Control of chaotic oscillations using neural networks
A. Mulpur, S. Mulpur, Bongseog Jang · 2002
This paper investigates the application of neural networks for the control of nonlinear systems that exhibit chaotic behavior. A simple chaotic model of thermal convection is considered and a neural network is trained to serve as the controller. During the training phase, a conventional controller is used as the teacher. Results obtained through simulation indicate that the neural net controller performs satisfactorily and adapts well to changes in system parameters.