Transportation Engineering最新文献_第3页

An experimental investigation on the performance of a single cylinder diesel engine at various partial loads 关于单缸柴油发动机在不同部分负荷下性能的实验研究

Q1 Engineering

Transportation Engineering

Pub Date : 2024-11-03 DOI: 10.1016/j.treng.2024.100288

Thong Duc Hong , Binh Thanh Thi Hoang , Thien Quoc Mai Ho , Phat Tan Truong , Minh Quang Pham

This study investigates various partial load characteristics of a diesel engine, including brake specific fuel consumption, torque, and power, to get insight into these performances in practice. Firstly, these characteristics were experimentally examined with approximate 25, 50, 75, and 85 % fuel rack settings at 900–2400 rpm engine speeds. Then, more operating modes were investigated to build characteristics corresponding to constant fuel quantity per engine cycle. The results indicate that the practical partial load characteristics significantly differ from the theory of full-load characteristics since the fuel quantity per cycle varies even though the rack is fixed. Especially at low loads, the fuel quantity per cycle increases enormously with engine speed due to the significant influence of pressure waves. Hence, torque and power increase continuously, making it challenging to control the engine operation. In contrast, because the reduction in fuel viscosity and pump efficiency balances the pressure wave effects at high loads, fuel quantity per cycle remains relatively constant, making the characteristics more similar to the theory. Besides, if fuel quantity per cycle is kept constant, the trends in partial load curves follow the theory, which can be approximately predicted. These findings reveal that considering fuel quantity per cycle is significant when studying diesel engine partial loads, notably at low loads. The study contributes a vital basis for further investigating and modeling the partial characteristics of diesel engines. Also, it is a crucial reference for estimating the suitable working conditions of engine-driven systems in practice.

本研究调查了柴油发动机的各种部分负荷特性，包括制动比油耗、扭矩和功率，以深入了解这些特性在实际中的表现。首先，在发动机转速为 900-2400 转/分时，对这些特性进行了实验性测试，燃油齿条设置分别为 25%、50%、75% 和 85%。然后，研究了更多的运行模式，以建立与每个发动机循环的恒定燃料量相对应的特性。结果表明，实际的部分负荷特性与理论上的全负荷特性有很大不同，因为即使齿条固定，每个循环的燃油量也会变化。特别是在低负荷时，由于压力波的显著影响，每个循环的燃油量随发动机转速的增加而大幅增加。因此，扭矩和功率不断增加，给发动机运行控制带来了挑战。相反，由于燃料粘度的降低和泵效率的提高平衡了高负荷时的压力波效应，因此每个循环的燃料量保持相对恒定，使其特性更接近理论。此外，如果每个循环的燃油量保持不变，则部分负荷曲线的趋势与理论一致，可以近似预测。这些研究结果表明，在研究柴油发动机部分负荷时，特别是在低负荷时，考虑每个循环的燃油量非常重要。这项研究为进一步研究和模拟柴油发动机的部分特性提供了重要依据。此外，它也是估算发动机驱动系统实际工作条件的重要参考。

{"title":"An experimental investigation on the performance of a single cylinder diesel engine at various partial loads","authors":"Thong Duc Hong , Binh Thanh Thi Hoang , Thien Quoc Mai Ho , Phat Tan Truong , Minh Quang Pham","doi":"10.1016/j.treng.2024.100288","DOIUrl":"10.1016/j.treng.2024.100288","url":null,"abstract":"<div><div>This study investigates various partial load characteristics of a diesel engine, including brake specific fuel consumption, torque, and power, to get insight into these performances in practice. Firstly, these characteristics were experimentally examined with approximate 25, 50, 75, and 85 % fuel rack settings at 900–2400 rpm engine speeds. Then, more operating modes were investigated to build characteristics corresponding to constant fuel quantity per engine cycle. The results indicate that the practical partial load characteristics significantly differ from the theory of full-load characteristics since the fuel quantity per cycle varies even though the rack is fixed. Especially at low loads, the fuel quantity per cycle increases enormously with engine speed due to the significant influence of pressure waves. Hence, torque and power increase continuously, making it challenging to control the engine operation. In contrast, because the reduction in fuel viscosity and pump efficiency balances the pressure wave effects at high loads, fuel quantity per cycle remains relatively constant, making the characteristics more similar to the theory. Besides, if fuel quantity per cycle is kept constant, the trends in partial load curves follow the theory, which can be approximately predicted. These findings reveal that considering fuel quantity per cycle is significant when studying diesel engine partial loads, notably at low loads. The study contributes a vital basis for further investigating and modeling the partial characteristics of diesel engines. Also, it is a crucial reference for estimating the suitable working conditions of engine-driven systems in practice.</div></div>","PeriodicalId":34480,"journal":{"name":"Transportation Engineering","volume":"18 ","pages":"Article 100288"},"PeriodicalIF":0.0,"publicationDate":"2024-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142660172","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

An examination of high-speed aircraft – Part 1: Past, Present, and Future 考察高速飞机--第 1 部分：过去、现在和未来

