A CPS-Enhanced Subway Operations Safety System Based on the Short-Term Prediction of the Passenger Flow
- 19 Downloads
The subway transport system is an effective means to mitigate the adverse effects of rapid urbanization and traffic congestion. The development of subway systems has created great challenges to subway operations safety management, including precaution and response efforts. Accurate predictions, timely control, and feedback-based continuous analysis and dispatch are critical to developing subway systems. We created a CPS-enhanced subway operations safety framework using the concept of CPS and short-term prediction techniques of subway passenger flow; our framework is characterized by a “flexible and controllable, real-time operation” composed of six components: system, adjust, facilities, early warning, time control, and yielding. In the framework, the forecasting methods of subway passenger flow are the core, and cyber-physical systems are used to couple other components into a safety management information platform in which the CPS is responsible for sensing, control, and feedback in the entire operating process. The entire operating process includes the input acquisition for the forecasting models, early warning publishing and emergency control, and feedback-based re-analysis and dispatch. The proposed framework can provide integrated services for disaster prevention and the control of subway operations.
KeywordsSubway passenger flow Cyber-physical system Short-term prediction Safety operations management
This paper was supported in part by the National Key R&D Program of China (No 2019YFF0301300) and the National Natural Science Foundation of China (Nos. 70901047 and 7177030217). We also appreciate support for this paper from the Beijing Key Laboratory of Operation Safety of Gas, Heating, and Underground Pipelines.
- 7.J. Zhao, W. Deng, Y. Song, Y. Zhu, What influences Metro station ridership in China? Insights from Nanjing. Cities 35, 114–124 (2013)Google Scholar
- 10.B.D. Taylor, D. Miller, H. Iseki, C. Fink, Nature and/or nurture? Analyzing the determinants of transit ridership across US urbanized areas. Transp. Res. A Policy Prac. 43(1), 60–77 (2009)Google Scholar
- 13.R. Xue, D.J. Sun, S. Chen, Short-term bus passenger demand prediction based on time series model and interactive multiple model approach. Discret. Dyn. Nat. Soc. 2015 (2015). https://doi.org/10.1155/2015/682390
- 15.Z. Xiong, S. Zhong, D. Song, Z. Yu, Q. Huang, A method of fitting urban rail transit passenger flow time series. China Saf. Sci. J. 28(11), 39–45 (2018)Google Scholar
- 28.J. Li, J.-H. Cheng, J.-Y. Shi, F. Huang, Brief introduction of back propagation (BP) neural network algorithm and its improvement, in Advances in Computer Science and Information Engineering (Springer, Berlin, 2012), pp. 553–558Google Scholar
- 30.K.G. Sheela, S.N. Deepa, Review on methods to fix number of hidden neurons in neural networks. Math. Probl. Eng. 2013 (2013). https://doi.org/10.1155/2013/425740
- 33.H.-P. Lu, Z.-Y. Sun, W.-C. Qu, Big data-driven based real-time traffic flow state identification and prediction. Discret. Dyn. Nat. Soc. 2015 (2015). https://doi.org/10.1155/2015/284906
- 34.X. Chen, J.W. Meaker, F.B. Zhan, Agent-based modeling and analysis of hurricane evacuation procedures for the Florida keys. Nat. Hazards 38(3), 321 (2006)Google Scholar
- 35.F. Rui, Z. Zuo, L. Li, Using LSTM and GRU neural network methods for traffic flow prediction. Youth Academic Conference of Chinese Association of Automation, 2017Google Scholar