A hybrid PSO-SVM-based model for determination of oil recovery factor in the low-permeability reservoir

Abstract

Oil recovery factor is one of the most important parameters in the development process of oil reservoir, especially in the low-permeability reservoir. In general, the determination of recovery factor can be obtained either experimentally or numerically. Experimental method is often time-consuming and expensive, while numerical method has been always confined to narrow range of application or relatively large error. Recently, an intelligent method has been proven as an efficient tool to model the complex and nonlinear phenomena. In this work, an intelligent model based on support vector machine in combination with the particle swarm optimization (PSO-SVM) technique was established to predict oil recovery factor in the low-permeability reservoir. Input variables of the proposed PSO-SVM model with the aid of a grey correlation analysis method are permeability, well spacing density, production-injection well ratio, porosity, effective thickness, crude oil viscosity and output parameter is oil recovery factor of low-permeability reservoir. The accuracy and reliability of the proposed model were evaluated through 34 data sets collected in the open literature and compared with PSO-BP neural network, empirical method from Oil and Gas Company. The results indicated that the PSO-SVM model gives the best results with average absolute relative deviation (AARD) of 3.79%, while AARDs for the PSO-BP neural network and empirical method are 9.18% and 10.0%, respectively. Furthermore, outlier detection was used on the basis of whole data sets to definite the valid domains of PSO-SVM and PSO-BP models by detecting the probable doubtful recovery factor data in the low-permeability reservoir.

Keywords

PSO-SVM / Recovery factor / Low permeability / Reservoir / Outlier detection

Acknowledgements

This work was Supported by National Natural Science foundation of China (No. 51404205), Open Fund (PLN 1207) of State Key Laboratory of Oil and Gas Reservoir Geology and Exploitation (Southwest Petroleum University), and Innovation team project of Sichuan Provincial Department of Education (No. 16TD0010).

References

[1] B.Y. Ji, Forecasting methods of oil field development indexes, Pet. Geol. Oilf. Dev. Daqing 18 (2) (1994) 20-21.

[2] X. Xu, G.S. Miao, Y.C. Liu, Correction to Tong's standard formula and its application, J. Jianghan Pet. Inst. 24 (1) (2002) 57-59.

[3] S. Macary, W.A. Hamid,Creation of the fractional flow curve from purely production data, in:Annual Technical Conference and Exhibition, 1999, pp. 1-4.

[4] S.M. Al-Fattah, R.A. Startzman,Predicting natural gas production using artificial neural network, in:Hydrocarbon Economics and Evaluation Symposium, 2001, pp. 1-5.

[5] A. Okpere, C. Ndibueze,Application of empirically derived oil recovery factor regression equations to water drive reservoirs in Niger delta, in:Nigeria Annual International Conference and Exhibition, 2013, pp. 1-11.

[6] A. Okpere, C. Njoku,Application of neural networks in developing an empirical oil recovery factor equation for water drive Niger delta reservoirs, in:Nigeria Annual International Conference and Exhibition, 2014, pp. 1-10.

[7] L.P. Dake, Developments in Petroleum Science 36: the Practice of Reservoir Engineering (Revised Edition), Elsevier, 2001.

[8] C.L. Li, Reservoir Engineering Principle, Petroleum Industry Press, Beijing, 2011, pp. 297-349.

[9] S.H. Wang, Z.H. Gao, J.K. Wang, Methods of calculating the recoverable reserves of low permeable oilfield, Pet. Geol. Oilf. Dev. Daqing 16 (2) (1997) 24-28.

[10] Y.L. Niu, L. Li, D.J. Han, A new method for calculating recovery factor of water drive in low-permeability reservoir, Acta Pet. Sin. 27 (2) (2006) 77-79.

[11] R.Z. Jiang, X.L. Zhang, J.P. Ma, A new method to calculate elastic energy recovery of ultra-low permeability reservoirs, China Offshore Oil Gas 22 (1) (2010) 27-29.

[12] J.H. Xiao,Research on Oil Recovery Factor Prediction in Low Permeability Reservoir, A thesis for master degree of China University of Petroleum, 2011, pp. 37-53.

[13] J.B. Wu,Research on Prediction Method of Recovery Factor in Low Permeability Oil Field, A thesis for master degree of Xi'an Petroleum University, 2013, pp. 51-54.

[14] M. Adibifard, S.A.R. Tabatabaei-Nejad, E. Khodapanah, Artificial Neural Network (ANN) to estimate reservoir parameters in naturally fractured reservoirs using well test data, J. Petrol. Sci. Eng. 122 (2014) 585-594.

