Mixed MDEA-PZ amine solutions for CO2 capture: Modeling and optimization using RSM and ANN approaches

Abstract

The process of capturing and reducing carbon dioxide (CO2) emissions through chemical absorption is widely acknowledged as the most effective technique, especially in dealing with natural gas streams or flue gases produced by fossil fuel power plants. In this research, we delve into the modeling and optimization of CO2 mass transfer flux (NCO₂). To accomplish this, employed a combination of Piperazine (PZ) and Methyldiethanolamine (MDEA) amines for CO2 absorption. The approach utilized artificial neural networks (ANN) and response surface methodology (RSM). We used Pi-Buckingham theory to derive dimensionless numbers for the input variables in both ANNs and RSM. The resulting models offer satisfactory outcomes by effectively capturing the influence of independent variables and their interactions on the objective function, thereby optimizing the CO2 capture process. The RSM approach employs a quadratic model. Through optimization, neural networks were fine-tuned to achieve the lowest error and the closest fit to experimental data. Both ANNs and RSM models demonstrated acceptable performance in predicting experimental data, with maximum R2 values of 0.99924 and 0.9663, respectively. Considering the mean squared error of 5.2 × 10−4 obtained from the simulations, the ANN is recommended as the preferred method for developing absorption simulation models.

Keywords

• CO2 capture
• ANN
• RSM
• MDEA-PZ
• Pi-Buckingham