A Method to Improve Accuracy of Velocity Prediction Using Markov Model

  • Ya-dan Liu
  • Liang Chu
  • Nan XuEmail author
  • Yi-fan Jia
  • Zhe Xu
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10638)


In order to predict the velocity in driving cycle, first-stage Markov chain (MC) predictor method is adopted. In the traditional Markov prediction model, only one state transition matrix was used to predict the speed. However it will produce a larger error to use the same matrix for predicting speed in different categories of driving cycles. Random Markov-Chain (RMC) model is adopted to improve the accuracy, but the accuracy is still not enough. In this paper, we propose that the state transition matrices in RMC model are divided into two categories: city and highway. Before the prediction, we use the neural network to choose state transition matrix by judging the kinematic parameters of velocity in driving cycles. The simulation results show that the effect of prediction using the state transition matrix after neural network classification is more accurate than no classification. Therefore, the improved RMC model can increase the accuracy of velocity prediction effectively.


Neural network Random Markov-Chain model Velocity prediction Classification State transition matrix 



Supported by Jilin Province Science and Technology Development Fund (20150520115JH); Energy Administration of Jilin Province [2016]35.


  1. 1.
    Sun, C., Hu, X., Moura, S.J., Sun, F.: Velocity predictors for predictive energy management in hybrid electric vehicles. IEEE Trans. Control Syst. Technol. 23(3), 1197–1204 (2015). IEEE Press, New YorkCrossRefGoogle Scholar
  2. 2.
    Zhao, D., Dai, Y., Zhang, Z.: Computational intelligence in urban traffic signal control: a survey. IEEE Trans. Syst. Man Cybern. 42(4), 485–494 (2012). IEEE Press, New YorkCrossRefGoogle Scholar
  3. 3.
    Borhan, H.A., Vahidi, A.: Model predictive control of a power-split hybrid electric vehicle with combined battery and ultracapacitor energy storage. In: American Control Conference, vol. 1, no. 4, pp. 5031–5036. IEEE Press, New York (2010)Google Scholar
  4. 4.
    Hagan, M.T., Demuth, H.B., Beale, M.H.: Neural Network Design. PWS-Kent, Boston (1996)Google Scholar
  5. 5.
    Shi, G., Liu, D., Wei, Q.: Energy consumption prediction of office buildings based on echo state networks. Neurocomputing 216, 478–488 (2016). Elsevier Science Publishers B.V., AmsterdamCrossRefGoogle Scholar
  6. 6.
    Bichi, M., Ripaccioli, G., Di Cairano, S., Bernardini, D., Bemporad A., Kolmanovsky, I.V.: Stochastic model predictive control with driver behavior learning for improved powertrain control. In: 49th IEEE Conference on Decision and Control, pp. 6077–6082. IEEE Press, New York (2010)Google Scholar
  7. 7.
    Moura, S.J., Fathy, H.K., Callaway, D.S., Stein, J.L.: A stochastic optimal control approach for power management in plug-in hybrid electric vehicles. IEEE Trans. Control Syst. Technol. 19(3), 545–555 (2008). IEEE Press, New YorkCrossRefGoogle Scholar
  8. 8.
    Pan, D.: Multi-scale Prediction of Urban Recycling Cycle and Driving Cycle of Hybrid Electric Vehicle. Beijing Institute of Technology (2015)Google Scholar
  9. 9.
    Ripaccioli, G., Bernardini, D., Cairano, S.D., Benporad, A., Kolmanovsky, I.: A stochastic model predictive control approach for series hybrid electric vehicle power management. In: American Control Conference, pp. 5844–5849. IEEE Press, New York (2010)Google Scholar
  10. 10.
    Tang, J., Alelyani, S., Liu, H.: Feature selection for classification: a review. In: Documentacion Administrativa, pp. 313–334 (2014)Google Scholar
  11. 11.
    Jiao, B., Ye, M.: The method of determining the number of hidden layer in BP neural network. J. Shanghai Motor Univ. 16(3), 113–116 (2013)Google Scholar
  12. 12.
    Shen, H.: Determination of the number of implied layer units in BP neural network. J. Tianjin Univ. Technol. 24(5), 13–15 (2008)Google Scholar
  13. 13.
    Liu, X.: Applied adaptive control. Northwestern Polytechnical University Press (2003)Google Scholar
  14. 14.
    Gao, D.: Hidden node pruning algorithm for forward multilayer neural networks. J. Electron., 114–115 (1997)Google Scholar
  15. 15.
    Lv, R.: HEV Control Strategy Based on Cycle and Driving Intention Recognition. Dalian University of Technology (2013)Google Scholar
  16. 16.
    Kohavi, R., John, G.H.: Wrappers for feature subset selection. Artif. Intell. 97(1–2), 273–324 (1997)CrossRefzbMATHGoogle Scholar
  17. 17.
    Belkin, M., Niyogi, P.: Laplacian eigenmaps and spectral techniques for embedding and clustering. In: International Conference on Neural Information Processing Systems, vol. 14, pp. 585–591. MIT Press Cambridge (2001)Google Scholar
  18. 18.
    He, X., Cai, D., Niyogi, P.: Laplacian score for feature selection. In: International Conference on Neural Information Processing Systems, vol. 18, pp. 507–514. MIT Press Cambridge (2005)Google Scholar
  19. 19.
    Wan, J., Yang, M., Chen, Y.: Discriminative cost sensitive Laplacian score for face recognition. Neurocomputing 152, 333–344 (2015)CrossRefGoogle Scholar
  20. 20.
    Li, L., Guo, Y., Yi, P.: Analyzing the principles for choosing dimensionless methods. J. Syst. Manag., 1040–1045 (2016)Google Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Ya-dan Liu
    • 1
  • Liang Chu
    • 1
  • Nan Xu
    • 1
    Email author
  • Yi-fan Jia
    • 1
  • Zhe Xu
    • 2
  1. 1.State Key Laboratory of Automotive Simulation and ControlJilin UniversityChangchunChina
  2. 2.R&D CenterChina FAW Group CorporationChangchunChina

Personalised recommendations