Oil Formation Volume Factor Determination Through a Fused Intelligence

• Autorzy: Gholami A.

Identyfikatory

DOI

10.1515/acgeo-2016-0099

• Języki publikacji: EN

Abstrakty

EN

Volume change of oil between reservoir condition and standard surface condition is called oil formation volume factor (FVF), which is very time, cost and labor intensive to determine. This study proposes an accurate, rapid and cost-effective approach for determining FVF from reservoir temperature, dissolved gas oil ratio, and specific gravity of both oil and dissolved gas. Firstly, structural risk minimization (SRM) principle of support vector regression (SVR) was employed to construct a robust model for estimating FVF from the aforementioned inputs. Subsequently, an alternating conditional expectation (ACE) was used for approximating optimal transformations of input/output data to a higher correlated data and consequently developing a sophisticated model between transformed data. Eventually, a committee machine with SVR and ACE was constructed through the use of hybrid genetic algorithm-pattern search (GA-PS). Committee machine integrates ACE and SVR models in an optimal linear combination such that makes benefit of both methods. A group of 342 data points was used for model development and a group of 219 data points was used for blind testing the constructed model. Results indicated that the committee machine performed better than individual models.

Słowa kluczowe

EN

PVT; ACE; support vector regression; SVR; oil formation volume factor; FVF; alternating conditional expectation

PL

PVT; ACE; Regresja wektora wsparcia; SVR

• Wydawca: Instytut Geofizyki PAN ; Springer
• Czasopismo: Acta Geophysica
• Rocznik: 2016
• Tom: Vol. 64, no. 6
• Strony: 2510--2529
• Opis fizyczny: Bibliogr. 59 poz.

Twórcy

autor

Gholami A.

