NEURAL NETWORKS AS SOFTWARE SENSORS IN ENZYME-PRODUCTION

Industrial applications of enzyme technology are rapidly increasing. O n-line control of enzyme production processes, however, is difficult, owing to the uncertainties typical of biological reactions and to the lack of suitable sensors. We demonstrate that well-trained feedforward backpropagation neural networks with one hidden layer can be employed to overcome such problems with no need for a priori knowledge of the relationships of the process variables involved. Neural network progra ms were written in Microsoft Visual C++ for Windows and implemented in a personal computer. The goodness of fit of the trained neural networ k to the reference data was determined by the coefficient of determina tion R(2). On-line slate estimation and multi-step ahead prediction of enzyme activity and biomass concentration, both in a yeast lipase and fungal glucoamylase production could be satisfactorily carried out. R esults showed an excellent fit for estimated lipase activity (R(2) = 0 .988) and biomass concentration (R(2) = 0.989). In glucoamylase produc tion, both enzyme activity and biomass concentration could also be rel iably predicted for 2 time intervals (10 h) ahead with only on-line me asurable parameter values as the input data. (C) 1997 Elsevier Science B.V.