A study on the Adaptive Controller with Chaotic Dynamic Neural Networks

다국어 초록 (Multilingual Abstract)

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.

목차 (Table of Contents)

• Abstract
• 1. Introduction
• 2. Dynamic Backpropagation Learning of CDNN
• 3. Simulation results with CDNN
• 4. Conclusion
• References

참고문헌 (Reference)

1 "Stable Dynamic Backpropagation Learning in Recurrent Neural Networks" 10 (10): 1321-1334, 2000.

2 "On response characteristics of a mathematical neuron model" 10 : 155-164, 1972.

3 "Nonlinear System" Prentice Hall.

4 "Gradient methods for optimization of dynamical systems containing neural networks" 2 : 252-262, 1991.

5 "Global Searching Ablity of Chaotic Neural Networks" 46 (46): 974-993, 1999.

6 "Chaotic simulated annealing by a neural network model with transient chaos" 8 (8): 915-930, 1995.

7 "Absolute Stability Conditions for Discrete-Time Recurrent Neural Networks" 5 : 954-964, 1994.