As the price of oil decreases, it is becoming increasingly important for oil companies to operate in the most cost-effective manner. This problem is especially apparent in Western Canada, where most oil production is dependent on costly enhanced oil recovery (EOR) techniques such as steam-assisted gravity drainage (SAGD). Therefore, the goal of this study is to create an artificial neural network (ANN) that is capable of accurately predicting the ultimate recovery factor of oil reservoirs by steam-assisted gravity drainage (SAGD). The developed ANN model featured over 250 unique entries for oil viscosity, steam injection rate, horizontal permeability, permeability ratio, porosity, reservoir thickness, and steam injection pressure collected from literature. The collected data set was entered through a feed-forward back-propagation neural network to train, validate, and test the model to predict the recovery factor of SAGD method as accurate as possible. Results from this study revealed that the neural network was able to accurately predict recovery factors of selected projects with less than 10% error. When the neural network was exposed to a new simulation data set of 64 points, the predictions were found to have an accuracy of 82% as measured by linear regression. Finally, the feasibility of ANN to predict the recovery performance of one of the most complicated enhanced heavy oil recovery techniques with reasonable accuracy was confirmed.
Acknowledgements
The authors would like thank Petroleum Systems Engineering department in the faculty of engineering and applied sciences at University of Regina for their help and guidance for this project. The authors also gratefully appreciate the financial support from Petroleum Technology Research Centre (PTRC), Canada and Mitacs, Canada.
| [1] |
Canadian Association of Petroleum Producers, Canada's energy resources,Retrieved April 04, 2018, from, 2018. https://www.capp.ca/canadian-oil-and-natural-gas/canadas-petroleum-resources.
|
| [2] |
X. Dong, H. Liu, Z. Zhang, L. Wang, Z. Chen, Performance of multiple thermal fluids assisted gravity drainage process in post SAGD reservoirs, J. Pet. Sci. Eng. 154 (2017) 528-536.
|
| [3] |
T.B.N. Nguyen, T.Q.C. Dang, W. Nguyen, X.H. Bae, A comprehensive evaluation of SAGD and fast-SAGD application in three major formations of alberta's oil sand, energy sources, Part A: recovery, utilization, Energy Sources, Part A Recovery, Util. Environ. Eff. 35 (2013) 604-621.
|
| [4] |
R. Butler, SAGD Comes of AGE!, Petroleum Society of Canada, 1998, https://doi. org/10.2118/98-07-DA.
|
| [5] |
D.W. Green, G.P. Willhite, Enhanced Oil Recovery, Henry L. Doherty Memorial Fund of AIME, Society of Petroleum Engineers, Richardson, TX, 2008.
|
| [6] |
S.M.F. Ali, Effect of Steam Injection Interruption on SAGD Performance, Society of Petroleum Engineers, 2016, https://doi.org/10.2118/179853-MS.
|
| [7] |
J.Y. Yuan, R. McFarlane, Evaluation of Steam Circulation Strategies for SAGD Start-Up, Petroleum Society of Canada, 2011, https://doi.org/10.2118/2009-014.
|
| [8] |
H. Shin, M. Polikar, Fast-Sagd Application in the Alberta Oil Sands Areas, Petroleum Society of Canada, 2005, https://doi.org/10.2118/2005-173.
|
| [9] |
H. Shin, A Reservoir Economic Indicator to Evaluate a SAGD Project, Petroleum Society of Canada, 2008, https://doi.org/10.2118/2008-072.
|
| [10] |
X. Dong, H. Liu, J. Hou, Z. Chen, T. Zhang, An Empirical Correlation to Predict the SAGD Recovery Performance, Society of Petroleum Engineers, 2015, https://doi. org/10.2118/176410-MS.
|
| [11] |
H. Shin, M. Polikar, New Economic Indicator to Evaluate SAGD Performance, Society of Petroleum Engineers, 2005, https://doi.org/10.2118/94024-MS.
|
| [12] |
P. Li, M. Chan, W. Froehlich, Steam Injection Pressure and the SAGD Ramp-Up Process, Petroleum Society of Canada, 2009, https://doi.org/10.2118/09-01-36.
|
| [13] |
S.M.T. Hosseini, S. Esfahani, M.H. Doulatabadi, A.H. Sarapardeh, A.H. Mohammadi, On the evaluation of steam assisted gravity drainage in naturally fractured oil reservoirs, Petroleum 3 (2017) 273-279.
|
| [14] |
A. Sarapardeh, H.H. Kiasari, N. Alizadeh, S. Mighani, A. Kamari, Application of Fast-SAGD in Naturally Fractured Heavy Oil Reservoirs: A Case Study, Society of Petroleum Engineers, 2013, https://doi.org/10.2118/164418-MS.
|
| [15] |
Y. Souraki, M. Ashrafi, H. Karimaie, O. Torsæter, Experimental Analyses of Athabasca Bitumen Properties and Field Scale Numerical Simulation Study of Effective Parameters on SAGD Performance, Energy and Environment Research, 2012, https://doi.org/10.5539/eer.v2n1p140.
|
| [16] |
P.E. Llaguno, F. Moreno, R. Garcia, Z. Mendez, E. Escobar, A Reservoir Screening Methodology for SAGD Applications, Petroleum Society of Canada, 2002, https://doi.org/10.2118/2002-124.
|
| [17] |
H.A. Mendoza, J.J. Finol, R.M. Butler, SAGD, Pilot Test in Venezuela, Society of Petroleum Engineers, 1999, https://doi.org/10.2118/53687-MS.
|
| [18] |
M. Mohammadpoor, Experimental, Numerical, and Soft Computing-Based Analysis of the Vapex Process in Heavy Oil Systems, Faculty of Graduate Studies and Research, University of Regina, 2014.
|
| [19] |
M. Mohammadpoor, F. Torabi, A new soft computing-based approach to predict oil production rate for vapour extraction (VAPEX) process in heavy oil reservoirs, Can. J. Chem. Eng. (2018), https://doi.org/10.1002/cjce.23111.
|
| [20] |
D.E. Rumelhart, G.E. Hinton, R.J. Williams, Learning representations by back-propagating errors, Nature 323 (1986) 533-536.
|
| [21] |
MathWorks, Documentation, Retrieved March 30, 2018, from https://www. MathWorks.com/help/nnet/.
|
| [22] |
Suncor,Suncor Firebag, AER performance presentation commercial scheme Approval No. 8870, Retrieved March 23, 2018, from, 2017. https://www.aer.ca/documents/oilsands/insitu-presentations/2017AthabascaSuncorFirebagSAGD8870.pdf.
|
| [23] |
G. Chen, K. Fu, Z. Liang, T. Sema, C. Li, P. Tontiwachwuthikul, R. Idem, The genetic algorithm based back propagation neural network for MMP prediction in CO2-EOR process, Fuel 126 (2014) 202-212.
|
PDF
