Prediction of carbon dioxide loading capacity in amino acid salt solutions as new absorbents using artificial neural network and Deshmukh–Mather models

摘要: Abstract The aim of this work is solubility prediction carbon dioxide (CO 2 ) in amino acid salt solutions as new absorbents over wide ranges operating conditions, utilizing Artificial Neural Network (ANN) and Deshmukh–Mather models. pH solutions, overall molar concentration, partial pressure CO , apparent molecular weight temperature was picked input variables the proposed ANN. A group 1364 literature experimental data points for have been congregated from to build network. best architecture developed ANN including numbers hidden layer, transfer function number neurons were attained by these points. Also solution modeled using model. Results show that has better performance compared trained Levenberg–Marquardt back-propagation algorithm two layers with 8 7 Tan-sigmoid output layers. model results ability predict accurately H S dissimilar correlation coefficient (R 0.9982 Average Relative Deviation (ARD) value 3.2976.