[15] M.A. Ahmadi, A. Bahadori, A LSSVM approach for determining well placement and conning phenomena in horizontal wells, Fuel 153 (2015) 276-283.

[16] S.R. Taghanaki, M. Arabloo, A. Chamkalani, et al., Implementation of SVM framework to estimate PVT properties of reservoir oil, Fluid Phase Equilib. 346 (2013) 25-32.

[17] E.A. El-Sebakhy, Forecasting PVT properties of crude oil systems based on support vector machines modeling scheme, J. Petrol. Sci. Eng. 64 (1) (2009) 25-34.

[18] H. Kaydani, A. Mohebbi, A. Baghaie, Permeability prediction based on reservoir zonation by a hybrid neural genetic algorithm in one of the Iranian heterogeneous oil reservoirs, J. Petrol. Sci. Eng. 78 (2011) 497-504.

[19] Y.F. Huang, G.H. Huang, M.Z. Dong, et al., Development of an artificial neural network model for predicting minimum miscibility pressure in CO₂ flooding, J. Petrol. Sci. Eng. 37 (2003) 83-95.

[20] M.A. Ahmadi, A. Bahadori, S.R. Shadizadeh, A rigorous model to predict the amount of dissolved calcium carbonate concentration throughout oil field brines: side effect of pressure and temperature, Fuel 139 (2015) 154-159.

[21] M.A. Ahmadi, M. Masoumi, R. Askarinezhad, Evolving connectionist model to monitor the efficiency of an in situ combustion process: application to heavy oil recovery, Energy Technol. 2 (9) (2014) 811-818.

[22] M.A. Ahmadi, M. Masumi, R. Kharrat, et al., Gas analysis by in situ combustion in heavy-oil recovery process: experimental and modeling studies, Chem. Eng. Technol. 37 (3) (2014) 409-418.

[23] M.A. Ahmadi, M. Ebadi, P.S. Marghmaleki, et al., Evolving predictive model to determine condensate-to-gas ratio in retrograded condensate gas reservoirs, Fuel 124 (2014) 241-257.

[24] M. Rajendra, P.C. Jena, H. Raheman, Prediction of optimized pretreatment process parameters for biodiesel production using ANN and GA, Fuel 88 (5) (2009) 868-875.

[25] E. Assareh, M.A. Behrang, M.R. Assari, et al., Application of PSO (particle swarm optimization) and GA (genetic algorithm) techniques on demand estimation of oil in Iran, Energy 35 (12) (2010) 5223-5229.

[26] B. Vasumathi, S. Moorthi, Implementation of hybrid ANN-PSO algorithm on FPGA for harmonic estimation, Eng. Appl. Artif. Intell. 25 (3) (2012) 476-483.

[27] M.A. Ahmadi, M. Lee, A. Bahadori, Prediction of a solid desiccant dehydrator performance using least squares support vector machines algorithm, J. Taiwan Inst. Chem. Eng. 50 (2015) 115-122.

[28] S.A.M. Dehghani, M.V. Sefti, A. Ameri, et al., Minimum miscibility pressure prediction based on a hybrid neural genetic algorithm, Chem. Eng. Res. Des. 82 (2008) 173-185.

[29] M.A. Ahmadi, Connectionist approach estimates gaseoil relative permeability in petroleum reservoirs: application to reservoir simulation, Fuel 140 (2015) 429-439.

[30] M.A. Ahmadi, M.R. Ahmadi, S.M. Hosseini, et al., Connectionist model predicts the porosity and permeability of petroleum reservoirs by means of petro-physical logs: application of artificial intelligence, J. Pet. Sci. Eng. 123 (2014) 183-200.

[31] M.A. Ahmadi, S.R. Shadizadeh, New approach for prediction of asphaltene precipitation due to natural depletion by using evolutionary algorithm concept, Fuel 102 (2012) 716-723.

[32] M.A. Ahmadi, Neural network based unified particle swarm optimization for prediction of asphaltene precipitation, Fluid Phase Equilib. 314 (2012) 46-51.

[33] M.A. Ahmadi, M. Golshadi, Neural network based swarm concept for prediction asphaltene precipitation due to natural depletion, J. Pet. Sci. Eng. 98 (2012) 40-49.

[34] M.A. Ahmadi, R. Soleimani, M. Lee, Determination of oil well production performance using artificial neural network (ANN) linked to the particle swarm optimization (PSO) tool, Petroleum 1 (2) (2015) 118-132.

