Operational Risk Analysis of Rail Transportation Network

  • Yong Qin
  • Limin Jia
Part of the Advances in High-speed Rail Technology book series (ADVHIGHSPEED)


In this chapter, the authors mainly analyze the operational risk of rail transportation network. Firstly, evaluation index systems of the metro station, the traffic line and traffic network are established respectively. Those evaluation index system are mainly composed of elements including people, equipment, environment and management. Then, risk prediction model based on ARMA model and GA-SVR model is used to build railway transportation network safety state prediction model and find a high precision prediction model through the comparative analysis, so as to realize the high precise prediction of railway transportation network safety state. Finally, field examples are listed to verify the effective of the proposed methods.


  1. 1.
    Y.K. Huang, Research of the assessment method of the city rail transportation network. Beijing Jiaotong University (2014)Google Scholar
  2. 2.
    B.L. Mishara, Railway and metro suicides: Understanding the problem and prevention potential. J. Crisis Interv. Suicide Prev. 28(S1), 36–43 (2007)CrossRefGoogle Scholar
  3. 3.
    Y.F. Shi, C. Yang, L.T. Sun, The management analysis of the city rail traffic. Res. City Rail Transp. 6(2), 26–28 (2003)Google Scholar
  4. 4.
    C.J. Lv, The operation safety analysis of the city rail traffic. Shanghai Railw. Technol. 3, 52–53 (2006)Google Scholar
  5. 5.
    Pw.W. Ye, The efficiency assessment research of the city rail transportation based on the envelope analysis. Beijing Jiaotong University (2009)Google Scholar
  6. 6.
    M. Li, The comprehensive assessment model research of the city rail traffic. Beijing Jiaotong University (2012)Google Scholar
  7. 7.
    X.I. Rong-Rong et al., Research survey of network safety situation awareness. J. Comput. Appl. 32(1), 1–133 (2012)Google Scholar
  8. 8.
    K. Gao et al., A hybrid safety situation prediction model for information network based on support vector machine and particle swarm optimization. Power Syst. Technol. 35(4), 176–182 (2011)Google Scholar
  9. 9.
    R.Y. Li, R. Kang, The research of the fault rate based on the ARMA model. Syst. Eng. Electron. Technol. 30(8), 1588–1591 (2008)Google Scholar
  10. 10.
    M.R. Endsley, R. Sollenberger, E. Stein, Situation awareness: A comparison of measures (2000)Google Scholar
  11. 11.
    M.A. Abdel-Aty, R. Pemmanaboina, Calibrating a real-time traffic crash-prediction model using archived weather and ITS traffic data. IEEE Trans. Intell. Transp. Syst. 7(2), 167–174 (2006)CrossRefGoogle Scholar
  12. 12.
    D. Wang et al., Prediction of total viable counts on chilled pork using an electronic noise combined with support vector machine. Meat Sci. 90(2), 373–377 (2012)CrossRefGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  • Yong Qin
    • 1
  • Limin Jia
    • 1
  1. 1.Beijing Jiaotong UniversityBeijingChina

Personalised recommendations