2018 International Conference on Intelligent Rail Transportation (ICIRT)最新文献_第7页

Reducing negative influence of strong wind on normal train operations based on data mining 基于数据挖掘减少强风对列车正常运行的负面影响

2018 International Conference on Intelligent Rail Transportation (ICIRT) Pub Date : 2018-12-01 DOI: 10.1109/ICIRT.2018.8641669

Rui Wang, F. Zhao, T. Shi, Yaqun Li, Y. Bao

{"title":"Reducing negative influence of strong wind on normal train operations based on data mining","authors":"Rui Wang, F. Zhao, T. Shi, Yaqun Li, Y. Bao","doi":"10.1109/ICIRT.2018.8641669","DOIUrl":"https://doi.org/10.1109/ICIRT.2018.8641669","url":null,"abstract":"Cross wind has an important influence on the safety of high-speed railways. Wind monitoring or early-warning system is widely used to provide real-time monitoring information or early warning information to train dispatching system for making appropriate measures like slowing down running speed of trains or suspending of train operations. But there is trade-off between safety and train operation efficiency for train operation in windy weather. Wind data mining method was proposed in this paper to reduce negative influence of strong wind on normal train operations and improve train operation efficiency. Three main objective factors that affects train operation efficiency were optimized, including optimizing wind alarm release time, merging wind alarm restriction sections and adding wind direction into wind alarm mechanism. Real-word case study show that wind alarm release time should be set according to the wind characteristic of different lines confronted. Wind alarm restriction sections were merged by analyzing the alarms relationship generated by adjacent wind motoring points, and the merging of wind alarm restriction sections can significantly decrease the number of wind alarm times that train dispatchers’ need to handle. Wind direction has remarkable influence to train operation and need to be added into wind alarm mechanism.","PeriodicalId":202415,"journal":{"name":"2018 International Conference on Intelligent Rail Transportation (ICIRT)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128233754","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Event-Driven Simulation of Consecutive Trains: An Analytic Approach for Asynchronous Railway Simulations 连续列车的事件驱动仿真:异步铁路仿真的一种解析方法

2018 International Conference on Intelligent Rail Transportation (ICIRT) Pub Date : 2018-12-01 DOI: 10.1109/ICIRT.2018.8641685

Merlin Becker, M. Schreckenberg

引用次数: 0

Radio-wave Propagation in Tunnel Structures at ISM Band: A Preliminary Study ISM波段隧道结构中无线电波传播的初步研究

2018 International Conference on Intelligent Rail Transportation (ICIRT) Pub Date : 2018-12-01 DOI: 10.1109/ICIRT.2018.8641553

Kalyankar Shravan Kumar, Y. Lee, Y. S. Meng

引用次数: 2

Analyzing and Evaluating Infrastructure Capacity of Railway Passenger Station by Mesoscopic Simulation Method 基于细观模拟方法的铁路客运站基础设施承载力分析与评价

2018 International Conference on Intelligent Rail Transportation (ICIRT) Pub Date : 2018-12-01 DOI: 10.1109/ICIRT.2018.8641593

Mingxuan Zhong, Y. Yue, Deyi Li

引用次数: 3

Optimized Utilization of Arrival and Departure Tracks on the High - Speed Railway Station 高速铁路进出站轨道的优化利用

2018 International Conference on Intelligent Rail Transportation (ICIRT) Pub Date : 2018-12-01 DOI: 10.1109/ICIRT.2018.8641637

Ran Chen, L. Meng, Weining Hao, Xuan Li

引用次数: 0

Mechanical Properties and Microstructural Analysis of Rail Thermite Welding Joints 钢轨铝热焊接头力学性能及显微组织分析

2018 International Conference on Intelligent Rail Transportation (ICIRT) Pub Date : 2018-12-01 DOI: 10.1109/ICIRT.2018.8641675

Yang Liu, Z. Tsakadze, H. Hoh, J. Pang, Ivan Christian, Tie Xuan Ng, Y. Ng

{"title":"Mechanical Properties and Microstructural Analysis of Rail Thermite Welding Joints","authors":"Yang Liu, Z. Tsakadze, H. Hoh, J. Pang, Ivan Christian, Tie Xuan Ng, Y. Ng","doi":"10.1109/ICIRT.2018.8641675","DOIUrl":"https://doi.org/10.1109/ICIRT.2018.8641675","url":null,"abstract":"Thermite welding is commonly applied to join running rails together and any failures related to it will result in delay or even catastrophe. In this paper, mechanical properties and microstructures of specimens extracted from plain rail and welding are analyzed to understand the potential factors affecting crack initiation and propagation in the head of rail and welding joints. It is found that there is a sharp decrease of hardness near the heat affected zone (HAZ), likely due to the rail undergoing a heat treatment such as annealing. To verify this assumption, the specimens are analyzed by optical microscope and Scanning Electron Microscope. The microstructure result shows that the region near welding can be clearly divided into four zones: Welding Metal Zone, Mixed Melted Zone, Heat Affected Zone (HAZ) and Unaffected Parent Rail with three subzones for HAZ: Coarse Grained HAZ, Fine Grained HAZ and Inter-critical HAZ based on the grain size and inter-lamellar spacing. The decrease of hardness in HAZ is due to softening because of fully annealing, partial annealing, “spheroidization” in three subzones respectively. This paper also found that the large amount of oxide inclusions in Mixed Melted Zone may cause the ease of crack initiation and propagation.","PeriodicalId":202415,"journal":{"name":"2018 International Conference on Intelligent Rail Transportation (ICIRT)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134640741","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