[35] M.A. Ahmadi, M. Zahedzadeh, S.R. Shadizadeh, et al., Connectionist model for predicting minimum gas miscibility pressure: application to gas injection process, Fuel 148 (2015) 202-211.

[36] X.Q. Bian, B. Han, Z.M. Du, et al., Integrating support vector regression with genetic algorithm for CO2-oil minimum miscibility pressure (MMP) in pure and impure CO₂ streams, Fuel 182 (2016) 550-557.

[37] M.A. Ahmadi, M. Ebadi, A. Yazdanpanah, Robust intelligent tool for estimating dew point pressure in retrograded condensate gas reservoirs: application of particle swarm optimization, J. Pet. Sci. Eng. 123 (2014) 7-19.

[38] M.A. Ahmadi, M. Ebadi, Evolving smart approach for determination dew point pressure through condensate gas reservoirs, Fuel 117 (2014) 1074-1084.

[39] V. Chan, C. Chan, Learning from a carbon dioxide capture system dataset: application of the piecewise neural network algorithm, Petroleum 3 (1) (2017) 56-67.

[40] V.N. Vapnik, The Nature of Statistical Learning Theory, second ed., Springer Science Business Media, New York, 2013.

[41] K.Y. Chen, Forecasting systems reliability based on support vector regression with genetic algorithms, Reliab. Eng. Syst. Saf. 92 (4) (2007) 423-432.

[42] M. Ghorbani, G. Zargar, H. Jazayeri-Rad, Prediction of asphaltene precipitation using support vector regression tuned with genetic algorithms, Petroleum 2 (3) (2016) 301-306.

[43] P.J.G. Nieto, J.R.A. Fernández, V.M.G. Suárez, A hybrid PSO optimized SVMbased method for predicting of the cyan toxin content from experimental cyanobacteria concentrations in the Trasona reservoir: a case study in Northern Spain, Appl. Math. Comput. 260 (2015) 175-178.

[44] J. Kennedy, R.C. Eberhart,Particle swarm optimization, in:Proceedings of the 1995 IEEE International Conference on Neural Networks Perth Australia, 1995.

[45] Y. Da, G. Xiurun, An improved PSO-based ANN with simulated annealing technique, Neuro Comput. 63 (2005) 527-533.

[46] E. Momeni, D.J. Armaghani, M. Hajihassani, Prediction of uniaxial compressive strength of rock samples using hybrid particle swarm optimization-based artificial neural networks, Measurement 60 (2015) 50-63.

[47] Y.L. Chai, Study of coal and gas prediction based on improvement of PSO and ANN, Electron. Signal Process. (2011) 695-702.

[48] F.Q. Song, C.Q. Liu, Factors effecting the water flooding recovery in low permeable reservoirs, Pet. Geol. Oilf. Dev. Daqing 19 (1) (2000) 30-36.

[49] B.Q. Xu, Q. Liu, M. Chen, EOR in low and extra low-permeability gas reservoirs, Nat. Gas Explor. Dev. 30 (2) (2007) 47-49.

[50] Z.X. Yuan, J.Y. Wang, S.X. Li, A new approach to estimation recovery factor for extra low permeability water flooding sandstone reservoir, Pet. Explor. Dev. 41 (3) (2014) 341-348.

[51] R.C. He,Low Permeability Reservoir Recoverable Reserves Calculation Method Research, A thesis for master degree of Northeast Petroleum University, 2012, pp. 8-16.

[52] Y. Feng, B. Ji, P. Gao, An Improved Grey Relation Analysis Method and its Application in Dynamic Description for a Polymer Flooding Pilot of Xingshugang Field, Daqing, SPE128510, 2010.

[53] J. Shi, Z. Ding, W.J. Lee, Hybrid forecasting model for very-short term wind power forecasting based on grey relational analysis and wind speed distribution features, Smart Grid IEEE Trans. 5 (1) (2014) 522-523.

[54] LIBSVM-3.1-[FarutoUltimate3.1Mode] toolbox (by faruto), 2011. Matalb-Sky.com.

[55] C.L. Huang, J.F. Dun, A distributed PSO-SVM hybrid system with feature selection and parameter optimization, Appl. Soft Comput. 8 (4) (2008) 1381-1391.

[56] P.J. Rousseeuw, A.M. Leroy, Robust Regression and Outlier Detection, John Wiley & Sons New York, 1987.

[57] C.R. Goodall, Computation Using the QR Decomposition Handbook in Statistics, vol. 9, Elsevier/North-Holland Amsterdam, 1993.

[58] P. Gramatica, Principles of QSAR models validation: internal and external, QSAR Comb. Sci. 26 (2007) 694-701.