{"title":"A Multi-task Learning Approach for Weather Classification on Railway Transportation","authors":"Shan Wang, Yidong Li, Songhe Feng","doi":"10.1109/ICIRT.2018.8641680","DOIUrl":"https://doi.org/10.1109/ICIRT.2018.8641680","url":null,"abstract":"Most of vision based urban transport dataset are designed to be executed in clear weather conditions. However, limited visibility in rain or cloudy strongly affects the accuracy of vision systems. To improve safety of railway transportation in actual weather situations, our newly constructed railway transportation dataset contains 4 situations from the real videos which has more adverse weather conditions. Taking into account railway transportation images are mainly single object with single background, which is limited to weather classification. We also collected a multi-class weather dataset to improve the generalization ability of the classification model. In order to capture a discriminate feature for each weather condition and avoid involving complicated pre-processing techniques. We provide a multi-task learning framework which formulate the classification problem as a multi-task regression problem by considering the classification on each weather class as a task. We capture the intrinsic relatedness among different tasks by a group Lasso regularization. With experiments on standard weather datasets and our own dataset, we demonstrate that the proposed framework achieves superior performance compared to the state-of-the-art methods.","PeriodicalId":202415,"journal":{"name":"2018 International Conference on Intelligent Rail Transportation (ICIRT)","volume":"90 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":"115224072","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}
{"title":"Energy-efficient operation of multi-trains for metro systems with considering the regenerative energy","authors":"Xuekai Wang, T. Tang, S. Su, X. Liu, Tiejun Ma","doi":"10.1109/ICIRT.2018.8641563","DOIUrl":"https://doi.org/10.1109/ICIRT.2018.8641563","url":null,"abstract":"Utilization of the regenerative energy has a great potential to reduce the energy consumption in metro systems, which is related to the train timetable as well as the driving strategy. This paper proposes an energy-efficient train operation approach by integrating the train scheduling and the driving strategy. Firstly, the models of calculating the traction energy and the reused of the regenerative energy are introduced. Then, the optimization model of train operation is then formulated by taking the systematical energy (i.e., the difference between the traction energy and the reused regenerative energy) as the objective function. Based on the space-time-speed network methodology, the optimization model is transformed to be a discrete decision problem and the dynamic programming method is used to obtain the corresponding solution. Finally, a case study is conducted in the end to illustrate the effectiveness of the proposed approach.","PeriodicalId":202415,"journal":{"name":"2018 International Conference on Intelligent Rail Transportation (ICIRT)","volume":"23 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":"132612761","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}
{"title":"An Accident Casual Model for Railway Based on Operational Scenario Cognition Conflict","authors":"Fei Yan, T. Tang, Junqiao Ma","doi":"10.1109/ICIRT.2018.8641574","DOIUrl":"https://doi.org/10.1109/ICIRT.2018.8641574","url":null,"abstract":"Traditionally, accident or incident analysis are focusing on the cause-consequence chain methods, like Fault Tree or Event Tree, which are hard to find root cause of accidents. To solve this problem, some system safety analysis methods come out, like Accimap, FRAM and CAST based on STAMP. However, they are good at solving safety management issues, functional failure analysis or causal scenarios analysis, and can be used to capture safety requirements and help system designers to deep understand safety requirements. But the true logic of accident or incident do not analyzed, which is related to human or equipment cannot conceive the right status of train operational status on time. If so, it's easy to ensure safety by train stop. The objective of this paper is to present the mismatch or inconsistency among human cognition, equipment execution and train operation of railway train control system. Also, railway accident is a kind of expression of operational scenario conflict. Singapore metro accident is analyzed as case study.","PeriodicalId":202415,"journal":{"name":"2018 International Conference on Intelligent Rail Transportation (ICIRT)","volume":"29 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":"131670781","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}
Wensong Wang, Zesheng Zheng, Yuanjin Zheng, K. Tan
{"title":"Wireless Power Transfer and Thermoacoustic Generation Applied in Rail","authors":"Wensong Wang, Zesheng Zheng, Yuanjin Zheng, K. Tan","doi":"10.1109/ICIRT.2018.8641617","DOIUrl":"https://doi.org/10.1109/ICIRT.2018.8641617","url":null,"abstract":"Coil designs and associated circuits for wireless power transfer have been extensively studied. This paper introduces the fundamentals of wireless power transfer application in rail, investigates transmitting coils with different conical angles and obtains the magnetic field intensity distributions at various lift-off distances between the coil and rail. An equivalent circuit model is built to illustrate the relationship between the coil and rail. Then finally, the thermoacoustic generated inside the rail is verified through experiment.","PeriodicalId":202415,"journal":{"name":"2018 International Conference on Intelligent Rail Transportation (ICIRT)","volume":"1 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":"131265172","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}
H. Tam, Kang-kuen Lee, Shun-yee Liu, L. Cho, K. Cheng
{"title":"Intelligent Optical Fibre Sensing Networks Facilitate Shift to Predictive Maintenance in Railway Systems","authors":"H. Tam, Kang-kuen Lee, Shun-yee Liu, L. Cho, K. Cheng","doi":"10.1109/ICIRT.2018.8641602","DOIUrl":"https://doi.org/10.1109/ICIRT.2018.8641602","url":null,"abstract":"This paper depicts an optical fibre sensing network based railway health condition monitoring system that can facilitate predictive maintenance in railways. Machine learning is applied to develop learning models that can be used to detect and identify different types of track defects such as rail corrugations, dipped weld joints and rail crossings.","PeriodicalId":202415,"journal":{"name":"2018 International Conference on Intelligent Rail Transportation (ICIRT)","volume":"9 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":"116782020","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}
