Estimation of water-hydrocarbon mutual solubility in gas processing operations using an intelligent model

An accurate prediction of the mutual solubilities of hydrocarbons and water is extremely useful in oil, gas, and chemical industries. Estimating the solubility of hydrocarbons in water is required to describe their phase distribution through the removal process and also in the design of separation equipment. The current study plays emphasis on applying the predictive model based on the least square support vector machine (LSSVM) to estimate mutual water-hydrocarbon solubility at a wide range of conditions. A genetic algorithm (GA) was employed to choose and optimize hyperparameters (γ and σ²), which are embedded in LSSVM model. Utilization of this model showed high competence of the applied model in terms of coefficient of determination (R²) of 0.9998 and 0.9994, Average absolute relative deviation (AARD) of 1.1378 and 1.12459 from experimental values for predicted water solubility in hydrocarbons and hydrocarbon solubility in water, correspondingly. Using this method is quite simple and accurate to determine the mutual water-hydrocarbon solubility with negligible uncertainty.