Transportation Engineering最新文献_第6页

Pareto-optimal performance-based robust design of SDCM column-reinforced embankments: A parametric optimization study 基于pareto最优性能的SDCM柱加固路堤稳健设计：参数优化研究

Q1 Engineering

Transportation Engineering

Pub Date : 2025-07-16 DOI: 10.1016/j.treng.2025.100371

Chana Phutthananon , Pornkasem Jongpradist , Sasipim Sanboonsiri , Pattaramon Jongpradist , Suphanut Kongwat , Daniel Dias , Pitthaya Jamsawang

This study introduces a multi-objective optimization framework that integrates response surface methodology (RSM) with Pareto front analysis for the design of embankments supported by stiffened deep cement mixing (SDCM) columns, compared to conventional deep cement mixing (DCM) columns. The framework addresses trade-offs among column construction costs, ultimate limit states, and serviceability criteria in soft clay ground improvement. Key design parameters, column diameter, length, spacing, strength, and core pile characteristics, are examined through parametric analysis. Results show that SDCM columns provide column construction cost savings of approximately 48–55 % under stringent serviceability constraints. Column spacing and dimensions have the greatest influence on performance, while core pile length plays a critical role in overall performance. For a target global factor of safety of 1.5, optimal SDCM configurations can reduce column construction costs by up to 73 % compared to a documented DCM-supported highway embankment. These cost comparisons are specific to Bangkok clay conditions and exclude core pile installation costs; actual savings may differ based on site-specific soil properties and construction practices. The use of Pareto front solutions allows engineers to efficiently assess trade-offs between cost and safety without relying on trial-and-error methods. The proposed framework is especially useful during preliminary design phases when multiple design alternatives must be evaluated. It is also adaptable to other soil conditions by updating the finite element modeling and RSM parameters. Overall, the study provides a systematic and flexible approach for cost-effective ground improvement, particularly relevant to highway and railway embankments where both safety and economic efficiency are essential.

本研究引入了一个多目标优化框架，该框架将响应面法（RSM）与帕累托前分析相结合，用于与常规深层水泥搅拌柱（DCM）相比，设计由加强型深层水泥搅拌柱（SDCM）支撑的路堤。该框架解决了在软粘土地基改善中柱结构成本、极限状态和适用性标准之间的权衡。关键的设计参数，柱直径，长度，间距，强度和核心桩的特点，通过参数分析进行审查。结果表明，在严格的适用性约束下，SDCM柱提供了大约48 - 55%的柱建设成本节约。柱间距和柱径对性能影响最大，芯桩长度对整体性能影响最大。对于1.5的目标全局安全系数，与已有的dcm支持的公路路堤相比，最佳SDCM配置可以减少高达73%的柱施工成本。这些成本比较是针对曼谷粘土条件的，不包括芯桩安装成本；实际的节约可能会因场地特定的土壤特性和施工实践而有所不同。使用Pareto front解决方案，工程师可以有效地评估成本和安全性之间的权衡，而无需依赖于反复试验的方法。当必须评估多个设计方案时，建议的框架在初步设计阶段特别有用。通过更新有限元模型和RSM参数，该方法也能适应其他土壤条件。总体而言，该研究为具有成本效益的地面改善提供了系统和灵活的方法，特别是与安全和经济效率至关重要的公路和铁路路堤相关的方法。

{"title":"Pareto-optimal performance-based robust design of SDCM column-reinforced embankments: A parametric optimization study","authors":"Chana Phutthananon , Pornkasem Jongpradist , Sasipim Sanboonsiri , Pattaramon Jongpradist , Suphanut Kongwat , Daniel Dias , Pitthaya Jamsawang","doi":"10.1016/j.treng.2025.100371","DOIUrl":"10.1016/j.treng.2025.100371","url":null,"abstract":"<div><div>This study introduces a multi-objective optimization framework that integrates response surface methodology (RSM) with Pareto front analysis for the design of embankments supported by stiffened deep cement mixing (SDCM) columns, compared to conventional deep cement mixing (DCM) columns. The framework addresses trade-offs among column construction costs, ultimate limit states, and serviceability criteria in soft clay ground improvement. Key design parameters, column diameter, length, spacing, strength, and core pile characteristics, are examined through parametric analysis. Results show that SDCM columns provide column construction cost savings of approximately 48–55 % under stringent serviceability constraints. Column spacing and dimensions have the greatest influence on performance, while core pile length plays a critical role in overall performance. For a target global factor of safety of 1.5, optimal SDCM configurations can reduce column construction costs by up to 73 % compared to a documented DCM-supported highway embankment. These cost comparisons are specific to Bangkok clay conditions and exclude core pile installation costs; actual savings may differ based on site-specific soil properties and construction practices. The use of Pareto front solutions allows engineers to efficiently assess trade-offs between cost and safety without relying on trial-and-error methods. The proposed framework is especially useful during preliminary design phases when multiple design alternatives must be evaluated. It is also adaptable to other soil conditions by updating the finite element modeling and RSM parameters. Overall, the study provides a systematic and flexible approach for cost-effective ground improvement, particularly relevant to highway and railway embankments where both safety and economic efficiency are essential.</div></div>","PeriodicalId":34480,"journal":{"name":"Transportation Engineering","volume":"21 ","pages":"Article 100371"},"PeriodicalIF":0.0,"publicationDate":"2025-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144696580","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 comprehensive review of clustering methods applications in electric mobility 聚类方法在电动交通中的应用综述

