Advanced monitoring, fault detection, automatic control and optimisation of
the beer fermentation process require on-line prediction and off-line simu
lation of key variables. Three dynamic models for the beer fermentation pro
cess are proposed and validated in laboratory scale: a model based on biolo
gical knowledge of the fermentation process, an empirical model based on th
e shape of the experimental curves and a black-box model based on an artifi
cial neural network. The models take into account the fermentation temperat
ure, the top pressure and the initial yeast concentration, and predict the
wort density, the residual sugar concentration, the ethanol concentration,
and the released CO2. The models were compared in terms of prediction accur
acy, robustness and generalisation ability (interpolation and extrapolation
), reliability of parameter identification and interpretation of the parame
ter values. Not surprisingly, in the case of a relatively limited experimen
tal data (10 experiments in various operating conditions), models that incl
ude more process knowledge appear equally accurate but more reliable than t
he neural network. The achieved prediction accuracy was 5% for the released
CO2 volume, 10% for the density and the ethanol concentration and 20% for
the residual sugar concentration. (C) 2001 IMACS. Published by Elsevier Sci
ence B.V. All rights reserved.