Progress and perspective of data-driven train delay propagation

doi:10.16265/j.cnki.issn1003-3033.2019.S2.001

Abstract

Abstract: The research aims to summarize and analyze the latest progress of train delay propagation and to clarify the application status of data-driven methods. Firstly, the connotation of delay propagation wasexpounded, and the delay propagation process was analyzed.The researches on delay propagation driven by traditional mathematical methods were analyzed. Next, the data-driven models of train delay propagation werereviewed, and the application of statistical models, computational intelligence, and machine learning models wereanalyzed for delay prediction and delay recoverywhich are two key issues fordelay propagation. Finally, the shortcomings of existing researches were concludedfrom four aspects andthe trend of future research was pointed out.The results show thatthe proposed train delay propagation and recovery models based on artificial intelligence and deep learning can assist dispatchers in improving the quality of dispatching decisions and reducing the workload of dispatchers.

Key words: railway, real-world train operation data, delay prediction, delay recovery, delay propagation, data-driven models

CLC Number:

X951

WEN Chao, LI Zhongcan, HUANG Ping, TIAN Rui, MOU Weiwei, LI Li. Progress and perspective of data-driven train delay propagation[J]. China Safety Science Journal, 2019, 29(S2): 1-9.

References 64

[1]	孟令云, 栾晓杰. 列车晚点传播问题[M]. 10 000个科学难题-交通运输科学卷. 北京: 科学出版社, 2018: 805-808.
[2]	彭其渊, 文超. 轨道交通调度指挥智能化及风险预警[M]. 10 000个科学难题-交通运输科学卷. 北京: 科学出版社, 2018: 797-799.
[3]	FUMEO E, ONETO L, CLERICO G, et al. Big data analytics for train delay prediction: a case study in the italian railway network, innovative applications of big data in the railway industry[M]. Hershey: IGI Global, 2018: 320-348.
[4]	ONETO L, FUMEO E, CLERICO G, et al. Train delay prediction systems: a big data analytics perspective[J]. Big Data Research, 2018,11(3):54-64.
[5]	黄平, 李忠灿, 文超, 等. 高速铁路故障时空分布及持续时长分布特征研究[J]. 中国安全科学学报, 2018, 28(增2): 99-104.HUANG Ping, LI Zhongcan, WEN Chao, et al.Studyonspatial-temporal and duration distribution characteristics of high-speed railway disruptions[J]. China Safety Science Journal,2018, 28(S2): 99-104.
[6]	黄平, 彭其渊, 文超, 等. 高速铁路故障分类及其影响列车数模型[J]. 中国安全科学学报, 2018, 28(增2): 46-53.HUANG Ping, PENG Qiyuan, WEN Chao, et al. Study on high-speed railway disruption classification and model of its influence on train number[J]. China Safety Science Journal,2018, 28(S2): 46-53.
[7]	WANG Yangpeng, WEIDMANN U A, WANG Huashen. Using catastrophe theory to describe railway system safety and discuss system risk concept[J]. Safety Science, 2017, 91: 269-285.
[8]	文超, 彭其渊, 文欢. 高速铁路列车运行冲突管理研究现状综述[J]. 中国安全科学学报, 2010, 20(5): 140-150.WEN Chao, PENG Qiyuan, WEN Huan. Review on conflict managememt of train operation on high-speed railway[J]. China Safety Science Journal, 2010, 20(5): 140-150.
[9]	GOVERDE R M P. A delay propagation algorithm for large-scale railway traffic networks[J]. Transportation Research Part C: Emerging Technologies, 2010, 18(3): 269-287.
[10]	BKER T, SEYBOLD B. Stochastic modelling of delay propagation in large networks[J]. Journal of Rail Transport Planning & Management, 2012, 2(1): 34-50.
[11]	MEESTER L E, MUNS S. Stochastic delay propagation in railway networks and phase-type distributions[J]. Transportation Research Part B: Methodological, 2007, 41(2): 218-230.