Q1 Engineering

Transportation Engineering

Pub Date : 2025-07-14 DOI: 10.1016/j.treng.2025.100360

Marcelo Forte , Cindy P. Guzman , Lucas Pereira , Hugo Morais

The continuous growth of electric vehicles (EVs) has been boosted by the need to achieve society’s decarbonization targets. The mass adoption of EVs introduces new challenges in the power systems planning and operation, mainly due to the uncertainty related to EV users’ behavior and charging needs. Some of the difficulties motivated by the uncoordinated behavior of EVs are the occurrence of voltage instabilities, system overcurrents, and harmonic distortion. In this context, clustering can help better understand and categorize the behavior of EVs and electric vehicle supply equipment (EVSE) usage, with multiple research studies devoted to the study of clustering methods to offer solutions for these problems. This manuscript comprehensively presents a review of clustering methods applications for electric mobility that focus on the possibility of identifying different groups of EV charging processes, through clustering, to provide support in characterizing EV charging profiles, EV user behavior, and EVSE accessibility and location. For that, we present a roadmap that starts with cluster analysis, in which the most utilized mathematical clustering and validation techniques are detailed. Then, several EV charging datasets are described, followed by a review of research works focusing on clustering applications in EV data, considering three main categories, namely EV charging profiles, EV user behavior, and EVSE accessibility and location.

实现社会脱碳目标的需求推动了电动汽车（ev）的持续增长。电动汽车的大规模普及给电力系统的规划和运行带来了新的挑战，主要是由于电动汽车用户行为和充电需求的不确定性。电动汽车的不协调行为引发的一些困难是电压不稳定、系统过流和谐波畸变的发生。在这种背景下，聚类可以帮助更好地理解和分类电动汽车和电动汽车供电设备（EVSE）的使用行为，有许多研究致力于研究聚类方法，为这些问题提供解决方案。本文全面回顾了聚类方法在电动汽车领域的应用，重点介绍了通过聚类识别不同组电动汽车充电过程的可能性，从而为表征电动汽车充电概况、电动汽车用户行为以及电动汽车可达性和位置提供支持。为此，我们提供了一个从聚类分析开始的路线图，其中详细介绍了最常用的数学聚类和验证技术。然后，介绍了几种电动汽车充电数据集，然后回顾了专注于电动汽车数据聚类应用的研究工作，考虑了三个主要类别，即电动汽车充电概况，电动汽车用户行为和电动汽车可及性和位置。

{"title":"A comprehensive review of clustering methods applications in electric mobility","authors":"Marcelo Forte , Cindy P. Guzman , Lucas Pereira , Hugo Morais","doi":"10.1016/j.treng.2025.100360","DOIUrl":"10.1016/j.treng.2025.100360","url":null,"abstract":"<div><div>The continuous growth of electric vehicles (EVs) has been boosted by the need to achieve society’s decarbonization targets. The mass adoption of EVs introduces new challenges in the power systems planning and operation, mainly due to the uncertainty related to EV users’ behavior and charging needs. Some of the difficulties motivated by the uncoordinated behavior of EVs are the occurrence of voltage instabilities, system overcurrents, and harmonic distortion. In this context, clustering can help better understand and categorize the behavior of EVs and electric vehicle supply equipment (EVSE) usage, with multiple research studies devoted to the study of clustering methods to offer solutions for these problems. This manuscript comprehensively presents a review of clustering methods applications for electric mobility that focus on the possibility of identifying different groups of EV charging processes, through clustering, to provide support in characterizing EV charging profiles, EV user behavior, and EVSE accessibility and location. For that, we present a roadmap that starts with cluster analysis, in which the most utilized mathematical clustering and validation techniques are detailed. Then, several EV charging datasets are described, followed by a review of research works focusing on clustering applications in EV data, considering three main categories, namely EV charging profiles, EV user behavior, and EVSE accessibility and location.</div></div>","PeriodicalId":34480,"journal":{"name":"Transportation Engineering","volume":"21 ","pages":"Article 100360"},"PeriodicalIF":0.0,"publicationDate":"2025-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144653103","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 random forest and SHAP-based analysis of motorcycle crash severity in Thailand: Urban-rural and day-night perspectives 泰国摩托车碰撞严重程度的随机森林和基于shap的分析：城乡和昼夜视角

Q1 Engineering

Transportation Engineering

Pub Date : 2025-07-11 DOI: 10.1016/j.treng.2025.100369

Sonita Sum , Chamroeun Se , Thanapong Champahom , Sajjakaj Jomnonkwao , Sanjeev Sinha , Vatanavongs Ratanavaraha

Road traffic crashes pose significant public safety concern globally, causing severe injuries and fatalities. Motorcyclists face heightened crash risks and injury severity, particularly in developing countries like Thailand, where motorcycles serve as a primary mode of transportation. This study examines motorcycle crash severity across four distinct scenarios: urban daytime, urban nighttime, rural daytime, and rural nighttime. Analyzing 12,266 crashes from Thailand's Highway Accident Information Management System (HAIMS) spanning 2020–2022, Random Forest (RF) modeling combined with SHapley Additive exPlanations (SHAP) was applied to identify key severity determinants while enhancing model interpretability. The analysis revealed significant variations across scenarios based on roadway characteristics, environmental conditions, crash causes, and vehicle involvement. Crashes involving large trucks, head-on collisions, roads with depressed medians, and darkness were associated with increased severity. Conversely, those involving passenger cars, side-swipe collisions, roads with barrier medians, and well-lit locations exhibited lower severity. To assess its effectiveness, RF was benchmarked against Logistic Regression and Decision Tree models and consistently outperformed them across all crash scenarios. The models achieved classification accuracies of 66.5 % (urban day), 64.7 % (urban night), 63.8 % (rural day), and 65.9 % (rural night), while SHAP analysis illuminated the factors driving these predictions. These findings offer critical insights for policymakers and transportation planners, enabling the development of targeted interventions tailored to specific environmental and temporal conditions. By integrating machine learning with explainable artificial intelligence, this study advances data-driven approaches for enhancing motorcycle safety and crash prevention measures.

