|
Abstract
|
In this communication, modeling of carbon dioxide absorption by various amino acid
solutions is presented as a function of operational parameters using the Least-Squares Support
Vector Machine (LSSVM) algorithm joint with three different evolutionary algorithms, namely
Genetic Algorithm (GA), Particle Swarm Optimization (PSO) and Hybrid GA and PSO
(HGAPSO). A databank containing 255 data of carbon dioxide absorption by amino acids of
potassium taurate, potassium glycinate, potassium prolinate, and potassium lysinate at different
temperatures, partial pressures, and concentrations was prepared from different sources to trainand test the proposing algorithms. The R2 values of LSSVM optimized by HGAPSO, PSO and GA
are 0.9944, 0.9915 and 0.9891, respectively and the various errors were determined close to zero.
On the other hand, the visual comparison of models outputs and actual carbon dioxide adsorption
was employed to clarify performance of the models. During comparison analysis, it was found that
the LSSVM- HGAPSO is the most accurate model for estimation of carbon dioxide loading. Also,
comparison of our proposed models with previously-reported artificial neural network indicates
the impressive estimation capability of LSSVM algorithm. According to sensitivity analysis, it
becomes obvious that pressure is the most effective parameter on carbon dioxide absorption.
|