Abstract
b Dipartimento di Ingegneria Industriale (DIIn), Università degli Studi di Salerno, via Giovanni Paolo II 132, 84084 Fisciano (SA), Italy, michele.miccio@unisa.itThis work proposes, through simulations in the Matlab/Simulink software environment, a neural network predictive adaptive fuzzy control (NNPAFC) of a penicillin production process taking place in a batch-fed reactor. The results of such an implementation are presented and discussed. The outcomes of the simulations under realistic process control conditions confirm that this control strategy is, more than the others, a suitable strategy for the production of penicillin. This will ensure the production of high-quality penicillin and, at the same time, guarantee high production rates, maximizing penicillin yield, and minimizing waste of raw materials and production time.