道路交通碰撞在全球造成重大公共安全问题，造成严重伤害和死亡。骑摩托车的人面临着更高的撞车风险和严重伤害，特别是在泰国等发展中国家，摩托车是主要的交通方式。本研究考察了四种不同情景下摩托车碰撞的严重程度：城市白天、城市夜间、农村白天和农村夜间。分析了泰国公路事故信息管理系统（HAIMS）在2020-2022年间的12,266起事故，应用随机森林（RF）模型结合SHapley加性解释（SHAP）来确定关键的严重程度决定因素，同时提高了模型的可解释性。分析显示，根据道路特征、环境条件、碰撞原因和车辆卷入情况，不同情况下的差异很大。涉及大型卡车、正面碰撞、道路中位数较低以及黑暗的事故与严重程度增加有关。相反，那些涉及乘用车、侧滑碰撞、有障碍物的道路和光线充足的地方的事故表现出较低的严重性。为了评估其有效性，RF与逻辑回归和决策树模型进行了基准测试，并在所有碰撞场景中始终优于它们。这些模型的分类准确率分别为66.5%（城市白天）、64.7%（城市夜晚）、63.8%（农村白天）和65.9%（农村夜晚），而SHAP分析阐明了驱动这些预测的因素。这些发现为政策制定者和交通规划者提供了重要的见解，使他们能够针对特定的环境和时间条件制定有针对性的干预措施。通过将机器学习与可解释的人工智能相结合，本研究推进了数据驱动的方法，以增强摩托车安全和碰撞预防措施。

{"title":"A random forest and SHAP-based analysis of motorcycle crash severity in Thailand: Urban-rural and day-night perspectives","authors":"Sonita Sum , Chamroeun Se , Thanapong Champahom , Sajjakaj Jomnonkwao , Sanjeev Sinha , Vatanavongs Ratanavaraha","doi":"10.1016/j.treng.2025.100369","DOIUrl":"10.1016/j.treng.2025.100369","url":null,"abstract":"<div><div>Road traffic crashes pose significant public safety concern globally, causing severe injuries and fatalities. Motorcyclists face heightened crash risks and injury severity, particularly in developing countries like Thailand, where motorcycles serve as a primary mode of transportation. This study examines motorcycle crash severity across four distinct scenarios: urban daytime, urban nighttime, rural daytime, and rural nighttime. Analyzing 12,266 crashes from Thailand's Highway Accident Information Management System (HAIMS) spanning 2020–2022, Random Forest (RF) modeling combined with SHapley Additive exPlanations (SHAP) was applied to identify key severity determinants while enhancing model interpretability. The analysis revealed significant variations across scenarios based on roadway characteristics, environmental conditions, crash causes, and vehicle involvement. Crashes involving large trucks, head-on collisions, roads with depressed medians, and darkness were associated with increased severity. Conversely, those involving passenger cars, side-swipe collisions, roads with barrier medians, and well-lit locations exhibited lower severity. To assess its effectiveness, RF was benchmarked against Logistic Regression and Decision Tree models and consistently outperformed them across all crash scenarios. The models achieved classification accuracies of 66.5 % (urban day), 64.7 % (urban night), 63.8 % (rural day), and 65.9 % (rural night), while SHAP analysis illuminated the factors driving these predictions. These findings offer critical insights for policymakers and transportation planners, enabling the development of targeted interventions tailored to specific environmental and temporal conditions. By integrating machine learning with explainable artificial intelligence, this study advances data-driven approaches for enhancing motorcycle safety and crash prevention measures.</div></div>","PeriodicalId":34480,"journal":{"name":"Transportation Engineering","volume":"21 ","pages":"Article 100369"},"PeriodicalIF":0.0,"publicationDate":"2025-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144632566","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

Mission profiles and energy management strategies for electric trucks with fuel cell range extenders 带有燃料电池增程器的电动卡车的任务概况和能量管理策略

Q1 Engineering

Transportation Engineering

Pub Date : 2025-07-11 DOI: 10.1016/j.treng.2025.100356

Igor William Santos Leal Cruz, Lennart Buck, Timo Wyszynski, Marco Schramm, Ludger Frerichs

In electric trucks equipped with fuel cell range extenders, energy management strategies are used to control and distribute the power demand between the battery pack and the fuel cell system. Energy management performance can be analysed with driving cycles, which specify speed profiles to be followed in a simulation or on a chassis dynamometer. Simulations or tests using standardised driving cycles lead to inaccurate performance predictions if the cycles are not representative of actual driving patterns. This paper presents a method for deriving driving cycles from simulations of vehicle use and employs these cycles in the development of energy management strategies. The cycles are specified in the form of mission profiles that define a target speed and a slope over time. They are generated stochastically with Markov chains based on the speed and slope profiles of trips simulated with a freight distribution model. The speed profiles of the simulated trips combine speed limits with stochastic speed reduction events that model traffic conditions. The slope profiles are obtained from elevation data. The probability distribution of the speed reduction events follows from the results of microscopic traffic simulations. Mission profiles were synthesised using data generated in the simulation of three different freight distribution scenarios. The profiles were used in longitudinal vehicle dynamics simulations to evaluate vehicle performance with a thermostat (on/off) energy management strategy. The results revealed a tank-to-wheel efficiency between 35% and 39% and a total energy consumption between 342 kWh and 526 kWh over distances between 202 km and 272 km.

