Fractured reservoir history matching improved based on artificial intelligent

Abstract

In this paper, a new robust approach based on Least Square support Vector Machine (LSSVM) as a proxy model is used for an automatic fractured reservoir history matching. The proxy model is made to model the history match objective function (mismatch values) based on the history data of the field. This model is then used to minimize the objective function through Particle Swarm Optimization (PSO) and Imperialist Competitive Algorithm (ICA). In automatic history matching, sensitive analysis is often performed on full simulation model. In this work, to get new range of the uncertain parameters (matching parameters) in which the objective function has a minimum value, sensitivity analysis is also performed on the proxy model. By applying the modified ranges to the optimization methods, optimization of the objective function will be faster and outputs of the optimization methods(matching parameters) are produced in less time and with high precision. This procedure leads to matching of history of the field in which a set of reservoir parameters is used. The final sets of parameters are then applied for the full simulation model to validate the technique. The obtained results show that the present procedure in this work is effective for history matching process due to its robust dependability and fast convergence speed. Due to high speed and need for small data sets, LSSVM is the best tool to build a proxy model. Also the comparison of PSO and ICA shows that PSO is less time-consuming and more effective.

Keywords

Proxy model / LSSVM / PSO / ICA / Sensitive analysis

References

[1] X. Zhang, H. Hou, D. Wang, T. Mu, J. Wu, X. Lu, An automatic history matching method of reservoir numerical simulation based on improved genetic algorithm, International Workshop on Information and Electronics Engineering (IWIEE), Procedia Eng. 29 (2012) 3924-3928.

[2] N. Bjorndalen, E. Kuru, D.J. Schiozer,Application of neural network and global optimization in history matching, J. Can. Petroleum Technol. 47 (Issue. 11) (2008). PETSOC-08-11-22-TN.

[3] S.N. Lophaven, H.B. Nielsen, J. Sondergaard, DACE: a Mathlab Kriging Toolbox Version 2.0, Technical Report IMM-TR-2002-12, Technical University of Denmark, Lyngby, Denmark, 2002, 1st August.

[4] F. Jurecka, Robust Design Optimization Based on Metamodeling Techniques, Ph.D. thesis, Technische Universität München, München, 2007.

[5] D.I. Zubarev, Pros and cons of applying proxy models as a substitute for full reservoir simulations, SPE 124815, in: Proceedings of the SPE Annual Technical Conference and Exhibition Held in New Orleans, Louisiana, USA, 2009.

[6] A.S. Cullick, D. Johnson, G. Shi, Improved and more-rapid history matching with a nonlinear proxy and global optimization, SPE 101933, in: SPE Annual Technical Conference and Exhibition Held in San Antonio, Texas, U.S.A., 24e27 September, 2006. http://dx.doi.org/10.2118/101933-MS.

[7] T. Yu, D.Wilkinson, A. Castellini, Constructing reservoir flowsimulator proxies using genetic programming for history matching and production forecast uncertainty analysis, J. Artificial Evol. Appl. 2008 (2008). Article ID 263108.

[8] M.H. Rammay, A. Abdulraheem, Automated history matching using combination of Adaptive Neuro Fuzzy system (ANFIS) and differential evolution algorithm,in:Society of Petroleum Engineers, SPE Large Scale Computing and Big Data Challenges in Reservoir Simulation Conference and Exhibition, Istanbul, Turkey, SPE-172992-MS, 15e17 September, 2014.

[9] C. Maschio, D.J. Schiozer, Bayesian history matching using artificial neural network and Markov Chain Monte Carlo, Engineering 123 (2014) 62-71.

[10] N. Goodwin, Bridging the gap between deterministic and probabilistic uncertainty quantification using advanced proxy based methods, in: SPE Reservoir Simulation Symposium, 23e 25 February, Houston, Texas, USA, SPE-173301-MS, 2015.

[11] J. He, J. Xie, X. Wen, W. Chen, Improved proxy for history matching using proxy-for-data approach and reduced order modeling, in: SPE Western Regional Meeting, 27e 30 April, Garden Grove, California, USA, SPE-174055-MS, 2015.

