Bubble Pressure Prediction of Reservoir Fluids using Artificial Neural Network and Support Vector Machine

Document Type : Research Paper

Authors

Faculty of Chemical Engineering, Babol Noshirvani University of Technology, Babol, Iran

Abstract

Bubble point pressure is an important parameter in equilibrium calculations of reservoir fluids and having other applications in reservoir engineering. In this work, an artificial neural network (ANN) and a least square support vector machine (LS-SVM) have been used to predict the bubble point pressure of reservoir fluids. Also, the accuracy of the models have been compared to two-equation state-based models, i.e. SRK-EOS and PR-EOS and four empirical equations, i.e. Whitson, Standing, Wilson and Ghafoori et al. Compared to the experimental data, the average relative deviations (ARD) of bubble pressure prediction for these equations were obtained to be 14%, 29%, 66%, 30%, 38%, and 11%, respectively. The best semi-empirical equation has an ARD of about 11% while, the ANN and LS-SVM models have an ARD of 8% and 4.68%, respectively. Thus, it can be concluded that generally, these soft computing models appear to be more accurate than the empirical and EOS based methods for prediction of bubble point pressure of reservoir fluids.  

Keywords

References

[1]     Souders M, Selheimer C, Brown GG. III.-Equilibria between Liquid and Vapor Solutions of Paraffin Hydrocarbons. Industrial & Engineering Chemistry. 1932 May;24(5):517-9.
[2]     Hoffman AE, Crump JS, Hocott CR. Equilibrium constants for a gas-condensate system. Journal of Petroleum Technology. 1953 Jan 1;5(1):1-0.
[3]     Brinkman FH, Sicking JN. Equilibrium ratios for reservoir studies. Petrole Trans AIME 1960;219:313-9.
[4]     Jaubert JN, Mutelet F. VLE predictions with the Peng–Robinson equation of state and temperature dependent kij calculated through a group contribution method. Fluid Phase Equilibria. 2004 Oct 1;224(2):285-304.
[5]     Ahmed T. Reservoir engineering handbook. 2nd ed. Houston. Texas:Gulf Publishing; 2001.
[6]     Standing MB. A set of equations for computing equilibrium ratios of a crude oil/natural gas system at pressures below 1,000 psia. Journal of Petroleum Technology. 1979 Sep 1;31(09):1-93.
[7]     Whitson CH, Torp SB. Evaluating constant volume depletion data. InSPE Annual Technical Conference and Exhibition 1981 Jan 1.
[8]     Ghafoori MJ, Aghamiri SF, Talaie MR. A new empirical K-value equation for reservoir fluids. Fuel. 2012 Aug 1;98:236-42.
[9]     Vapnik V. Statistical learning theory. New York: John Wiley and Sons Inc.;1998.
[10]  Li CH, Zhu XJ, Cao GY, Sui S, Hu MR. Identification of the Hammerstein model of a PEMFC stack based on least squares support vector machines. Journal of Power Sources. 2008 Jan 3;175(1):303-16.
[11]  Suykens JA, Vandewalle J. Least squares support vector machine classifiers. Neural processing letters. 1999 Jun 1;9(3):293-300.
[12]  Kelly Jr JD, Davis L. A Hybrid Genetic Algorithm for Classification. InIJCAI 1991 Aug 24 (Vol. 91, pp. 645-650).
[13]  Lahiri SK, Ghanta KC. Artificial neural network model with the parameter tuning assisted by a differential evolution technique: The study of the hold up of the slurry flow in a pipeline. Chemical Industry and Chemical Engineering Quarterly/CICEQ. 2009;15(2):103-17.
[14]  Cartwright HM. Applications of artificial intelligence in chemistry. Oxford: Oxford University Press; 1993.
[15]  Zhang Y. An improved QSPR study of standard formation enthalpies of acyclic alkanes based on artificial neural networks and genetic algorithm. Chemometrics and Intelligent Laboratory Systems. 2009 Oct 15;98(2):162-72.