在配备燃料电池增程器的电动卡车中，能源管理策略用于控制和分配电池组和燃料电池系统之间的电力需求。能源管理性能可以通过驾驶周期进行分析，在模拟或底盘测力仪上指定要遵循的速度曲线。使用标准化驾驶循环的模拟或测试，如果循环不能代表实际驾驶模式，则会导致不准确的性能预测。本文提出了一种从车辆使用模拟中推导驾驶周期的方法，并将这些周期用于能源管理策略的开发。周期以任务剖面的形式指定，该剖面定义了目标速度和随时间的斜率。它们是用马尔可夫链随机生成的，该马尔可夫链基于货运分配模型模拟的行程速度和坡度曲线。模拟行程的速度分布将速度限制与模拟交通状况的随机减速事件相结合。坡度剖面由高程数据获得。减速事件的概率分布根据微观交通模拟的结果得出。任务概况是利用模拟三种不同货运分配情景所产生的数据进行综合的。这些剖面被用于纵向车辆动力学模拟，以评估具有恒温（开/关）能量管理策略的车辆性能。结果显示，在202公里至272公里的距离内，油箱到车轮的效率在35%至39%之间，总能耗在342至526千瓦时之间。

{"title":"Mission profiles and energy management strategies for electric trucks with fuel cell range extenders","authors":"Igor William Santos Leal Cruz, Lennart Buck, Timo Wyszynski, Marco Schramm, Ludger Frerichs","doi":"10.1016/j.treng.2025.100356","DOIUrl":"10.1016/j.treng.2025.100356","url":null,"abstract":"<div><div>In electric trucks equipped with fuel cell range extenders, energy management strategies are used to control and distribute the power demand between the battery pack and the fuel cell system. Energy management performance can be analysed with driving cycles, which specify speed profiles to be followed in a simulation or on a chassis dynamometer. Simulations or tests using standardised driving cycles lead to inaccurate performance predictions if the cycles are not representative of actual driving patterns. This paper presents a method for deriving driving cycles from simulations of vehicle use and employs these cycles in the development of energy management strategies. The cycles are specified in the form of mission profiles that define a target speed and a slope over time. They are generated stochastically with Markov chains based on the speed and slope profiles of trips simulated with a freight distribution model. The speed profiles of the simulated trips combine speed limits with stochastic speed reduction events that model traffic conditions. The slope profiles are obtained from elevation data. The probability distribution of the speed reduction events follows from the results of microscopic traffic simulations. Mission profiles were synthesised using data generated in the simulation of three different freight distribution scenarios. The profiles were used in longitudinal vehicle dynamics simulations to evaluate vehicle performance with a thermostat (on/off) energy management strategy. The results revealed a tank-to-wheel efficiency between 35% and 39% and a total energy consumption between 342 kWh and 526 kWh over distances between 202 km and 272 km.</div></div>","PeriodicalId":34480,"journal":{"name":"Transportation Engineering","volume":"21 ","pages":"Article 100356"},"PeriodicalIF":0.0,"publicationDate":"2025-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144605726","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

Role of lithium-ion batteries in microgrid system 锂离子电池在微电网系统中的作用

Q1 Engineering

Transportation Engineering

Pub Date : 2025-07-08 DOI: 10.1016/j.treng.2025.100368

Balvender Singh , Pushpendra Singh , Ghanshyam G. Tejani , Sunil Kumar Sharma , Seyed Jalaleddin Mousavirad

Microgrid systems are a beneficial alternative to decentralized power grids that can provide greener and high quality power with greater efficiency. Use of lithium-ion batteries (LIBs) in the microgrid systems has rapidly gained attention because of their remarkable energy density, durability, and performance characteristics. This paper explores the advantages of using LIBs in microgrid systems including energy storage, load adjustment, and peak shaving, and examines their advantages: high energy efficiency, less carbon footprint, and superior reliability and resilience. Furthermore, the discussion on challenges associated with the use of LIBs in microgrid systems such as cost, safety and need for maintenance and monitoring. The study has also discussed the importance of numerous artificial intelligence (AI) techniques for battery management. In order to create more resilient and sustainable energy systems, this paper emphasizes the significant interest in and promise of LIBs in microgrid systems.

微电网系统是分散电网的有益替代方案，可以提供更环保、更高效的高质量电力。锂离子电池（LIBs）由于其卓越的能量密度、耐久性和性能特点，在微电网系统中的应用迅速引起了人们的关注。本文探讨了在微电网系统中使用lib的优势，包括储能、负荷调节和调峰，并考察了它们的优势：高能效、低碳足迹、卓越的可靠性和弹性。此外，还讨论了在微电网系统中使用lib所面临的挑战，如成本、安全性以及维护和监控的需要。该研究还讨论了许多人工智能（AI）技术对电池管理的重要性。为了创建更具弹性和可持续性的能源系统，本文强调了对lib在微电网系统中的重大兴趣和前景。

引用次数: 0

Fuel consumption and CO₂ emissions prediction in road transport using a hybrid deep learning approach 基于混合深度学习方法的道路运输燃料消耗和二氧化碳排放预测

Q1 Engineering

Transportation Engineering

Pub Date : 2025-07-04 DOI: 10.1016/j.treng.2025.100364

Sami Shaffiee Haghshenas, Sina Shaffiee Haghshenas, Vittorio Astarita, Giuseppe Guido

