Xingliang Liu, Shuang Deng, Tangzhi Liu, Tong Liu, Song Wang
Due to the complex traffic characteristics in highway merging areas, drivers tend to exhibit high-risk driving behaviors. To address the characteristics of driving behavior in highway merging areas, we have developed a real-time identification model for risky drivers by combining a driver risk level labeling method with load balancing-ensemble learning (LB-EL). In this paper, we explore four types of maneuver indicator indexes (MIIs)—acute direction, stomp pedal, dangerous following, and dangerous lane changing—that can describe the negative behaviors of both individual vehicles and vehicle platoons in highway merging areas. To quantize the label driver risk level, we use the interquartile range (IQR) method and Criteria Importance Though Intercriteria Correlation (CRITIC), while we evaluate the reliability of the MII using spatial analysis. Furthermore, we balance the dataset using three load balancing (LB) algorithms and create nine ensemble strategies by pairing adaptive boosting (AdaBoost), extreme gradient boosting (XGBoost), and light gradient boosting machine (LGBM) with the three LB algorithms. Finally, we validate the proposed model using trajectory data extracted from UAV videos. The results indicate that the distribution laws of risky driving behaviors in the acute direction and stomp pedal show a high degree of similarity and good matching with the distribution laws of traffic conflict points in existing research. Moreover, the SMOTE-LGBM ensemble model achieves the best performance, reaching an accuracy rate of 93.4% and a recall rate of 92.1%, which demonstrates the validity of our proposed model. This model can be widely applied to recognize risky drivers in video-based surveillance systems.
由于高速公路合流区交通特征复杂，驾驶员往往表现出高风险驾驶行为。针对高速公路合流区驾驶行为的特点，我们将驾驶员风险等级标注方法与负载平衡-集合学习（LB-EL）相结合，建立了风险驾驶员实时识别模型。本文探讨了四种机动指标（MIIs）--急打方向、蹬踏踏板、危险跟车和危险变道--它们可以描述高速公路并线区域内单个车辆和车辆编队的负面行为。为了量化标签驾驶员的风险水平，我们使用了四分位数间距法（IQR）和标准重要度衡量标准间相关性法（CRITIC），同时使用空间分析法评估 MII 的可靠性。此外，我们使用三种负载平衡（LB）算法平衡数据集，并通过将自适应提升（AdaBoost）、极梯度提升（XGBoost）和轻梯度提升机（LGBM）与三种 LB 算法配对，创建了九种集合策略。最后，我们使用从无人机视频中提取的轨迹数据验证了所提出的模型。结果表明，急打方向和蹬踏板的危险驾驶行为分布规律与现有研究中的交通冲突点分布规律具有高度相似性和良好的匹配性。此外，SMOTE-LGBM 集合模型的性能最佳，准确率达到 93.4%，召回率达到 92.1%，这证明了我们提出的模型的有效性。该模型可广泛应用于基于视频监控系统的风险驾驶员识别。
{"title":"A maneuver indicator and ensemble learning-based risky driver recognition approach for highway merging areas","authors":"Xingliang Liu, Shuang Deng, Tangzhi Liu, Tong Liu, Song Wang","doi":"10.1093/tse/tdae015","DOIUrl":"https://doi.org/10.1093/tse/tdae015","url":null,"abstract":"\u0000 Due to the complex traffic characteristics in highway merging areas, drivers tend to exhibit high-risk driving behaviors. To address the characteristics of driving behavior in highway merging areas, we have developed a real-time identification model for risky drivers by combining a driver risk level labeling method with load balancing-ensemble learning (LB-EL). In this paper, we explore four types of maneuver indicator indexes (MIIs)—acute direction, stomp pedal, dangerous following, and dangerous lane changing—that can describe the negative behaviors of both individual vehicles and vehicle platoons in highway merging areas. To quantize the label driver risk level, we use the interquartile range (IQR) method and Criteria Importance Though Intercriteria Correlation (CRITIC), while we evaluate the reliability of the MII using spatial analysis. Furthermore, we balance the dataset using three load balancing (LB) algorithms and create nine ensemble strategies by pairing adaptive boosting (AdaBoost), extreme gradient boosting (XGBoost), and light gradient boosting machine (LGBM) with the three LB algorithms. Finally, we validate the proposed model using trajectory data extracted from UAV videos. The results indicate that the distribution laws of risky driving behaviors in the acute direction and stomp pedal show a high degree of similarity and good matching with the distribution laws of traffic conflict points in existing research. Moreover, the SMOTE-LGBM ensemble model achieves the best performance, reaching an accuracy rate of 93.4% and a recall rate of 92.1%, which demonstrates the validity of our proposed model. This model can be widely applied to recognize risky drivers in video-based surveillance systems.","PeriodicalId":52804,"journal":{"name":"Transportation Safety and