Q1 Engineering

Transportation Engineering

Pub Date : 2024-11-02 DOI: 10.1016/j.treng.2024.100290

Luke Pollock , Graham Wild

This paper provides an examination of the modern high-speed aircraft industry, including a compilation of recent developments and planned aircraft. The potential for a civil high-speed airliner is examined from a financial and contemporary perspective. Mach 4 is introduced as the economic line, below which high-speed flight is shown as financially viable. Despite this, a preliminary analysis from historic data highlights flight below Mach 2.12 as relatively low risk, with a hypersonic airliner not envisioned until the next century. Several challenges that are less discussed in literature are reviewed here with safety and reliability being the principal among them. This paper hence serves as the first part, which is followed by a comprehensive review of high-speed vehicle accidents.

本文对现代高速飞机工业进行了研究，包括最新发展和计划中的飞机的汇编。本文从财务和现代角度研究了民用高速客机的潜力。4 马赫作为经济线被引入，低于这条线的高速飞行在经济上是可行的。尽管如此，根据历史数据进行的初步分析表明，低于 2.12 马赫的飞行风险相对较低，高超音速客机要到下个世纪才会出现。本文对文献中讨论较少的几项挑战进行了综述，安全性和可靠性是其中的主要挑战。因此，本文将作为第一部分，随后对高速飞行器事故进行全面回顾。

引用次数: 0

A comparative study of vehicle powertrain efficiency: Data-driven analyzing energy consumption and environmental impact 汽车动力总成效率比较研究：数据驱动分析能源消耗和环境影响

Q1 Engineering

Transportation Engineering

Pub Date : 2024-10-28 DOI: 10.1016/j.treng.2024.100286

Witsarut Achariyaviriya , Wongkot Wongsapai , Damrongsak Rinchumphu , Nakorn Tippayawong , Korrakot Yaibuathet Tippayawong , Pana Suttakul

This study investigates the energy consumption of electric vehicles (EVs) in real-world driving conditions, using in-vehicle sensor data and location tracking. The energy consumption of EVs is compared to that of an internal combustion engine vehicle (ICEV) under similar driving tests. Furthermore, an energy-centric life cycle assessment was conducted to assess the environmental impact of the transition to electrified transportation by reporting the carbon emissions of the EVs and ICEV. Since a large volume of driving data was acquired in the experiment, machine learning (ML) techniques are employed to interpret the obtained data and identify a key feature. ML algorithms can help develop predictive models that estimate energy consumption and explain the major factors that impact such consumption. The findings also offer valuable insights into energy consumption, emission, and the underlying factors that can inform policy discussion related to transport electrification and enhance energy efficiency. This research is significant in comprehending the potential of current EVs and their superiority over traditional vehicles. It is vital to facilitate the shift toward electric transportation, which can be driven by the results.

本研究利用车载传感器数据和位置跟踪，调查了电动汽车（EV）在实际驾驶条件下的能耗。电动汽车的能耗与内燃机汽车（ICEV）在类似驾驶测试下的能耗进行了比较。此外，还进行了以能源为中心的生命周期评估，通过报告电动汽车和内燃机汽车的碳排放量，评估向电气化交通过渡对环境的影响。由于在实验中获取了大量的驾驶数据，因此采用了机器学习（ML）技术来解释获取的数据并识别关键特征。ML 算法有助于开发预测模型，以估算能源消耗并解释影响能源消耗的主要因素。研究结果还提供了有关能源消耗、排放和潜在因素的宝贵见解，可为有关交通电气化和提高能源效率的政策讨论提供信息。这项研究对于理解当前电动汽车的潜力及其相对于传统汽车的优越性具有重要意义。它对于促进向电动交通的转变至关重要，而这正是研究成果所能推动的。

{"title":"A comparative study of vehicle powertrain efficiency: Data-driven analyzing energy consumption and environmental impact","authors":"Witsarut Achariyaviriya , Wongkot Wongsapai , Damrongsak Rinchumphu , Nakorn Tippayawong , Korrakot Yaibuathet Tippayawong , Pana Suttakul","doi":"10.1016/j.treng.2024.100286","DOIUrl":"10.1016/j.treng.2024.100286","url":null,"abstract":"<div><div>This study investigates the energy consumption of electric vehicles (EVs) in real-world driving conditions, using in-vehicle sensor data and location tracking. The energy consumption of EVs is compared to that of an internal combustion engine vehicle (ICEV) under similar driving tests. Furthermore, an energy-centric life cycle assessment was conducted to assess the environmental impact of the transition to electrified transportation by reporting the carbon emissions of the EVs and ICEV. Since a large volume of driving data was acquired in the experiment, machine learning (ML) techniques are employed to interpret the obtained data and identify a key feature. ML algorithms can help develop predictive models that estimate energy consumption and explain the major factors that impact such consumption. The findings also offer valuable insights into energy consumption, emission, and the underlying factors that can inform policy discussion related to transport electrification and enhance energy efficiency. This research is significant in comprehending the potential of current EVs and their superiority over traditional vehicles. It is vital to facilitate the shift toward electric transportation, which can be driven by the results.</div></div>","PeriodicalId":34480,"journal":{"name":"Transportation Engineering","volume":"18 ","pages":"Article 100286"},"PeriodicalIF":0.0,"publicationDate":"2024-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142571712","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Mobility challenges for women: A case study of bus rapid transit Peshawar 妇女面临的交通挑战：白沙瓦快速公交案例研究

