APPLICATION OF RADIAL BASIS FUNCTION AND FEEDFORWARD ARTIFICIAL NEURAL NETWORKS TO THE ESCHERICHIA-COLI FERMENTATION PROCESS

Radial basis function and feedforward neural networks are considered f or modelling of the recombinant Escherichia coli fermentation process. The models use industrial on-line data from the process as input vari ables in order to estimate the concentrations of biomass and recombina nt protein, normally only available from off-line laboratory analysis, The models performances are compared by prediction error and graphica l fit using results obtained from a common testing set of fermentation data. (C) 1998 Published by Elsevier Science B.V. All rights reserved .