PRELIMINARY SCREENING OF NEURAL-NETWORK CONFIGURATIONS FOR BIOREACTORAPPLICATIONS

A methodology and a computer code have been devised to perform a preli minary analysis of six types of neural networks commonly employed for bioreactor problems. Both static and time-varying data can be analysed , and the values of the parameters and/or sampling times can be chosen according to the system behavior. The results help to select a suitab le network configuration for detailed training and application. This i s illustrated for a fed-batch fermentation to produce recombinant beta -galactosidase.