Q1 Engineering

Transportation Engineering

Pub Date : 2024-10-28 DOI: 10.1016/j.treng.2024.100285

Altaf Ayaz , Hamza Saleem , Muhammad Usama Bin Ayyub , Abdul Qadeer

In Pakistan, women face significant barriers to urban mobility. This is due to limited access to safe, affordable, and sustainable public transportation, exacerbated by socio-cultural norms and experiences of harassment. Addressing these challenges is crucial for promoting gender equality and unlocking women's potential for growth. This research inspects women's mobility experiences and challenges and proposes potential improvements for bus rapid transit (BRT) Peshawar. Interviews were conducted for data collection, and statistical tools and methods were employed to analyze the results. The most common modes of travel to and from the BRT stations were walk (39%&45%) followed by Taxi/Rickshaw (32%each) and car/bike (15%&9%), respectively. Most users accessed the BRT system within a 3km radius (55%) and typically traveled during the daytime (56% from 6–10 am and 51% from 2–6 pm). The main challenges identified, mainly for the younger users, were harassment faced at stations (66% for 18–30 years and 52% for 31–45 years of age groups, respectively) while on the buses with 54% for <18 years and 56% for 18–30 years of age groups, respectively, with a visual type of harassment in major. The study highlights women's unique mobility challenges with Peshawar BRT. Addressing these issues can boost their education and economic prospects, as a major study sample was comprised of lower-income employees (80% having an income less than 40,000 PKR¹) and middle-aged students (48%). The findings provide valuable insights for BRT Peshawar and future BRT projects in developing countries. Despite separate seats, challenges persist during peak hours due to the absence of partitions between male and female sections within buses and other BRT amenities.

在巴基斯坦，妇女在城市交通方面面临巨大障碍。这是由于获得安全、负担得起和可持续的公共交通的机会有限，而社会文化规范和骚扰经历又加剧了这一问题。应对这些挑战对于促进性别平等和释放妇女的发展潜力至关重要。本研究考察了妇女的出行经验和挑战，并提出了白沙瓦快速公交系统（BRT）的潜在改进措施。通过访谈收集数据，并采用统计工具和方法对结果进行分析。往返快速公交系统站点最常见的出行方式是步行（39%&45%），其次分别是出租车/人力车（各占 32%）和汽车/自行车（15%&9%）。大多数用户在半径为 3 公里的范围内使用快速公交系统（55%），通常在白天出行（56%在上午 6 时至 10 时，51%在下午 2 时至 6 时）。已确定的主要挑战（主要针对年轻用户）是在车站受到骚扰（18-30 岁年龄组和 31-45 岁年龄组分别占 66% 和 52%），而在公交车上，18 岁年龄组和 18-30 岁年龄组分别占 54%和 56%，主要是视觉类型的骚扰。这项研究强调了女性在白沙瓦快速公交系统中面临的独特出行挑战。解决这些问题可以改善她们的教育和经济前景，因为研究的主要样本是低收入雇员（80%的收入低于 40,000 PKR1）和中年学生（48%）。研究结果为白沙瓦快速公交和发展中国家未来的快速公交项目提供了宝贵的启示。尽管实行了男女分座，但由于公交车和其他快速公交设施没有对男女乘客进行分隔，因此在高峰时段仍然存在挑战。

{"title":"Mobility challenges for women: A case study of bus rapid transit Peshawar","authors":"Altaf Ayaz , Hamza Saleem , Muhammad Usama Bin Ayyub , Abdul Qadeer","doi":"10.1016/j.treng.2024.100285","DOIUrl":"10.1016/j.treng.2024.100285","url":null,"abstract":"<div><div>In Pakistan, women face significant barriers to urban mobility. This is due to limited access to safe, affordable, and sustainable public transportation, exacerbated by socio-cultural norms and experiences of harassment. Addressing these challenges is crucial for promoting gender equality and unlocking women's potential for growth. This research inspects women's mobility experiences and challenges and proposes potential improvements for bus rapid transit (BRT) Peshawar. Interviews were conducted for data collection, and statistical tools and methods were employed to analyze the results. The most common modes of travel to and from the BRT stations were walk (39%&45%) followed by Taxi/Rickshaw (32%each) and car/bike (15%&9%), respectively. Most users accessed the BRT system within a 3km radius (55%) and typically traveled during the daytime (56% from 6–10 am and 51% from 2–6 pm). The main challenges identified, mainly for the younger users, were harassment faced at stations (66% for 18–30 years and 52% for 31–45 years of age groups, respectively) while on the buses with 54% for <18 years and 56% for 18–30 years of age groups, respectively, with a visual type of harassment in major. The study highlights women's unique mobility challenges with Peshawar BRT. Addressing these issues can boost their education and economic prospects, as a major study sample was comprised of lower-income employees (80% having an income less than 40,000 PKR<span><span><sup>1</sup></span></span>) and middle-aged students (48%). The findings provide valuable insights for BRT Peshawar and future BRT projects in developing countries. Despite separate seats, challenges persist during peak hours due to the absence of partitions between male and female sections within buses and other BRT amenities.</div></div>","PeriodicalId":34480,"journal":{"name":"Transportation Engineering","volume":"18 ","pages":"Article 100285"},"PeriodicalIF":0.0,"publicationDate":"2024-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142553421","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Safety and bicycle route choice: To what extent do accident risk and perceived safety influence bicycle route choice? 安全与自行车路线选择：事故风险和安全感对自行车路线选择有多大影响？