[12]	CAREY M, KWIECIŃSKI A. Stochastic approximation to the effects of headways on knock-on delays of trains[J]. Transportation Research Part B: Methodological, 1994, 28(4): 251-267.
[13]	CAREY M, CARVILLE S. Testing schedule performance and reliability for train stations[J]. Journal of the Operational Research Society, 2000, 51(6): 666-682.
[14]	MEER D J, GOVERDE R M, HANSEN I A. Prediction of train running times using historical track occupation data[R]. Delft University of Technology, 2009.
[15]	KINGSTON J H. Hierarchical timetable construction[J]. Practice and Theory of Automated Timetabling VI, 2007, 3867: 294-307.
[16]	YUAN Jianxin, HANSEN I A. Optimizing capacity utilization of stations by estimating knock-on train delays[J]. Transportation Research Part B-Methodological, 2007, 41(2): 202-217.
[17]	MEHTA F, ROSSIGER C, MONTIGEL M. Latent energy savings due to the innovative use of advisory speeds to avoid occupation conflicts[J]. Computers in Railways Xii: Computer System Design and Operation in Railways and Other Transit Systems, 2010, 114: 99-108.
[18]	胡思继, 孙全欣, 胡锦云,等. 区段内列车晚点传播理论的研究[J]. 中国铁道科学, 1994, 15(2): 41-54.HU Siji, SUN Quanxin, HU Jinyun, et al. Research on theories of train delay propagation in a railway district[J]. China Railway Science, 1994, 15(2): 41-54.
[19]	周华亮, 高自友, 李克平. 准移动闭塞系统的元胞自动机模型及列车延迟传播规律的研究[J]. 物理学报, 2006, 55(4): 1 706-1 710.ZHOU Hualiang, GAO Ziyou, LI Keping. Cellular automation model for moving-like block system and study of train's delay propagation[J]. Acta Physica Sinica, 2006, 55(4): 1 706-1 710.
[20]	周华亮. 3种移动闭塞模式下列车延迟传播规律的研究[J]. 铁道运输与经济, 2005, 27(12): 90-91.ZHOU Hualiang. Study on the transmit law of train delay under three different moving block modes[J]. Railway Transport and Economy, 2005, 27(12): 90-91.
[21]	王昕, 聂磊, 李文俊. 基于动车运用的高速铁路列车运行图鲁棒性研究[J]. 铁道运输与经济, 2014, 36(11): 50-55.WANG Xin, NIE Lei, LI Wenjun.Study on robustness of high-speed train working diagram based on EMU utilization[J]. Railway Transport and Economy, 2014, 36(11): 50-55.
[22]	刘宇, 黄凯. 基于极大代数的城际高速列车晚点传播研究[J]. 综合运输, 2017, 39(9): 68-73.LIU Yu,HUANG Kai. Analysis of delay propagation of network using max-plus theory[J]. Comprehensive Transportation, 2017, 39(9): 68-73.
[23]	殷勇, 刘杰, 刘庆. 基于 SIR 模型车站晚点传播仿真研究[J]. 综合运输, 2017, 39(7): 60-65.YIN Yong, LIU Jie, LIU Qing. Simulation research of station delay propagation based on SIR model[J]. Comprehensive Transportation, 2017, 39(7): 60-65.
[24]	CACCHIANI V, HUISMAN D, KIDD M, et al. An overview of recovery models and algorithms for real-time railway rescheduling[J].Transportation Research Part B: Methodological, 2014, 63(5): 15-37.
[25]	CORMAN F, MENG Lingyun. A review of online dynamic models and algorithms for railway traffic management[J]. IEEE Transactions on Intelligent Transportation Systems, 2015, 16(3): 1274-1284.
[26]	CADARSO L. Recovery of disruptions in rapid transit networks with origin-destination demand[J]. Procedia-Social and Behavioral Sciences, 2014, 111: 528-537.
[27]	CADARSO L, MARÍNÁ, MARÓTI G. Recovery of disruptions in rapid transit networks[J]. Transportation Research Part E: Logistics and Transportation Review, 2013, 53: 15-33.
[28]	D'ARIANO A, PRANZO M, HANSEN I A. Conflict resolution and train speed coordination for solving real-time timetable perturbations[J]. Ieee Transactions on Intelligent Transportation Systems, 2007, 8(2): 208-222.
[29]	TRNQUIST KRASEMANN J. Design of an effective algorithm for fast response to the re-scheduling of railway traffic during disturbances[J]. Transportation Research Part C: Emerging Technologies, 2012, 20(1): 62-78.
