The Prediction of Derailment Coefficient Based on Neural Networks

  • Xiulian Yu
  • Guangwu Liu
  • Yong Qin
  • Yuan Zhang
  • Zongyi Xing
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 288)

Abstract

Derailment coefficient is an important criterion to evaluate the operating safety of rail vehicles. A derailment coefficient prediction method based on neural network is proposed in this paper. First, the basic concepts of derailment coefficient are briefly discussed. Then the principle of BP and NARX networks and their related learning rules are presented. BP network is compared to NARX network and their disadvantages are outlined. Finally, BP and NARX neural networks are established to analyze their prediction performances. The experimental result shows that, compared with BP neural network, NARX neural network offers better predictive performance of the derailment coefficient.

Keywords

Prediction Derailment coefficient BP neural network NARX neural network 

Notes

Acknowledgments

This research was sponsored by National High-tech R&D Program of China (863 Program, No.2011AA110501) and National Key Technology R&D Program of China (No. 2011BAG01B05). The supports are gratefully acknowledged.

References

  1. 1.
    Zeng J, Guan Q (2007) Wheelset climb derailment criteria for evaluation of railway vehicle running safety. J Traffic Transp Eng7(6):1–5 (in Chinese)Google Scholar
  2. 2.
    Zhai W, Chen G (2001) Method and criteria for evaluation of wheel derailment based on wheel vertical rise. J China Railw Soc 23(2):17–26 (in Chinese)Google Scholar
  3. 3.
    Guan Q (2006) Study on the derailment mechanism and running safety of trains. Southwest Jiaotong University, BeijingGoogle Scholar
  4. 4.
    Chang C, Wang C, Li L (2007) Study on numerical test of instrumented wheelset for continuous measurement. Railw Locomot Car 27(5):50–54 (in Chinese)Google Scholar
  5. 5.
    Christoph, W (2010) State-of-the-art railway vehicle design with multi-body simulation. J Mech Syst Transp Logist 3(1):12–26Google Scholar
  6. 6.
    Huo W (2007) Vehicle-track coupling dynamics, 2nd edn. China Railway Publishing House, Beijing (in Chinese)Google Scholar
  7. 7.
    Luber B (2009) Railway track quality assessment method based on vehicle system identification. Elektrotechnik und Informationstechnik 126(5):180–185CrossRefGoogle Scholar
  8. 8.
    Fujie X, Colin C, Peter W (2007) An inverse railway wagon model and its applications.Veh Syst Dyn 45(6):583–605 (in Chinese)Google Scholar
  9. 9.
    Gualano L, Iwnicki SD, Ponnapalli PVS, Allen PD (2006) Prediction of wheel-rail forces, derailment and passenger comfort using artificial neural networks. In: Proceedings of the EURNEX-ZEL conference, Zilina, Slovakia 30th–31st May 2006Google Scholar
  10. 10.
    Wong CX, Worden K (2007) Generalised NARX shunting neural network modelling of friction. Mech Syst Signal Process 21(1):553–572CrossRefGoogle Scholar
  11. 11.
    Zhang S, Kang X, Liu X (2008) Characteristic analysis of the power spectral density (PSD) of track irregularity on Beijing–Tianjin inter-city railway. China Railw Sci 29(5):25–29Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2014

Authors and Affiliations

  • Xiulian Yu
    • 1
  • Guangwu Liu
    • 2
  • Yong Qin
    • 3
  • Yuan Zhang
    • 3
  • Zongyi Xing
    • 1
  1. 1.School of Mechanical EngineeringNanjing University of Science and TechnologyNanjingChina
  2. 2.Engineering Technology Research CenterGuangzhou Metro CorporationGuangzhouChina
  3. 3.State Key Laboratory of Rail Traffic Control and SafetyBeijing Jiaotong UniversityBeijingChina

Personalised recommendations