Estimation of oxygen mass transfer coefficient in stirred tank reactors using artificial neural networks

The estimation of volumetric mass transfer coefficient, k(L)a, in stirred t ank reactors using artificial neural networks has been studied. Several ope rational conditions (N and V-s), properties of fluid (mu (a)) and geometric al parameters (D and T) have been taken into account. Learning sets of inpu t-output patterns were obtained by k(L)a experimental data in stirred tank reactors of different volumes. The inclusion of prior knowledge as an appro ach which improves the neural network prediction has been considered. The h ybrid model combining a neural network together with an empirical equation provides a better representation of the estimated parameter values. The out puts predicted by the hybrid neural network are compared with experimental data and some correlations previously proposed in the literature for tanks of different sizes. (C) 2001 Elsevier Science Inc. All rights reserved.