Prediction of asphaltene precipitation using support vector regression tuned with genetic algorithms

Abstract

Due to the severe and costly problems caused by asphaltene precipitation in petroleum industry, developing a quick and accurate model, to predict the asphaltene precipitation under different conditions, seems crucial. In this study, a new model, namely genetic algorithm -support vector regression (GA-SVR) is proposed, which is applied to predict the amount of asphaltene precipitation. GA is used to select the best optimal values of SVR parameters and kernel parameter, simultaneously, to increase the generalization performance of the SVR. The GA-SVR model is trained and tested on the experimental data sets reported in literature. The performance of the GA-SVR model is compared with two scaling equation models, using statistical error measures and graphical analyses. The results show that the prediction performance of the proposed model, is highly reliable and satisfactory.

Keywords

Asphaltene precipitation / Prediction / support Vector Regression (SVR) / Genetic Algorithm (GA) / Parameter optimization

References

[1] T. Fan, J.S. Buckley, Rapid and accurate SARA analysis of medium gravity crude oils, Energy & Fuels 16 (6) (2002) 1571-1575.

[2] O.C. Mullins, E.Y. Sheu, Structures and Dynamics of Asphaltenes, Springer, 1999.

[3] K.J. Leontaritis, G. Ali Mansoori, Asphaltene deposition: a survey of field experiences and research approaches, J. Petrol. Sci. Eng. 1 (3) (1988) 229-239.

[4] L.H. Ali, K.A. Al-Ghannam, Investigations into asphaltenes in heavy crude oils. I. Effect of temperature on precipitation by alkane solvents, Fuel 60 (11) (1981) 1043-1046.

[5] H. Van Poollen, Fundamentals of Enhanced Oil Recovery, 1980.

[6] M. Blunt, F.J. Fayers,F.M. Orr Jr., Carbon dioxide in enhanced oil recovery, Energy Convers. Manag. 34 (9) (1993) 1197-1204.

[7] R.N. Mehta, V.R. Jain, Microbial enhanced oil recovery, in: Separation Processes: Emerging Technologies for Sustainable Development, 434, 2009.

[8] R. Thawer, D.C. Nicoll, G. Dick, Asphaltene deposition in production facilities, SPE Prod. Eng. 5 (04) (1990) 475-480.

[9] Z.M. Liu, G.Y. Yang, Y. Lu, B.X. Han, H.K. Yan, Phase equilibria of the CO₂-Jiangsu crude oil system and precipitation of heavy components induced by supercritical CO2, J. Supercrit. Fluids 16 (1) (9/15/1999) 27-31.

[10] K. Leontaritis, J. Amaefule, R. Charles, A systematic approach for the prevention and treatment of formation damage caused by asphaltene deposition, SPE Prod. Facil. 9 (03) (1994) 157-164.

[11] A.M. Mofidi, M. Edalat, A simplified thermodynamic modeling procedure for predicting asphaltene precipitation, Fuel 85 (17) (2006) 2616-2621.

[12] A. Hirschberg, L. DeJong, B. Schipper, J. Meijer, Influence of temperature and pressureonasphalteneflocculation, Soc.Petrol.Eng. J. 24(03) (1984)283-293.

[13] L.X. Nghiem, D.A. Coombe, S. Farouq Ali,Compositional simulation of asphaltene deposition and plugging, in:SPE Annual Technical Conference, 1998, pp. 129-140.

[14] K. Leontaritis, G. Mansoori, Asphaltene flocculation during oil production and processing: a thermodynamic colloidal model, in: Paper SPE, 16258, 1987, pp. 4-6.

[15] H. Pan, A. Firoozabadi, A thermodynamic micellization model for asphaltene precipitation: Part I: Micellar size and growth,in: SPE Annual Technical Conference, 1996, pp. 593-605.

[16] H. Rassamdana, B. Dabir, M. Nematy, M. Farhani, M. Sahimi, Asphalt flocculation and deposition: I. The onset of precipitation, AIChE J. 42 (1) (1996) 10-22.

[17] A.K. Menshad, A.M. Mofidi, F. Shariatpanahi, M. Edalat, Developing of scaling equation with function of pressure to determine onset of asphaltene precipitation, J. Jpn. Petrol. Inst. 51 (2) (2008) 102-106.

[18] S. Ashoori, A. Abedini, R. Abedini, K.Q. Nasheghi, Comparison of scaling equation with neural network model for prediction of asphaltene precipitation, J. Petrol. Sci. Eng. 72 (1) (2010) 186-194.

[19] M.A. Ahmadi, Prediction of asphaltene precipitation using artificial neural network optimized by imperialist competitive algorithm, J. Petrol. Explor. Prod. Technol. 1 (2-4) (2011) 99-106.

[20] A.H. Mohammadi, A. Eslamimanesh, F. Gharagheizi, D. Richon, A novel method for evaluation of asphaltene precipitation titration data, Chem. Eng. Sci. 78 (2012) 181-185.

[21] Y.F. Hu, T.M. Guo, Effect of temperature and molecular weight of n-alkane precipitants on asphaltene precipitation, Fluid Phase Equilibria 192 (1) (2001) 13-25.

[22] V. Vapnik, The Nature of Statistical Learning Theory, springer, 2000.

[23] K. Duan, S.S. Keerthi, A.N. Poo, Evaluation of simple performance measures for tuning SVM hyperparameters, Neurocomputing 51 (2003) 41-59.

[24] V. Kecman, Support Vector Machines: Theory and Applications, Springer, 2005, pp. 1-47.

[25] C. Campbell, N. Cristianini, J. Shawe-Taylor,Dynamically adapting kernels in support vector machines, Adv. Neural Inf. Process. Syst. 11 (1999) 204-210.

[26] Y. Zhu, C. Li, Y. Zhang,Advances in Neural NetworkseISNN 2004, Springer, 2004, pp. 518-523.

[27] P. Rivas-Perea, J. Cota-Ruiz, J.P. Venzor, D.G. Chaparro, J.G. Rosiles, LP-SVR model selection using an inexact globalized Quasi-Newton Strategy, J. Intelligent Learn. Syst. Appl. 5 (2013) 19.

[28] J.E. Wang, J.Z. Qiao, Parameter selection of SVR based on improved K-Fold Cross validation, Appl. Mech. Mater. 462 (2014) 182-186.

[29] J.H. Holland, Adaptation in Natural and Artificial Systems:an Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence, U Michigan Press, 1975.

[30] D.E. Goldberg, Genetic Algorithms in Search, Optimization, and Machine Learning, Addison-Wesley, 1989.

[31] Global Optimization Toolbox User's Guide, The MathWorks, Inc, 2014.

[32] Canu S., Grandvalet Y., Guigue V., and Rakotomamonjy A. SVM and Kernel Methods Matlab Toolbox. 2005.