Authors: Hamed Panjalizadeh; Nasser Alizadeh; Hadi Mashhadi
Addresses: Petroleum Engineering Department, Amir-kabir University of Technology, No. 424, Hafez Ave., Tehran, Iran ' Schlumberger Information Solution, 17th Floor, Sentra Mulia, Jl. Rasuna Saeid, Kav. X-6, No. 8, Jakarta 12940, Indonesia ' Petroleum Engineering Department, Amir-kabir University of Technology, No. 424, Hafez Ave., Tehran, Iran
Abstract: Many uncertainties exist in development of oil fields. Developing proxy models as substitutes for reservoir simulators is a fast method for uncertainty analysis. Artificial neural network (ANN) and polynomial regression models (PR) were used as proxy models in a sector of an Iranian heavy oil reservoir under steam flooding scenario. Screening analysis was used to find influential uncertain parameters. Different experimental designs have been applied to construct proxy models. A combination of Box-Behnken and inscribed central composite designs was most informative design. Comparison between proxy models results and simulator outputs shows that ANN and PR models can accurately predict the simulator outputs. However, the deviation of ANN from actual results is less than quadratic polynomials. The constructed proxy models were used in Monte Carlo simulation to obtain probabilistic production forecasts. The combination of experimental design and proxy models is a fast and accurate tool for risk analysis and prediction. [Received: July 12, 2012; Accepted: November 8, 2012]
Keywords: risk assessment; proxy models; artificial neural networks; ANNs; experimental design; Monte Carlo simulation; steam flooding; uncertainty assessment; modelling; oil fields; oil field development; reservoir simulation; Iran; heavy oil reservoirs; production forecasts.
International Journal of Oil, Gas and Coal Technology, 2014 Vol.7 No.1, pp.29 - 51
Available online: 21 Oct 2013Full-text access for editors Access for subscribers Purchase this article Comment on this article