An Observer-Based Neural Network Controller for Chaotic Lorenz System
ISICA '08 Proceedings of the 3rd International Symposium on Advances in Computation and Intelligence
Synchronization of chaotic systems from a fuzzy regulation approach
Fuzzy Sets and Systems
IEEE Transactions on Neural Networks
Hi-index | 0.00 |
This paper presents a neural network controller for synchronization of two Duffing-Holmes oscillators. A Duffing-Holmes oscillator is a chaotic system describing a dynamics of the forced vibration of a buckled elastic beam. The controller is a feedforward neural network trained to drive the first Duffing-Holmes oscillator so that its states converge to those of the other Duffing-Holmes. The training scheme is based on a model reference strategy with imposing stability conditions on the controller's parameters. The stability condition guarantees the convergence of the synchronization errors. Numerical simulations are conducted to illustrate the feasibility and effectiveness of the stable neural network controller.