International Journal of Fuzzy Logic and Intelligent Systems

  • 제7권4호
  • /
  • Pages.236-241
  • /
  • 2007
  • /
  • 1598-2645(pISSN)
  • /
  • 2093-744X(eISSN)
한국지능시스템학회 (Korean Institute of Intelligent Systems)
권호 표지
DOI QR코드

DOI QR Code

A study on the Adaptive Controller with Chaotic Dynamic Neural Networks

  • Kim, Sang-Hee (School of Electronic Engineering, Kumoh National Instute of Technology) ;
  • Ahn, Hee-Wook (School of Electronic Engineering, Kumoh National Instute of Technology) ;
  • Wang, Hua O. (Dept. of Aerospace/Mechanical Engineering, Boston University)
  • 발행 : 2007.12.01
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

This paper presents an adaptive controller using chaotic dynamic neural networks(CDNN) for nonlinear dynamic system. A new dynamic backpropagation learning method of the proposed chaotic dynamic neural networks is developed for efficient learning, and this learning method includes the convergence for improving the stability of chaotic neural networks. The proposed CDNN is applied to the system identification of chaotic system and the adaptive controller. The simulation results show good performances in the identification of Lorenz equation and the adaptive control of nonlinear system, since the CDNN has the fast learning characteristics and the robust adaptability to nonlinear dynamic system.

키워드

참고문헌

  1. J. Nagumo and S. Sato, 'On response characteristics of a mathematical neuron model,' Kybernetik, vol. 10, pp. 155-164, 1972 https://doi.org/10.1007/BF00290514
  2. L. Chen and K. Aihara, 'Chaotic simulated annealing by a neural network model with transient chaos,' Neural Networks, vol. 8, no. 6, pp. 915-930, 1995 https://doi.org/10.1016/0893-6080(95)00033-V
  3. L. Chen and K. Aihara, 'Global Searching Ablity of Chaotic Neural Networks', IEEE Trans. Circuits and System-I, vol 46, No 8, pp. 974-993, 1999 https://doi.org/10.1109/81.780378
  4. K. S. Narendra and K. Parthasarathy, 'Gradient methods for optimization of dynamical systems containing neural networks,' IEEE Trans Neural Networks, vol. 2, no. 2, pp 252-262, 1991 https://doi.org/10.1109/72.80336
  5. H. K. Khalil, 'Nonlinear System', Prentice Hall
  6. L. Jin, N. Nikiforuk, and M. Gupta, 'Absolute Stability Conditions for Discrete-Time Recurrent Neural Networks', IEEE Trans. Neural Networks, Vol. 5, No.6, pp. 954-964, 1994 https://doi.org/10.1109/72.329693
  7. L. Jin and M. Gupta, 'Stable Dynamic Backpropagation Learning in Recurrent Neural Networks', IEEE Trans. Neural Networks, Vol. 10, No.5, pp. 1321-1334, 2000 https://doi.org/10.1109/72.809078