Kian Lun Soon, Robin Kuok Cheong Chan, J. Lim, R. Parthiban
{"title":"Short-term traffic forecasting model – prevailing trends and guidelines","authors":"Kian Lun Soon, Robin Kuok Cheong Chan, J. Lim, R. Parthiban","doi":"10.1093/tse/tdac058","DOIUrl":"https://doi.org/10.1093/tse/tdac058","url":null,"abstract":"\u0000 The design parameters serve as an integral part of developing a robust short-term traffic forecasting model. These parameters include scope determination, input data preparation, output parameters, and modelling techniques. This paper takes a further leap to analyse the recent trend of design parameters through a Systematic Literature Review (SLR) based on peer-reviewed articles up to 2021. The key important findings are summarised along with the challenges to performing short-term traffic forecasting. Intuitively, this paper offers insights into the next wave of research that contributes significantly to industries.","PeriodicalId":52804,"journal":{"name":"Transportation Safety and Environment","volume":null,"pages":null},"PeriodicalIF":2.2,"publicationDate":"2022-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46795689","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}
{"title":"Railway switch fault diagnosis based on Multi heads Channel Self Attention, Residual Connection and Deep CNN","authors":"Xirui Chen, Hui Liu, Zhu Duan","doi":"10.1093/tse/tdac045","DOIUrl":"https://doi.org/10.1093/tse/tdac045","url":null,"abstract":"\u0000 A novel switch diagnosis method based on self-attention and residual deep Convolutional Neural Networks (CNN) is proposed. Because of the imbalanced dataset, the Kmeans synthetic minority oversampling technique (SMOTE) is applied to balancing the dataset at first. Then, the deep CNN is utilized to extract local features from long power curves, and the residual connection is performed to handle the performance degeneration. In the end, the Multi-heads Channel Self Attention focuses on those important local features. The ablation and comparison experiments are applied to verifying the effectiveness of the proposed methods. With the residual connection and Multi-heads Channel Self Attention, the proposed method has achieved an accuracy of 99.83% impressively. The t-SNE based visualizations for features of the middle layers enhance the trustworthiness.","PeriodicalId":52804,"journal":{"name":"Transportation Safety and Environment","volume":null,"pages":null},"PeriodicalIF":2.2,"publicationDate":"2022-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42705840","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}
Y. Chen, Christian Buerger, Miao Lin, Xudong Li, Volker Labenski, Haixia Jin, Hai Wang, Yang Liu, Tsuyoshi Ino, Harald Feifel, Tian Tan, Fangrong Chang
{"title":"Left turn across path and opposite direction accidents in China: CIDAS accident study","authors":"Y. Chen, Christian Buerger, Miao Lin, Xudong Li, Volker Labenski, Haixia Jin, Hai Wang, Yang Liu, Tsuyoshi Ino, Harald Feifel, Tian Tan, Fangrong Chang","doi":"10.1093/tse/tdac070","DOIUrl":"https://doi.org/10.1093/tse/tdac070","url":null,"abstract":"\u0000 Left Turn Across Path with Opposite Direction (LTAP/OD) conflicts are one of the most common crash types at intersections. The research aims to reveal the general and dynamic information about the conflict for the most relevant street layouts for each conflict configuration of the LTAP/OD accidents involving passenger cars, motorcycles and Ebikes. The analysis was based on 276 LTAP/OD accidents collected by China In-Depth Accident Study (CIDAS 2011–2019). The LTAP/OD accidents include 44 car-to-car conflicts, 157 car-to-motorcycle conflicts and 75 car-to-Ebike conflicts. Most of accidents belonging to three types were observed at the W0 street layout without green belt separating the oncoming lane and no offset lane between the turning car and the oncoming traffic, the main distance between both vehicles in the beginning of the critical situation being about four meters, occurring in the clear day with no rain and at junctions lighted either because of daylight or based on street lighting. In terms of the turning car initial speed, the range is between 15-30 km/h for most car-to-car and car-to-motorcycle accidents but 30-40 km/h for most car-to-Ebike accidents. As for the collision speed, this range is between 10 and 20 km/h for car-to-car and car-to-Ebike accidents and between 10 and 25 km/h for car-to-motorcycle crashes. Based on the distributions of objective motorcycles’ and Ebike's positions in collisions with passenger cars, the maximum longitudinal distance is 60 m for both two types of accidents and the maximum lateral distance ranges from -20 m to 20 m and from -15 m to 15 m, respectively.","PeriodicalId":52804,"journal":{"name":"Transportation Safety and Environment","volume":null,"pages":null},"PeriodicalIF":2.2,"publicationDate":"2022-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49166064","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}