Q1 Engineering

Transportation Engineering

Pub Date : 2024-10-26 DOI: 10.1016/j.treng.2024.100240

Stefan Huber , Paul Lindemann , Bettina Schröter

Safety is a major concern in bicycle traffic, and understanding safety-related factors that influence bicycle route choice is crucial for improving safety and promoting sustainable transportation. However, there is a notable lack of research on the impact of accident risk and perceived safety on cyclists' route choices. This study addresses this gap by investigating whether accident-prone areas or perceived insecure locations affect actual route choice decisions. The contribution explores this relationship by leveraging an extensive dataset comprising approximately 4000 trips from around 170 participants, alongside additional data on infrastructure, operations, exposure, accidents, and mobility diaries reporting critical incidents. The findings broadly confirm results from other studies regarding the influence of route characteristics (e.g., existence of cycling infrastructure, volumes of motorized traffic, or presence of signal-controlled intersections). Moreover, the study reveals that a high accident risk along a route does have a slight negative influence on route choice. Surprisingly, perceived safety does not significantly influence cyclists' route choice.

安全是自行车交通中的一个主要问题，了解影响自行车路线选择的安全相关因素对于提高安全性和促进可持续交通至关重要。然而，关于事故风险和安全感对骑车人路线选择的影响的研究明显不足。本研究通过调查事故多发地区或感知的不安全地点是否会影响实际的路线选择决策，弥补了这一空白。研究利用了一个广泛的数据集，其中包括来自约 170 名参与者的约 4000 次出行，以及有关基础设施、运营、风险暴露、事故和报告突发事件的移动日记等其他数据，来探讨这种关系。研究结果广泛证实了其他研究中关于路线特征（如是否有自行车基础设施、机动车流量或是否有信号控制交叉路口）影响的结果。此外，研究还发现，沿线事故风险高确实会对路线选择产生轻微的负面影响。令人惊讶的是，安全感并不会对骑车人的路线选择产生重大影响。

{"title":"Safety and bicycle route choice: To what extent do accident risk and perceived safety influence bicycle route choice?","authors":"Stefan Huber , Paul Lindemann , Bettina Schröter","doi":"10.1016/j.treng.2024.100240","DOIUrl":"10.1016/j.treng.2024.100240","url":null,"abstract":"<div><div>Safety is a major concern in bicycle traffic, and understanding safety-related factors that influence bicycle route choice is crucial for improving safety and promoting sustainable transportation. However, there is a notable lack of research on the impact of accident risk and perceived safety on cyclists' route choices. This study addresses this gap by investigating whether accident-prone areas or perceived insecure locations affect actual route choice decisions. The contribution explores this relationship by leveraging an extensive dataset comprising approximately 4000 trips from around 170 participants, alongside additional data on infrastructure, operations, exposure, accidents, and mobility diaries reporting critical incidents. The findings broadly confirm results from other studies regarding the influence of route characteristics (e.g., existence of cycling infrastructure, volumes of motorized traffic, or presence of signal-controlled intersections). Moreover, the study reveals that a high accident risk along a route does have a slight negative influence on route choice. Surprisingly, perceived safety does not significantly influence cyclists' route choice.</div></div>","PeriodicalId":34480,"journal":{"name":"Transportation Engineering","volume":"18 ","pages":"Article 100240"},"PeriodicalIF":0.0,"publicationDate":"2024-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142561219","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Ensemble-based model to investigate factors influencing road crash fatality for imbalanced data 基于集合的模型，研究不平衡数据中影响道路交通事故死亡率的因素