[16]  Mehdizadeh B, Movagharnejad K. A comparative study between LS-SVM method and semi empirical equations for modeling the solubility of different solutes in supercritical carbon dioxide. Chemical Engineering Research and Design. 2011 Nov 1;89(11):2420-7.
[17]  Bakhshi H, Dehghani A, Jafaripanah S. Using the Genetic Algorithm based on the Riedel Equation to Predict the Vapor Pressure of Organic Compounds. International Journal of Engineering. 2018 Jun 1;31(6):863-9.
[18]  Aghaeinejad-Meybodi A, Ebadi A, Shafiei S, Khataee A, Kiadehi AD. Degradation of Fluoxetine using catalytic ozonation in aqueous media in the presence of nano-γ-alumina catalyst: Experimental, modeling and optimization study. Separation and Purification Technology. 2019 Mar 18;211:551-63.
[19]  Gas processors suppliers association engineering data book. 12th ed., FPS version. Oklahoma. 2004.
[20]  Standing MB. Volumetric and phase behavior of oil field hydrocarbon systems. Society of petroleum engineers of AIME; 1977.
[21]  Privat R, Jaubert JN, Mutelet F. Addition of the nitrogen group to the PPR78 model (predictive 1978, Peng Robinson EOS with temperature-dependent k ij calculated through a group contribution method). Industrial & Engineering Chemistry Research. 2008 Mar 19;47(6):2033-48.
[22]  Elsharkawy AM. An empirical model for estimating the saturation pressures of crude oils. Journal of Petroleum Science and Engineering. 2003 May 1;38(1-2):57-77.
[23]  Coats KH, Smart GT. Application of a regression-based EOS PVT program to laboratory data. SPE Reservoir Engineering. 1986 May 1;1(03):277-99.
[24]  Wiesepape CF, Kennedy HT, Crawford PB. A crude oil-natural gas system vapor-liquid equilibrium ratios (data at 250. degree. F and system containing 20% C7+). Journal of Chemical and Engineering Data. 1977 Jul;22(3):260-1.
[25]  Wu R, Rosenegger L. Integrated oil PVT characterization-lessons from four case histories. Journal of Canadian Petroleum Technology. 1999 Dec 1;38(13).
[26]  Jaubert JN, Avaullee L, Souvay JF. A crude oil data bank containing more than 5000 PVT and gas injection data. Journal of Petroleum Science and Engineering. 2002 Jun 1;34(1-4):65-107.
[27]  Danesh A, Xu DH, Todd AC. A grouping method to optimize oil description for compositional simulation of gas-injection processes. SPE reservoir engineering. 1992 Aug 1;7(03):343-8.
[28]  Pedersen KS, Blilie AL, Meisingset KK. PVT calculations on petroleum reservoir fluids using measured and estimated compositional data for the plus fraction. Industrial & engineering Chemistry Research. 1992 May;31(5):1378-84.
[29]  Mohammed SA. A simplified method for computing phase behavior of crude oil-carbon-dioxide mixtures. [Ph.D. dissertation]. College Station: Texas A&M University: 1988.
[30]  Burke NE, Hobbs RE, Kashou SF. Measurement and Modeling of Asphaltene Precipitation (includes associated paper 23831). Journal of Petroleum Technology. 1990 Nov 1;42(11):1-440.
[31]  Almehaideb RA, Al-Khanbashi AS, Abdulkarim M, Ali MA. EOS tuning to model full field crude oil properties using multiple well fluid PVT analysis. Journal of Petroleum Science and Engineering. 2000 May 1;26(1-4):291-300.
[32]  Pedersen KS, Fredenslund A, Thomassen P. Properties of oils and natural gases. Gulf Pub Co; 1989.
Journal of Chemical and Petroleum Engineering
Volume 53, Issue 2
December 2019
Pages 177-189

Files

History

  • Receive Date: 07 October 2018
  • Revise Date: 19 August 2019
  • Accept Date: 02 September 2019

Share

How to cite

Statistics