are critical for assessing freeze–thaw induced damage mechanisms such as frost heave and thaw settlement, which impact pavement durability. Future research should build upon this thermal foundation by integrating more complex moisture and ice content models to enable physical damage prediction. The developed approach represents an important step towards supporting the long-term resilience of permeable pavement systems in cold climates.</div></div>","PeriodicalId":34480,"journal":{"name":"Transportation Engineering","volume":"22 ","pages":"Article 100400"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145623805","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Cyclic and post-cyclic behavior of stabilized marl soil for pavement engineering applications 稳定泥质土的循环和后循环特性在路面工程中的应用

Q1 Engineering

Transportation Engineering

Pub Date : 2025-12-01 DOI: 10.1016/j.treng.2025.100413

Mehran Moallemi , Mahdi Khodaparast , Majid Yazdandoust

Marl is a clayey soil that exhibits a significant reduction in strength when exposed to moisture. As a result, it is considered problematic in civil engineering and often stabilized to improve performance. High-strength stabilization is not always required for road construction applications. In such cases, Metakaolin and rice husk ash provide suitable and eco-friendly alternatives to cement. Although the monotonic behavior of stabilized marl has been studied, less is known about its response under and after cyclic loading. The current study evaluated the cyclic and post-cyclic behavior of marl soil stabilized with metakaolin and rice husk ash after curing for 1, 7, and 28 days. The unconfined compressive strength (UCS) and secant modulus at 50 % maximum strength (E₅₀) of the stabilized soil were determined under monotonic and cyclic axial tests following the monotonic compression tests. The damping ratio, secant modulus, and axial strain accumulated during cyclic loading also were evaluated, with SEM used for microstructural analysis. The results showed that, unlike samples with 30 % metakaolin after cyclic loading, the specimen containing RHA experienced an increase in strength compared to the monotonic loading condition. The greatest UCS and E₅₀ values were observed in samples with 15% rice husk ash and 15 % metakaolin under monotonic loading following cyclic preloading. After 30 cycles, the stabilized specimens recorded lower damping ratios than for non-stabilized soil, although the effect of curing time on the damping ratio was negligible.

泥灰岩是一种粘土，当暴露于潮湿时，其强度会显著降低。因此，它在土木工程中被认为是有问题的，并且经常稳定以提高性能。道路施工应用并不总是需要高强度稳定。在这种情况下，偏高岭土和稻壳灰是水泥的合适且环保的替代品。稳定泥灰岩的单调特性已被研究过，但其在循环荷载作用下和循环荷载作用后的响应尚不清楚。本研究评估了偏高岭土和稻壳灰稳定的灰土在养护1、7和28天后的循环和后循环行为。在单调压缩试验之后，分别进行了单调和循环轴向试验，测定了稳定土的无侧限抗压强度（UCS）和50%最大强度（E50）割线模量。对循环加载过程中累积的阻尼比、割线模量和轴向应变进行了评估，并用扫描电镜进行了微观结构分析。结果表明，与循环加载30%偏高岭土的试样不同，含RHA的试样强度比单调加载条件下有所提高。循环预压后的单调加载条件下，稻壳灰和偏高岭土含量分别为15%和15%的样品的UCS和E50值最大。循环30次后，稳定土的阻尼比低于非稳定土，但固化时间对阻尼比的影响可以忽略不计。

{"title":"Cyclic and post-cyclic behavior of stabilized marl soil for pavement engineering applications","authors":"Mehran Moallemi , Mahdi Khodaparast , Majid Yazdandoust","doi":"10.1016/j.treng.2025.100413","DOIUrl":"10.1016/j.treng.2025.100413","url":null,"abstract":"<div><div>Marl is a clayey soil that exhibits a significant reduction in strength when exposed to moisture. As a result, it is considered problematic in civil engineering and often stabilized to improve performance. High-strength stabilization is not always required for road construction applications. In such cases, Metakaolin and rice husk ash provide suitable and eco-friendly alternatives to cement. Although the monotonic behavior of stabilized marl has been studied, less is known about its response under and after cyclic loading. The current study evaluated the cyclic and post-cyclic behavior of marl soil stabilized with metakaolin and rice husk ash after curing for 1, 7, and 28 days. The unconfined compressive strength (UCS) and secant modulus at 50 % maximum strength (<em>E</em><sub>50</sub>) of the stabilized soil were determined under monotonic and cyclic axial tests following the monotonic compression tests. The damping ratio, secant modulus, and axial strain accumulated during cyclic loading also were evaluated, with SEM used for microstructural analysis. The results showed that, unlike samples with 30 % metakaolin after cyclic loading, the specimen containing RHA experienced an increase in strength compared to the monotonic loading condition. The greatest UCS and <em>E</em><sub>50</sub> values were observed in samples with 15% rice husk ash and 15 % metakaolin under monotonic loading following cyclic preloading. After 30 cycles, the stabilized specimens recorded lower damping ratios than for non-stabilized soil, although the effect of curing time on the damping ratio was negligible.</div></div>","PeriodicalId":34480,"journal":{"name":"Transportation Engineering","volume":"22 ","pages":"Article 100413"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145747062","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A comparison of functional characteristics of railway rolling stock based on resilience indicators 基于弹性指标的铁路车辆功能特性比较

Q1 Engineering

Transportation Engineering

Pub Date : 2025-12-01 DOI: 10.1016/j.treng.2025.100411

Luca De Matteis , Marilisa Botte , Rosario Stefanelli , Luca D’Acierno

Rail systems are recognized for their sustainability and high operational performance; however, they remain highly vulnerable to disruptions. Therefore, service reliability and operational resilience result to be a critical priority for transport operators. Among the factors influencing network resilience, rolling stock procurement plays a significant role, yet its impact is often underestimated. This study emphasises the importance of incorporating resilience metrics into rolling stock acquisition decisions to enhance overall system robustness. To illustrate how this approach can be applied, Line 1 of the Naples metro system in Italy has been selected as a case study.

铁路系统因其可持续性和高运营绩效而得到认可；然而，它们仍然极易受到干扰。因此，服务可靠性和运营弹性成为运输运营商的关键优先事项。在影响网络弹性的因素中，机车车辆采购发挥着重要作用，但其影响往往被低估。本研究强调了将弹性指标纳入机车车辆购置决策以增强整体系统稳健性的重要性。为了说明如何应用这种方法，意大利那不勒斯地铁系统的1号线被选为案例研究。

引用次数: 0