Estimation of Carbon Dioxide Equilibrium Adsorption Isotherms Using Adaptive Neuro-Fuzzy Inference Systems (ANFIS) and Regression Models

Removal of CO2 fro m industrial facilities such as refineries and power plants for emission reduction has attracted considerable interest. Among currently used CO2 capturing processes, the use of microporous solids is considered to be one of the most promising approaches. A description of the CO2 adsorption on microporous material focuses on some captivating problems of present adsorption studies. In present study, robust and accurate methods are designed for the estimation of CO2 adsorption onto microporous solids as a function of CO2 partial pressure and temperature. The performance and accuracy of the developed models were tested and validated by their ability to predict, the literature data. It. was concluded that the designed adaptive neuro-fuzzy inference systems (ANFIS) models and mathematical equations demonstrated a superior predictive performance on estimation of CO2 adsorption data over well-known classic adsorption isotherms. Findings of present study indicate that the neuro-fuzzy modeling approach is a practicable method, for analysis and design of CO2 separation and purification technology. (C) 2017 American Institute of Chemical Engineers.