Determination of bubble size distribution in a bubble column reactor using artificial neural network

In the present study, bubble size distribution (BSD) within a bubble column reactor was modeled using an artificial neural network (ANN). The fluids tested in the bubble column consisted of 11 different oil mixtures, each containing two different oils. Pure water was also tested. BSD was determined for various superficial gas velocities by photographing the state of the fluid. It was found that bubble size as well as distribution depended on parameters, such as gas flow rate, liquid properties, sparger pore diameter and distance from the sparger in the column. The proposed ANN model is based on more than 4500 data points collected for BSD estimation. Through statistical testing, it was found that the model has a correlation coefficient greater than 70% and upon experimental testing was found to better predict BSD than currently used correlations found in the literature. Copyright (c) 2011 Curtin University of Technology and John Wiley & Sons, Ltd.