[30]	彭其渊,朱松年,闫海峰. 列车运行图可调整度评价系统研究[J]. 西南交通大学学报, 1998, 33(4): 367-371.PENG Qiyuan, ZHU Songnian, YAN Haifeng. A system for evaluation of train diagram elasticity[J]. Journal of Southwest Jiaotong University. 1998,33(4): 367-371.
[31]	刘敏, 韩宝明. 列车运行图可恢复鲁棒性优化模型[J]. 铁道学报, 2013, 35(10): 1-8. LIU Min, HAN Baoming. Recoverable robust timetabling models for railways[J]. Journal of the China Railway Science, 2013, 35(10): 1-8.
[32]	柏赟, 何天健, 毛保华. 一种交叉线干扰情形下列车晚点恢复运行控制方法[J]. 交通运输系统工程与信息, 2011, 11(5): 114-122.BAI Yun, HE Tianjian, MAO Baohua. Train Control to reduce delays upon service disturbances at railway junctions[J]. Journal of Transportation Systems Engineering and Information Technology, 2011, 11(5): 114-122.
[33]	CHANG C S, THIA B S. Online rescheduling of mass rapid transit systems: fuzzy expert system approach[J]. IEE Proceedings-Electric Power Applications, 1996, 143(4): 307-316.
[34]	YUAN Jianxin, HANSEN I A. Optimizing capacity utilization of stations by estimating knock-on train delays[J]. Transportation Research Part B: Methodological, 2007, 41(2): 202-217.
[35]	GUO Jingwen, MENG Lingyun, KECMAN P, et al. Modeling delay relations based on mining historical train monitoring data: a Chinese railway case[C]. 6th International Conference on Railway Operations Modelling and Analysis. 2015: 23-26.
[36]	YUAN Jianxin, GOVERDE R, HANSEN I A. Propagation of train delays in stations[J]. WIT Transactions on The Built Environment, 2002, 61(5):975-984.
[37]	KECMAN P, GOVERDE R M. Predictive modelling of running and dwell times in railway traffic[J]. Public Transport, 2015, 7(3): 295-319.
[38]	GOVERDE R M, HANSEN I A, HOOGHIEMSTRA G, et al. Delay distributions in railway stations[C]. 9th World Conference on Transport Research, 2001:22-27.
[39]	YAMAMURA A, KORESAWA M, ADACHI S, et al. Taking effective delay reduction measures and using delay elements as indices for Tokyo's metropolitan railways[J]. 2014, 1: 3-15.
[40]	CERRETO F, NIELSEN O A, HARROD S, et al. Causal analysis of railway running delays[C]. 11th World Congress on Railway Research (WCRR 2016),2016:2343263569.
[41]	KECMAN P, GOVERDE R M P. Online data-driven adaptive prediction of train event times[J]. IEEE Transactions on Intelligent Transportation Systems, 2015, 16(1): 465-474.
[42]	BARTA J, RIZZOLI A E, SALANI M, et al. Statistical modelling of delays in a rail freight transportation network[C]. 2012 Winter Simulation Conference, 2012:13730084.
[43]	ŞAHIN $\dot{I}$ Markov chain model for delay distribution in train schedules: assessing the effectiveness of time allowances[J]. Journal of Rail Transport Planning & Management, 2017, 7(3): 101-113.
[44]	MILINKOVIĆ S, MARKOVIĆ M, VESKOVIĆ S, et al. A fuzzy Petri net model to estimate train delays[J]. Simulation Modelling Practice and Theory, 2013, 33: 144-157.
[45]	ZILKO A, HANEA A, KUROWICKA D, et al. Non-parametric Bayesian network to forecast railway disruption lengths[C]. 2nd International Conference on Railway Technology: Research, Development and Maintenance2014.
[46]	MARTIN L J. Predictive reasoning and machine learning for the enhancement of reliability in railway systems[C]. International Conference on Reliability, Safety and Security of Railway Systems, Paris, France, June 28-30,2016: 178-188.
[47]	MARTIN L J, ROMANOVSKY A. A formal approach to designing reliable advisory systems[C]. International Workshop on Software Engineering for Resilient Systems, Gothenburg, Sweden, 2016: 28-42.
