Modeling train operation as sequences: A study of delay prediction with operation and weather data

Abstract This paper presents a carefully designed train delay prediction model, called FCLL-Net, which combines a fully-connected neural network (FCNN) and two long short-term memory (LSTM) components, to capture operational interactions. The performance of FCLL-Net is tested using data from two high speed railway lines in China. The results show that FCLL-Net has significantly improved prediction performance, over 9.4% on both lines, in terms of the selected absolute and relative metrics compared to the commonly used state-of-the-art models. Additionally, the sensitivity analysis demonstrates that interactions of train operations and weather-related features are of great significance to consider in delay prediction models.

[1]  Norbert Pavlovic,et al.  A fuzzy Petri net model to estimate train delays , 2013, Simul. Model. Pract. Theory.

[2]  Rob M.P. Goverde,et al.  Estimation of train dwell time at short stops based on track occupation event data , 2015 .

[3]  Davide Anguita,et al.  Train Delay Prediction Systems: A Big Data Analytics Perspective , 2017, Big Data Res..

[4]  Liping Fu,et al.  A hybrid Bayesian network model for predicting delays in train operations , 2019, Comput. Ind. Eng..

[5]  Marco Laumanns,et al.  An ensemble prediction model for train delays , 2019, Transportation Research Part C: Emerging Technologies.

[6]  Hadi Meidani,et al.  Predicting Near-Term Train Schedule Performance and Delay Using Bi-Level Random Forests , 2019, Transportation Research Record: Journal of the Transportation Research Board.

[7]  Liping Fu,et al.  A hybrid model to improve the train running time prediction ability during high-speed railway disruptions , 2020 .

[8]  Keith Briggs,et al.  Modelling train delays with q-exponential functions , 2007 .

[9]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[10]  Rob M.P. Goverde,et al.  Propagation of train delays in stations , 2002 .

[11]  Gabriele Malavasi,et al.  Simulation of stochastic elements in railway systems using self-learning processes , 2001, Eur. J. Oper. Res..

[12]  Pavle Kecman,et al.  Online Data-Driven Adaptive Prediction of Train Event Times , 2015, IEEE Transactions on Intelligent Transportation Systems.

[13]  Ingo A. Hansen,et al.  Online train delay recognition and running time prediction , 2010, 13th International IEEE Conference on Intelligent Transportation Systems.

[14]  Ismail Sahin,et al.  Markov chain model for delay distribution in train schedules: Assessing the effectiveness of time allowances , 2017, J. Rail Transp. Plan. Manag..

[15]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[16]  Francesco Corman,et al.  Railway line capacity consumption of different railway signalling systems under scheduled and disturbed conditions , 2013, J. Rail Transp. Plan. Manag..

[17]  Rob M.P. Goverde,et al.  A delay propagation algorithm for large-scale railway traffic networks , 2010 .

[18]  Liping Fu,et al.  Train Dispatching Management With Data- Driven Approaches: A Comprehensive Review and Appraisal , 2019, IEEE Access.

[19]  Davide Anguita,et al.  Dynamic Delay Predictions for Large-Scale Railway Networks: Deep and Shallow Extreme Learning Machines Tuned via Thresholdout , 2017, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[20]  Rob M.P. Goverde,et al.  Recent applications of big data analytics in railway transportation systems: A survey , 2018 .

[21]  Bernhard Schölkopf,et al.  A tutorial on support vector regression , 2004, Stat. Comput..

[22]  Loo Hay Lee,et al.  Enhancing transportation systems via deep learning: A survey , 2019, Transportation Research Part C: Emerging Technologies.

[23]  Liping Fu,et al.  Statistical investigation on train primary delay based on real records: evidence from Wuhan–Guangzhou HSR , 2017 .

[24]  Yee Whye Teh,et al.  A Fast Learning Algorithm for Deep Belief Nets , 2006, Neural Computation.

[25]  Daniel B. Work,et al.  Prediction of arrival times of freight traffic on US railroads using support vector regression , 2018, Transportation Research Part C: Emerging Technologies.

[26]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[27]  Ludolf E. Meester,et al.  Stochastic delay propagation in railway networks and phase-type distributions , 2007 .

[28]  Jouni Wallander,et al.  Data mining in rail transport delay chain analysis , 2012 .

[29]  Chao Wen,et al.  Modeling the Influence of Disturbances in High-Speed Railway Systems , 2019, Journal of Advanced Transportation.

[30]  Geoffrey E. Hinton,et al.  Speech recognition with deep recurrent neural networks , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[31]  Michael F. Gorman,et al.  Statistical estimation of railroad congestion delay , 2009 .

[32]  Francesco Corman,et al.  Train delay evolution as a stochastic process , 2015 .

[33]  Dewang Chen,et al.  Position computation models for high-speed train based on support vector machine approach , 2015, Appl. Soft Comput..

