Six different modelling techniques were considered for the recombinant
Escherichia coli fermentation process. These are Multiple Linear Regr
ession (MLR), Principal Component Regression (PCR), Partial Least Squa
res (PLS), Auto-Regressive Moving Average with eXogeneous inputs (ARMA
X), Non-linear ARMAX (NARMAX) and Artificial Neural Networks. The mode
ls use industrial on-line data from the process as input variables in
order to forecast the concentrations of biomass and recombinant protei
n normally only available from off-line laboratory analysis. The model
s' performances are compared by prediction error and graphical fit usi
ng results obtained from a common testing set of fermentation data.