%0 Journal Article
%T Development of a numerical model prediction of condensate stabilization unit of south pars gas processing plant
%J American Journal of Oil and Chemical Technologies
%I Petrotex Library
%Z 2326-6570
%A Adib, H
%A Falsafi, A.R
%A Iranshahi, D
%D 2018
%\ 06/01/2018
%V 6
%N 2
%P 130-142
%! Development of a numerical model prediction of condensate stabilization unit of south pars gas processing plant
%K Gas sweetening plant
%K Stabilizer column
%K Least square support vector machine
%K RBF
%R
%X In present study, Least Square Support Vector Machine (LSSVM) and Radial Basis Function (RBF) are employed to develop modelsto predict Reid vapor pressure of a sour condensate which is the output variable of stabilizer column of Assaluyeh industrial naturalgas sweetening plant. A set of 4 input/output plant data each consisting of 660 data has been used to train, optimize, and test themodels. Model development that consists of training, optimization and test was performed using randomly selected 80%, 10%, and10% of available data respectively. Test results from the LSSVM developed model showed to be in better agreement with operatingplant data. Squared correlation coefficients for developed models are 0.83 and 0.91 for RBF and LSSVM based results, respectively.According to the results of the present case study, LSSVM could be regarded as a reliable accurate approach for modeling of a naturalgas processing plant.
%U