• Reservoir Engineering Division, Iranian Offshore Oil Company, Tehran, Iran

Bibliografia

• Afshar, M., A. Gholami, and M. Asoodeh (2014), Genetic optimization of neural network and fuzzy logic for oil bubble point pressure modeling, Korean. J. Chem. Eng. 31, 3, 496-502, DOI: 10.1007/s11814-013-0248-8.
• Ahmed, T. (2000), Reservoir Engineering Handbook, 2th ed., Gulf Professional Publishing, Burlington, 863 pp.
• Al-Anazi, A.F., and I.D. Gates (2010), Support vector regression for porosity prediction in a heterogeneous reservoir: A comparative study, Comput. Geosci. 36, 12, 1494-1503, DOI: 10.1016/j.cageo.2010.03.022.
• Al-Marhoun, M.A. (1988), PVT correlations for Middle East crude oils, J. Petrol. Technol. 40, 5, 650-666, DOI: 10.2118/13718-PA.
• Al-Marhoun, M.A., and E.A. Osman (2002), Using artificial neural networks to develop new PVT correlations for Saudi crude oils, SPE Paper 78592, DOI: 10.2118/78592-MS.
• Almehaideb, R.A. (1997), Improved PVT correlations for UAE crude oils, SPE Paper 26644, DOI: 10.2118/37691-MS.
• Al-Shammasi, A.A. (1999), Bubble Point pressure and oil formation volume factor correlations, SPE Paper 53185.
• Asoodeh, M. (2013), Prediction of Poisson’s ratio from conventional well log data: A committee machine with intelligent systems approach, Energy Sources A 35, 10, 962-975, DOI: 10.1080/15567036.2011.557693.
• Asoodeh, M., and P. Bagheripour (2012a), Estimation of bubble point pressure from PVT data using a power-law committee with intelligent systems, J. Pet. Sci. Eng. 90-91, 1-11, DOI: 10.1016/j.petrol.2012.04.021.
• Asoodeh, M., and P. Bagheripour (2012b), Prediction of compressional, shear, and stoneley wave velocities from conventional well log data using a committee machine with intelligent systems, Rock. Mech. Rock. Eng. 45, 1, 45-63, DOI: 10.1007/s00603-011-0181-2.
• Asoodeh, M., and P. Bagheripour (2013a), Neuro-fuzzy reaping of shear wave velocity correlations derived by hybrid genetic algorithm-pattern search technique, Open Geosci. 5, 2, 272-284, DOI: 10.2478/s13533-012-0129-4.
• Asoodeh, M., and P. Bagheripour (2013b), Fuzzy classifier based support vector regression framework for Poisson’s ratio determination, J. Appl. Geophys. 96, 7-10, DOI: 10.1016/j.jappgeo.2013.06.006.
• Asoodeh, M., and P. Bagheripour (2013c), Core porosity estimation through different training approaches for neural network: Back-propagation learning vs. genetic algorithm, Int. J. Comput. Appl. 63, 5, 11-15, DOI: 10.5120/10461- 5172.
• Asoodeh, M., and K. Kazemi (2013), Estimation of bubble point pressure using a genetic integration of empirical formulas, Energy Sources A 35, 12, 1102- 1109, DOI: 10.1080/15567036.2011.574195.
• Asoodeh, M., A. Gholami, and P. Bagheripour (2014a), Asphaltene precipitation of titration data modeling through committee machine with stochastically optimized fuzzy logic and optimized neural network, Fluid. Phase Equilibr. 364, 67-74, DOI: 10.1016/j.fluid.2013.12.016.
• Asoodeh, M., A. Gholami, and P. Bagheripour (2014b), Oil-CO2 MMP determination in competition of Neural Network, support vector regression and committee machine, J. Disper. Sci. Technol. 35, 4, 564-571, DOI: 10.1080/ 01932691.2013.803255.
• Asoodeh, M., A. Gholami, and P. Bagheripour (2014c), Renovating scaling equation through hybrid genetic algorithm-pattern search tool for asphaltene precipitation modeling, J. Disper. Sci. Technol. 35, 4, 607-611, DOI: 10.1080/ 01932691.2013.825209.
• Bagheripour, P., and M. Asoodeh (2013), Fuzzy ruling between core porosity and conventional well logs: subtractive clustering vs. genetic algorithm-pattern search, J. Appl. Geophys. 99, 35-41, DOI: 10.1016/j.jappgeo.2013.09.014.
