An application of neuro-fuzzy technology for analysis of the CO2 capture process

The objective of this paper is to study the relationships among the significant parameters impacting carbon dioxide (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 work adopted a fuzzy logic approach that explores the relationships among the parameters involved in the amine-based post combustion CO2 capture process at the International Test Centre for CO2 Capture (ITC) located in Regina, Saskatchewan of Canada. The key process parameters were selected based on a review of relevant literature and interviews with experts. The adaptive-network-based fuzzy inference system (ANFIS) technique was trained with historical data and generated the membership functions and rules which best interpret the input/output relationships in the process. Four fuzzy inference systems were independently developed for four output parameters, each of which consists of four inputs and 144 rules. The model validation process showed that modeling accuracies of these fuzzy inference systems are within acceptable limits. The developed fuzzy inference systems constitute a knowledge base on the parameters involved in the CO2 capture process, and can be further expanded and improved for prediction and optimization of the CO2 capture process in the future.