In recent times, due to the substantial increase in population and the number of vehicles, road transportation has emerged as a crucial factor contributing to energy consumption and the release of CO2 emissions. In road transportation, the analysis of driver behavior is one of the most significant approaches to evaluating vehicle fuel consumption (FC) and CO2 emissions. Driver behavior analysis provides valuable insights into the influence of driving habits and characteristics on FC and CO2 emissions, including factors such as driving style, average vehicle speed, and acceleration pedal usage. This analysis provides a comprehensive understanding of how these factors impact real-world fuel efficiency. For this purpose, this study utilizes two non-linear methods, an artificial neural network (ANN) and a hybrid deep learning method called long short-term memory with multi-verse optimizer (LSTM-MVO), to predict FC and CO2 emissions. In this study, 370 data points were recorded, and relevant driver behaviors’ parameters were measured from mobile technology and the OBD interface for FC and CO2 emissions, respectively. The input data for modeling and determining an optimized function for predicting the amount of fuel consumed and CO2 emissions include Fuel_flow_rate/hour (FFRH), Engine_RPM (ERMP), Speed (S), Acceleration (A), and Grade (G). Also, the amount of FC and CO2 emissions are also considered outputs data. The results clearly showed that the LSTM-MVO approach can provide higher performance capacity in predicting fuel consumption and CO2 emissions compared to ANN. Finally, the results of this study emphasize its potential as a promising approach to address specific issues related to driver behavior and environmental pollution.

近年来，由于人口和车辆数量的大幅增加，道路运输已成为导致能源消耗和二氧化碳排放的关键因素。在道路交通中，驾驶员行为分析是评价车辆燃油消耗和二氧化碳排放的重要手段之一。驾驶员行为分析提供了有关驾驶习惯和特征对FC和CO2排放的影响的宝贵见解，包括驾驶风格、平均车速和加速踏板使用等因素。该分析提供了对这些因素如何影响现实世界燃油效率的全面理解。为此，本研究利用两种非线性方法，即人工神经网络（ANN）和混合深度学习方法长短期记忆与多空间优化器（LSTM-MVO），来预测FC和CO2排放。本研究记录了370个数据点，并分别从移动技术和OBD接口测量了FC和CO2排放的相关驾驶员行为参数。用于建模和确定预测燃油消耗量和二氧化碳排放量的优化函数的输入数据包括燃料流量/小时（FFRH）、发动机转速（ERMP）、速度(S)、加速度(A)和等级(G)。此外，碳氟化合物和二氧化碳排放量也被视为输出数据。结果表明，与人工神经网络相比，LSTM-MVO方法在预测油耗和CO2排放方面具有更高的性能。最后，本研究的结果强调了它作为解决与驾驶员行为和环境污染相关的具体问题的有前途的方法的潜力。

{"title":"Fuel consumption and CO₂ emissions prediction in road transport using a hybrid deep learning approach","authors":"Sami Shaffiee Haghshenas, Sina Shaffiee Haghshenas, Vittorio Astarita, Giuseppe Guido","doi":"10.1016/j.treng.2025.100364","DOIUrl":"10.1016/j.treng.2025.100364","url":null,"abstract":"<div><div>In recent times, due to the substantial increase in population and the number of vehicles, road transportation has emerged as a crucial factor contributing to energy consumption and the release of CO2 emissions. In road transportation, the analysis of driver behavior is one of the most significant approaches to evaluating vehicle fuel consumption (FC) and CO2 emissions. Driver behavior analysis provides valuable insights into the influence of driving habits and characteristics on FC and CO2 emissions, including factors such as driving style, average vehicle speed, and acceleration pedal usage. This analysis provides a comprehensive understanding of how these factors impact real-world fuel efficiency. For this purpose, this study utilizes two non-linear methods, an artificial neural network (ANN) and a hybrid deep learning method called long short-term memory with multi-verse optimizer (LSTM-MVO), to predict FC and CO2 emissions. In this study, 370 data points were recorded, and relevant driver behaviors’ parameters were measured from mobile technology and the OBD interface for FC and CO2 emissions, respectively. The input data for modeling and determining an optimized function for predicting the amount of fuel consumed and CO2 emissions include Fuel_flow_rate/hour (FFRH), Engine_RPM (ERMP), Speed (S), Acceleration (A), and Grade (G). Also, the amount of FC and CO2 emissions are also considered outputs data. The results clearly showed that the LSTM-MVO approach can provide higher performance capacity in predicting fuel consumption and CO2 emissions compared to ANN. Finally, the results of this study emphasize its potential as a promising approach to address specific issues related to driver behavior and environmental pollution.</div></div>","PeriodicalId":34480,"journal":{"name":"Transportation Engineering","volume":"21 ","pages":"Article 100364"},"PeriodicalIF":0.0,"publicationDate":"2025-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144580480","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

Mobility as a service (MaaS) adoption: Assessing heterogeneity across university communities 移动即服务（MaaS）采用：评估大学社区的异质性

Q1 Engineering

Transportation Engineering

Pub Date : 2025-07-03 DOI: 10.1016/j.treng.2025.100366

Fulvio Silvestri , Valentina Costa , Luca Pastorelli

This study investigates the willingness to adopt (WTA) Mobility as a Service (MaaS) solutions among members of Italian university communities, based on over 4000 responses collected through two survey campaigns at the Politecnico di Milano and the University of Genoa. Ordered logit models were estimated to assess the influence of socio-demographic characteristics, travel habits, and individual perceptions on MaaS adoption. Identified key determinants include travelers’ satisfaction with current transport options, which is negatively associated with WTA, in line with existing findings that satisfied users are less likely to change travel behavior. Results partially align with prior studies that identify private car ownership as a barrier. Use of journey planning apps is positively associated with MaaS adoption, reinforcing prior research on the importance of digital familiarity. This study also presents findings that diverge from previous literature: age does not significantly influence WTA, and services such as bike sharing and car sharing do not yield measurable utility in the adoption decision. The analysis reveals substantial heterogeneity in preferences both across and within the two university contexts, as confirmed by the significance of several random parameters capturing individual-level variation. These results underscore the importance of developing flexible, context-sensitive MaaS strategies. Given the diversity of preferences and influencing factors, a one-size-fits-all approach is unlikely to be effective.

