Estimation of the volumetric oxygen transfer coefficient (k(L)a) from the gas balance and using a neural network technique

This paper reports on the use of the gas balance and dynamic methods to obt ain an estimate of the volumetric oxygen transfer coefficient (k(L)a) in a conventional reactor during the growth phase of the microorganism Cephalosp orium acremonium. A new way of calculating k(L)a by the dynamic method empl oying an electrode with a slow response, is proposed. The calculated values of k(L)a were used in the training of a feedforward neural network, for wh ich the inputs were the parameter measurements of the related variables. Th e neural network technique proved effective, predicting values of k(L)a acc urately from input data not used during the training phase. In contrast, th e gas balance method was shown to be less useful. This could be attributed to the poor data obtained with the apparatus used to measure the oxygen in the exhaust gas, explained by the low rate of oxygen consumption by the mic roorganism.