Application of Genetic Algorithm Based Support Vector Machine Model in Second Virial Coefficient Prediction of Pure Compounds

Document Type : Research Article


1 Faculty of Engineering Modern Technologies, Amol University of Special Modern Technologies, 4616849767 Amol, I.R. IRAN

2 National Iranian South Oil Company, Ahwaz, I.R. IRAN

3 Faculty of Chemical Engineering, Babol University of Technology, Babol, I.R. IRAN


In this work, a Genetic Algorithm boosted Least Square Support Vector Machine model by a set of linear equations instead of a quadratic program, which is improved version of Support Vector Machine model, was used for estimation of 98 pure compounds second virial coefficient. Compounds were classified to the different groups. Finest parameters were obtained 
by Genetic Algorithm method for training data. The accuracy of the Genetic Algorithm boosted Least Square Support Vector Machine was compared with four empirical equations that are well-known and are claimed can predict all compounds second virial coefficients (Pitzer, Tesonopolos, Gasanov RK and Long Meng). Results showed that in all classes of compounds, the Genetic Algorithm boosted Least Square Support Vector Machine method was more accurate than these empirical correlations. The Average Relative Deviation percentage of overall data set was 2.53 for the Genetic Algorithm boosted Least Square Support Vector Machine model while the best Average Relative Deviation percentage for empirical models (Tesonopolos) was 15.38. When the molecules become more complex, the difference in accuracy becomes sharper for empirical models where the proposed Genetic Algorithm boosted Least Square Support Vector Machine model have predicted good results for classes of compounds that empirical correlations usually fail to give good estimates.


