In this work a SISO non-linear predictive controller was developed for an extractive alcoholic fermentation process. The internal model of the controller was represented by a functional link network (FLN). This model was identified using simulated data generated from a deterministic mathematical model whose kinetic parameters were determined experimentally. The FLN structure presented good non-linear approximation ability, with the advantage that the estimation of its weights is a linear optimization problem. The results show that the proposed algorithm has a great potential to identification and control of non-linear processes. (C) 2002 Elsevier Science Ltd. All rights reserved.385743750