Evolving a prediction model based on machine learning approach for hydrogen sulfide removal from sour condensate of south pars natural gas processing plant

• H2S concentration and RVP of sweet condensate of a natural gas processing plant were investigated.
• SVM approach has been applied to predict output variables of this industrial plant.
• The effect of various operating variables on stabilizer column of this plant has been investigated.
• High accuracy SVM model prediction for this industrial plant has been obtained.
• SVM as a modeling tool showed to be applicable in oil and gas industry.

In present study Support Vector Machine (SVM) is employed to develop a model to estimate process output variables of stabilizer column of an industrial natural gas sweetening plant. The developed model is evaluated by process operating data of south pars natural gas processing plant in Asalouyeh/Iran. A set of 6 input/output plant data each consisting of 660 data has been used to train, optimize, and test the model. Model development that consists of training, optimization and test was performed using randomly selected 80%, 10%, and 10% of available data respectively. Test results from the SVM based model showed to be in better agreement with operating plant data. The minimum calculated squared correlation coefficient for estimated process variables are 0.97 for H2S concentration and 0.94 for Reid vapor pressure (RVP). Based on the results of this case study SVM proved that it can be a reliable accurate estimation method.