Applications of three data analysis techniques for modeling the carbon dioxide capture process

The objective of this paper is to study the relationships among the significant parameters impacting CO2 production. An enhanced understanding of the intricate relationships among the process parameters enables prediction and optimization, thereby improving efficiency of the CO2 capture process. Our modeling study used the operational data collected over a 3-year period from the amine-based post combustion CO2 capture process at the International Test Centre of CO2 Capture (ITC) located in Regina, Saskatchewan of Canada. This paper describes the data modeling process using the approaches of: (1) statistical study, (2) artificial neural network (ANN) modeling combined with sensitivity analysis (SA), and (3) neuro-fuzzy technique. It was observed that the neuro-fuzzy modeling technique generated the most accurate predictive models and best support explication of the nature of the relationships among the key parameters in the CO2 capture process.