prediction of equilibrium solubility of co2 in aqueous alkanolamines through artificial neural network

Abstract

The removal of acid gases from gas streams by using suitable solvent like alkanolamine, commonly referred to as gas sweetening, is a technology that has been in use industrially for over half a century. In this work artificial neural network (ANN) has been used to predict the equilibrium solubility of CO2 over the alkanolamine solvents N-methyldiethanolamine (MDEA) and 2-amino-2-methyl-1-propanol (AMP) instead of using any thermodynamic model. A multilayer feed forward network with back propagation training algorithm has been used here in an effort to predict the VLE data of CO2-MDEA-H2O and CO2-AMP-H2O system with a comparable accuracy to those predictions based on rigorous thermodynamic model. It has been found that the predictions are within accuracy of 5% for 95 % of the data.