{"title":"Road traffic anomaly monitoring and warning based on DeepWalk algorithm","authors":"Zihe Wang, Junqing Ye, Jinjun Tang","doi":"10.1093/tse/tdac049","DOIUrl":"https://doi.org/10.1093/tse/tdac049","url":null,"abstract":"\u0000 In the complex urban road traffic network, a sudden accident leads to rapid congestion in the nearby traffic region, which even makes the local traffic network capacity quickly reduced. Therefore, an efficient monitoring system for abnormal conditions of urban road network plays a crucial role in the tolerance of urban road network. The traditional traffic monitoring system not only costs a lot in construction and maintenance, but also may not cover the road network comprehensively, which could not meet the basic needs of traffic management. Only a more comprehensive and intelligent monitoring method is able to identify traffic anomalies more effectively and quickly so that it provide more effective support for traffic management decisions. The extensive use of positioning equipment makes us to obtain accurate trajectory data. This paper presents a traffic anomaly monitoring and prediction method based on vehicle trajectory data. This model uses deep learning to detect abnormal trajectory on the traffic road network. The method effectively analyzes the abnormal source and potential anomaly to judge the abnormal region, which provides an important reference for the traffic department to take effective traffic control measures. Finally, the paper uses Internet vehicle trajectory data of Chengdu to test and gets an accurate result.","PeriodicalId":52804,"journal":{"name":"Transportation Safety and Environment","volume":null,"pages":null},"PeriodicalIF":2.2,"publicationDate":"2022-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49312556","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}
{"title":"Flexible Optimal Model and Algorithm for Track Utilization in High-speed Railway Stations","authors":"Quan Gao, Yinggui Zhang, Zhiya Chen, Yuan Chen","doi":"10.1093/tse/tdac057","DOIUrl":"https://doi.org/10.1093/tse/tdac057","url":null,"abstract":"\u0000 Track utilization is the most important technical operation in high-speed railway stations. It's an effective way to take flexible management based on dispatchers’ decision preferences into consideration for making track utilization plans to relieve the influence caused by unmeasurable unstructured factors. Thus, based on flexible management concept and taken the flexible optimal for track utilization in high-speed railway stations as the object, time and space occupation safety trajectories of arrival routes, departure routes and tracks are all analyzed. Then, taking following constraints into consideration, i.e. minimum safety time intervals for various routes and tracks occupation, space-time arc occupation and decision-makers’ preferences, a flexible optimal model for track utilization in high-speed railway stations are established to maximize its balance and robustness and to minimize its volatility at the same time. Further, a flexible optimal solution based on a simulated annealing algorithm is designed to make a safety track utilization plan in high-speed railway stations integrating the dispatchers’ decision preference. The results gained from given experiments show that the proposed methodology can effectively make satisfied safety track utilization plans based on decision-makers’ preferences, which can improve its balance and robustness level significantly. Meanwhile, its volatility can be reduced as much as possible caused by flexible management based on artificial intervention to ensure the relative stability of the plan.","PeriodicalId":52804,"journal":{"name":"Transportation Safety and Environment","volume":null,"pages":null},"PeriodicalIF":2.2,"publicationDate":"2022-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47506086","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}
