Your browser does not support JavaScript!
http://iet.metastore.ingenta.com
1887

access icon free Switching LDS detection for GNSS-based train integrity monitoring system

© The Institution of Engineering and Technology
Received 18/03/2016, Accepted 01/03/2017, Revised 02/02/2017, Published 06/03/2017

Train integrity whilst in service establishes the foundation for railway safety. This study investigates train integrity detection which reliably deduces whether the train consists remain intact. A switching linear dynamic system (SLDS) based train integrity detection method is proposed for Global Navigation Satellite System (GNSS) based train integrity Monitoring System (TIMS) using the relative distance, velocity and acceleration of the locomotive and the last van. There, Expectation Maximisation (EM) algorithm estimates the parameters of SLDS model while the Gaussian Sum Filter infers train integrity state. After that, to cope with false detection and misdetection, a verification procedure and train parting time estimation are designed. The approach is evaluated with both field trials and simulated data. Results show that the false alarm rate and misdetection rate of SLDS-based integrity detection approach are 0 and 0.09% respectively, which proves better than the estimated train length based detection model and Hidden Markov Model (HMM).

Inspec keywords: railway safety; expectation-maximisation algorithm; satellite navigation; hidden Markov models

Other keywords: train integrity detection method; EM algorithm; verification procedure; relative distance; train parting time estimation; expectation maximisation algorithm; hidden Markov model; HMM; GNSS-based train integrity monitoring system; train length based detection model; switching linear dynamic system; false alarm rate; railway safety; Gaussian sum filter; misdetection rate; TIMS; global navigation satellite system; SLDS model