{"title":"Next Generation Train-Centric Communication-Based Train Control System with Train-to-Train (T2T) Communications","authors":"Xiaoxuan Wang, Lingjia Liu, T. Tang, Li Zhu","doi":"10.1109/ICIRT.2018.8641649","DOIUrl":"https://doi.org/10.1109/ICIRT.2018.8641649","url":null,"abstract":"High-reliability and low-latency are crucial for urban rail transits. In this paper, we introduce communication strategies for urban rail transit systems using Long Term Evolution for Train-to-Train (LTE-T2T) communication. The transmission latency is set as a system metric to evaluate the performance of urban rail transit system. First, a novel train-centric Communication- Based Train Control (CBTC) model is established using LTE- T2T communications. Then, we introduce a novel sensing-based semi-persistent scheduling method for resource allocation in this proposed system. Based on the introduced method, extensive field test and simulation are executed. The related results show that the transmission latency of safety-critical information in urban rail transit system can be improved using the introduced scheme.","PeriodicalId":202415,"journal":{"name":"2018 International Conference on Intelligent Rail Transportation (ICIRT)","volume":"51 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":"122827256","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}
S. Chadwick, Phillip James, M. Roggenbach, Tom Wetner
{"title":"Formal Methods for Industrial Interlocking Verification","authors":"S. Chadwick, Phillip James, M. Roggenbach, Tom Wetner","doi":"10.1109/ICIRT.2018.8641579","DOIUrl":"https://doi.org/10.1109/ICIRT.2018.8641579","url":null,"abstract":"In this paper, we present an overview of research jointly undertaken by the Swansea Railway Verification Group towards verification techniques for automatically checking safety for train control systems. We present a comprehensive modelling of safety principles in first order logic. We conclude by applying verification methods developed by Swansea Railway Verification Group in order to check the modelled safety principles against a real world railway interlocking system.","PeriodicalId":202415,"journal":{"name":"2018 International Conference on Intelligent Rail Transportation (ICIRT)","volume":"89 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":"122842569","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}
{"title":"A Bayesian Machine Learning Approach for Online Wheel Condition Detection Using Track-side Monitoring","authors":"Y. Ni, Qiu-Hu Zhang","doi":"10.1109/ICIRT.2018.8641663","DOIUrl":"https://doi.org/10.1109/ICIRT.2018.8641663","url":null,"abstract":"Online wheel condition monitoring can suffer from the stochastic wheel/rail dynamics and measurement noises. This paper aims to develop a Bayesian statistical approach for probabilistic assessment of wheel conditions using track-side monitoring. In this approach, the wheel quality-related components are first extracted from monitoring data and their Fourier amplitude spectra are normalized to obtain a set of cumulative distribution functions that characterize wheel quality information. Then a data-driven reference model is established by means of sparse Bayesian learning for modelling these characteristic functions for healthy wheels. Bayes factor is finally employed to discriminate the new observations from the reference model, with which a quantitative evaluation of wheel qualities is achieved in real time. To validate the feasibility and effectiveness, the proposed approach is examined by using strain monitoring data of rail bending acquired from a track-side monitoring system based on optical fiber sensors.","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":"129110171","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}
{"title":"Data Exchange Design in Thai Rail Operations","authors":"Tanasanee Phienthrakul, Massaya Samnienggam, Bundid Kungwannarongkul","doi":"10.1109/ICIRT.2018.8641554","DOIUrl":"https://doi.org/10.1109/ICIRT.2018.8641554","url":null,"abstract":"The rail operations in Thailand have been developing for many decades. The most important parts of rail transport development are the exchange of the operating data. This study is focused on the data exchange standards in rail operations, the designing of the data exchange systems, and the developing of a prototype web-based application for exchange data. The data exchange technique in this study called RailML (Railway Markup Language). RailML is an open-source, XMLbased data format for data interoperability of railway applications. It uses a very simple and flexible format that used to describe railway-related data. The design of the data exchange system is using a responsive design which makes the rail data exchange system render well on a variety of devices and windows sizes. The result of this study is the data exchange standard specification for rail operations in Thailand based-on RailML, which include the data exchange format and the guideline in designing of a prototype rail data exchange system.","PeriodicalId":202415,"journal":{"name":"2018 International Conference on Intelligent Rail Transportation (ICIRT)","volume":"14 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":"125520440","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}
{"title":"Influence of Sleeper Distance on Rail Corrugation Growth","authors":"Andrew Keong Ng, L. Martua, G. Sun","doi":"10.1109/ICIRT.2018.8641668","DOIUrl":"https://doi.org/10.1109/ICIRT.2018.8641668","url":null,"abstract":"Rail corrugation is commonly found in most railway tracks worldwide. However, there is no solution to stop corrugation from growing. Therefore, to minimise corrugation growth, this paper aims to model, analyse, and predict rail corrugation growth under the influence of sleeper distance. A wheel-rail interaction model was developed based on three-dimensional finite element method in considerations of wheel-rail contact patch and vehicle-track dynamics. By applying Archard’s wear law to the wheel-rail interaction model, rail wear was calculated and rail surface profile was updated. Subsequently, rail corrugation growth was predicted using nonlinear regression technique. Simulated axle box acceleration signals were also analysed during the growth of rail corrugation. Results reveal that sleeper distance of 700 mm yields higher corrugation growth rate, with steeper exponential relationship between average wear depth and number of wheelset passages, than 500 mm sleeper distance. Rail corrugation dominant wavelengths for 700 mm and 500 mm sleeper distances also increase with corrugation growth. As such, sleeper distance of 500 mm is recommended to reduce rail corrugation growth, thereby lowering maintenance costs and improving reliability, maintainability, availability, and safety of rail transportation.","PeriodicalId":202415,"journal":{"name":"2018 International Conference on Intelligent Rail Transportation (ICIRT)","volume":"628 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":"117067195","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}