{"title":"Hazard-based Duration Modeling of Merging Time Interval on Freeway On-Ramps","authors":"Ye Li, Jichen Zhu, M. Haque, Jaeyoung Lee","doi":"10.1093/tse/tdac040","DOIUrl":"https://doi.org/10.1093/tse/tdac040","url":null,"abstract":"\u0000 Freeway on-ramps suffer high crash risks due to frequent merging behaviors. This study developed hazard-based duration models to investigate the merging time interval on freeway on-ramps based on microscopic trajectory data. Fixed effect, random effect, and random parameters Weibull distributed accelerated failure time models were developed to capture merging time as a function of various dynamic variables. The random parameters model was found to outperform the two counterparts since the unobserved heterogeneity of individual drivers were captured. Modeling estimation results indicate that drivers along the merging section with an auxiliary lane perform a smooth merging process and are easily affected by speed variables. Dynamics of leading and following vehicles on the merging and target lanes are found to influence the merging time interval for merging without an auxiliary lane, whereas the influence of surrounding vehicles is marginal for those with an auxiliary lane. The findings of this study identify potential countermeasures for improving safety during the merging process.","PeriodicalId":52804,"journal":{"name":"Transportation Safety and Environment","volume":null,"pages":null},"PeriodicalIF":2.2,"publicationDate":"2022-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47783885","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}
Shuai Li, Weijia Wu, Xiaofeng Ma, Ming Zhong, M. Safdar
{"title":"Modeling medium and long term purchasing plans for environment-oriented container truck: a case study of yangtze river port","authors":"Shuai Li, Weijia Wu, Xiaofeng Ma, Ming Zhong, M. Safdar","doi":"10.1093/tse/tdac043","DOIUrl":"https://doi.org/10.1093/tse/tdac043","url":null,"abstract":"\u0000 Transportation sector is the most significant contributor to anthropogenic greenhouse gas (GHG) emissions. Particularly, maritime transportation, which is predominantly powered by fossil-fuel engines, accounts for more than 90% of world freight movement and emits 3% of global carbon dioxide (CO2) emissions. China is the world's largest emitter of CO2 and plays a key role in mitigating global climate change. In order to tackle this pressing concern, this study analyzes the port's throughput, the current number of trucks, and their emissions during the container truck purchasing process. While the previous studies about container truck purchasing plans mostly focused on the trucks' price and port needs. The objective of this study is to minimize the total cost of a port's inland transportation using optimization technique such as the interval uncertainty planning model to convert container truck emissions into social costs. This study considers the port of Yangtze as a case study. This study has designed two scenarios. (i) The base scenario (business-as-usual (BAU)) is used to quantify the relationship between pollutant emissions and system cost. In the base scenario, no environmental control facilities are used during the planning period, and there is no need to purchase new energy container trucks (ii) Expected scenario, referred to as (scenario A), for three planning periods. In scenario A, the emissions levels are required to remain at the same level as the first planning period during the whole planning period. By solving the above model, the number of all truck types, system cost, container throughput, and truck emissions in the port area were analyzed. The results showed that if no emission reduction control measures are implemented in the next 9 years, the growth rate of pollutants in the port area can be exceeded up to 20%. In addition, The findings showed clearly that truck emissions are reduced by purchasing new energy trucks and restricting the number of fossil-fuel (diesel) trucks. This study could also help to minimize system costs associated with port planning and management.","PeriodicalId":52804,"journal":{"name":"Transportation Safety and Environment","volume":null,"pages":null},"PeriodicalIF":2.2,"publicationDate":"2022-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41390805","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}
{"title":"Regularity and sensitivity analysis of main parameters of plate effects on the aerodynamic braking drag of a high-speed train","authors":"Peng Li, Shan Huang, Y. Liu, J. Niu","doi":"10.1093/tse/tdac051","DOIUrl":"https://doi.org/10.1093/tse/tdac051","url":null,"abstract":"\u0000 With increase of train speed, braking plate technology has a good application prospect in the high-speed stage of the train. Based on the 1/8th scaled symmetrical train model composed by two half cars, Reynolds Average Navier-stokes (RANS) equations and Shear Stress Transfer (SST) k-ω turbulence model are adopted to simulate the aerodynamic performance of the train with plate, aerodynamic drag dependence of the single parameter of the plate (shape, area, angle, position and number) is analyzed, and the identification research of the main aerodynamic parameters of plate is also carried out. The numerical settings used in this paper is verified by wind tunnel test data. Results show that the braking plate with aspect ratio of 1 