Q1 Engineering

Transportation Engineering

Pub Date : 2024-10-22 DOI: 10.1016/j.treng.2024.100284

Nazmus Sakib , Tonmoy Paul , Nafis Anwari , Md. Hadiuzzaman

The rapid growth of urbanization and motorization has significantly increased traffic crashes, leading to both loss of life and diminished quality of life for crash survivors and their families. Identifying the factors influencing crash fatality is crucial for reducing such incidents. However, traffic crashes are inherently unpredictable, and crash fatality datasets are often imbalanced. This study provides a comprehensive evaluation of various machine learning (ML) techniques to analyze traffic crash fatality using an imbalanced dataset. It is the first to train eight distinct binary classification models: Classification and Regression Trees (CART), Random Forest (RF), Gradient Boosting Machine (GBM), Extreme Gradient Boost (XGBoost), Logistic Regression (LR), Support Vector Machine (SVM), K-Nearest Neighbors (KNN), and Naïve Bayes (NB) under three strategies: in isolation, with bagging, and with optimized bagging techniques (Grid Search CV, Random Search CV, and Bayesian Optimization). To handle data imbalance, eight resampling methods were employed, including SMOTE, Random Under-sampling (RUS), Random Over-sampling (ROS), ADASYN, Tomek Links, Near Miss, SMOTETomek, and SMOTEENN. Results show that GBM, combined with Bayesian optimized bagging and RUS, achieved the best performance with a G-mean score of 65.23 and an F1 score of 60.06. This study offers valuable insights into effective ML techniques, data resampling methods, and advanced optimization strategies for imbalanced crash severity datasets.

城市化和机动化的快速发展大大增加了交通事故的发生，导致车祸幸存者及其家人丧生，并降低了他们的生活质量。找出影响交通事故死亡的因素对于减少此类事故至关重要。然而，交通事故本身具有不可预测性，而且车祸死亡数据集往往是不平衡的。本研究对各种机器学习（ML）技术进行了全面评估，以利用不平衡数据集分析交通事故死亡率。它首次训练了八个不同的二元分类模型：分类和回归树 (CART)、随机森林 (RF)、梯度提升机 (GBM)、极端梯度提升 (XGBoost)、逻辑回归 (LR)、支持向量机 (SVM)、K-近邻 (KNN) 和奈夫贝叶斯 (NB)，并采用三种策略：单独、装袋和优化装袋技术（网格搜索 CV、随机搜索 CV 和贝叶斯优化）。为了处理数据不平衡问题，采用了八种重采样方法，包括 SMOTE、随机欠采样 (RUS)、随机过采样 (ROS)、ADASYN、Tomek Links、Near Miss、SMOTETomek 和 SMOTEENN。结果表明，GBM 与贝叶斯优化袋采样和 RUS 相结合，取得了最佳性能，G-mean 得分为 65.23，F1 得分为 60.06。这项研究为不平衡碰撞严重性数据集的有效 ML 技术、数据重采样方法和高级优化策略提供了宝贵的见解。

{"title":"Ensemble-based model to investigate factors influencing road crash fatality for imbalanced data","authors":"Nazmus Sakib , Tonmoy Paul , Nafis Anwari , Md. Hadiuzzaman","doi":"10.1016/j.treng.2024.100284","DOIUrl":"10.1016/j.treng.2024.100284","url":null,"abstract":"<div><div>The rapid growth of urbanization and motorization has significantly increased traffic crashes, leading to both loss of life and diminished quality of life for crash survivors and their families. Identifying the factors influencing crash fatality is crucial for reducing such incidents. However, traffic crashes are inherently unpredictable, and crash fatality datasets are often imbalanced. This study provides a comprehensive evaluation of various machine learning (ML) techniques to analyze traffic crash fatality using an imbalanced dataset. It is the first to train eight distinct binary classification models: Classification and Regression Trees (CART), Random Forest (RF), Gradient Boosting Machine (GBM), Extreme Gradient Boost (XGBoost), Logistic Regression (LR), Support Vector Machine (SVM), K-Nearest Neighbors (KNN), and Naïve Bayes (NB) under three strategies: in isolation, with bagging, and with optimized bagging techniques (Grid Search CV, Random Search CV, and Bayesian Optimization). To handle data imbalance, eight resampling methods were employed, including SMOTE, Random Under-sampling (RUS), Random Over-sampling (ROS), ADASYN, Tomek Links, Near Miss, SMOTETomek, and SMOTEENN. Results show that GBM, combined with Bayesian optimized bagging and RUS, achieved the best performance with a G-mean score of 65.23 and an F1 score of 60.06. This study offers valuable insights into effective ML techniques, data resampling methods, and advanced optimization strategies for imbalanced crash severity datasets.</div></div>","PeriodicalId":34480,"journal":{"name":"Transportation Engineering","volume":"18 ","pages":"Article 100284"},"PeriodicalIF":0.0,"publicationDate":"2024-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142528754","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A global approach to detecting and characterizing water leakage in a concrete bridge deck: Parametric study to validate an adapted Full-Waveform Inversion method

