LAUSR

Abstract In this study, gene expression programing (GEP) is utilized to predict of viscosity of branched alkanes. One of the important thermo- physical properties is the viscosity which expresses the resistance of a fluid to flow. The model is developed using a comprehensive database obtained from the literature. The validity of the proposed model is verified by applying it to estimate the viscosity of branched alkanes of a portion of test results that are not included in the analysis. Correlation factor (R2), root mean squared error (RMSE), standard deviation (STD), and average absolute relative deviation (AARD) are used for measuring the models’ performance. As this study is purely computational, 228 experimental data points were gathered from literature for training and validation of the model. Finally, it was found that GEP model is robust and precise in the estimation of literature viscosity data of branched alkanes.