Skip to main content
SpringerLink
Log in

Position calculation models by neural computing and online learning methods for high-speed train

  • Original Article
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

For high-speed trains, high precision of train positioning is important to guarantee train safety and operational efficiency. By analyzing the operational data of Beijing–Shanghai high-speed railway, we find that the currently used average speed model (ASM) is not good enough as the relative error is about 2.5 %. To reduce the positioning error, we respectively establish three models for calculating train positions by advanced neural computing methods, including back-propagation (BP), radial basis function (RBF) and adaptive network-based fuzzy inference system (ANFIS). Furthermore, six indices are defined to evaluate the performance of the three established models. Compared with ASM, the positioning error can be reduced by about 50 % by neural computing models. Then, to increase the robustness of neural computing models and real-time response, online learning methods are developed to update the parameters in the last layer of neural computing models by the gradient descent method. With the online learning methods, the positioning error of neural computing models can be further reduced by about 10 %. Among the three models, the ANFIS model is the best in both training and testing. The BP model is better than the RBF model in training, but worse in testing. In a word, the three models can reduce the half number of transponders to save the cost under the same positioning error or reduce the positioning error about 50 % in the case of the same number of transponders.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16
Fig. 17
Fig. 18

Similar content being viewed by others

References

  1. Givoni M (2006) Development and impact of the modern high-speed train: a review. Transp Policy 26(5):593–611

    Google Scholar 

  2. Smith RA (2003) The japanese shinkansen: catalyst for the renaissance of rail. J Transp Hist 24(2):222–237

    Article  Google Scholar 

  3. Ebeling K (2005) High-speed railways in germany. Jpn Railw Transp Rev 40:36–45

    Google Scholar 

  4. Eberhard J (2005) Railway infrastructure and the development of high-speed rail in germany. Railw Tech Rev Int J Rail Eng Oper Sci 2:3–11

    Google Scholar 

  5. Vickerman R (1997) High-speed rail in europe: experience and issues for future development. Ann Reg Sci 31(1):21–38

    Article  Google Scholar 

  6. Takagi K (2011) Development of high-speed railways in china. Jpn Railw Transp Rev 57:36–41

    Google Scholar 

  7. Zhao C (2014) Development and trend analysis of china’s high-speed railway. Technol Innov Appl 1:200

    Google Scholar 

  8. Chen RM (2010) Brief overview of the development of china’s high-speed railway. Contemp Econ 16:82–83

    Google Scholar 

  9. Zhang Y, Zhang HY (2011) Research on technology of train tracing and position determination for modern railway. Railw Comput Appl 20(4):1–3

    Google Scholar 

  10. Dong H, Ning B, Cai B et al (2010) Automatic train control system development and simulation for high-speed railways. IEEE Circuits Syst Mag 10(2):6–18

    Article  Google Scholar 

  11. Lu J (2011) On the development process of china’s high-speed railway. Technol Mark 18(5):222–222

    Google Scholar 

  12. Sandidzadeh MA, Heydari A, Khodadadi A (2013) Genetic algorithm and particle swarm optimization algorithm for speed error reduction in railway signaling systems. Int J Adapt Control Signal Process 27(6):478–487

    Article  MathSciNet  MATH  Google Scholar 

  13. Zhu AH, Li B, Yang L (2013) The research on positioning technology and portfolio positioning system of high-speed train. Chin Railw 5:59–63

    Google Scholar 

  14. Vapnik VN (1996) The nature of statistical learning theory. Springer, New York

    MATH  Google Scholar 

  15. Vapnik VN (1998) Statistical learning theory. Wiley, New York

    MATH  Google Scholar 

  16. Guo G, Zhang JS, Zhang GY (2009) A method to sparsify the solution of support vector regression. Neural Comput Appl 18(8):919–926

    Article  Google Scholar 

  17. Science and Technology Department of Chinese Ministry of Railways. System Requirement Specification of Level-3 Chinese Train Control System (CTCS). China Railway Publishing House, v1.0 edition, 2008

  18. Science and Technology Department of Chinese Ministry of Railways. General Technology Scheme of Level-3 Chinese Train Control System (CTCS). China Railway Publishing House, 2008