Q1 Engineering

Transportation Engineering

Pub Date : 2024-10-09 DOI: 10.1016/j.treng.2024.100283

Viktoriia Buliuk , Amine Ihamouten , Christophe Heinkele , Xavier Dérobert

The objective of this study is to address issues related to defects in waterproofing membranes through the use of Ground Penetration Radar to detect water leakage into the concrete layer of bridge decks. Given that processing radar signals based solely on temporal data introduces significant estimation errors, an advanced method optimized from Full-Waveform Inversion (FWI) is employed. This method accounts for several unknown factors, including boundary conditions, antenna positioning inaccuracies, and approximations inherent in 2D modeling during the inversion process. The method is adaptable and capable of reconstructing both the dielectric and geometric parameters of a multilayered structure with any number of layers and unknown parameters using just a few A-scans (up to 10, depending on the number of parameters and layers). In contrast, other methods typically require several hundred A-scans. This efficiency is achieved due to the two-dimensional nature of the layer system. Additionally, the simplicity of the structure facilitates a much faster and more straightforward inversion algorithm, hence making these features especially advantageous for practical applications. The optimized Full-Waveform Inversion approach allows for an accurate determination of unknown parameters within a multilayered medium. The high accuracy of this method is validated through a direct comparison with experiments, wherein the exact parameters are known. Such an approach enables the attainment of a low relative error using the currently available measurement device.

{"title":"A global approach to detecting and characterizing water leakage in a concrete bridge deck: Parametric study to validate an adapted Full-Waveform Inversion method","authors":"Viktoriia Buliuk , Amine Ihamouten , Christophe Heinkele , Xavier Dérobert","doi":"10.1016/j.treng.2024.100283","DOIUrl":"10.1016/j.treng.2024.100283","url":null,"abstract":"<div><div>The objective of this study is to address issues related to defects in waterproofing membranes through the use of Ground Penetration Radar to detect water leakage into the concrete layer of bridge decks. Given that processing radar signals based solely on temporal data introduces significant estimation errors, an advanced method optimized from Full-Waveform Inversion (FWI) is employed. This method accounts for several unknown factors, including boundary conditions, antenna positioning inaccuracies, and approximations inherent in 2D modeling during the inversion process. The method is adaptable and capable of reconstructing both the dielectric and geometric parameters of a multilayered structure with any number of layers and unknown parameters using just a few A-scans (up to 10, depending on the number of parameters and layers). In contrast, other methods typically require several hundred A-scans. This efficiency is achieved due to the two-dimensional nature of the layer system. Additionally, the simplicity of the structure facilitates a much faster and more straightforward inversion algorithm, hence making these features especially advantageous for practical applications. The optimized Full-Waveform Inversion approach allows for an accurate determination of unknown parameters within a multilayered medium. The high accuracy of this method is validated through a direct comparison with experiments, wherein the exact parameters are known. Such an approach enables the attainment of a low relative error using the currently available measurement device.</div></div>","PeriodicalId":34480,"journal":{"name":"Transportation Engineering","volume":"19 ","pages":"Article 100283"},"PeriodicalIF":0.0,"publicationDate":"2024-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143164946","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Predicting Marshall stability and flow parameters in asphalt pavements using explainable machine-learning models 利用可解释的机器学习模型预测沥青路面的马歇尔稳定性和流动参数

Q1 Engineering

Transportation Engineering

Pub Date : 2024-10-05 DOI: 10.1016/j.treng.2024.100282

Ibrahim Asi , Yusra I. Alhadidi , Taqwa I. Alhadidi

The traditional method for determining the Marshall stability (MS) and Marshall flow (MF) of asphalt pavements is laborious, time consuming, and costly. This study aims to predict these parameters using explainable machine-learning techniques. A comprehensive database comprising 721 hot mix asphalt (HMA) data points was established, including variables such as aggregate percentage, asphalt content, and specific gravity. Models were constructed using the PyCaret Python library, and their performance was assessed using metrics such as the mean absolute error (MAE) and coefficient of determination (R²). The CatBoost regression model outperformed the other models, achieving R² values of 0.835 and 0.845 for MS and MF, respectively. Additionally, Shapley values were used to quantify the variable effects on the predictions. This approach enables the efficient preselection of design variables, reducing the need for extensive laboratory testing and promoting sustainable construction practices.

确定沥青路面马歇尔稳定度（MS）和马歇尔流动度（MF）的传统方法费力、费时、费钱。本研究旨在利用可解释的机器学习技术预测这些参数。研究建立了一个包含 721 个热拌沥青（HMA）数据点的综合数据库，其中包括集料百分比、沥青含量和比重等变量。使用 PyCaret Python 库构建了模型，并使用平均绝对误差 (MAE) 和判定系数 (R²) 等指标评估了模型的性能。CatBoost 回归模型的表现优于其他模型，MS 和 MF 的 R² 值分别为 0.835 和 0.845。此外，还使用 Shapley 值来量化变量对预测的影响。这种方法可以有效地预选设计变量，减少对大量实验室测试的需求，促进可持续建筑实践。

引用次数: 0

Calibration of SUMO Microscopic Simulation for Heterogeneous Traffic Condition: The Case of the City of Khulna, Bangladesh 针对异质交通状况的 SUMO 微观模拟校准：孟加拉国库尔纳市案例

