Model based in neural networks for the prediction of the mass transfer coefficients in bubble columns. Study in Newtonian and non-Newtonianian fluids

A comprehensive study for the prediction of the volumetric transfer coefficient kLa with Newtonian and Non-Newtonian fluids in bubble columns is the objective of this work. The evaluation of the hydrodynamic characteristics of the bubble columns and delineated the different hydrodynamic regimes considering column geometry, gas flow, liquid height and type of fluid (Newtonian and non-Newtonian) suggest a general applicability of the proposed model. A new learning pattern based in the design parameters of the bubble columns is proposed.