• Bagheripour, P., and M. Asoodeh (2014), Genetic implanted fuzzy model for water saturation determination, J. Appl. Geophys. 103, 232-236, DOI: 10.1016/ j.jappgeo.2014.02.002.
• Bagheripour, P., M. Asoodeh, and A. Asoodeh (2013), Oil formation volume factor modeling: Traditional NN vs. stochastically optimized neural network, Open Geosci. 5, 4, 508-513, DOI: 10.2478/s13533-012-0154-3.
• Bagheripour, P., A. Gholami, and M. Asoodeh (2014), Support vector regression between PVT data and bubble point pressure, J. Petrol. Explor. Prod. Technol. 5, 3, 227-231, DOI: 10.1007/s13202-014-0128-8.
• Bagheripour, P., A. Gholami, M. Asoodeh, and M. Vaezzadeh-Asadi (2015), Support vector regression based determination of shear wave velocity, J. Petrol. Sci. Eng. 125, 95-99, DOI: 10.1016/j.petrol.2014.11.025.
• Bello, O., K. Reinicke, and P. Patil (2008), Comparison of the performance of empirical models used for the prediction of the PVT properties of crude oils of the Niger delta, Petrol. Sci. Technol. 26, 5, 593-609, DOI: 10.1080/ 10916460701204685.
• Breiman, L., and J.H. Friedman (1985), Estimating optimal transformations for multiple regression and correlation, J. Am. Stat. Assoc. 80, 391, 580-598, DOI: 10.1080/01621459.1985.10478157.
• Dake, L.P. (1988), Fundamental of Reservoir Engineering, 17th ed., Elsevier Science.
• Dindoruk, B., and P.G. Christman (2001), PVT properties and viscosity correlations for Gulf of Mexico oils, SPE Paper 26644, DOI: 10.2118/71633-MS.
• Dokla, M.E., and M.E Osman (1990), Correlation of PVT properties for U.A.E. crudes.
• Dutta, S., and J.P. Gupta (2010), PVT correlations for Indian crude using artificial neural networks, J. Petrol. Sci. Eng. 72, 1-2, 93-109, DOI: 10.1016/j.petrol. 2010.03.007.
• El-Banbi, A.H., K.A. Fattah, and M.H. Sayyouh (2006), New modified black-oil correlations for gas condensate and volatile oil fluids, SPE Paper 26644, DOI: 10.2118/102240-MS.
• Elmabrouk, S., A. Zekri, and E. Shirif (2010), Prediction of bubble point pressure and bubble point oil formation volume factor in the absence of PVT analysis, SPE Paper 26644.
• Elsharkawy, A.M. (1998), Modeling the properties of crude oil and gas system using RBF network, SPE Paper 26644, DOI: 10.2118/49961-MS.
• Elsharkawy, A.M., and R.B.C. Gharbi (2000), Comparing classical and neural regression techniques in modeling crude oil viscosity, Adv. Eng. Softw. 32, 3, 215-224, DOI: 10.1016/S0965-9978(00)00083-1.
• Farshad, F.F., J.L. Leblance, J.D. Garber, and J.G. Osorio (1996), A new correlation for bubble point pressure according to the separator conditions, SPE Paper 26644.
• Fattahi, H., A. Gholami, S. Amiribakhtiar, and S. Moradi (2014), Estimation of asphaltene precipitation from titration data: a hybrid support vector regression with harmony search, Neural Comput. Appl. 26, 4, 789-798, DOI: 10.1007/ s00521-014-1766-y.
• Gharbi, R.B., and A.M. Elsharkawy (1996), Neural network model for estimating the PVT properties of Middle East crude oils, SPE Paper 56850.
• Gholami, A., M. Asoodeh, and P. Bagheripour (2014a), Fuzzy assessment of asphaltene stability in crude oils, J. Dispersion. Sci. Technol. 35, 4, 556-563, DOI: 10.1080/01932691.2013.800457.
• Gholami, A., M. Asoodeh, and P. Bagheripour (2014b), Smart determination of difference index for asphaltene stability evaluation, J. Dispersion. Sci. Technol. 35, 4, 572-576, DOI: 10.1080/01932691.2013.805654.
• Gholami, A., M. Asoodeh, and P. Bagheripour (2014c), How committee machine with SVR and ACE estimates bubble point pressure of crudes, Fluid Phase Equilibr. 382, 139-149, DOI: 10.1016/j.fluid.2014.08.033.
• Gholami, A., S. Moradi, M. Asoodeh, P. Bagheripour, and M. Vaezzadeh-Asadi (2014d), Asphaltene precipitation modeling through ACE reaping of scaling equations, Sci. Chin. Chem. 57, 12, 1774-1780, DOI: 10.1007/s11426- 014-5253-1.
