Neural network modeling of Hydantoinase production

This paper describes the use of a back propagation neural network modeling technique for the prediction and forecasting of production of Hydantoinase in a fed batch fermentor. Forecasting biomass production is useful for real time estimation as well as for on-line soft sensor process control. This artificial neural network model was found to be superior to statistical nonlinear regression model. Several transfer functions were tried to arrive at the best set of results.