Q1 Engineering

Transportation Engineering

Pub Date : 2024-10-03 DOI: 10.1016/j.treng.2024.100281

Md. Mynul Hossain Chowdhury, Tanmoy Chakraborty

In the context of Bangladesh, Efficient modeling of vehicular traffic is a challenging task. Simulation is one of the approaches for traffic modeling. As cities become more urbanized, intelligent transportation systems (ITS) are becoming progressively more important to the development of future smart cities. The purpose of this research is to compare simulation data with field data to calibrate the SUMO simulation model tool. In this study, a microscopic traffic simulation model for some CBD areas of Khulna City has been calibrated. However, the focus area of Powerhouse is strategically located at the intersection of four key places in Khulna City, encompassing the central business district (CBD) and the city's railway station. During the peak hour, congestion frequently occurs at this crossroads. This research aims to provide alternative scenarios to reduce queue and travel time in the Powerhouse intersect. Types of observation data are flow, length of queue, and travel time that are observed during field survey. The calibration process is done by minimizing the root mean square error (RMSE) of queue, and travel time, and combining both of them between observation and calibrated model. After the calibration process, the sigma and tau values came out to be 0.3 and 1.4, respectively. By using this calibrated value, the travel time output may accurately reflect real-world scenarios, allowing for experimentation with various scenarios. This study presented two alternate scenarios aimed at enhancing the performance of Powerhouse. Alternate: 1 is more of a geometric modification with the installment of Channelization, it will reduce travel time substantially for each lane, nearly 10 % to 30% of its current time. Alternate: 2 is more of applying strict and fast regulations for the traffic which is Traffic light management, it is a more convenient option that appears. The results generated by utilizing SUMO can be reliable and helpful in developing and optimizing urban transportation systems in the future. It is essential to understand that traffic simulation with SUMO is merely a transportation decision-making and planning tool and must be linked with field observations and reliable data for suitable and efficient transportation solutions.

在孟加拉国，车辆交通的高效建模是一项具有挑战性的任务。模拟是交通建模的方法之一。随着城市化进程的加快，智能交通系统（ITS）对未来智能城市的发展越来越重要。本研究的目的是将模拟数据与实地数据进行比较，以校准 SUMO 模拟模型工具。在本研究中，对库尔纳市一些 CBD 区域的微观交通仿真模型进行了校准。然而，Powerhouse 的重点区域位于库尔纳市四个重要地点的交汇处，包括中央商务区（CBD）和该市的火车站，地理位置十分重要。在高峰时段，该十字路口经常出现拥堵现象。本研究旨在提供替代方案，以减少动力室十字路口的车龙和行车时间。观测数据类型包括在实地调查中观测到的流量、排队长度和旅行时间。校准过程是通过最小化排队长度和旅行时间的均方根误差（RMSE），并在观测数据和校准模型之间将两者结合起来。校准过程结束后，sigma 值和 tau 值分别为 0.3 和 1.4。通过使用该校准值，旅行时间输出可准确反映真实世界的情景，从而可对各种情景进行试验。本研究提出了两个备选方案，旨在提高 "动力室 "的性能。备选方案 1备选方案 1 更多的是通过安装渠化装置进行几何改造，这将大幅缩短每条车道的行车时间，比目前缩短近 10% 至 30%。备选方案 2 更多地是对交通实施严格而快速的管理，即红绿灯管理，这是一种更方便的选择。利用 SUMO 得出的结果是可靠的，有助于未来开发和优化城市交通系统。必须认识到，SUMO 的交通模拟只是一种交通决策和规划工具，必须与实地观测和可靠数据相结合，才能找到合适、高效的交通解决方案。

{"title":"Calibration of SUMO Microscopic Simulation for Heterogeneous Traffic Condition: The Case of the City of Khulna, Bangladesh","authors":"Md. Mynul Hossain Chowdhury, Tanmoy Chakraborty","doi":"10.1016/j.treng.2024.100281","DOIUrl":"10.1016/j.treng.2024.100281","url":null,"abstract":"<div><div>In the context of Bangladesh, Efficient modeling of vehicular traffic is a challenging task. Simulation is one of the approaches for traffic modeling. As cities become more urbanized, intelligent transportation systems (ITS) are becoming progressively more important to the development of future smart cities. The purpose of this research is to compare simulation data with field data to calibrate the SUMO simulation model tool. In this study, a microscopic traffic simulation model for some CBD areas of Khulna City has been calibrated. However, the focus area of Powerhouse is strategically located at the intersection of four key places in Khulna City, encompassing the central business district (CBD) and the city's railway station. During the peak hour, congestion frequently occurs at this crossroads. This research aims to provide alternative scenarios to reduce queue and travel time in the Powerhouse intersect. Types of observation data are flow, length of queue, and travel time that are observed during field survey. The calibration process is done by minimizing the root mean square error (RMSE) of queue, and travel time, and combining both of them between observation and calibrated model. After the calibration process, the sigma and tau values came out to be 0.3 and 1.4, respectively. By using this calibrated value, the travel time output may accurately reflect real-world scenarios, allowing for experimentation with various scenarios. This study presented two alternate scenarios aimed at enhancing the performance of Powerhouse. Alternate: 1 is more of a geometric modification with the installment of Channelization, it will reduce travel time substantially for each lane, nearly 10 % to 30% of its current time. Alternate: 2 is more of applying strict and fast regulations for the traffic which is Traffic light management, it is a more convenient option that appears. The results generated by utilizing SUMO can be reliable and helpful in developing and optimizing urban transportation systems in the future. It is essential to understand that traffic simulation with SUMO is merely a transportation decision-making and planning tool and must be linked with field observations and reliable data for suitable and efficient transportation solutions.</div></div>","PeriodicalId":34480,"journal":{"name":"Transportation Engineering","volume":"18 ","pages":"Article 100281"},"PeriodicalIF":0.0,"publicationDate":"2024-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142445614","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Exploring the relationship between data sample size and traffic flow prediction accuracy 探索数据样本大小与交通流量预测准确性之间的关系