Environment","volume":null,"pages":null},"PeriodicalIF":2.2,"publicationDate":"2024-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140692561","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Traffic crashes are a prominent cause of fatalities around the world. This study focuses on the dynamics of traffic safety by analyzing factors influencing crash frequency during both nighttime and daytime conditions. Four years data derived from the Fatality Analysis Reporting System (FARS) database were analyzed statistically based on the negative binomial regression model, to identify the contributions of several factors affecting crash outcomes. The findings reveal significant related factors including the area type, roadway alignment, speeding-related factors, gender, number of lanes, grade, surface type, and weather conditions that contributed to the expected crash frequency during both daytime and nighttime conditions. Through quantitative analysis, the extent to which each factor contributes to the expected crash frequency was determined, offering effective insights for policymaking to boost roadway safety. The findings highlight the necessity of implementing targeted strategies to minimize the risk of crashes by creating safer road environments.
{"title":"Unraveling the veil of traffic safety: A comprehensive analysis of factors influencing crash frequency across U.S. States","authors":"M. Obeidat, Rahma Mohammad Obeidat, F. Dweiri","doi":"10.1093/tse/tdae016","DOIUrl":"https://doi.org/10.1093/tse/tdae016","url":null,"abstract":"\u0000 Traffic crashes are a prominent cause of fatalities around the world. This study focuses on the dynamics of traffic safety by analyzing factors influencing crash frequency during both nighttime and daytime conditions. Four years data derived from the Fatality Analysis Reporting System (FARS) database were analyzed statistically based on the negative binomial regression model, to identify the contributions of several factors affecting crash outcomes. The findings reveal significant related factors including the area type, roadway alignment, speeding-related factors, gender, number of lanes, grade, surface type, and weather conditions that contributed to the expected crash frequency during both daytime and nighttime conditions. Through quantitative analysis, the extent to which each factor contributes to the expected crash frequency was determined, offering effective insights for policymaking to boost roadway safety. The findings highlight the necessity of implementing targeted strategies to minimize the risk of crashes by creating safer road environments.","PeriodicalId":52804,"journal":{"name":"Transportation Safety and Environment","volume":null,"pages":null},"PeriodicalIF":2.2,"publicationDate":"2024-04-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140707154","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Honggang Wang, Xinghua Wang, Yong Peng, Xin Lou, Zaining Li
To meet the requirements for high-risk testing scenarios in the safety assessment of advanced driver assistance systems (ADAS), this study selected 239 vehicle-to-powered two-wheeler accidents occurring in Xiangtan County from the China In-depth Mobility Safety Study—Traffic Accident (CIMSS-TA) database. Seven scenario elements were selected from the levels of static road elements, dynamic traffic participants and environment elements. The accident characteristics were obtained through statistical analysis. The results showed 75.73% of accidents occurred at T-junctions/intersections, and 34.73% of accidents were caused by the visual obstructions. Six typical vehicle-to-powered two-wheeler crash scenarios were established by cluster analysis, including two straight road scenarios (scenario 3 and 6), two T-junction scenarios (scenario 1 and 5), and two intersection scenarios (scenario 2 and 4). Furthermore, six vehicle-to-powered two-wheeler testing scenarios, which represent the traffic environment characteristics of Chinese county-level districts, were constructed by analyzing the vehicle/PTW speed, the first collision point of vehicle, obstacle type and location, etc. The results showed the vehicle speed in scenario 4 was higher than that in scenario 2, with the average values of 34.32 km/h and 21.99 km/h, respectively. The results of this study provided testing scenarios for the safety assessment of ADAS, and contributed to improving the vehicle active safety technology.
