INSTITUTE OF INFORMATION TECHNOLOGIES - BAS

Cybernetics and Information Technologies
Volume 4, No 1. Sofia, 2004, Bulgarian Academy of Sciences


Adaptive Control Schemes Based on Recurrent Trainable Neural Networks

Ieroham Baruch1, Jose Martin Flores1, Boyka Nenkova2

1 CINVESTAV-IPN, av. IPN No 2508, Mexico D.F. 07560, Mexico
E-Mail: baruch@ctrl.cinvestav.mx
2 Institute of Information Technologies, 1113 Sofia


Abstract: The aim of the present paper is to integrate a recurrent neural network in two schemes of real-time soft computing neural control. There are applied the following control schemes: an indirect and a direct trajectory tracking control, using the state and parameter information, given by an identification recurrent neural network. The applicability of the proposed control schemes is confirmed by simulation and experimental results, which exhibits a good convergence.

Keywords: neural networks, soft computing control, adaptive schemes.