Abstract :

Prediction of Dead oil viscosity using experimental measurements is highly exorbitant and time consuming, hence the use of forecasting models. Dead oil viscosity is a very important PVT parameter that solve numerous reservoir engineering problems and one of the most required factors for enhanced oil recovery processes. This study utilized two machine learning algorithms of Artificial   Neural Network (ANN) and Support Vector Machine (SVM) to predict dead oil viscosity. A total number of 243 data set was obtained from PVT report from Niger-Delta, out of which, 70% were used to train the models, 15% for testing and 15% for validation.  Quantitative and qualitative analysis was carried out to compare the performance and reliability of the new developed machine learning models with some selected empirical correlations. The result revealed that the Artificial Neural Network Outperformed Support Vector Machine (SVM) as well as common dead oil viscosity empirical correlations with the best rank of 0.144, highest correlation coefficient of 0.984, Mean Absolute Error (Ea) of 0.205, with a better performance plot, followed by Support Vector Machine model with correlation coefficient of 0.926, Mean Absolute Error (Ea) of 0.199 and the rank of 0.176. The new developed Artificial Neural Network model can potentially replace the empirical models for dead oil viscosity predictions for Niger Delta region.

---

Keywords :

Artificial Neural Network, Dead Oil Viscosity, Empirical Correlation, Machine learning Algorithm, Statical Analysis

---

References :

1. Ahmed, T. (2013). Equations of State and PVT Analysis; Gulf Publishing Company: Houston, TX, USA.
2. McCain, W. D. (1991). “Reservoir fluid property correlations- State of the Art,” SPE Reservoir Engineering, pp 266-272.
3. Rowane, A.J., Babu, V.M., Rokni, H.B., Moore, J.D., Gavaises, M., Wensing, M., Gupta, A., Mchugh, M.A. (2019). “Effect of composition, temperature, and pressure on the viscosities and densities of three diesel fuels”. J. Chem. Eng. Data 64 (12), 5529–5547. https://doi.org/10.1021/acs.jced.9b00652.
4. Safdari, M. and Shadloo, M.S., (2020). “Application of support vector machines for accurate prediction of convection heat transfer coefficient of nanofluids through circular pipes”. Int. J. Numer. Methods Heat Fluid Flow 2017002. https://doi.org/ 10.1108/HFF-09-2020-0555. S
5. Derevich, I.V. and Gromadskaya, R.S. (2002). “Effect of dissolved gases on the viscosity of petroleum”. Theor. Found. Chem. Eng. 36 (6), 583–588.
6. Talebkeikhah, M., Amar, M.N., Naseri, A., Humand, M., Hemmati-Sarapardeh, A., Dabir, B. and Seghier, M.E.A.B. (2020). “Experimental measurement and compositional modeling of crude oil viscosity at reservoir conditions”. J. Taiwan Inst. Chem. Eng. 109, 35–50. https://doi.org/10.1016/j.jtice.2020.03.001.
7. Giwa, S.O., Sharifpur, M., Goodarzi, M., Alsulami, H. and Meyer, J.P. (2021). “Influence of base fluid, temperature, and concentration on the thermophysical properties of hybrid nanofluids of alumina–ferrofluid: experimental data, modeling through enhanced ANN, ANFIS, and curve fitting”. J. Therm. Anal. Calorim. 143 (6), 4149–4167. https://doi.osrg/10.1007/s10973-020-09372-w.
8. Hemmati-Sarapardeh A, Aminshahidy B, Pajouhandeh A. (2016). “A soft computing approach for the determination of crude oil viscosity: light and intermediate crude oil systems”. J Taiwan Inst Chem Eng 59:1–10
9. Bahonar, E. Chahardowli M,  Ghalenoei, Y and  Simjoo, M (2021). “New correlations to predict oil viscosity using data mining techniques”, Journal of Petroleum Science and Engineering https://doi.org/10.1016/j.petrol.2021.109736
10. Beal, C. (1946). “The viscosity of air, water, natural gas, crude oil and its associated gases at oil field temperatures and pressures”. Trans AIME 165:94–115
11. Beggs, H. D. and Robinson, J. R. (1975). “Estimating the viscosity of crude oil systems”. J Pet Technol 27:1140–1141
12. Glaso, O. (1980). “Generalized Pressure-Volume-Temperature Correlations.” J. Petrol. Technol. (32), 785–795. https://doi.org/10.2118/8016-pa
13. Kaye, S.E. (1985). “Offshore California Viscosity Correlations”, Technical Report, No. TS85000940; Chevron Oil Field Research Co. (COFRC): La Habra, CA, USA.
14. Al-Khafaji, A.H., Abdul-Majeed, G.H. and Hassoon, S.F., (1987). “Viscosity correlation for dead, live and undersaturated crude oils”. J. Petrol. Res 6 (2), 1–16.
15. Petrosky, G. E. and Farshad, F.F. (1995). “Viscosity Correlations for Gulf of Mexico Crude Oils”. SPE 29468, Production Operations Symposium, Oklahoma City, Oklahoma,2-4, ISBN 978-1-55563- 448-3.
16. Egbogah, E.O. and Jack N. T. (1990). “An improved temperature-viscosity correlation for crude oil systems”. J. Pet. Sci. Eng., 4, 197–200.
17. Labedi, R. (1982). “Improved correlations for predicting the viscosity of light crudes”. J. Pet. Sci. Engineering. (Journal of Petroleum Science and Engineering), 8, 221– 234.
18. Kartoatmodjo T, and Schmidt, Z. (1994) “Large data bank improves crude physical property correlations”. Oil Gas J 92(27):27
19. De Ghetto G, and Villa, M. (1994). “Reliability analysis on PVT correlations”. In: European petroleum conference, SPE, London, 25–27
20. Bennison, T., (1998). “Prediction of heavy oil viscosity. In: IBC Heavy Oil Field Development”, Conference, vol. 2, p. 4. December.
21. Elsharkawy, A.M., and Alikhan, A.A. (1997). “Correlation for Predicting Solution Gas/Oil Ratio, Oil Formation Volume Factor, and Undersaturated Oil Compressibility”, J. Petrol. Sci. Eng. (17), 291–302. https://doi.org/10.1016/S0920-4105(96)00075-7.
22. Hossain,M.S., Sarica, C., Zhang, H.-Q., Rhyne, L. and Greenhill, K. (2005). “Assessment and development of heavy oil viscosity correlations”. In Proceedings of the SPE International Thermal Operations and Heavy Oil Symposium, Calgary, AB, Canada, 1–3.
23. Naseri, A., Nikazar, M. and Dehghani, S.M. (2005). “A correlation approach for prediction of crude oil viscosities”. J. Pet. Sci. Eng., 47, 163–174
24. Al-amoudi, L.A., Salem, B., Fahd, K., Patil, S. and Baarimah, S.O., (2019). “Development of Artificial Intelligence Models for Prediction of Crude Oil Viscosity”.
25. Ikiensikimama, S. S. (2009). Reservoir Fluid Property Correlations, Chi Ikoku Petroleum Engineering Series, IPS Publications, Port Harcourt.
26. Andrade, E.N. da C. And Group, N. P., 1930. The viscosity of liquids. Nature 125 (3148), 309–310
27. Hadavimoghaddam, F., Ostadhassan, M., Heidaryan, E., Sadri, M. A., Chapanova, I., Popov, E., Cheremisin, A. and Rafieepour, Rafieepour S. (2021). “Prediction of Dead Oil Viscosity: Machine Learning vs. Classical Correlations”, https://doi.org/10.3390/en1404930.
28. Oloso MA, Khoukhi A, Abdulraheem A, and Elshafei M. (2009). “Prediction of crude oil viscosity and gas/oil ratio curves using recent advances to neural networks”. In: SPE/EAGE Reservoir Characterization and Simulation Conference, SPE, Abu Dhabi,UAE, 19–21.
29. Makinde, F.; Ako, C.; Orodu, O. and Asuquo, I. (2012). “Prediction of crude oil viscosity using feed-forward back-propagation neural network