  19. Wang JF, Wang XS (2012) Ctcs-3 research on data fusion of ctcs-3 train control system. J China Railw Soc 34(9):70–74

    Google Scholar 

  20. Pascoe R, Eichorn T (2009) What is communication-based train control. IEEE Veh Technol Mag 4(4):16–21

    Article  Google Scholar 

  21. Guo Z, Wu J, Lu H et al (2011) A case study on a hybrid wind speed forecasting method using bp neural network. Knowl Based Syst 24(7):1048–1056

    Article  Google Scholar 

  22. Wu QH, Ding S (2013) A matlab-based study on approximation performances of improved algorithms of typical bp neural networks. Appl Mech Mater 313:1353–1356

    Google Scholar 

  23. Mandal D, Pal SK, Saha P (2007) Back propagation neural network based modeling of multi-response of an electrical discharge machine process. Int J Knowl Based Intell Eng Syst 11:381–390

    Article  Google Scholar 

  24. Neaupane K, Achet S (2004) Some applications of a back propagation neural network in geo-engineering. Environ Geol 45(4):567–575

    Article  Google Scholar 

  25. Xu C, Xu C (2013) Analysis of dynamic sample number and hidden layer node number based on bp neural network. In: Proceedings of the eighth international conference on bio-inspired computing: theories and applications (BIC-TA) 2013. Springer, Berlin Heidelberg, p 687–695

  26. Han HG, Qiao JF, Chen QL (2012) Model predictive control of dissolved oxygen concentration based on a self-organizing rbf neural network. Control Eng Pract 20(4):465–476

    Article  Google Scholar 

  27. Han HG, Qiao JF (2012) Adaptive computation algorithm for rbf neural network. IEEE Trans Neural Netw Learn Syst 23(2):342–347

    Article  MathSciNet  Google Scholar 

  28. Hou M, Han X (2010) Constructive approximation to multivariate function by decay rbf neural network. IEEE Trans Neural Netw 21(9):1517–1523

    Article  Google Scholar 

  29. Nagare A, Shalini B (2012) Traffic flow control using neural network. Int J Appl Inf Syst 1(2):50–52

    Google Scholar 

  30. Qiao JF, Han HG (2010) Optimal structure design for RBFNN structure. Acta Autom Sin 36(6):865–872

    Article  MathSciNet  Google Scholar 

  31. Nazari A, Khalaj G, Riahi S (2013) ANFIS-based prediction of the compressive strength of geopolymers with seeded fly ash and rice huskCbark ash. Neural Comput Appl 22(3–4):689–701

    Article  Google Scholar 

  32. Zhang HQ, Yu YF (2002) Modeling and simulation applying adaptive neural-fuzzy inference system (anfis). Comput Simul 19(4):47–49

    Google Scholar 

  33. He S, Zou Y, Quan D, et al (2012) Application of rbf neural network and anfis on the prediction of corrosion rate of pipeline steel in soil. In: Recent advances in computer science and information engineering, vol 124. Springer, p 639–644

  34. Madandoust R, Bungey JH, Ghavidel R (2012) Prediction of the concrete compressive strength by means of core testing using gmdh-type neural network and anfis models. Comput Mater Sci 51(1):261–272

    Article  Google Scholar 

  35. Hakim SJS, Abdul Razak H (2013) Adaptive neuro fuzzy inference system (anfis) and artificial neural networks (anns) for structural damage identification. Struct Eng Mech 45(6):779–802

    Article  Google Scholar 

Download references

Acknowledgments

This work has been partially funded by research projects from the State Key Laboratory of Rail Traffic Control and Safety under grant RCS2014ZZ02, Beijing Municipal Natural Science Foundation Under Grant 4142044, the National Science Foundation of China under grant 61103153/F020503 and the Start Funding for Minjiang Chair Professor by Fujian Province.

Author information

Authors and Affiliations

  1. College of Mathematics and Computer Science, Fuzhou University, Fuzhou, 350116, China

    Dewang Chen

  2. State Key Laboratory of Rail Traffic Control and Safety, Beijing Jiaotong University, Beijing, 100044, China

    Xiaojie Han, Ruijun Cheng & Lixing Yang

Authors
  1. Dewang Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Xiaojie Han
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Ruijun Cheng
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Lixing Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Dewang Chen.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Chen, D., Han, X., Cheng, R. et al. Position calculation models by neural computing and online learning methods for high-speed train. Neural Comput & Applic 27, 1617–1628 (2016). https://doi.org/10.1007/s00521-015-1960-6

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-015-1960-6

Keywords

Search

Navigation