NEURAL SIMULATION OF AN UNSTEADY-STATE CONTINUOUS RECOMBINANT FERMENTATION WITH IMPERFECT MIXING

A continuous fermentation based on a recombinant Escherichia coli stra in producing tryptophan synthetase has been simulated by a back-propag ation neural network. Data for the network were generated through know n kinetics applied to a reactor model with an adjustable degree of mac romixing of the broth. A network with just one hidden layer performed satisfactorily for both poor and good macromixing. The best performanc e was at an intermediate level of mixing, in the region of maximum pro ductivity of the recombinant protein.