This paper presents a new application of neural networks to the modelling o
f a chemical pilot plant: a pulsed liquid-liquid extraction column. This se
paration process presents a highly non-linear behaviour and time-varying dy
namics. Usually, physical simulation models of chemical plants describing s
ome aspects of hydrodynamics and mass transfer are static or very complex a
nd need excessive computer time. It is proposed that improved predictions c
an be obtained using a multilayer artificial neural network instead of the
physical model of the process. The results obtained illustrate the successf
ul application of such a neural network modelling approach. (C) 2000 Elsevi
er Science S.A. All rights reserved.