为满足高级驾驶辅助系统（ADAS）安全评估对高风险测试场景的要求，本研究从中国交通安全深度研究-交通事故（CIMSS-TA）数据库中选取了发生在湘潭县的239起车碰车事故。从静态道路要素、动态交通参与者和环境要素三个层面选取了七个场景要素。通过统计分析获得事故特征。结果显示，75.73% 的事故发生在 T 型路口/交叉口，34.73% 的事故由视觉障碍物引起。通过聚类分析，确定了六种典型的车辆与电动二轮车碰撞情景，包括两种直行道路情景（情景 3 和 6）、两种 T 形路口情景（情景 1 和 5）以及两种交叉路口情景（情景 2 和 4）。此外，通过分析车辆/二轮摩托车速度、车辆第一碰撞点、障碍物类型和位置等，构建了代表中国县级地区交通环境特征的六个车辆对二轮摩托车测试场景。结果表明，情景 4 中的车辆速度高于情景 2，平均值分别为 34.32 km/h 和 21.99 km/h。研究结果为 ADAS 的安全评估提供了测试场景，有助于改进车辆主动安全技术。
{"title":"An investigation of ADAS testing scenarios based on vehicle-to-powered two-wheeler accidents occurring in a county-level district in Hunan province","authors":"Honggang Wang, Xinghua Wang, Yong Peng, Xin Lou, Zaining Li","doi":"10.1093/tse/tdae013","DOIUrl":"https://doi.org/10.1093/tse/tdae013","url":null,"abstract":"\u0000 To meet the requirements for high-risk testing scenarios in the safety assessment of advanced driver assistance systems (ADAS), this study selected 239 vehicle-to-powered two-wheeler accidents occurring in Xiangtan County from the China In-depth Mobility Safety Study—Traffic Accident (CIMSS-TA) database. Seven scenario elements were selected from the levels of static road elements, dynamic traffic participants and environment elements. The accident characteristics were obtained through statistical analysis. The results showed 75.73% of accidents occurred at T-junctions/intersections, and 34.73% of accidents were caused by the visual obstructions. Six typical vehicle-to-powered two-wheeler crash scenarios were established by cluster analysis, including two straight road scenarios (scenario 3 and 6), two T-junction scenarios (scenario 1 and 5), and two intersection scenarios (scenario 2 and 4). Furthermore, six vehicle-to-powered two-wheeler testing scenarios, which represent the traffic environment characteristics of Chinese county-level districts, were constructed by analyzing the vehicle/PTW speed, the first collision point of vehicle, obstacle type and location, etc. The results showed the vehicle speed in scenario 4 was higher than that in scenario 2, with the average values of 34.32 km/h and 21.99 km/h, respectively. The results of this study provided testing scenarios for the safety assessment of ADAS, and contributed to improving the vehicle active safety technology.","PeriodicalId":52804,"journal":{"name":"Transportation Safety and Environment","volume":null,"pages":null},"PeriodicalIF":2.2,"publicationDate":"2024-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140374819","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The advanced diagnosis of faults in railway point machines is momentous to ensure the efficient and stable operation of the turnout conversion system. Numerous mature deep learning methods have been extensively applied in this domain. While robust perception has yielded excellent diagnostic outcomes, the deficiency in decision-making capability has led to a lack of overall intelligence. To deal with this, this study proposes an end-to-end deep reinforcement learning (DRL) framework for diagnosing faults in railway point machines. Firstly, a one-dimensional convolutional neural network (1DCNN) is used for the automatic extraction of features from the current signal. Subsequently, the deep Q network (DQN) algorithm is introduced as the core of the diagnostic framework. This involves designing an interactive environment for fault classification and optimizing the agent training network. Finally, leveraging fault data, the agent and the environment engage in continuous interactive learning to produce the ideal classification policy. Multiple comparative experiments are conducted to validate the proposed method. The results demonstrate that the diagnostic accuracy reaches 98.41%, and the average accuracy after many iterations is as high as 99.12%. Notably, this research introduces a creative application of DRL to address the challenge of diagnosing faults in railway point machines. The incorporation of decision thought effectively enhances the intelligence of fault diagnosis.
