Comparing Different Modelling Techniques for the Escherichia Coli Fermentation Process

Abstract

Four different modelling techniques are considered for the Escherichia coli fermentation process. These are Multiple Linear Regression (MLR), Principal Component Regression (TCR), Non-linear Auto-Regressive Moving Average with eXogencous inputs (NARMAX) and Artificial Neural Networks (ANNs). The models use industrial on-line data from the process as inputs in order to forecast the concentrations of biomass and recombinant protein, normally only available from offline laboratory analysis. The models’ performances are compared by prediction accuracy and graphical fit using results obtained from a common set of fermentation data.