has better performance on aerodynamic drag. The area, opening angle and number of plates are basically positively correlated with the total aerodynamic drag of the target car and plate. Arranging plates at the downstream of the vehicle is a good method of raising total aerodynamic drag. Within the range of plate parameter design in this paper, by using orthogonal design of experiment and method of range analysis and analysis of variance, the influence degrees of plate parameters on aerodynamic drag are determined, and the order is number, area and opening angle of plate. The research results provide theoretical support for the design and safe operation of high-speed train with aerodynamic braking plate.","PeriodicalId":52804,"journal":{"name":"Transportation Safety and Environment","volume":null,"pages":null},"PeriodicalIF":2.2,"publicationDate":"2022-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41835982","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}
{"title":"Parameterization of the Propeller Thrust for Modelling Ship Braking within Ice Channel behind Icebreaker","authors":"V. Goncharov, N. Klementieva","doi":"10.1093/tse/tdac042","DOIUrl":"https://doi.org/10.1093/tse/tdac042","url":null,"abstract":"\u0000 Cargo ship sailing within the ice channel that assisting icebreaker tracks in the compact ice cover is the usual practice of the navigation for the difficult ice conditions in the freezing seas and in the Arctic water areas. When the icebreaker or an ahead vessel stops before the insuperable ice obstacle or because the engine trouble, the danger of an emergency appears, namely, the collision with the icebreaker or the ahead ship, if the interval between them is not sufficient for the effective braking and stop. The paper presents the equation that describes the ship braking process within an ice channel and includes the thrust of the propeller that works under the reverse regime. The specific of this regime is following: the ship continues the motion “forward» and the propeller rotates “backward”. Analytical method for description of the ship propeller work on the reverse regime is absent because the detached flow on its blades. The paper describes the developed empirical method of this regime parameterization on the base of the serial models of propellers testing. The outcomes of this investigation will be applied for the ship braking process simulation and the safe interval between the ship and the icebreaker evaluation in what follows.","PeriodicalId":52804,"journal":{"name":"Transportation Safety and Environment","volume":null,"pages":null},"PeriodicalIF":2.2,"publicationDate":"2022-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42493190","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}
Bo Sun, Guang Chen, Jun Chen, Xiao-bai Li, Ming-zan Tang, Mu Zhong
{"title":"Performance of Vehicle-mounted Anemometer under Crosswind—Simulation and Experiment","authors":"Bo Sun, Guang Chen, Jun Chen, Xiao-bai Li, Ming-zan Tang, Mu Zhong","doi":"10.1093/tse/tdac053","DOIUrl":"https://doi.org/10.1093/tse/tdac053","url":null,"abstract":"\u0000 Environmental wind measurements are essential for ensuring the operational safety of rail vehicles. In our previous work, an anemometer that can be mounted on the top of a train to achieve real-time measurements of wind speed and direction was proposed based on the pressure distributions around the cylindrical anemometer. However, the flow field on the top of the train is significantly influenced by the train; thus, the measured data might differ from the actual environmental wind parameters, particularly when trains are subjected to windbreak walls. In this study, simulations considering flow fields around trains installed with the proposed anemometer were conducted, and an improved delayed detached eddy simulation approach was adopted. Through simulations, the flow field at the top of the train was analysed, and the aerodynamic characteristics of the anemometer were investigated. Accordingly, relationships between the measured wind characteristics and environmental wind characteristics are presented under various situations herein. Field experiments were performed for the proposed anemometer installed on a certain type of high-speed train along the Nanjiang Railway in China. The results obtained from both the numerical and experimental studies show that the proposed method has high accuracy for measuring environmental wind speed and direction when mounted on the top of a train.","PeriodicalId":52804,"journal":{"name":"Transportation Safety and Environment","volume":null,"pages":null},"PeriodicalIF":2.2,"publicationDate":"2022-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46250350","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}