Bubble size is one of the key parameters in the design of two-phase gas-liq
uid bubble column reactors. Accurate knowledge of this parameter is essenti
al for the prediction of gas holdup, heat and mass transfer coefficients. T
he previous findings, particularly with respect to the influence of orifice
size and physical proper-ties of the liquid phase on bubble size, are ofte
n of contradictory nature. In this paper, extensive new experimental result
s are presented for regions where published data are insufficient. The suit
ability of artificial neural networks for identification of the process var
iables and modeling is evaluated. The Radial Basis Function (RBF) neural ne
twork architecture was used successfully to generate a nonlinear correlatio
n for the prediction of bubble diameter. This correlation predicts the pres
ent data and the control data of other investigators with excellent accurac
y.