[48]	PETERS J, EMIG B, JUNG M, et al. Prediction of delays in public transportation using neural networks[C]. Computational Intelligence for Modelling, Control and Automation, 2005 and International Conference on Intelligent Agents, Web Technologies and Internet Commerce,2005: 92-97.
[49]	LULLI A, ONETO L, CANEPA R, et al. Large-scale railway networks train movements: a dynamic, interpretable, and robust hybrid data analytics system[C]. 2018 IEEE 5th International Conference on Data Science and Advanced Analytics (DSAA),2018: 371-380.
[50]	LEE W H, YEN L H, CHOU C M. A delay root cause discovery and timetable adjustment model for enhancing the punctuality of railway services[J]. Transportation Research Part C: Emerging Technologies, 2016, 73: 49-64.
[51]	MARKOVIĆ N, MILINKOVIĆ S, TIKHONOV K S, et al. Analyzing passenger train arrival delays with support vector regression[J]. Transportation Research Part C: Emerging Technologies, 2015, 56: 251-262.
[52]	BARBOUR W, MORI J C M, KUPPA S, et al. Prediction of arrival times of freight traffic on US railroads using support vector regression[J]. Transportation Research Part C: Emerging Technologies, 2018, 93(8): 211-227.
[53]	CHEN Dewang, WANG Lijuan, LI Lingxi. Position computation models for high-speed train based on support vector machine approach[J]. Applied Soft Computing, 2015, 30: 758-766.
[54]	KARIYAZAKI K, HIBINO N, MORICHI S. Simulation model for estimating train operation to recover knock-on delay earlier[J]. Asian Transport Studies, 2013, 2(3): 284-294.
[55]	NAOHIKO H, OSAMU N, SHIGERU M, et al. Recovery measure of disruption in train operation in Tokyo metropolitan area[J]. Transportation Research Procedia, 2017, 25: 4 370-4 380.
[56]	LIEBCHEN C, LÜBBECKE M, MÖHRING R, et al. The concept of recoverable robustness, linear programming recovery, and railway applications, robust and online large-scale optimization[M]. Berlin: Springer, 2009: 1-27.
[57]	KHADILKAR H. Data-enabled stochastic modeling for evaluating schedule robustness of railway networks[J]. Transportation Science, 2016, 51(4): 1 161-1 176.
[58]	孟令云, GOVERDE R M. 基于实际数据分析的列车晚点传播过程构建方法与实例[J]. 北京交通大学学报, 2012, 36(6): 15-20.MENG Lingyun, GOVERDE R M. A method for constructing train delay propagation process by mining train record data[J]. Journal of Beijing Jiaotong University, 2012, 36(6): 15-20.
[59]	刘岩,郭竞文,罗常津,等. 列车运行实绩大数据分析及应用前景展望[J]. 中国铁路, 2015 (6): 70-73.LIU Yan, GUO Jingwen, LUO Changjin, et al. Big data analyzing and application prospect expectation of train operation records[J]. Chinese Railways, 2015(6): 70-73.
[60]	WEN Chao, LESSAN J, FU Liping, et al. Data-driven models for predicting delay recovery in high-speed rail[C]. 4th International Conference on Transportation Information and Safety (ICTIS),2017: 144-151.
[61]	LANGE J, WERNER F. Approaches to modeling train scheduling problems as job-shop problems with blocking constraints[J]. Journal of Scheduling, 2018, 21(2): 191-207.
[62]	QUAGLIETTA E, PELLEGRINI P, GOVERDE R M, et al. The on-time real-time railway traffic management framework: a proof-of-concept using a scalable standardised data communication architecture[J]. Transportation Research Part C: Emerging Technologies, 2016, 63: 23-50.
[63]	WEN Chao, HUANG Ping, LI Zhongcan, et al. Train dispatching management with data-driven approaches: a comprehensive review and appraisal[J]. IEEE Access, 2019, 7: 114 547-114 571.
[64]	黄平, 文超, 李忠灿, 等. 高速铁路列车晚点时间实时预测的神经网络模型[J].中国安全科学学报, 2019, 29(增1):20-26.HUANG Ping, WEN Chao, LI Zhongcan, et al. A neural network model for real-time prediction of high-speed railway delays[J]. China Safety Science Journal,2019, 29(S1):20-26.