• Glaso, O. (1980), Generalized pressure-volume-temperature correlations, J. Petrol. Technol. 34, 85-95, DOI: 10.2118/8016-PA.
• Hemmati, M.N., and R. Kharrat (2007), A correlation approach for prediction of crude oil PVT properties, SPE Paper 26644, DOI: 10.2118/104543-MS.
• Katz, D.L. (1942), Prediction of the shrinkage of crude oils, SPE Paper 26644.
• Kazemi, K., S. Moradi, and M. Asoodeh (2013), A neural network based model for prediction of saturation pressure from molecular components of crude oil, Energy Source A 35, 11, 1039-1045, DOI: 10.1080/15567036.2011.584127.
• Keerthi, S.S., and C.J. Lin (2003), Asymptotic behavior of support vector machines with Gaussian kernel, Neural Comput. 15, 7, 1667-1689, DOI: 10.1162/ 089976603321891855.
• Knopp, C.R., and L.A. Ramsey (1960), Correlation of oil formation volume factor and solution gas-oil ratio, J. Petrol. Technol. 12, 8, 27-29, DOI: 10.2118/ 1433-G.
• Mahmood, M.A., and M.A. Al-Marhoun (1996), Evaluation of empirically derived PVT properties for Pakistani crude oils, J. Petrol. Sci. Eng. 16, 4, 275-290, DOI: 10.1016/S0920-4105(96)00042-3.
• MATLAB User’s Guide (2011), Fuzzy logic, neural network & GA and direct search toolboxes, MATLAB CD-rom, Mathworks, Inc.
• Moghadam, J.N., K. Salahshoor, and R. Kharrat (2011), Introducing a new method for predicting PVT properties of Iranian crude oils by applying artificial neural networks, Petrol Sci. Technol. 29, 10, 1066-1079, DOI: 10.1080/ 10916460903551040.
• Mohaghegh, S. (2000), Virtual-intelligence applications in petroleum engineering: Part 2 – evolutionary computing, J. Petrol. Technol. 52, 10, 40-46, DOI: 10.2118/61925-JPT.
• Na’imi, S.R., A. Gholami, and M. Asoodeh (2014), Prediction of crude oil asphaltene precipitation using support vector regression. J. Disper. Sci. Technol. 35, 4, 518-525, DOI: 10.1080/01932691.2013.798585.
• Obomanu, D.A., and G.A. Okpobiri (1987), Correlating the PVT properties of Nigerian crudes, J. Energy Resour. Technol. 109, 4, 214-217, DOI: 10.1115/ 1.3231349.
• Omar, M.I., and A.C. Todd (1993), Development of new modified black oil correlations for Malaysian crudes, SPE-25338-MS, Asia Pacific Oil and Gas Conference, 8-10 February, Singapore, DOI: 10.2118/25338-MS.
• Petrosky, J., and F. Farshad (1993), Pressure volume temperature correlation for the Gulf of Mexico, SPE, Annual Technical Conference and Exhibition, 3-6 October, Houston, USA, SPE-26644-MS, DOI: 10.2118/26644-MS.
• Rafiee-Taghanaki, S., M. Arabloo, A. Chamkalani, M. Amani, M.H. Zargari, and M.R. Adelzadeh (2013), Implementation of SVM framework to estimate PVT properties of reservoir oil, Fluid Phase Equilibr. 346, 25-32, DOI: 10.1016/j.fluid.2013.02.012.
• Shokir, E.M. (2007), CO2-oil minimum miscibility pressure model for impure and pure CO2 streams, J. Petrol. Sci. Eng. 58, 1-2, 173-185, DOI: 10.1016/ j.petrol.2006.12.001.
• Vapnik, V. (1995), The Nature of Statistical Learning Theory, Springer, New York.
• Vazquez, M., and H.D. Beggs (1970), Correlation for fluid physical property prediction, J. Petrol. Technol. 32, 06, 103-107, DOI: 10.2118/6719-PA.
• You, Z., Z. Yin, K. Han, D. Huang, and X. Zhou (2014), A semi-supervised learning approach to predict synthetic genetic interactions by combining functional and topological properties of functional gene network, BMC Bioinformatics 11, 343-355, DOI: 10.1186/1471-2105-11-343.
• Zargar, G., P. Bagheripour, and M. Asoodeh (2014), Fuzzy modeling of volume reduction of oil due to dissolved gas run off and pressure release, J. Petrol. Explor. Prod. Technol. 4, 4, 439-442, DOI: 10.1007/s13202-014-0099-9.

Uwagi

Opracowanie ze środków MNiSW w ramach umowy 812/P-DUN/2016 na działalność upowszechniającą naukę (zadania 2017)