Urban Rail Transit Plus-Train Passenger Flow Analysis Method Based on Network Real-time Reachability 基于网络实时可达性的城市轨道交通+列车客流分析方法

2018 International Conference on Intelligent Rail Transportation (ICIRT) Pub Date : 2018-12-01 DOI: 10.1109/ICIRT.2018.8641597

Rudong Yang, R. Xu, Zhiyuan Huang

{"title":"Urban Rail Transit Plus-Train Passenger Flow Analysis Method Based on Network Real-time Reachability","authors":"Rudong Yang, R. Xu, Zhiyuan Huang","doi":"10.1109/ICIRT.2018.8641597","DOIUrl":"https://doi.org/10.1109/ICIRT.2018.8641597","url":null,"abstract":"Nowadays, to meet passengers' nighttime travel needs and stimulate urban nighttime economic development, subways in some megacities extend their operation hours. In the extended operation period, some routes connecting a given origin and destination (O-D) pair become unreachable which made the transit service providers can’t use the conventional method to analysis the passenger flow of plus-train in the extended operation period. This paper proposed a methodology for calculating the passenger flow of the plus-trains based on automatic fare collection (AFC) data and realized train timetable. Considering real-time reachability of the routes which connected an O-D pair, a weighted assignment function among the remaining reachable routes is provided. Then we calculate the passenger flow of each plus-train by estimating which trains were chosen. Initial case study on Shanghai metro shows that the proposed method works well, the calculated plus-train flow and actual survey results match more than 90% which could provide reliable passenger flow data for the optimization of the network plus-train schedule.","PeriodicalId":202415,"journal":{"name":"2018 International Conference on Intelligent Rail Transportation (ICIRT)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114238496","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Condition Monitoring of Power Feeder with Multiple Parallel Cables Based on Inductive Coupling Method 基于电感耦合法的多并联电缆馈线状态监测

2018 International Conference on Intelligent Rail Transportation (ICIRT) Pub Date : 2018-12-01 DOI: 10.1109/ICIRT.2018.8641583

Kangrong Li, K. See, N. Narampanawe, Arjuna Weerasinghe, V. Tong

引用次数: 0

Condition Monitoring of High Voltage Power Delivery Path to Train using Non-Invasive Impedance Measurement Method 基于无创阻抗测量法的列车高压供电路径状态监测

2018 International Conference on Intelligent Rail Transportation (ICIRT) Pub Date : 2018-12-01 DOI: 10.1109/ICIRT.2018.8641567

N. Narampanawe, K. See, Kangrong Li, V. Tong

引用次数: 0

Two-Stage Ensemble of Deep Convolutional Neural Networks for Object Recognition 用于对象识别的深度卷积神经网络两阶段集成

2018 International Conference on Intelligent Rail Transportation (ICIRT) Pub Date : 2018-12-01 DOI: 10.1109/ICIRT.2018.8641581

Rom Uddamvathanak, Feng Yang, Xulei Yang, A. Das, Yan Shen, Mohamed Salahuddin, Shaista Hussain, S. Chawla

{"title":"Two-Stage Ensemble of Deep Convolutional Neural Networks for Object Recognition","authors":"Rom Uddamvathanak, Feng Yang, Xulei Yang, A. Das, Yan Shen, Mohamed Salahuddin, Shaista Hussain, S. Chawla","doi":"10.1109/ICIRT.2018.8641581","DOIUrl":"https://doi.org/10.1109/ICIRT.2018.8641581","url":null,"abstract":"Deep Convolutional Neural Networks (CNNs) have been widely used for object recognition in images. However, due to the complexity in setting the structures and related parameters for deep CNNs, performance of individual CNN models may vary largely and lack robustness. In realizing this problem, this paper proposed a two-stage ensemble of deep CNNs for object recognition. To increase model diversity for ensemble, multiple basic CNN models/structures are first pre-defined. For each basic CNN model, multiple rounds of training are conducted based on sub-sampling the training dataset. In the first stage of ensemble, multiple outputs from each basic CNN model is integrated using the MinMax median. This is followed by the second stage of ensemble to combine the outputs from all basic CNN models. The proposed method was implemented and experiments were carried out on Kaggle’s ‘Statoil/CCORE Iceberg Classifier Challenge’ image data for iceberg and ship recognition, as well as on ‘Northeastern University surface defect dataset’ for surface defect classification problem. The experimental results showed that the proposed ensemble method outperformed the individual CNN models, and achieved the-state-of-the-art performance as compared to the best submission to the Kaggle’s challenge using CNNs.","PeriodicalId":202415,"journal":{"name":"2018 International Conference on Intelligent Rail Transportation (ICIRT)","volume":"142 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116325711","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2