Neural Network Meta-Modeling of Steam Assisted Gravity Drainage Oil Recovery Processes

Document Type : Research Article

Authors

Faculty of Chemical & Petroleum Engineering, Sharif University of Technology, Tehran, I.R. IRAN

Abstract

Production of highly viscous tar sand bitumen using Steam Assisted Gravity Drainage (SAGD) with a pair of horizontal wells has advantages over conventional steam flooding. This paper explores the use of Artificial Neural Networks (ANNs) as an alternative to the traditional SAGD simulation approach. Feed forward, multi-layered neural network meta-models are trained through the Back-Error-Propagation (BEP) learning algorithm to provide a versatile SAGD forecasting and analysis framework. The constructed neural network architectures are capable of estimating the recovery factors of the SAGD production as an enhanced oil recovery method satisfactorily. Rigorous studies regarding the hybrid static-dynamic structure of the proposed network are conducted to avoid the over-fitting phenomena. The feed forward artificial neural network-based simulations are able to capture the underlying relationship between several parameters/operational conditions and rate of bitumen production fairly well, which proves that ANNs are suitable tools for SAGD simulation.

Keywords

Main Subjects


[1] Godec M.L., “Characterization and Potential ofU.S.Heavy Oil.” Proceedings of the 5th UNITAR International Conference on Heavy Crude Oil and Tar Sands,Caracas,Venezuela, Aug. 4-9 (1991).
[2] Mahmood S.M., Olsen D.K., Thomas C.P., "Heavy Oil Production fromAlaska", Proceedings of the 6th UNITAR International Conference on Heavy Crude Oil and Tar Sands,Houston,TX, Feb. 12-17 (1995).
[3] ButlerR.M., Steam Assisted Gravity Drainage: Concept, Development, Performance and Future, J. of Canadian Petroleum Technology, 33 (1994).
[4] Jiang Q.,ButlerR.M., Yee C.T., "Development of the Steam and Gas Push (SAGP) Process", The 7th UNITAR International Conference of Heavy Crude and Tar Sands, Oct. 27-30,Beijing,China. Paper 59 (1998).
[5] ButlerR.M., “Horizontal Wells for the Recovery of Oil, Gas and Bitumen. Petroleum Society Monograph”, Prentice-Hall, EnglewoodCliffs, NJ, 2, pp. 169-200 (1994).
[6] Mendoza H.A., Finol J.J., Butler R.M., "SAGD, Pilot Test in Venezuela", Paper SPE 53687, presented at the Latin American and Caribbean Petroleum Engineering Conference Held in Caracas, Venezuela, April 21–23 (1999).
[7] ButlerR.M., “Thermal Recovery of Oil and Bitumen”. Prentice-Hall,EnglewoodCliffs, NJUSA, p. 285-359 (1991).
[8] Joshi S.D., “A Laboratory Study of Thermal Oil Recovery Using Horizontal Wells,” Paper SPE/DOE 14916 Presented at the SPE/DOE Fifth Symposium on Enhanced Oil Recovery Held in Tulsa, OK, April 20-23 (1986).
[9] Fonseca D.J., Navaresse D.O., Moynihan G.P., "Simulation Metamodeling Through Artificial Neural Networks. Department of Industrial Engineering, TheUniversityofAlabama",Box 870288,Tuscaloosa,AL35487-0288,USA. (2003).
[10] "Engineering Applications of Artificial Intelligence", Volume 16, Issue 3, Pages 177-183 (2003).
[11] Afonin P.V., Derjabkina V.V., Kozhukhova A.A., Lamskova O.Y., The Design and Analysis of Complex System Neural Network Metamodels, Journal Optical Memory & Neural Networks, 16(3), p. 154 (2007).
[12] Singhal A., Das S.K., Leggitt S.M., Kasraie M., Ito Y., "Screening of Reservoir for Exploitation by Application of Steam Assisted Gravity Drainage/ Vapex processes". Paper SPE 37144, presented at the SPE International Conference on Horizontal Well Technology held in Calgary, Alberta, Canada, Nov. 18-20 (1996).
[13] Edmunds N.R., Suggett J.C., "Design of a Commercial SAGD Heavy Oil Project", Paper SPE 30277, Presented at the SPE International Heavy Oil Symposium held in Calgary, Alberta, Canada, June 19-21 (1995).
[14]ButlerR.M., Rise of Interfering Steam Chambers. JCPT 26 (3), 70-75, May- June.Butler, R.M., 1994. “Horizontal Wells for the Recovery of Oil, Gas and Bitumen. Petroleum Society Monograph”, vol. 2. Prentice-Hall,EnglewoodCliffs, NJ, pp. 169-200 (1987).
[15] ButlerR.M., A New Approach to the Modeling of Steam Assisted Gravity Drainage, JCPT 24 (3), 42-51, May-June (1985).
[16] Reis  J.C.,  A  Steam-Assisted  Gravity  Drainage Model for Tar Sands: Linear Geometry, JCPT, 31 (10), 14-20, December (1992).
[17] Scott Ferguson F.R., Butler R.M., Steam-Assisted Gravity Drainage Model Incorporating Energy Recovery from a Cooling Stream Chamber, JCPT, 27(5), 75-83, September-October (1988).
[18] Yang  G.,  Butler  R.M.,  Effects  of  Reservoir Heterogeneities on Heavy Oil Recovery by Steam-Assisted Gravity Drainage, JCPT, 31(8), 37-43, October (1992).
[19] Nasr T.S., Law D.H.-S., Golbeck H., Korpany G., Counter Current Aspect of the SAGD Process, JCPT, 39(1), 41-47, January (2000).
[20] Kamath V.A., Hatzignatiou D.G., "Simulation Study of Steam Assisted Gravity Drainage Process in Ugnu Tar Sand Reservoir", Paper SPE 26075, Presented at the Western Regional Meeting Held inAnchorage, AK, USA, May 26-28 (1993).
[21] Kisman K.E., Yeung K.C., "Numerical Study of the SAGD Process in the Burnt Lake Oil Sands Lease", Paper SPE 30276, Presented at the International Heavy Oil Symposium Held inCalgary,Alberta,Canada, June 19-21 (1995).
[22] Queipo N.V., Goicochea J.V., Pintos S., Surrogate Modeling-Based Optimization of SAGD Processes. Journal of Petroleum Science and Engineering, 35, p. 83 (2002).
[23] Keller  R.M.,  Dungan  J.L.,  Meta-Modeling: a Knowledge-Based Approach to Facilitating Process Model Construction and Reuse, Ecological Modeling, 119, p. 89 (1990).
[24] Peaceman D.W., Exxon Production Research Co. Interpretation of Well-Block Pressures in Numerical Reservoir Simulation With Nonsquare Grid Blocks and Anisotropic Permeability, SPE Journal, 23(3), p. 531 (1983).
[25] Thomas S., Enhanced Oil Recovery-An Overview, Oil & Gas Science and Technology Journal – Rev. IFP, 63(1), p. 9 (2008).
[26] MacKay, D.J.C., Bayesian interpolation, Neural Computation, 4(3), p. 415 (1992).
[27] Foresee F.D., Hagan, M.T., Gauss-Newton Approximation to Bayesian Regularization, Proceedings of the International Joint Conference on Neural Networks, p. 1930 (1997).