本研究调查了意大利大学社区成员采用（WTA）移动即服务（MaaS）解决方案的意愿，基于米兰理工大学和热那亚大学两次调查活动收集的4000多份回复。使用有序logit模型评估社会人口特征、旅行习惯和个人认知对MaaS采用的影响。确定的关键决定因素包括旅行者对当前交通选择的满意度，这与WTA呈负相关，这与现有的研究结果一致，即满意的用户不太可能改变旅行行为。研究结果部分与之前的研究一致，认为私家车是一个障碍。旅行规划应用程序的使用与MaaS的采用呈正相关，这加强了之前关于数字熟悉度重要性的研究。本研究也提出了与以往文献不同的发现：年龄对WTA没有显著影响，共享单车和共享汽车等服务在采用决策中没有产生可衡量的效用。该分析揭示了两所大学背景之间和内部偏好的实质性异质性，这一点得到了几个捕获个人水平差异的随机参数的重要性的证实。这些结果强调了开发灵活的、上下文敏感的MaaS策略的重要性。考虑到偏好和影响因素的多样性，一刀切的方法不太可能有效。

{"title":"Mobility as a service (MaaS) adoption: Assessing heterogeneity across university communities","authors":"Fulvio Silvestri , Valentina Costa , Luca Pastorelli","doi":"10.1016/j.treng.2025.100366","DOIUrl":"10.1016/j.treng.2025.100366","url":null,"abstract":"<div><div>This study investigates the willingness to adopt (WTA) Mobility as a Service (MaaS) solutions among members of Italian university communities, based on over 4000 responses collected through two survey campaigns at the Politecnico di Milano and the University of Genoa. Ordered logit models were estimated to assess the influence of socio-demographic characteristics, travel habits, and individual perceptions on MaaS adoption. Identified key determinants include travelers’ satisfaction with current transport options, which is negatively associated with WTA, in line with existing findings that satisfied users are less likely to change travel behavior. Results partially align with prior studies that identify private car ownership as a barrier. Use of journey planning apps is positively associated with MaaS adoption, reinforcing prior research on the importance of digital familiarity. This study also presents findings that diverge from previous literature: age does not significantly influence WTA, and services such as bike sharing and car sharing do not yield measurable utility in the adoption decision. The analysis reveals substantial heterogeneity in preferences both across and within the two university contexts, as confirmed by the significance of several random parameters capturing individual-level variation. These results underscore the importance of developing flexible, context-sensitive MaaS strategies. Given the diversity of preferences and influencing factors, a one-size-fits-all approach is unlikely to be effective.</div></div>","PeriodicalId":34480,"journal":{"name":"Transportation Engineering","volume":"21 ","pages":"Article 100366"},"PeriodicalIF":0.0,"publicationDate":"2025-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144580481","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

Improving pavements through an innovative asphalt graphene-modified thin layer: a case study 通过新型沥青石墨烯改性薄层改善路面：案例研究

Q1 Engineering

Transportation Engineering

Pub Date : 2025-07-01 DOI: 10.1016/j.treng.2025.100367

Francesca Maltinti, James Rombi, Mauro Coni

Road agencies must prioritize efficient pavement preservation while exploring innovative materials and techniques to reduce maintenance durations, costs, and traffic disruptions. This paper presents an innovative and original graphene-modified thin asphalt layer (GMTL), positioned between the binder and wearing course, offering great potential for restoring road pavements. Various tests were conducted both in the laboratory and on the construction site to assess the impact of the GMTL. Results show a remarkable volumetric behaviour of the GMTL, with mean void values of 14.3 % at 10 cycles, 5.6 % at 120 cycles, and 4.6 % at 230 cycles along with good mixture workability. Moreover, tests performed on core samples with GMTL showed an increase of 33.2 % in indirect tensile strength and 10 % in indirect tensile stiffness modulus values. The fatigue curves show particularly high performance with a very good resistance to cyclic loads in terms of both stress and deformation.

Original tests were carried out using a falling weight deflectometer (FWD) to characterize the deformability and stiffness of the pavement in a trial section. According to the results, the GMTL raises the hot mix asphalt (HMA) base stiffness by 14 % and the binder modulus by 22 %. In addition, an increase of 26 % was observed in the rigidity of the cement-treated base layer.

道路管理机构必须优先考虑有效的路面保护，同时探索创新的材料和技术，以减少维护时间、成本和交通中断。本文提出了一种新颖的石墨烯改性薄沥青层（GMTL），它位于粘结剂和磨损层之间，具有巨大的修复道路路面的潜力。在实验室和建筑工地进行了各种测试，以评估GMTL的影响。结果表明，GMTL具有显著的体积特性，在10次循环时，平均孔隙率为14.3%，120次循环时为5.6%，230次循环时为4.6%，并且具有良好的混合和易性。此外，用GMTL对岩心样品进行的试验表明，间接抗拉强度增加33.2%，间接抗拉刚度模量增加10%。疲劳曲线表现出特别高的性能，在应力和变形方面都具有很好的抗循环载荷能力。最初的测试是使用一个下降重量偏转计（FWD）来表征试验路段路面的变形能力和刚度。结果表明，GMTL使热拌沥青（HMA）基层刚度提高14%，粘结剂模量提高22%。此外，水泥处理基层的刚度提高了26%。