Main Subjects

[1] Meng L., Duan Y.Y., Prediction of the Second Cross Virial Coefficients of Nonpolar Binary MixturesFluid Phase Equilib.238(2): 229-238 (2005).
[2] Meng L., Duan Y.Y., Li L., Correlations for Second and Third Virial Coefficients of Pure FluidsFluid Phase Equilib., 226(10): 109-120 (2004).
[3] Rashtchian D., Ovaysi S., Taghikhani V., Ghotbi C., Application of the Genetic Algorithm to Calculate the Interaction Parameters for Multiphase and Multicomponent SystemsIranian Journal of Chemistry and Chemical Engineering (IJCCE)26(3): 89-102 (2007).
[5] Rakel N., Bauer K.C., Galm L., Hubbuch J., From Osmotic Second Virial Coefficient (B22) to Phase Behavior of a Monoclonal AntibodyBiotechnol. Progr.31(2): 438-451 (2015).
[6] Tomberli B., Goldman S., Gray C., Predicting Solubility in Supercritical Solvents Using Estimated Virial Coefficients and Fluctuation TheoryFluid Phase Equilib., 187: 111-130 (2001).
[7] Herhut M., Brandenbusch C., Sadowski G., Modeling and Prediction of Protein Solubility Using the Second Osmotic Virial CoefficientFluid Phase Equilib.422(25): 32-42 (2016).
[8] Pitzer K.S., Curl Jr R., The Volumetric and Thermodynamic Properties of Fluids. III. Empirical Equation for the Second Virial Coefficient1J. Am. Chem. Soc., 79(10): 2369-2370 (1957).
[9] Tsonopoulos C., An empirical Correlation of Second Virial CoefficientsAIChE Journal20(2): 263-272 (1974).
[10] Di Nicola G., Falone M., Pierantozzi M., Stryjek R., An Improved Group Contribution Method for the Prediction of Second Virial CoefficientsIndustrial & Engineering Chemistry Research53(35): 13804-13809 (2014).
[11] Di Nicola G., Coccia G., Pierantozzi M., Falone M., A Semi-Empirical Correlation for the Estimation of the Second Virial Coefficients of RefrigerantsInternational Journal of Refrigeration68: 242-251 (2016).
[12] Vetere A., An Empirical Model for Calculating Second Virial CoefficientsChem. Eng. Sci.43(12): 3119-3127 (1988).
[13] Vetere A., On the Calculation of the Second Virial Coefficients of Pure Compounds and MixturesChem. Eng. Sci.46(7): 1787-1794 (1991).
[14] Vetere A., An Improved Method to Predict the Second Virial Coefficients of Pure CompoundsFluid Phase Equilib.164(1): 49-59 (1999).
[15] Mathias P.M., The Second Virial Coefficient and the Redlich-Kwong EquationIndu. Eng. Chem. Res.42(26): 7037-7044 (2003).
[16] Estela-Uribe J., Jaramillo J., Generalised Virial Equation of State for Natural Gas SystemsFluid Phase Equilib.231(1): 84-98 (2005).
[17] Vapnik V., "Statistical Learning Theory", Wiley, New York, (1998).
[18] Torabi Dashti H., Masoudi-Nejad A., Zare F., Finding Exact and Solo LTR-Retrotransposons in Biological Sequences Using SVMIranian Journal of Chemistry and Chemical Engineering (IJCCE)31(2): 111-116 (2012).
[19] Peng Z., Yin H., ECT and LS-SVM Based Void Fraction Measurement of Oil-Gas Two-Phase FlowIranian Journal of Chemistry and Chemical Engineering (IJCCE)29(1): 41-50 (2010).
[20] Adankon M.M., Cheriet M., Support Vector MachineEncyclopedia of Biometrics, 1504-1511 (2015).
[21] Suykens J.A.K., Vandewalle J., Least Squares Support Vector Machine ClassifiersNeural process. lett.9(3): 293-300 (1999).
[23] Afshari S., Aminshahidy B., Pishvaie M.R., Well Placement Optimization Using Differential Evolution AlgorithmIranian Journal of Chemistry and Chemical Engineering (IJCCE)34(2): 109-116 (2015).
[24] Lv Y., Liu J., Yang T., Zeng D., A Novel Least Squares Support Vector Machine Ensemble Model for NOx Emission Prediction of a Coal-Fired BoilerEnergy55(15): 319-329 (2013).
[25] Niazi A., Jameh-Bozorghi S., Nori-Shargh D., Prediction of Toxicity of Nitrobenzenes Using ab Iinitio and Least Squares Support Vector MachinesJ. Hazard. Mater.151(2): 603-609 (2008).
[26] Zendehboudi A., Tatar A., Li X., A comparative Study and Prediction of the Liquid Desiccant Dehumidifiers Using Intelligent ModelsRenewable Energy114: 1023-1035 (2017).
[27] Li C.H., Zhu X.J., Cao G.Y., Sui S., Hu M.R., Identification of the Hammerstein Model of a PEMFC Stack Based on Least Squares Support Vector MachinesJ. Power Sources175(1): 303-316 (2008).
[28] Wang X., Chen J., Liu C., Pan F., Hybrid Modeling of Penicillin Fermentation Process Based on Least Square Support Vector MachineChem. Eng. Res. Des.88(4): 415-420 (2010).
[29] Li L., Su H., Chu J., Modeling of Isomerization of C8 Aromatics by Online Least Squares Support Vector MachineChin. J. Chem. Eng.17(3): 437-444 (2009).
[31] Torabi Dashti H., Masoudi-Nejad A., Mining Biological Repetitive Sequences Using Support Vector Machines and Fuzzy SVMIranian Journal of Chemistry and Chemical Engineering (IJCCE)29(4): 1-17 (2010).
[32] Li J., Liu H., Yao X., Liu M., Hu Z., Fan B., Structure-Activity Relationship Study of Oxindole-Based Inhibitors of Cyclin-Dependent Kinases Based on Least-Squares Support Vector MachinesAnal. Chim. Acta581(2): 333-342 (2007).
[33] Tayyebi S., Shahrokhi M., Bozorgmehry Boozarjomehry R., Fault Diagnosis in a Yeast Fermentation Bioreactor by Genetic Fuzzy SystemIranian Journal of Chemistry and Chemical Engineering (IJCCE)29(3): 61-72 (2010).
[35] Sastry K., Goldberg D.E., Kendall G., "Genetic Algorithms, In: Burke E., Kendall G., editors Search Methodologies", Springer, Boston, MA (2014).