{"title":"Research on intelligent fault diagnosis for railway point machines using deep reinforcement learning","authors":"Shuai Xiao, Qingsheng Feng, Hong Li, Xue Li","doi":"10.1093/tse/tdae007","DOIUrl":"https://doi.org/10.1093/tse/tdae007","url":null,"abstract":"\u0000 The advanced diagnosis of faults in railway point machines is momentous to ensure the efficient and stable operation of the turnout conversion system. Numerous mature deep learning methods have been extensively applied in this domain. While robust perception has yielded excellent diagnostic outcomes, the deficiency in decision-making capability has led to a lack of overall intelligence. To deal with this, this study proposes an end-to-end deep reinforcement learning (DRL) framework for diagnosing faults in railway point machines. Firstly, a one-dimensional convolutional neural network (1DCNN) is used for the automatic extraction of features from the current signal. Subsequently, the deep Q network (DQN) algorithm is introduced as the core of the diagnostic framework. This involves designing an interactive environment for fault classification and optimizing the agent training network. Finally, leveraging fault data, the agent and the environment engage in continuous interactive learning to produce the ideal classification policy. Multiple comparative experiments are conducted to validate the proposed method. The results demonstrate that the diagnostic accuracy reaches 98.41%, and the average accuracy after many iterations is as high as 99.12%. Notably, this research introduces a creative application of DRL to address the challenge of diagnosing faults in railway point machines. The incorporation of decision thought effectively enhances the intelligence of fault diagnosis.","PeriodicalId":52804,"journal":{"name":"Transportation Safety and Environment","volume":null,"pages":null},"PeriodicalIF":2.2,"publicationDate":"2024-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140221333","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
To achieve better control effect of the controller on the liquid level of LNG carrier and achieve the goal of energy saving and carbon reduction. This paper took the loaded square tank of an S175 high-speed container ship as the research plant, combined with the closed-loop gain-shaping algorithm (CGSA) and nonlinear modification technology to further optimize the controller. We initially employed a third-order CGSA approach in formulating the foundation of our linear controller. Subsequently, we introduced a non-linear modification to this controller by harnessing the power of the hyperbolic tangent function, and the control effect is verified by the MATLAB simulation experiment. Based on the outcomes of our MATLAB simulations, by integrating the third-order CGSA technique and introducing non-linear modification through the hyperbolic tangent function, we observed a significant enhancement in the controller's performance. Specifically, it outperformed the traditional PID controller by a substantial margin, demonstrating a remarkable 19% boost in control efficacy. Additionally, it provides better energy savings than the non-linear controller. The controller designed in this paper has a better control effect on liquid tank level control of LNG ships, the control process is more energy-saving, and the purpose of carbon reduction is realized.
