HYBRID MODELING OF BIOCHEMICAL PROCESSES - A COMPARISON WITH THE CONVENTIONAL APPROACH

This paper addresses attitudes and forms of process modelling in bioch emical engineering. Baker's yeast production in a fed-batch fermenter, at laboratory scale, is employed as case-study. Three modelling appro aches are described and compared, viz. - the conventional mechanistic approach, formulations based on different artificial neural network (A NN) topologies and a hybrid mechanistic-ANN structure. A standard 2-st ep procedure of model development, estimation (training) and validatio n with two independent sets of experiments, has been carried out. The mechanistic model, using reaction kinetic schemes from the literature, fine tuned by classical non-linear regression, gave smooth prediction s for the validation data runs, but showed limited ability in predicti ng the test data. The ANN were able to describe experiments at the tra ining stage, but failed the validation (i.e. extrapolation) procedure, giving oscillatory predictions of the process state. Additionally, th is approach suffers from a strong influence of the net parameters, whi ch must be chosen by trial and error. The hybrid model predictions are good with the training and very satisfactory with the experimental te st data. The indication is that the latter is a powerful tool for proc ess modelling in biochemical engineering, particularly when limited th eoretical knowledge of the process is available.