[12] B.E. Boser, I.M. Guyon, V. Vapnik, A training algorithm for optimal margin, in: D. Haussler (Ed.), Proceedings of the Annual Workshop on Computational Learning Theory. Pittsburgh, PA, ACM, New York, NY, 1992, pp. 144-152.

[13] A.J. Smolatand Bernhard Scholkof, A Tutorial on Support Vector Regression, 2003.

[14] J.A.K. Suykens, J. Vandewalle, Neural Processing Letters, vol. 9, 1999, pp. 293-300.

[15] p. Samui, Application of least square support vector machine (LSSVM) for determination of evaporation losses in reservoirs, Engineering 3 (2011) 431-434.

[16] S. Kh Elmabrouk,Application of Function Approximations to Reservoir Engineering, Ph.D. thesis, Department of Petroleum Engineering, University of Regina, 2012.

[17] D.F. Shi, N.G. Nabil, Tool wear predictive model based on least squares support vector machines, Mech. Syst. Signal Process. 21 (2007) 1799-1814.

[18] J. Kennedy, R. Eberhart, Particle swarm optimization, in: Proceedings of the IEEE International Conference on Neural Networks, Piscataway, NJ, USA, vol. 4, 1995, pp. 1942-1948.

[19] S.H. Riazi, H. Heydari, E. Ahmadpour, A. Gholami, S. Parvizi, Development of novel correlation for prediction of hydrate formation temperature based on intelligent optimization algorithms, J. Nat. Gas Sci. Eng. 18 (2014) 377-384.

[20] L. Mohamed, Mike Christie, Vasily Demyanov, Reservoir Model History Matching with Particle Swarms, Institute of Petroleum Engineering, HerioteWatt University, Edinburgh, UK, 2010. SPE 129152.

[21] R. Hassan, B. Cohanim, O.Weck, G. Venter,A Copmarison of Particle Swarm Optimization and the Genetic Algorithm, in:Proceedings of the 1st AIAA Multidisciplinary Design Optimization Specialist Conference, 18e21 April, Austin, Texas, 2005, pp. 1-13.

[22] R. Martinez-Soto, A. Rodriguez, O. Castillo, T. Aguilar, Gain optimization for inertia wheel pendulum stabilization using particle swarm optimization and genetic algorithms, in: International Journal of Innovative Computing, Information and Control vol. 8, 2012, pp. 4421-4430.

[23] Gh Mokhtari A.J. Ghanizadeh E. Ebrahimi, Application of imperialist competitive algorithm to solve constrained economic dispatch, Electrical Engineering Department, Amirkabir University of Technology, Tehran, Iran, Int. J. Electr. Eng. Inf. 4 (No. 4) (2012).

[24] E. Atashpaz-Gargari, C. Lucas, Imperialist Competitive Algorithm: An Algorithm for Optimization Inspired by Imperialistic Competition, IEEE Congress on Evolutionary Computation, Singapore, 2007, pp. 4661-4667.

[25] H. Towsyfyan, S.A. Adnani-Salehi, M. Ghayyem, F. Mosaedi, The comparison of imperialist competitive algorithm applied and genetic algorithm for machining allocation of clutch assembly, Int. J. Eng. 26 (No. 12) (2013) 1485-1494.

[26] I. Zabalza-Mezghani, E. Manceau, M. Feraille, A. Jourdan, Uncertainty management: from geological scenarios to production scheme optimization, J. Petroleum Sci. Eng. 44 (2004) 11-25.

[27] M. Espinoza, J.A.K. Suykens, B. De Moor, Least squares support vector machines and primal space estimation, in: Proceedings of the 42nd IEEE Conference on Decision and Control Maui Hawaii, USA, vol. 4, 2003, pp. 3451-3456.

[28] P. Nardone, Well Testing Project Management: Onshore and Offshore Operations, book, Gulf professional press, 2009, p. 61.