{"title":"Tank level robust control of LNG carrier based on hyperbolic tangent function nonlinear modification","authors":"Zongkuo Li, Xianku Zhang, Junpeng Huang","doi":"10.1093/tse/tdae010","DOIUrl":"https://doi.org/10.1093/tse/tdae010","url":null,"abstract":"\u0000 \u0000 \u0000 To achieve better control effect of the controller on the liquid level of LNG carrier and achieve the goal of energy saving and carbon reduction.\u0000 \u0000 \u0000 \u0000 This paper took the loaded square tank of an S175 high-speed container ship as the research plant, combined with the closed-loop gain-shaping algorithm (CGSA) and nonlinear modification technology to further optimize the controller. We initially employed a third-order CGSA approach in formulating the foundation of our linear controller. Subsequently, we introduced a non-linear modification to this controller by harnessing the power of the hyperbolic tangent function, and the control effect is verified by the MATLAB simulation experiment.\u0000 \u0000 \u0000 \u0000 Based on the outcomes of our MATLAB simulations, by integrating the third-order CGSA technique and introducing non-linear modification through the hyperbolic tangent function, we observed a significant enhancement in the controller's performance. Specifically, it outperformed the traditional PID controller by a substantial margin, demonstrating a remarkable 19% boost in control efficacy. Additionally, it provides better energy savings than the non-linear controller.\u0000 \u0000 \u0000 \u0000 The controller designed in this paper has a better control effect on liquid tank level control of LNG ships, the control process is more energy-saving, and the purpose of carbon reduction is realized.\u0000","PeriodicalId":52804,"journal":{"name":"Transportation Safety and Environment","volume":null,"pages":null},"PeriodicalIF":2.2,"publicationDate":"2024-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140244409","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The aim of this work is to investigate the Fog-related variable time headway (FVTH) model of connected and automated mixed flow considering multi-front vehicles information in a reduced visibility environment for driving safety. The car-following modes of mixed vehicles are analysed and the vehicle ratio for each mode based on Markov chain models is derived, where the number of front vehicles, CAVs penetration rate, and platoon intensity are considered. The combined coupling effect of visibility and driving speed on time headway is explored, and a variable time headway strategy is proposed. Their relationship equations are deduced as the FVTH model. The perturbation method is used to discuss the stability of traffic flow and obtain its stability judgment conditions. The proposed model was validated and the effects were discussed via simulation experiments. The results indicate that the acceleration and deceleration times of vehicles and collision possibility decrease significantly using the proposed method. When penetration rate is 50%, the number of front vehicles is three and platoon intensity is zero, the time to return to a stable state is reduced by 18.9%-30.3% and 24.7%-39.4%, respectively, and Time Exposed Time-to-collision (TET) is reduced by 26.1%-48.9% and 43.7%%-65.4%, respectively, compared with the basic IDM method and IDM method that considers multi-front vehicles information. As visibility decreases, the reduced degree of these indicator values increases. The driving efficiency and safety level can be enhanced.
{"title":"A variable time headway model for mixed car-following process considering multiple front vehicles information in foggy weather","authors":"Ziwei Liang, Mingbao Pang","doi":"10.1093/tse/tdae011","DOIUrl":"https://doi.org/10.1093/tse/tdae011","url":null,"abstract":"\u0000 The aim of this work is to investigate the Fog-related variable time headway (FVTH) model of connected and automated mixed flow considering multi-front vehicles information in a reduced visibility environment for driving safety. The car-following modes of mixed vehicles are analysed and the vehicle ratio for each mode based on Markov chain models is derived, where the number of front vehicles, CAVs penetration rate, and platoon intensity are considered. The combined coupling effect of visibility and driving speed on time headway is explored, and a variable time headway strategy is proposed. Their relationship equations are deduced as the FVTH model. The perturbation method is used to discuss the stability of traffic flow and obtain its stability judgment conditions. The proposed model was validated and the effects were discussed via simulation experiments. The results indicate that the acceleration and deceleration times of vehicles and collision possibility decrease significantly using the proposed method. When penetration rate is 50%, the number of front vehicles is three and platoon intensity is zero, the time to return to a stable state is reduced by 18.9%-30.3% and 24.7%-39.4%, respectively, and Time Exposed Time-to-collision (TET) is reduced by 26.1%-48.9% and 43.7%%-65.4%, respectively, compared with the basic IDM method and IDM method that considers multi-front vehicles information. As visibility decreases, the reduced degree of these indicator values increases. The driving efficiency and safety level can be enhanced.","PeriodicalId":52804,"journal":{"name":"Transportation Safety and Environment","volume":null,"pages":null},"PeriodicalIF":2.2,"publicationDate":"2024-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140244033","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
A novel mobile charging service that utilizes vehicle-to-vehicle (V2V) charging technology has recently been proposed as a supplement to fixed charging infrastructure (CI), enabling electric vehicles (EVs) to exchange electricity. This study formulates a vehicle routing problem (VRP) of vehicle-to-vehicle (V2V) charging, optimizing the routing of DVs to service RVs while taking into account their willingness to join the V2V charging platform. A mixed integer linear programming (MILP) model is established to optimize the VRP-V2V (i.e. the VRP of V2V charging), which is known to be NP-hard. To solve large-scale instances for real-world applications, we propose an adaptive large neighborhood search (ALNS) algorithm, which, when combined with the structure of the VRP-V2V problem, utilizes four local search procedures to enhance solution quality following destroy and repair operators. Results indicate that the proposed ALNS algorithm outperforms the optimization solver CPLEX in small-scale instances, and can solve large-scale instances that are infeasible using CPLEX solver. In a numerical analysis of Changsha's large-scale network, we demonstrate that the V2V platform can save an average of 33.1% on the charging cost of recharging vehicles, hence raising customer satisfaction with charging services and reducing range anxiety. The platform's profitability is also increased by using V2V charging in areas lacking fixed charging infrastructure.
