AI models for correlation of physical properties in system of 1DMA2P-CO2-H2O

In this work, the density, viscosity, and specific heat capacity of pure 1-dimethylamino-2-propanol (1DMA2P) as well as aqueous unloaded and CO2-loaded 1DMA2P solution (with a CO2 loading of 0.04-0.70 mol CO2/mol amine) were measured over the 1DMA2P concentration range of 0.5-3.0 mol/L and temperature range of 293-323 K. The observed experimental results of these thermophysical properties of the 1DMA2P-H2O-CO2 system were correlated using empirical models as well as artificial neural network (ANN) models (namely, back-propagation neural network [BPNN] and radial basis function neural network [RBFNN] models). It was found that the developed BPNN and RBFNN models could predict the experimental results of 1DMA2P-H2O-CO2 better than correlations using empirical models. The results could be treated as one of the accurate and potential methods to predict the physical properties for aqueous amine CO2 absorption systems.