Abstract
Rigorous analysis of the determinants of volumetric mass transfer coefficient (kLa) and its accurate forecasting are of vital importance for effectively designing and operating stirred reactors. Majority of the available literature is limited to systems with low solids concentration, while there has always been a need to investigate the gas-liquid hydrodynamics in tanks handling high solid loadings. Several models have been proposed for predicting kLa values, but the application of neuro-fuzzy logic for modeling kLa based on combined operational and geometrical conditions is still unexplored. In this paper, an ANFIS (adaptive neuro-fuzzy inference system) model was designed to map three operational parameters (agitation speed (RPS), solid concentration, superficial gas velocity (cm/s)) and one geometrical parameter (number of curved blades) as input data, to kLa as output data. Excellent performance of ANFIS's model in predicting kLa values was demonstrated by various performance indicators with a correlation coefficient of 0.9941.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: Iranian Journal of Chemistry & Chemical Engineering-international English Edition
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