{"title":"The electric vehicle routing problem of a new mobile charging service","authors":"Kanghui Ren, Maosheng Li, Xuekai Cen, Helai Huang","doi":"10.1093/tse/tdae012","DOIUrl":"https://doi.org/10.1093/tse/tdae012","url":null,"abstract":"\u0000 A novel mobile charging service that utilizes vehicle-to-vehicle (V2V) charging technology has recently been proposed as a supplement to fixed charging infrastructure (CI), enabling electric vehicles (EVs) to exchange electricity. This study formulates a vehicle routing problem (VRP) of vehicle-to-vehicle (V2V) charging, optimizing the routing of DVs to service RVs while taking into account their willingness to join the V2V charging platform. A mixed integer linear programming (MILP) model is established to optimize the VRP-V2V (i.e. the VRP of V2V charging), which is known to be NP-hard. To solve large-scale instances for real-world applications, we propose an adaptive large neighborhood search (ALNS) algorithm, which, when combined with the structure of the VRP-V2V problem, utilizes four local search procedures to enhance solution quality following destroy and repair operators. Results indicate that the proposed ALNS algorithm outperforms the optimization solver CPLEX in small-scale instances, and can solve large-scale instances that are infeasible using CPLEX solver. In a numerical analysis of Changsha's large-scale network, we demonstrate that the V2V platform can save an average of 33.1% on the charging cost of recharging vehicles, hence raising customer satisfaction with charging services and reducing range anxiety. The platform's profitability is also increased by using V2V charging in areas lacking fixed charging infrastructure.","PeriodicalId":52804,"journal":{"name":"Transportation Safety and Environment","volume":null,"pages":null},"PeriodicalIF":2.2,"publicationDate":"2024-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140248173","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Di Zhang, Jiale Tao, C. Wan, Liang Huang, Ming Yang
As supply chains in today's world become more complex and fragile, enhancing the resilience of maritime transport is increasingly imperative. The COVID-19 epidemic in 2020 exposed the vulnerability of existing supply chains, causing substantial impacts such as supply shortages, procurement constraints, logistics delays, and port congestion, highlighting the need to build resilient maritime transportation networks (MTN) and reigniting research on the resilience of maritime transport. Based on science mapping, we quantitatively analyzed the domain of resilience of MTN. We mainly study the resilience of MTN from the following aspects: construction of MTN and their topological characterization, vulnerability-oriented resilience analysis of MTN, recovery-oriented resilience analysis of MTN, investment decision-oriented resilience analysis of MTN, climate change-oriented resilience analysis of MTN and pandemic-oriented resilience analysis of MTN. This study reviews recent advances in MTN resilience research, highlighting research topics, shortcomings, and future research agenda.
