SimProxy Decision Support System: A Neural Network Proxy Applied to Reservoir and Surface Integrated Optimization

The development of an oil reservoir consists in drilling wells that maximize revenue. The quest for this configuration is often based on optimization processes that use the net present value as the evaluation function. Determining quantity, location, type, and trajectory of wells in a reservoir is a complex optimization problem, which has a high computational cost due to the continuous use of simulators. Many researchers have proposed the replacement of the reservoir simulator by a proxy, to reduce the computational cost, with promising results. However, in order to analyze all relevant variables and obtain a better solution, a comprehensive proxy model must also consider the conditions of the surface behavior, incorporating the complete integrated system. None of the previous works has developed a model based on the integrated simulation behavior. This article presents the proposal of a new proxy model based on neural networks, called SimProxy, which integrates reservoir and surface behavior, to reduce the computational cost of a decision support system. The proposed model was evaluated in a real oil reservoir. The results indicate that SimProxy can efficiently replace the use of commercial simulators in an optimization process, providing good accuracy with a substantial decrease in computational cost.

[1]  Jianchao Zeng,et al.  Surrogate-Assisted Cooperative Swarm Optimization of High-Dimensional Expensive Problems , 2017, IEEE Transactions on Evolutionary Computation.

[2]  Takashi Goda,et al.  History matching with iterative Latin hypercube samplings and parameterization of reservoir heterogeneity , 2014 .

[3]  Oscar Martinez,et al.  Solving the Challenges of Short and Long-Term Production Forecasting and Uncertainty Using a Fully-Coupled Implicit Integrated Production Modelling System , 2016 .

[4]  Eugene Fedutenko,et al.  Time-Dependent Neural Network Based Proxy Modeling of SAGD Process , 2014 .

[5]  Louis J. Durlofsky,et al.  Error modeling for surrogates of dynamical systems using machine learning , 2017 .

[6]  Ehsan Amirian,et al.  Cognitive Data-Driven Proxy Modeling for Performance Forecasting of WaterfloodingProcess , 2017 .

[7]  S. Hyakin,et al.  Neural Networks: A Comprehensive Foundation , 1994 .

[8]  Alberto Cominelli,et al.  The Benefits of Integrated Asset Modelling: Lessons Learned from Field Cases , 2008 .

[9]  I. Jolliffe.  Principal Component Analysis , 2002 .

[10]  William Pao,et al.  Dynamic Surrogate Reservoir Model with well constraints , 2016, 2016 3rd International Conference on Computer and Information Sciences (ICCOINS).

[11]  Eric Whittet Bhark,et al.  Best Practices of Assisted History Matching Using Design of Experiments , 2018, SPE Journal.

[12]  Soumya Mishra,et al.  Analysis of Levenberg-Marquardt and Scaled Conjugate gradient training algorithms for artificial neural network based LS and MMSE estimated channel equalizers , 2015, 2015 International Conference on Man and Machine Interfacing (MAMI).

[13]  Diane Rossiter,et al.  An input pre-screening technique for control structure selection , 1997 .

[14]  Xu Xu,et al.  Convolutional Neural Network Based on Principal Component Analysis Initialization for Image Classification , 2016, 2016 IEEE First International Conference on Data Science in Cyberspace (DSC).

[15]  Rui Jiang,et al.  Implementation and detailed assessment of a GNAT reduced-order model for subsurface flow simulation , 2019, J. Comput. Phys..

[16]  Ehsan Khamehchi,et al.  A Novel Approach to Assist History Matching Using Artificial Intelligence , 2015 .

[17]  Majid Siavashi,et al.  Efficient Particle Swarm Optimization of Well Placement to Enhance Oil Recovery Using a Novel Streamline-Based Objective Function , 2016 .

[18]  Francisco Javier Martinez-de-Pison,et al.  Metamodel-based design optimization of structural one-way slabs based on deep learning neural networks to reduce environmental impact , 2018 .

[19]  K. M. Teo,et al.  Well Placement, Infrastructure Design, Facility Allocation, and Production Planning in Multireservoir Oil Fields with Surface Facility Networks , 2014 .

[20]  Marley M. B. R. Vellasco,et al.  Optimization system for valve control in intelligent wells under uncertainties , 2010 .

[21]  S. Keleş,et al.  Sparse partial least squares regression for simultaneous dimension reduction and variable selection , 2010, Journal of the Royal Statistical Society. Series B, Statistical methodology.

[22]  Shahab D. Mohaghegh,et al.  Reservoir Simulation Using Smart Proxy in SACROC Unit - Case Study , 2016 .

[23]  Benjamin Baran,et al.  Multi-objective optimization of monitoring well location for CO2 leakage detection , 2016, 2016 35th International Conference of the Chilean Computer Science Society (SCCC).

[24]  Jose A. Romagnoli,et al.  An Integrated Machine-Learning Approach to Shale-Gas Supply-Chain Optimization and Refrac Candidate Identification , 2019, SPE Reservoir Evaluation & Engineering.

[25]  Michèle Hibon,et al.  Exponential smoothing: The effect of initial values and loss functions on post-sample forecasting accuracy , 1991 .

[26]  Z. Michalewicz,et al.  Genocop III: a co-evolutionary algorithm for numerical optimization problems with nonlinear constraints , 1995, Proceedings of 1995 IEEE International Conference on Evolutionary Computation.

[27]  Dilza Szwarcman,et al.  Well Placement Optimization Using a Genetic Algorithm With Nonlinear Constraints , 2009 .

[28]  Shahab Mohaghegh,et al.  A data-driven smart proxy model for a comprehensive reservoir simulation , 2016, 2016 4th Saudi International Conference on Information Technology (Big Data Analysis) (KACSTIT).

[29]  Yván Túpac,et al.  Dynamic and recursive oil-reservoir proxy using Elman neural networks , 2016, 2016 IEEE ANDESCON.

[30]  Lorenzo Livi,et al.  Investigating echo state networks dynamics by means of recurrence analysis , 2016, IEEE Trans. Neural Networks Learn. Syst..

[31]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[32]  Eduardo Camponogara,et al.  Integrated Methodology for Production Optimization from Multiple Offshore Reservoirs in the Santos Basin , 2017, IEEE Transactions on Automation Science and Engineering.

[33]  E. A. Ageh,et al.  Using Integrated Production Modeling (IPM) as an Optimization tool for Field Development Planning and Management , 2010 .

[34]  Marley M. B. R. Vellasco,et al.  Controlling Oil Production in Smart Wells by MPC Strategy With Reinforcement Learning , 2010 .

[35]  Lidong Mi,et al.  Optimization of Well Location, Type and Trajectory by a Modified Particle Swarm Optimization Algorithm for the PUNQ-S3 Model , 2015 .

[36]  Bachar Zineddin,et al.  A massively parallel coupled reservoir and surface facilities simulator , 2015, ANSS 2015.

[37]  J. Trivedi,et al.  Robust optimization of the production profile of the steam assisted gravity drainage reservoir using a polynomial chaos expansion-based proxy model , 2018, 2018 18th International Conference on Control, Automation and Systems (ICCAS).

[38]  B. Pradhan,et al.  Landslide susceptibility mapping at Vaz Watershed (Iran) using an artificial neural network model: a comparison between multilayer perceptron (MLP) and radial basic function (RBF) algorithms , 2013, Arabian Journal of Geosciences.