(FFBPNN)”. Pet. Coal, 54, 120–131.

30. Anadu, F. and Mbachu, I. I. (2023). “Gas Compressibility Factor Prediction Using Machining Learning Algorithmic Protocol for Niger – Delta Gas Reservoir”, International Journal of Current Science Research and Review, DOI: 10.47191/ijesrr/V-i10/-16
31. Elsharkawy, A M (1998). “Modeling the properties of crude oil and gas systems using RBF network”. In: SPE Asia pacific oil and gas
32. Naseri, A., Yousefi, S.H., Sanaei, A. and Gharesheikhlou, A.A., (2012). “A neural network model and an updated correlation for estimation of dead crude oil viscosity’. Brazilian J. Petrol. Gas 6 (1), 31–41. https://doi.org/10.5419/bjpg2012-0003..jk,l,
33. Omole O, Falode O. A. and Deng A D. (2009). “Prediction of Nigerian crude oil viscosity using artificial neural network”. Pet Coal 151:181–188
34. Adeeyo, Y.A., and Saaid, I. M., (2017). “Artificial neural network modelling of viscosity at bubblepoint pressure and dead oil viscosity of Nigerian crude oi”l. In: SPE Nigeria Annual International Conference and Exhibition, pp. 95–106. https://doi.org/ 10.2118/189142-ms.
35. Al-amoudi, L.A., Salem, B., Fahd, K., Patil, S., Baarimah, S.O., 2019. Development of Artificial Intelligence Models for Prediction of Crude Oil Viscosity.
36. Sinha, U., Dindoruk, B., Soliman, M., 2020. Machine learning augmented dead oil viscosity model for all oil types. J. Petrol. Sci. Eng. 195, 107603. https://doi.org/ 10.1016/j.petrol.2020.107603.
37. Ghorbani, B., Ziabasharhagh, M. and Amidpour, M. (2014). “A hybrid artificial neural network and genetic algorithm for predicting viscosity of Iranian crude oils”. J. Nat. Gas Sci. Eng., 18, 312–323
38. Duggle, N. (2023). Introduction of Artificial Intelligence A Beginner’s Guide Art Materials , Simple Learn.
39. Terra, J. (2023). Exploring Intelligent Agents in Artificial Intelligent
40. White H. (1989): “Learning in Artificial Neural: A Statistical Perspective”. Neural Computer., 1:425–464.
41. Zhoa, C. Y. Zhang, H.X Liu, M.C, Hua Z.D., and B.T Fan, “Application of Support Vector Machine (SVN) for Prediction Toxic Activity of Different Data Sets”, Toxicology 217, pp. 105-119, 2006.