{"title":"Resilience analysis of maritime transportation networks: A systematic review","authors":"Di Zhang, Jiale Tao, C. Wan, Liang Huang, Ming Yang","doi":"10.1093/tse/tdae009","DOIUrl":"https://doi.org/10.1093/tse/tdae009","url":null,"abstract":"\u0000 As supply chains in today's world become more complex and fragile, enhancing the resilience of maritime transport is increasingly imperative. The COVID-19 epidemic in 2020 exposed the vulnerability of existing supply chains, causing substantial impacts such as supply shortages, procurement constraints, logistics delays, and port congestion, highlighting the need to build resilient maritime transportation networks (MTN) and reigniting research on the resilience of maritime transport. Based on science mapping, we quantitatively analyzed the domain of resilience of MTN. We mainly study the resilience of MTN from the following aspects: construction of MTN and their topological characterization, vulnerability-oriented resilience analysis of MTN, recovery-oriented resilience analysis of MTN, investment decision-oriented resilience analysis of MTN, climate change-oriented resilience analysis of MTN and pandemic-oriented resilience analysis of MTN. This study reviews recent advances in MTN resilience research, highlighting research topics, shortcomings, and future research agenda.","PeriodicalId":52804,"journal":{"name":"Transportation Safety and Environment","volume":null,"pages":null},"PeriodicalIF":2.2,"publicationDate":"2024-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140259856","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
With the increasing development of intelligent detection devices, a vast amount of traffic flow data can be collected from intelligent transportation systems. However, these data often encounter issues such as missing and abnormal values, which can adversely affect the accuracy of future tasks like traffic flow forecasting. To address this problem, this paper proposes the Attention-based Spatiotemporal Generative Adversarial Imputation Network (ASTGAIN) model, comprising a generator and a discriminator, to conduct traffic volume imputation. The generator incorporates an information fuse module, a spatial attention mechanism, a causal inference module, and a temporal attention mechanism, enabling it to capture historical information and extract spatiotemporal relationships from the traffic flow data. The discriminator features a Bidirectional Gated Recurrent Unit (BiGRU), which explores the temporal correlation of the imputed data to distinguish between imputed and original values. Additionally, we have devised an imputation filling technique that fully leverages the imputed data to enhance the imputation performance. Comparison experiments with several traditional imputation models demonstrate the superior performance of the ASTGAIN model across diverse missing scenarios.
{"title":"Traffic Volume Imputation Using Attention-based Spatiotemporal Generative Adversarial Imputation Network","authors":"Yixin Duan, Chengcheng Wang, Chao Wang, Jinjun Tang, Qun Chen","doi":"10.1093/tse/tdae008","DOIUrl":"https://doi.org/10.1093/tse/tdae008","url":null,"abstract":"\u0000 With the increasing development of intelligent detection devices, a vast amount of traffic flow data can be collected from intelligent transportation systems. However, these data often encounter issues such as missing and abnormal values, which can adversely affect the accuracy of future tasks like traffic flow forecasting. To address this problem, this paper proposes the Attention-based Spatiotemporal Generative Adversarial Imputation Network (ASTGAIN) model, comprising a generator and a discriminator, to conduct traffic volume imputation. The generator incorporates an information fuse module, a spatial attention mechanism, a causal inference module, and a temporal attention mechanism, enabling it to capture historical information and extract spatiotemporal relationships from the traffic flow data. The discriminator features a Bidirectional Gated Recurrent Unit (BiGRU), which explores the temporal correlation of the imputed data to distinguish between imputed and original values. Additionally, we have devised an imputation filling technique that fully leverages the imputed data to enhance the imputation performance. Comparison experiments with several traditional imputation models demonstrate the superior performance of the ASTGAIN model across diverse missing scenarios.","PeriodicalId":52804,"journal":{"name":"Transportation Safety and Environment","volume":null,"pages":null},"PeriodicalIF":2.2,"publicationDate":"2024-03-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140078484","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The study on Reynolds number (Re) effects is crucial for high-speed trains for optimizing the aerodynamics, enhance safety, and reduce energy consumption. In this paper, a wind tunnel test was carried out to investigate the influence of Re on the train aerodynamic performance considering the shift of the air compressibility, which has not yet been explored to date. The test was conducted in a low-speed & large-scale tunnel with a stationary floor and the vehicle model was based on a 1/8th scaled train with 3 units. The Re ranges from Re=0.75×106∼ Re=3.12×106 by accelerating the uniform wind speed from U=27.8 m/s to U=115 m/s with zero-yaw. The Mach number (Ma) of the maximum speed scenario has exceeded 0.3, indicating that the airflow can be considered as compressible range. The results show that the aerodynamic characteristics of high-speed trains exhibit a self-similarity region of the Re, which is dependent on the flow velocity. The aerodynamic loads little changes when the Re ≥ 1.51×106, which corresponds U ≥55.6 m/s. Therefore, the compressibility of the airflow within the range up to U=115 m/s has a negligible effect on aerodynamic loads, thus can be disregarded. However, the surface pressure significantly decreases when the incoming flow surpasses 0.3Ma and transitions into a compressible state. While the compressibility has a relatively minor impact on macroscopic aerodynamics, it cannot be overlooked when considering detailed flow field, such as surface pressure.
