Machine learning models for predicting characteristics of PVAm membranes for post-combustion CO2 capture application

Facilitated transport membranes fabricated by Polyvinylamine show great potential to competewith convenient carbon capture technologies in a post-combustion CO2/N2 separation, with lowerenergy consumption and zero toxicity. Precise mathematical models are needed to predict membranecharacteristics for designing suitable membrane equipment and optimizing process configuration. Twomain features of a membrane are the Permeance of CO2 gas and CO2/N2 Selectivity that shows theoverall performance of each membrane by considering the solution-diffusion model. Two knownmachine learning algorithms were employed to predict the Permeance and Selectivity of a recentlydeveloped membrane based on its four major parameters. Both MLP-ANN and SVM functions had greatpotential to fit experimental data, while the MLP-ANN method works better for Permeance (R2 equal to0.975) and the SVM method fits Selectivity better (R2 equal to 0.948).

Machine learning models for predicting characteristics of PVAm membranes for post-combustion CO2 capture application Keywords:

CO2 Capture , Polyvinylamine Membrane , Machine Learning , Support vector machine , Artificial neural network