Development of unified correlations for volumetric mass-transfer coefficient and effective interfacial area in bubble column reactors for various gas-liquid systems using support vector regression

Abstract

The objective of this study was to develop a unified correlation for the volumetric mass-transfer coefficient (k_La) and effective interfacial area (a) in bubble columns for various gas-liquid systems using support vector regression (SVR-) based modeling technique. From the data published in the open literature, 1600 data points from 27 open sources spanning the years 1965-2007 for k_La and 1330 data points from 28 open sources spanning the years 1968-2007 for a were collected. Generalized SVR-based models were developed for the relationship between k_La (and a) and each design and operating parameters such as column and sparger geometry, gas-liquid physical properties, operating temperature, pressure, superficial gas velocity, and so on. Further, these models for k_La and a are available online at http://www.esnips.com/web/UICT-NCL. The proposed generalized SVR-based correlations for k_La and a have prediction accuracies of 99.08% and 98.6% and average absolute relative errors (AAREs) of 7.12% and 5.01%, respectively. Also, the SVR-based correlation provided much improved predictions compared to those obtained using empirical correlations from the literature.