雷诺数（Re）效应研究对于高速列车优化空气动力学性能、提高安全性和降低能耗至关重要。本文通过风洞试验研究了雷诺数（Re）对列车空气动力学性能的影响，其中考虑了空气可压缩性的变化。试验在一个低速、大型、地面静止的风洞中进行，车辆模型以 1/8 比例的 3 节列车为基础。通过将均匀风速从 U=27.8 m/s 加速到 U=115 m/s，在零偏航的情况下，Re 范围从 Re=0.75×106∼Re=3.12×106 不等。最大速度情况下的马赫数（Ma）已超过 0.3，表明气流可被视为可压缩范围。结果表明，高速列车的气动特性表现出 Re 值的自相似性区域，该区域与流速有关。当 Re ≥ 1.51×106 时，相当于 U ≥ 55.6 m/s，气动载荷变化不大。因此，在 U=115 m/s 之前的范围内，气流的可压缩性对空气动力载荷的影响可以忽略不计。然而，当进入的气流超过 0.3Ma 并过渡到可压缩状态时，表面压力会明显降低。虽然可压缩性对宏观空气动力学的影响相对较小，但在考虑详细流场（如表面压力）时却不容忽视。
{"title":"Effects of Reynolds number on train aerodynamics considering the air compressibility: A wind tunnel study","authors":"Zhixiang Huang, Wenhui Li, Li Chen","doi":"10.1093/tse/tdae006","DOIUrl":"https://doi.org/10.1093/tse/tdae006","url":null,"abstract":"\u0000 The study on Reynolds number (Re) effects is crucial for high-speed trains for optimizing the aerodynamics, enhance safety, and reduce energy consumption. In this paper, a wind tunnel test was carried out to investigate the influence of Re on the train aerodynamic performance considering the shift of the air compressibility, which has not yet been explored to date. The test was conducted in a low-speed & large-scale tunnel with a stationary floor and the vehicle model was based on a 1/8th scaled train with 3 units. The Re ranges from Re=0.75×106∼ Re=3.12×106 by accelerating the uniform wind speed from U=27.8 m/s to U=115 m/s with zero-yaw. The Mach number (Ma) of the maximum speed scenario has exceeded 0.3, indicating that the airflow can be considered as compressible range. The results show that the aerodynamic characteristics of high-speed trains exhibit a self-similarity region of the Re, which is dependent on the flow velocity. The aerodynamic loads little changes when the Re ≥ 1.51×106, which corresponds U ≥55.6 m/s. Therefore, the compressibility of the airflow within the range up to U=115 m/s has a negligible effect on aerodynamic loads, thus can be disregarded. However, the surface pressure significantly decreases when the incoming flow surpasses 0.3Ma and transitions into a compressible state. While the compressibility has a relatively minor impact on macroscopic aerodynamics, it cannot be overlooked when considering detailed flow field, such as surface pressure.","PeriodicalId":52804,"journal":{"name":"Transportation Safety and Environment","volume":null,"pages":null},"PeriodicalIF":2.2,"publicationDate":"2024-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140078797","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：