Prediction of CO2 Mass Transfer Flux in Amine Solutions Using Neural Networks

In this work, multilayer perceptron network are used to predict the mass transfer flux of CO2 in Piperazine solution. The effective parameters on the absorption flux of CO2 such as interfacial and bulk concentration, CO2 loading, ratio of diffusion coefficient of gas to liquid of CO2, ratio of the CO2 partial pressure to the total pressure, ratio of film thickness of gas to liquid and the film parameter as input variables and mass transfer flux of CO2 as output variables were selected. Experimental data presented in the literature were used for training and evaluating the multilayer neural network of Perceptron. A total of 104 experimental data were used and total concentrations of piperazine were 2-8 mol/lit. The predicting results of neural network indicated that the mean square error for mass transfer flux was 8.61%. In addition, the results of neural network were compared with the predictions of other researchers and the findings revealed that the artificial neural network computes the mass transfer flux of CO2 more accurately and quickly.