{"title":"Improving pavements through an innovative asphalt graphene-modified thin layer: a case study","authors":"Francesca Maltinti, James Rombi, Mauro Coni","doi":"10.1016/j.treng.2025.100367","DOIUrl":"10.1016/j.treng.2025.100367","url":null,"abstract":"<div><div>Road agencies must prioritize efficient pavement preservation while exploring innovative materials and techniques to reduce maintenance durations, costs, and traffic disruptions. This paper presents an innovative and original graphene-modified thin asphalt layer (GMTL), positioned between the binder and wearing course, offering great potential for restoring road pavements. Various tests were conducted both in the laboratory and on the construction site to assess the impact of the GMTL. Results show a remarkable volumetric behaviour of the GMTL, with mean void values of 14.3 % at 10 cycles, 5.6 % at 120 cycles, and 4.6 % at 230 cycles along with good mixture workability. Moreover, tests performed on core samples with GMTL showed an increase of 33.2 % in indirect tensile strength and 10 % in indirect tensile stiffness modulus values. The fatigue curves show particularly high performance with a very good resistance to cyclic loads in terms of both stress and deformation.</div><div>Original tests were carried out using a falling weight deflectometer (FWD) to characterize the deformability and stiffness of the pavement in a trial section. According to the results, the GMTL raises the hot mix asphalt (HMA) base stiffness by 14 % and the binder modulus by 22 %. In addition, an increase of 26 % was observed in the rigidity of the cement-treated base layer.</div></div>","PeriodicalId":34480,"journal":{"name":"Transportation Engineering","volume":"21 ","pages":"Article 100367"},"PeriodicalIF":0.0,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144611526","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

Development of an unsupervised learning-based annotation method for road quality assessment 基于无监督学习的道路质量评价标注方法研究

Q1 Engineering

Transportation Engineering

Pub Date : 2025-07-01 DOI: 10.1016/j.treng.2025.100358

Roland Nagy , István Szalai

Ensuring road quality is essential for traffic safety, vehicle longevity, and passenger comfort. Recently, cost-effective road quality measurement systems based on vehicle vibrations have emerged, often relying on supervised machine learning models. However, these models require high-quality labeled data, which is typically unavailable at the necessary resolution. Manual labeling is impractical due to the large data volume, leading to lower spatial resolution and inflexible datasets that cannot easily adapt to evolving requirements. This study presents a novel Machine In the Loop (MIL) annotation method based on unsupervised learning for automated pavement quality assessment, an area where previously only manual labeling methods were used. The proposed approach utilizes vehicle-mounted sensors to collect vibration data, which is then processed through feature extraction, frequency-domain transformations, and statistical segmentation. A Gaussian Mixture Model clustering algorithm categorizes road sections by quality, significantly reducing reliance on manual labeling. To assess the effectiveness of MIL annotation, a supervised Random Forest classifier is trained on the labeled dataset, achieving a classification accuracy of 91%. The methodology is validated through extensive real-world testing across diverse road conditions using multiple vehicle types. The results demonstrate that the novel MIL annotation with a subsequent supervised learning approach enables scalable, cost-effective, and high-resolution road quality assessment with minimal human intervention. This study highlights the feasibility of integrating unsupervised learning-based annotation into road management workflows, offering a flexible and adaptive solution for infrastructure monitoring and maintenance planning.

确保道路质量对交通安全、车辆寿命和乘客舒适度至关重要。最近，基于车辆振动的具有成本效益的道路质量测量系统已经出现，通常依赖于监督机器学习模型。然而，这些模型需要高质量的标记数据，而这些数据在必要的分辨率下通常是不可用的。由于数据量大，手动标记是不切实际的，导致空间分辨率较低，数据集不灵活，无法轻松适应不断变化的需求。本研究提出了一种新的基于无监督学习的机器在循环（MIL）标注方法，用于自动路面质量评估，这是以前只使用手动标记方法的领域。该方法利用车载传感器采集振动数据，然后通过特征提取、频域变换和统计分割进行处理。高斯混合模型聚类算法根据质量对路段进行分类，大大减少了对人工标记的依赖。为了评估MIL标注的有效性，在标记的数据集上训练一个有监督的随机森林分类器，分类准确率达到91%。该方法已通过多种车型在不同道路条件下的广泛实际测试得到验证。结果表明，新的MIL注释与随后的监督学习方法可以在最少的人为干预下实现可扩展、经济高效和高分辨率的道路质量评估。本研究强调了将基于无监督学习的标注集成到道路管理工作流程中的可行性，为基础设施监控和维护规划提供了灵活和自适应的解决方案。

