Advertisement

Particle Swarm Optimization of a Recurrent Neural Network Control for an Underactuated Rotary Crane with Particle Filter Based State Estimation

  • Sam Chau Duong
  • Hiroshi Kinjo
  • Eiho Uezato
  • Tetsuhiko Yamamoto
Chapter
Part of the Studies in Computational Intelligence book series (SCI, volume 363)

Abstract

This paper addresses the control problem of an underactuated rotary crane system by using a recurrent neural network (RNN) and a particle filter (PF) based state estimation. The RNN is used as a state feedback controller which is designed by a constricted particle swarm optimization (PSO). As the study also considers the problem with assuming that the velocities of the system are not obtained, PF is utilized to estimate the latent states. Simulations show that the RNN could provide a superior evolutionary performance and less computational cost compared to a feed forward NN and that the PF is effective in estimating the unobserved states.

Keywords

recurrent neural network particle swarm optimization nonlinear control underactuated system particle filter sequential Monte Carlo method 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Fleming, P.J., Purshouse, R.C.: Evolutionary algorithms in control systems engineering: a survey. Control Engineering Practice 10, 1223–1241 (2002)CrossRefGoogle Scholar
  2. 2.
    Linkens, D.A., Nyongesa, H.O.: Learning systems in intelligent control: An appraisal of fuzzy, neural and genetic control applications. IEEE Proc. Control Theory and Applications 143(4), 367–386 (1996)zbMATHCrossRefGoogle Scholar
  3. 3.
    Kristinsson, K., Dumont, G.A.: System identification and control using genetic algorithms. IEEE Trans. Systems, Man, and Cybernetics 22(5), 1033–1046 (1992)zbMATHCrossRefGoogle Scholar
  4. 4.
    Zerkaoui, S., Druaux, F., Leclercq, E., Lefebvre, D.: Stable adaptive control with recurrent neural networks for square MIMO non-linear systems. Engineering Applications of Artificial Intelligence 22, 702–717 (2009)CrossRefGoogle Scholar
  5. 5.
    Blanco, A., Delgado, M., Pegalajar, M.C.: A real-coded genetic algorithm for training recurrent neural networks. Neural Networks 14, 93–105 (2001)CrossRefGoogle Scholar
  6. 6.
    Angeline, P.J., Saunders, G.M., Pollack, J.B.: An evolutionary algorithm that constructs recurrent neural networks. IEEE Trans. Neural Networks 5, 54–65 (1994)CrossRefGoogle Scholar
  7. 7.
    Clerc, M., Kennedy, J.: The particle swarm-explosion, stability, and convergence in a multidimensional complex space. IEEE Trans. on Evolutionary Computation 6(1), 58–73 (2002)CrossRefGoogle Scholar
  8. 8.
    Yasuda, K., Iwasaki, N., Ueno, G., Aiyoshi, E.: Particle Swarm Optimization: A numerical stability analysis and parameter adjustment based on swarm activity. IEEJ Trans. Electrical and Electronic Engineering 3, 642–659 (2008)CrossRefGoogle Scholar
  9. 9.
    Gudise, V., Venayagamoorthy, G.: Comparison of Particle swarm optimization and backpropagation as training algorithms for neural networks. In: Proc. IEEE Swarm Intelligence Symp., pp. 110–117 (2003)Google Scholar
  10. 10.
    Kitagawa, G.: Monte-Carlo filter and smoother for non-Gaussian nonlinear state-space models. Journal of Computational and Graphical Statistics 5(1), 1–25 (1996)CrossRefMathSciNetGoogle Scholar
  11. 11.
    Cany, J.V.: Bootstrap Particle Filtering. IEEE Signal Processing Magazine 24(4), 73–85 (2007)CrossRefGoogle Scholar
  12. 12.
    Sakawa, Y., Shindo, Y.: Optimal control of container cranes. Automatica 18(3), 257–266 (1982)zbMATHCrossRefGoogle Scholar
  13. 13.
    Kondo, R., Shimahara, S.: Anti-sway control of a rotary crane via two-mode switching control. Trans. Society of Instrument and Control Engineers 41(4), 307–313 (2005) (in Japanese)Google Scholar
  14. 14.
    Kolmanovsky, N., McClamroch, N.H.: Developments in Nonholonomic Control Problems. IEEE Control Systems 15(6), 20–36 (1995)CrossRefGoogle Scholar
  15. 15.
    Furuta, K., Kawaji, S., Mita, T., Hara, S.: Mechanical System Control, Ohm-sha, Japan, pp. 192–197 (1984) (in Japanese)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Sam Chau Duong
    • 1
  • Hiroshi Kinjo
    • 1
  • Eiho Uezato
    • 1
  • Tetsuhiko Yamamoto
    • 2
  1. 1.Faculty of EngineeringUniversity of the RyukyusJapan
  2. 2.Tokushima College of TechnologyJapan

Personalised recommendations