[34]  Andrew W. Senior,et al.  Long short-term memory recurrent neural network architectures for large scale acoustic modeling , 2014, INTERSPEECH.

[35]  Chao Wen,et al.  A deep learning approach for multi-attribute data: A study of train delay prediction in railway systems , 2020, Inf. Sci..

[36]  Amaury Lendasse,et al.  High-Performance Extreme Learning Machines: A Complete Toolbox for Big Data Applications , 2015, IEEE Access.

[37]  Paul Schonfeld,et al.  Analyzing passenger train arrival delays with support vector regression , 2015 .

[38]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

[39]  Xiaolei Ma,et al.  Learning traffic as a graph: A gated graph wavelet recurrent neural network for network-scale traffic prediction , 2020 .

[40]  Liping Fu,et al.  Stochastic Model of Train Running Time and Arrival Delay: A Case Study of Wuhan–Guangzhou High-Speed Rail , 2018, Transportation Research Record: Journal of the Transportation Research Board.

[41]  Andy Liaw,et al.  Classification and Regression by randomForest , 2007 .

[42]  Taghi M. Khoshgoftaar,et al.  Deep learning applications and challenges in big data analytics , 2015, Journal of Big Data.

[43]  Yong Wang,et al.  Learning Traffic as Images: A Deep Convolutional Neural Network for Large-Scale Transportation Network Speed Prediction , 2017, Sensors.

[44]  Francesco Corman,et al.  Stochastic prediction of train delays in real-time using Bayesian networks , 2018 .

[45]  János Barta,et al.  Statistical modelling of delays in a rail freight transportation network , 2012, Proceedings Title: Proceedings of the 2012 Winter Simulation Conference (WSC).

[46]  J. van der Wal,et al.  Dynamic Delay Management at Railways - a Semi-Markovian Decision Approach , 2003 .

[47]  Pavle Kecman,et al.  Predictive modelling of running and dwell times in railway traffic , 2015, Public Transp..

[48]  Malachy Carey,et al.  Testing schedule performance and reliability for train stations , 2000, J. Oper. Res. Soc..

[49]  Liping Fu,et al.  Forecasting primary delay recovery of high-speed railway using multiple linear regression, supporting vector machine, artificial neural network, and random forest regression , 2019, Canadian Journal of Civil Engineering.

[50]  V LeelavathiM,et al.  AN ARCHITECTURE OF DEEP LEARNING METHOD TO PREDICT TRAFFIC FLOW IN BIG DATA , 2016 .

[51]  Masoud Yaghini,et al.  Railway Passenger Train Delay Prediction via Neural Network Model , 2013 .

[52]  Daniel Svozil,et al.  Introduction to multi-layer feed-forward neural networks , 1997 .

[53]  Chee Kheong Siew,et al.  Extreme learning machine: Theory and applications , 2006, Neurocomputing.

[54]  I. A. Hansen,et al.  Optimizing capacity utilization of stations by estimating knock-on train delays , 2007 .

[55]  Maged Dessouky,et al.  A delay estimation technique for single and double-track railroads , 2010 .

[56]  Yuan Yu,et al.  TensorFlow: A system for large-scale machine learning , 2016, OSDI.

[57]  Otto Anker Nielsen,et al.  Application of Data Clustering to Railway Delay Pattern Recognition , 2018 .

[58]  Malachy Carey,et al.  Stochastic approximation to the effects of headways on knock-on delays of trains , 1994 .

[59]  Rob M.P. Goverde,et al.  Modeling railway disruption lengths with Copula Bayesian Networks , 2016 .

[60]  Liping Fu,et al.  A Bayesian network model to predict the effects of interruptions on train operations , 2020 .

[61]  Yuxiang Yang,et al.  Statistical delay distribution analysis on high-speed railway trains , 2019, Journal of Modern Transportation.

[62]  Harshad Khadilkar,et al.  Data-Enabled Stochastic Modeling for Evaluating Schedule Robustness of Railway Networks , 2017, Transp. Sci..

[63]  Thorsten Büker,et al.  Stochastic modelling of delay propagation in large networks , 2012, J. Rail Transp. Plan. Manag..

[64]  Chao Wen,et al.  Modelling the running states of high-speed trains using triangular fuzzy number workflow nets , 2014 .

[65]  Richard J. Boucherie,et al.  Running times on railway sections with heterogeneous train traffic , 1998 .

[66]  Lucas P. Veelenturf,et al.  An overview of recovery models and algorithms for real-time railway rescheduling , 2014 .

[67]  Stephen Grossberg,et al.  Recurrent neural networks , 2013, Scholarpedia.

[68]  Francesco Corman,et al.  Evaluating Disturbance Robustness of Railway Schedules , 2014, J. Intell. Transp. Syst..

[69]  Yoshua Bengio,et al.  Greedy Layer-Wise Training of Deep Networks , 2006, NIPS.