Exploiting Terrain Information for Enhancing Fuel Economy of Cruising Vehicles by Supervised Training of Recurrent Neural Optimizers

Chapter
First Online:
Part of the Annals of Information Systems book series (AOIS, volume 17)

Abstract

In this chapter, we present a novel data driven approach based on supervised training of feed forward neural networks for solving nonlinear optimization problems. Then we extend the approach to approximate the solution of deterministic, discrete dynamic programming problems by using recurrent networks. We apply this data driven methodology on a real-world fuel economy application in which we train a neural optimizer to prescribe the optimum cruise speed that minimizes fuel consumption, based on the instantaneous and a limited history of the vehicle speeds and road grades, with no a priori knowledge of the future path. The optimizer is tested in simulation on novel road segments. In simulation tests, the optimizer prescribed grade based modulated speed, has achieved about 8–10.6 % fuel savings over driving with constant cruise speed on the same roads, out of which 3.7–10.6 % were due to exploiting the road grades.

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

References

  1. 1.
    Balakrishnan, S.N., Ding, J., Lewis, F.L.: Issues on stability of adp feedback controllers for dynamical systems. IEEE Trans. Syst. Man Cybern. B Cybern. 38(4), 913–917 (2008)CrossRefGoogle Scholar
  2. 2.
    Feldkamp, L.A., Puskorius, G.: A signal processing framework based on dynamic neural networks with application to problems in adaptation, filtering and classification. In: Proceedings of the IEEE, vol. 86, pp. 2259–2277 (2009)Google Scholar
  3. 3.
    Feldkamp, L., Abou-Nasr, M., Kolmanovsky, I.: Recurrent neural network training for energy management of a mild hybrid electric vehicle with an ultra-capacitor. In: IEEE Workshop on Computational Intelligence in Vehicles and Vehicular Systems, pp. 29–36 (2009)Google Scholar
  4. 4.
    Hellstrom, E., Froberg, A., Nielsen, L.: A real-time fuel optimal cruise controller for heavy trucks using road topography information. Tech. Rep. 2006-01-0008, SAE Paper (2006)Google Scholar
  5. 5.
    Hellstrom, E., Ivarsson, M., Aslund, J., Nielsen, L.: Look-ahead control for heavy trucks to minimize trip time and fuel consumption. Control Eng. Pract. vol. 17, 245–254 (2009)Google Scholar
  6. 6.
    Huang, W., Bevly, D.M.: Evaluation of 3d road geometry based heavy truck fuel optimization. Int. J. Veh. Autonom. Syst. vol. 8, 39–55 (2010)Google Scholar
  7. 7.
    Kolmanovsky, I., Filev, D.: Stochastic optimal control of systems with soft constraints and opportunities for automotive applications. In: Proc. IEEE Conference on Control Applications, pp. 1265–1270 (2009)Google Scholar
  8. 8.
    Kolmanovsky, I.V., Filev, D.P.: Terrain and traffic optimized vehicle speed control. In: Proceedings of 6th IFAC Symposium on Advances in Automotive Control (2010)Google Scholar
  9. 9.
    Prokhorov, D.: Toyota prius hev neurocontrol. In: International Joint Conference on Neural Networks, pp. 2129–2134 (2007)Google Scholar
  10. 10.
    Prokhorov, D.V., Wunsch, D.C.: Adaptive critic designs. IEEE Trans. Neur. Netw. 8(5), 997–1007 (1997)CrossRefGoogle Scholar
  11. 11.
    Werbos, P.J.: Neural networks for control and system identification. In: Proceedings of the IEEE Conference on Decision Control, vol. 1, pp. 260–265 (1989)Google Scholar
  12. 12.
    Werbos, P.J.: Approximate dynamic programming for real-time control and neural modeling. In: White, D.A., Sofge, D.A. (eds.) Handbook of Intelligent Control, chap. 13. Van Nostrand Reinhold, New York (1992)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Mahmoud Abou-Nasr
    • 1
  • John Michelini
    • 1
  • Dimitar Filev
    • 1
  1. 1.Research and Advanced Engineering, Research & Innovation CenterFord Motor CompanyDearbornUSA

Personalised recommendations