Q1 Engineering

Transportation Engineering

Pub Date : 2024-09-27 DOI: 10.1016/j.treng.2024.100279

Jianhu Zheng , Minghua Wang , Mingfang Huang

Efficiently extracting and analyzing large urban traffic data, accurately predicting traffic conditions, and improving urban traffic management require careful selection of an appropriate data sample size. The suitable size of data sample assumes paramount importance in fostering sustainable transportation development. This paper investigates the relationship between traffic flow prediction performance and data sample size, considering data sample missing rates, duration, and road segment coverage. Real traffic flow data from 13 road sections in Changsha, China, are analyzed using the Decision Tree, Support Vector Machine, Gaussian Process Regression and Artificial Neural Network models. Some key findings include: Lower data sample loss rates improve prediction accuracy by capturing traffic flow patterns effectively, while higher loss rates decrease accuracy; an optimal data sample duration of around 7 days balances prediction accuracy and data stability, with longer durations providing more historical data but risking complexity; Broader road segment coverage gives a more comprehensive traffic flow information, but excessive coverage introduces noise and impacts the improvement of prediction accuracy. The results highlight the significant impact of data sample size on prediction performance. Enhancing reliability can be achieved by reducing data loss, selecting suitable durations, and considering appropriate road segment coverage, supporting improved traffic management and route planning.

要有效提取和分析城市交通大数据、准确预测交通状况并改善城市交通管理，就必须谨慎选择合适的数据样本大小。合适的数据样本大小对促进交通的可持续发展至关重要。本文在考虑数据样本缺失率、持续时间和路段覆盖范围的基础上，研究了交通流量预测性能与数据样本大小之间的关系。本文使用决策树、支持向量机、高斯过程回归和人工神经网络模型对中国长沙 13 个路段的真实交通流量数据进行了分析。一些主要发现包括较低的数据样本丢失率可有效捕捉交通流模式，从而提高预测准确性，而较高的丢失率则会降低预测准确性；7 天左右的最佳数据样本持续时间可平衡预测准确性和数据稳定性，较长的持续时间可提供更多历史数据，但存在复杂性风险；较广的路段覆盖范围可提供更全面的交通流信息，但过大的覆盖范围会引入噪声，影响预测准确性的提高。结果凸显了数据样本大小对预测性能的重要影响。通过减少数据丢失、选择合适的持续时间以及考虑适当的路段覆盖范围，可以提高可靠性，从而为改进交通管理和路线规划提供支持。

{"title":"Exploring the relationship between data sample size and traffic flow prediction accuracy","authors":"Jianhu Zheng , Minghua Wang , Mingfang Huang","doi":"10.1016/j.treng.2024.100279","DOIUrl":"10.1016/j.treng.2024.100279","url":null,"abstract":"<div><div>Efficiently extracting and analyzing large urban traffic data, accurately predicting traffic conditions, and improving urban traffic management require careful selection of an appropriate data sample size. The suitable size of data sample assumes paramount importance in fostering sustainable transportation development. This paper investigates the relationship between traffic flow prediction performance and data sample size, considering data sample missing rates, duration, and road segment coverage. Real traffic flow data from 13 road sections in Changsha, China, are analyzed using the Decision Tree, Support Vector Machine, Gaussian Process Regression and Artificial Neural Network models. Some key findings include: Lower data sample loss rates improve prediction accuracy by capturing traffic flow patterns effectively, while higher loss rates decrease accuracy; an optimal data sample duration of around 7 days balances prediction accuracy and data stability, with longer durations providing more historical data but risking complexity; Broader road segment coverage gives a more comprehensive traffic flow information, but excessive coverage introduces noise and impacts the improvement of prediction accuracy. The results highlight the significant impact of data sample size on prediction performance. Enhancing reliability can be achieved by reducing data loss, selecting suitable durations, and considering appropriate road segment coverage, supporting improved traffic management and route planning.</div></div>","PeriodicalId":34480,"journal":{"name":"Transportation Engineering","volume":"18 ","pages":"Article 100279"},"PeriodicalIF":0.0,"publicationDate":"2024-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142358991","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0