{"title":"Development of an unsupervised learning-based annotation method for road quality assessment","authors":"Roland Nagy , István Szalai","doi":"10.1016/j.treng.2025.100358","DOIUrl":"10.1016/j.treng.2025.100358","url":null,"abstract":"<div><div>Ensuring road quality is essential for traffic safety, vehicle longevity, and passenger comfort. Recently, cost-effective road quality measurement systems based on vehicle vibrations have emerged, often relying on supervised machine learning models. However, these models require high-quality labeled data, which is typically unavailable at the necessary resolution. Manual labeling is impractical due to the large data volume, leading to lower spatial resolution and inflexible datasets that cannot easily adapt to evolving requirements. This study presents a novel Machine In the Loop (MIL) annotation method based on unsupervised learning for automated pavement quality assessment, an area where previously only manual labeling methods were used. The proposed approach utilizes vehicle-mounted sensors to collect vibration data, which is then processed through feature extraction, frequency-domain transformations, and statistical segmentation. A Gaussian Mixture Model clustering algorithm categorizes road sections by quality, significantly reducing reliance on manual labeling. To assess the effectiveness of MIL annotation, a supervised Random Forest classifier is trained on the labeled dataset, achieving a classification accuracy of 91%. The methodology is validated through extensive real-world testing across diverse road conditions using multiple vehicle types. The results demonstrate that the novel MIL annotation with a subsequent supervised learning approach enables scalable, cost-effective, and high-resolution road quality assessment with minimal human intervention. This study highlights the feasibility of integrating unsupervised learning-based annotation into road management workflows, offering a flexible and adaptive solution for infrastructure monitoring and maintenance planning.</div></div>","PeriodicalId":34480,"journal":{"name":"Transportation Engineering","volume":"21 ","pages":"Article 100358"},"PeriodicalIF":0.0,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144557329","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 grouping of heavy goods vehicles phenomenon. A case study based on Weigh-in-Motion data on a French highway 重型货车的分组现象。基于法国高速公路动态称重数据的案例研究

Q1 Engineering

Transportation Engineering

Pub Date : 2025-06-27 DOI: 10.1016/j.treng.2025.100363

Christophe Mundutéguy , Özgür Aycik , Jean-François Bercher , Emmanuel Cohen , Franziska Schmidt

This study deals with the manual grouping phenomenon of heavy vehicles (over 3.5 tons), which refers to vehicles following a vehicle of the same group (rigid box truck, bobtail truck…) in the same lane with time gaps less than or equal to 2 s and which presents a speed differential of zero, or more or less equal to the margin of error of the measuring instruments. By focusing precisely on these time gaps, we sought to determine the share of heavy truck drivers who play with the net headway imposed by the highway code in close-following conditions and who might also the most likely to adopt platooning technology given the similarity between the two situations. The data explored in this study was recorded by weigh-in-motion (WIM) systems located on several French high-speed roads. Each time a vehicle passes, the system increments an indicator and for each truck records: time, total weight and axle weight, number of axles, and instantaneous speed… We worked on a database containing about two million records, generated by a WIM system located in the south of France during the calendar year 2015. After a presentation of how we completed, organized and pre-processed the information in this database not designed for this purpose, we indicate how we constructed relevant variables from these data and conducted linear regression model on inter-distance and K-means classification in order to distinguish subgroups of truck drivers in the close following situations. The results show that this phenomenon which is rare on this type of road, is more correlated with the level of heavy vehicle traffic than with general traffic.

本研究研究的是重型车辆（3.5吨以上）的人工分组现象，即车辆跟随同一组车辆（刚性箱式货车、短尾货车等）在同一车道上，时间间隔小于等于2秒，速度差为零，或大致等于测量仪器的误差范围。通过精确地关注这些时间间隔，我们试图确定重型卡车司机在紧随其后的情况下使用公路法规规定的净车头时距的比例，以及考虑到两种情况之间的相似性，谁也最有可能采用队列技术。本研究中探索的数据是由位于法国几条高速公路上的动态称重（WIM）系统记录的。每当车辆通过时，系统就会增加一个指示器，并为每个卡车记录增加一个指标：时间、总重量和车轴重量、车轴数和瞬时速度……我们对一个包含大约200万条记录的数据库进行了研究，该数据库是由位于法国南部的WIM系统在2015日历年生成的。在介绍了我们如何完成、组织和预处理这个非为此目的而设计的数据库中的信息之后，我们说明了我们如何从这些数据中构建相关变量，并对间隔和k均值分类进行线性回归模型，以便在以下情况下区分卡车司机的子组。结果表明，该现象在该类型道路上罕见，与重型车辆交通水平的相关性大于与一般交通的相关性。

{"title":"The grouping of heavy goods vehicles phenomenon. A case study based on Weigh-in-Motion data on a French highway","authors":"Christophe Mundutéguy , Özgür Aycik , Jean-François Bercher , Emmanuel Cohen , Franziska Schmidt","doi":"10.1016/j.treng.2025.100363","DOIUrl":"10.1016/j.treng.2025.100363","url":null,"abstract":"<div><div>This study deals with the manual grouping phenomenon of heavy vehicles (over 3.5 tons), which refers to vehicles following a vehicle of the same group (rigid box truck, bobtail truck…) in the same lane with time gaps less than or equal to 2 s and which presents a speed differential of zero, or more or less equal to the margin of error of the measuring instruments. By focusing precisely on these time gaps, we sought to determine the share of heavy truck drivers who play with the net headway imposed by the highway code in close-following conditions and who might also the most likely to adopt platooning technology given the similarity between the two situations. The data explored in this study was recorded by weigh-in-motion (WIM) systems located on several French high-speed roads. Each time a vehicle passes, the system increments an indicator and for each truck records: time, total weight and axle weight, number of axles, and instantaneous speed… We worked on a database containing about two million records, generated by a WIM system located in the south of France during the calendar year 2015. After a presentation of how we completed, organized and pre-processed the information in this database not designed for this purpose, we indicate how we constructed relevant variables from these data and conducted linear regression model on inter-distance and K-means classification in order to distinguish subgroups of truck drivers in the close following situations. The results show that this phenomenon which is rare on this type of road, is more correlated with the level of heavy vehicle traffic than with general traffic.</div></div>","PeriodicalId":34480,"journal":{"name":"Transportation Engineering","volume":"21 ","pages":"Article 100363"},"PeriodicalIF":0.0,"publicationDate":"2025-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144535933","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