Subjects: Markov processes; Radionavigation and direction finding

References

    1. 1)
      • 25. Robert, C., Casella, G.: ‘Monte carlo statistical methods’ (Springer Science & Business Media Press, Berlin, 2013).
    2. 2)
      • 16. Wegener, M., Brahmi, M., Siedersberger, K.: ‘Requirements on reference systems for vehicle localisation’, ATZelektronik worldwide, 2012, 7, (5), pp. 58–63.
    3. 3)
      • 5. Wegener, M., Schnieder, E.: ‘A measurement standard for vehicle localization and its ISO-compliant measurement uncertainty evaluation’, IEEE Trans. Instrum. Meas., 2012, 61, (11), pp. 3003–3013.
    4. 4)
      • 28. Freitas, N., Dearden, R., Hutter, F., et al: ‘Diagnosis by a waiter and a mars explorer’, Proc of IEEE, 2004, 92, (3), pp. 455–468.
    5. 5)
      • 4. Simsky, A., Wilms, F., Franckart, J.: ‘GNSS-based failsafe train positioning system for low-density traffic lines based on one dimensional positioning algorithm’. Proc. Conf. NAVITEC, Noordwijk, Netherland, December 2004, pp. 1–8.
    6. 6)
      • 8. Sehchan, Y., Yoon, Y., Kim, K., et al: ‘Design of train integrity monitoring system for radio based train control system’. Proc. Conf. Control, Automation and Systems, JeJu Island, Korea, October 2012, pp. 1237–1240.
    7. 7)
      • 13. Pavlovic, V., Rehg, J., MacCormick, J.: ‘Learning switching linear models of human motion’. Conf. Neural Information Processing Systems, Denver, USA, March 2000, pp. 981–987.
    8. 8)
      • 22. Sang, M., Ranganathan, A., Rehg, J., et al: ‘A variational inference method for switching linear dynamic systems’. GVU Technical Report, GIT-GVU-05-16, 2005.
    9. 9)
      • 19. Pavlovic, V., Rehg, J., Cham, T., et al: ‘A dynamic bayesian network approach to figure tracking using learned dynamic models’. Proc, Conf. Computer Vision, Corfu, Greece, September 1999, pp. 94–101.
    10. 10)
      • 30. Zoeter, O., Heskes, T.: ‘Hierarchical visualization of time-series data using switching linear dynamical systems’, IEEE Transaction on Pattern Analysis and Machine Intelligence, 2003, 25, (10), pp. 1201–1214.
    11. 11)
      • 18. West, M., Harrison, J.: ‘Bayesian forecasting and dynamic models’ (Springer Press, Berlin, 1997).
    12. 12)
      • 33. Su, S., Tang, T., Roberts, C.: ‘A cooperative train control model for energy saving’, IEEE Transaction on Intelligent Transportation Systems, 2015, 16, (2), pp. 622–631.
    13. 13)
      • 7. Scholten, H., Westenberg, R., Schoemaker, M.: ‘Sensing train integrity’. Proc. Conf. Sensors, Canterbury, New Zealand, October 2009, pp. 669–674.
    14. 14)
      • 29. Ghahramani, Z., Hinton, G.: ‘Variational Learning for Switching State-Space Models’, Neural Comput., 2000, 12, (4), pp. 831–864.
    15. 15)
      • 34. Sun, Z.: ‘Study of train traction calculation’ (Railroad Publication House of China. Press, Beijing, 2005).
    16. 16)
      • 6. Scholten, H., Westenberg, R., Schoemaker, M.: ‘Trainspotting, a WSN-based train integrity system’. Proc. Conf. Networks, Washington, USA, March 2009, pp. 226–231.
    17. 17)
      • 9. Acharya, A., Sadhu, S., Ghoshal, T.: ‘Train localization and parting detection using data fusion’, Transportation Research Part C: Emerging Technologies, 2011, 19, (1), pp. 75–84.
    18. 18)
      • 17. Lu, D., Schnieder, E.: ‘Performance evaluation of GNSS for train localization’, IEEE Transaction on Intelligent Transportation System, 2015, 16, (2), pp. 1054–1059.
    19. 19)
      • 1. Zhang, S.: ‘General technical scheme of CTCS-3 train control system’ (China Railway Publishing House Press, Beijing, 2008).
    20. 20)
      • 10. Neri, A., Rispoli, F., Salvatori, P.: ‘A train integrity solution based on GNSS double-difference approach’. ION GNSS + , Tampa, USA, September 2014, pp. 34–50.
    21. 21)
      • 27. Murphy, K., Russell, S.: ‘Rao-blackwellised particle filtering for dynamic bayesian networks’. Proc. Conf. Sequential Monte Carlo methods in practice, San Francisco, USA, 2001, pp. 499–515.
    22. 22)
      • 20. Pavlovic, V., Rehg, J., Cham, T., et al: ‘A dynamic bayesian network approach to tracking using learned switching dynamic models’. Proc, Conf. Hybrid Systems: Computation and Control, Pittsburgh, USA, September 2000, pp. 366–380.
    23. 23)
      • 26. Doucet, A., Gordon, N., Krishnamurthy, V.: ‘Particle filters for state estimation of jump Markov linear systems’, IEEE Transaction on Signal Processing, 2001, 49, (3), pp. 613–624.
    24. 24)
      • 31. ‘Federal Railroad Administration Office of Safety Analysis’, http://safetydata.fra.dot.gov/OfficeofSafety, accessed October2015.
    25. 25)
      • 21. Sang, M., Rehg, J., Balch, T., et al: ‘Data-driven MCMC for learning and inference in switching linear dynamic systems’. Proc. Conf. Artificial Intelligence, Pittsburgh, USA, 2005, vol. 20, no. 2, pp. 944–949.
    26. 26)
      • 24. Lerner, U., Parr, R.: ‘Inference in hybrid networks: theoretical limits and practical algorithms’. Proc. Conf. Artificial Intelligence, San Francisco, USA, 2001, pp. 310–318.
    27. 27)
      • 32. Howlett, P., Pudney, P.: ‘Energy-efficient train control’ (Springer Science & Business Media Press, Berlin, 2012).
    28. 28)
      • 14. Sang, M., Rehg, J., Balch, T., et al: ‘Learning and inferring motion patterns using parametric segmental switching linear dynamic systems’, Int. Journal of Computer Vision, 2008, 1, (3), pp. 103–124.
    29. 29)
      • 11. An, Y., Cai, B., Ning, B., et al: ‘Research on train integrity monitoring method based on GPS and virtual-satellite’, Journal of China Railway Society, 2012, 34, (9), pp. 40–44.
    30. 30)
      • 15. AN10-1: ‘Annex 10 (Aeronautical Telecommunications) To The Convention On Interna tional Civil Aviation, Volume I - Radio Navigation Aids, International Standards And Recommended Practices (SARPs)’, 2001.
    31. 31)
      • 3. Filip, A., Mocek, H., Bazant, L.: ‘GPS/GNSS based train positioning for safety critical applications’, Signal Draht, 2001, 93, (5), pp. 51–55.
    32. 32)
      • 23. Ghahramani, Z., Hinton, G.: ‘Parameter estimation for linear dynamical systems’. Technical report, University of Toronto, 1996.
    33. 33)
      • 2. Beugin, J., Filip, A., Marais, J., et al: ‘Galileo for railway operations: question about the positioning performances analogy with the RAMS requirements allocated to safety applications’, Eur. Transp. Res. Rev., 2010, 2, (2), pp. 93–102.
    34. 34)
      • 12. Barber, D.: ‘Bayesian reasoning and machine learning’ (Cambridge University Press, London, 2012).
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-its.2016.0060
Loading

Related content

content/journals/10.1049/iet-its.2016.0060
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading
Print this page
This is a required field
Please enter a valid email address