PHENOMENOLOGICAL AND NEURAL-NETWORK MODELING OF CEPHALOSPORIN-C PRODUCTION BIOPROCESS

Cephalosporin C production process with Cephalosporium acremonium ATCC 48272 in synthetic medium was investigated and the experimental resul ts allowed the development of a mathematical model describing the proc ess behavior. The model was able to explain fairly well the diauxic ph enomenon, higher growth rate during the glucose-consumption phase, and the production occurring only in the sucrose-consumption phase. Moreo ver, the process was simulated utilizing the neural-networks technique . Two feed-forward neural-networks with one hidden layer were employed . Both models, phenomenological and neural-networks based, satisfactor ily describe the bioprocess. The difficulties in determining kinetic p arameters are avoided when neural networks are utilized.