Using Intelligent Methods and Optimization of the Existing Empirical Correlations for Iranian Dead Oil Viscosity

Document Type: paper


1 Prof. of Chemical Eng., Thermokin. Dept.,Chemical Eng. Faculty, Babol University of Technology, Babol.

2 MS. Student of Chemical Eng., Thermokin. Dept.,Chemical Eng. Faculty, Babol University of Technology, Babol.


Numerous empirical correlations exist for the estimation of crude oil viscosities. Most of these correlations are not based on the experimental and field data from Iranian geological zone. In this study several well-known empirical correlations including Beal, Beggs, Glasso, Labedi, Schmidt, Alikhan and Naseri were optimized and refitted with the Iranian oil field data. The results showed that the Beal and the Labedi methods were not suitable for estimation of the viscosity of the Iranian crudes, while the Beggs, Glasso and Schmidt methods gave reasonable results. The Naseri’s correlation and their present method proved to be the best classical methods investigated in this study. Two new intelligent methods to predict the viscosity of Iranian crudes have also been introduced. The study also showed that the neural network and SVM give much better results comparing to classical correlations. It is claimed that this study may provide more exact results for the prediction of Iranian oil viscosity.


[1] Mohaghegh, Sh., Arefi, R., Ameri, S., Amini, Kh. and  Nutter,  R.  (1996). “Petroleum reservoir characterization with the aid of artificial neural networks”, Journal of Petroleum Science and Engineering, Vol. 16, pp. 263-274.

[2] Romero,  C.E.  and  Carter,  J.N.  (2001).  “Using genetic algorithms for reservoir characterization”, Journal of Petroleum Science and Engineering, Vol.  31, pp. 113-123.

[3] Nikravesh, M. and Aminzadeh, F. (2001). “Past, present and future intelligent reservoir characterization trends”, Journal of Petroleum  Science and Engineering, Vol. 31, pp. 67-69.

[4] Esmaeilzadeh, F. and Nourafkan, E. (2009). “Calculation OOIP in oil reservoir by pressure matching method using genetic algorithm”, Journal of Petroleum Science and Engineering Vol. 64, p. 35-44.

[5] El-Sebakhy,  E.A.  (2009).  “Forecasting  PVT properties of crude oil systems based on support vector machines modeling scheme”, Journal of Petroleum Science and Engineering,  Vol.  64, pp. 25-34.

[6] Emera,  M.K.  and  Sarma,  H.K.  (2005).  “Use  of  genetic algorithm to estimate CO-oil minimum miscibility pressure a key parameter in design  of  CO2 miscible floods”, Journal  of  Petroleum  Science and Engineering, Vol. 46, pp. 37-52.

[7] Alomair,  A.,  Elsharkawy,  A.  and  alkandari,  H.(2014). “A viscosity prediction model for  Kuwaiti heavy crude oils at elevated tempera tures”,  Journal  of  Petroleum  Science  and  Engineering,  Vol. 120, pp. 102-110.

[8] Hemmati-sarapardeh, A., Aminshahidy, B., Pa jouhandeh, A., Yousefi, S.A. and  Hosseini-Kaldozakh, S.A. (2016). “A soft computing approach  for the determination of crude oil viscosity:  Light and intermediate crude oil systems”, Journal  of  the  Taiwan  Institute  of  Chemical  Engineers, Vol. 59, pp. 1-10.

[9] El-Hoshoudy, A.N., Farag, A.B., Ali, O.I.M., El- Batanoney, M.H., Desouky, S.E.M. and Ramzy, M. (2013). “New correlations for prediction of viscosity and density of Egyptian oil reservoirs”,  Fuel,  Vol. 112, pp. 277-282.

[10] Sanchez-Minero, F., Sanchez-Reyna, G., Ancheyta, J. and Marroquin, G. (2014). “Comparison of correlations based on API gravity for predicting viscosity of crude oils”,  Fuel,  Vol. 138, pp.  193-199.

[11] Al-Balushi, M., Mjalli, F. S., Al-Wahaibi, T. and  Al-Hashmi, A.Z. (2014), “Parametric study to develop an empirical correlation for undersat urated crude oil viscosity based on the minimum  measured  input  parameters”,  Fuel, Vol.  119, pp. 111-119.

[12] Beal, C. (1946). “Viscosity of air, water,  natural gas, crude oil and its associated gases at oil field temperature and pressures”,  Transactions of the AIME,  Vol. 165, pp. 114-127.

[13] Beggs,  H.D.  and  Robinson,  J.R.  (1975).  “Estimating the viscosity of crude oil system”,  Journal  of  Petroleum  Technology,  Vol.  9,  pp.   1140-1141.

[14] Glaso, O. (1980). “Generalized pressure–volume–temperature  correlation  for  crude  oil  system”, Journal  of  Petroleum  Technology,  Vol.  2, pp.785– 795.

[15] Labedi, R. (1992). “Improved correlations for  predicting the viscosity of light crudes”, Journal  of  Petroleum  Science  and  Engineering ,  vol.   8, pp. 221-234.

[16] Kartoatmodjo, F. and Schmidt, Z. (1994).  “Large  data bank improves crude physical property correlation”,  Oil and  Gas Journal,  Vol. 4, pp. 51- 55.

[17] El-sharkawy, A.M. and Alikhan, A.A. (1999),  “Models for predicting the viscosity of Middle  East crude oils”, Fuel, Vol. 78, pp. 891-903.

[18] Naseri, A., Nikazar, M. and Mousavi Dehghani,  S.A.  (2005).    “A correlation approach for prediction of crude oil viscosities”,  Journal of  Petroleum  Science and Engineering, Vol. 47, pp. 163-174.

[19] Haykin, S. (1994).  Neural Networks: A comprehensive foundation , Prentice Hall.

[20] Lekkas, D. F., Imrie, C.E. and  Lees, M.J. (2001).  “Improved non-linear transfer function and  neural network methods of flow routing for  real-time  forecasting”,  Journal  of  Hydroinformatics,  Vol. 3, pp. 153-164.

[21] Vapnik, V., (1998).  Statistical Learning Theory John Wiley, New York.

[22] Li,  J.Z.,  Liu,  H.X.,  Yao,  X.J.,  Liu,  M.C.,  Hu,  Z.D.,   and Fan, B.T., (2007). “Structure–activity relationship study of oxindole-based inhibitors  of cyclin-dependent kinases based on least- squares support vector machines”, Analytica  Chimica Acta , Vol. 581, pp. 333-342.