Proxy models for evaluation of permeability, three-phase relative permeability, and capillary pressure curves from rate-transient data

This study developed a data-driven forecasting tool that predicts petrophysical properties from rate-transient data. Traditional estimations of petrophysical properties, such as relative permeability (RP) and capillary pressure (CP), strongly rely on coring and laboratory measurements. Coring and laboratory measurements are typically conducted only in a small fraction of wells. To contend with this constraint, in this study, we develop artificial neural network (ANN)-based tools that predict the three-phase RP relationship, CP relationship, and formation permeability in the horizontal and vertical directions using the production rate and pressure data for black-oil reservoirs. Petrophysical properties are related to rate-transient data as they govern the fluid flow in oil/gas reservoirs. An ANN has been proven capable of mimicking any functional relationship with a finite number of discontinuities. To generate an ANN representing the functional relationship between rate-transient data and petrophysical properties, an ANN structure pool is first generated and trained. Cases covering a wide spectrum of properties are then generated and put into training. Training of ANNs in the pool and comparisons among their performance yield the desired ANN structure that performs the most effectively among the ANNs in the pool. The developed tool is validated with blind tests and a synthetic field case. Reasonable predictions for the field cases are obtained. Within a fraction of second, the developed ANNs infer accurate characteristics of RP and CP for three phases as well as residual saturation, critical gas saturation, connate water saturation, and horizontal permeability with a small margin of error. The predicted RP and CP relationship can be generated and applied in history matching and reservoir modeling. Moreover, this tool can spare coring expenses and prolonged experiments in most of the field analysis. The developed ANNs predict the characteristics of three-phase RP and CP data, connate water saturation, residual oil saturation, and critical gas saturation using rate-transient data. For cases fulfilling the requirement of the tool, the proposed technique improves reservoir description while reducing expenses and time associated with coring and laboratory experiments at the same time.

[1]  F. G. McCaffery,et al.  An Improved Unsteady-State Procedure for Determining the Relative-Permeability Characteristics of Heterogeneous Porous Media (includes associated papers 8028 and 8777 ) , 1979 .

[2]  H. D. Beggs,et al.  Estimating the Viscosity of Crude Oil Systems , 1975 .

[3]  Turgay Ertekin,et al.  Advanced Well Structures: An Artificial Intelligence Approach to Field Deployment and Performance Prediction , 2014 .

[4]  Crotti,et al.  Relative Permeability Curves: The Influence of Flow Direction and Heterogeneities. , 1998 .

[5]  E. F. Johnson,et al.  Calculation of Relative Permeability from Displacement Experiments , 1959 .

[6]  Mohammad Piri,et al.  Pore-Scale Modelling of Three-Phase Flow , 2003 .

[7]  R. H. Brooks,et al.  Properties of Porous Media Affecting Fluid Flow , 1966 .

[8]  Turgay Ertekin,et al.  Artificial neural network based design for dual lateral well applications , 2014 .

[9]  A. T. Watson,et al.  Determination of Three-Phase Relative Permeabilities From Displacement Experiments , 1997 .

[10]  M. B. Standing,et al.  Volumetric and phase behavior of oil field hydrocarbon systems , 1952 .

[11]  P. Egermann,et al.  A New Three-Phase Relative Permeability Model For Various Wettability Conditions , 1999 .

[12]  Zhenzihao Zhang,et al.  Production data analysis for dual-porosity gas/liquid systems: A density-based approach , 2017 .

[13]  Mario H. Gonzalez,et al.  The Viscosity of Natural Gases , 1966 .

[14]  Bin Yuan,et al.  A novel integrated workflow for evaluation, optimization, and production predication in shale plays , 2017 .

[15]  S. Goodyear,et al.  New Coreflood Interpretation Method for Relative Permeabilities Based on Direct Processing of In-Situ Saturation Data , 2001 .

[16]  Martin J. Blunt.  An Empirical Model for Three-Phase Relative Permeability , 2000 .

[17]  Ali Abedini,et al.  Comparison of scaling equation with neural network model for prediction of asphaltene precipitation , 2010 .

[18]  L. Ayala H.,et al.  Analytical dual-porosity gas model for reserve evaluation of naturally fractured gas reservoirs using a density-based approach , 2018, Journal of Natural Gas Science and Engineering.

[19]  T. Ertekin,et al.  A Neurosimulation Tool for Predicting Performance in Enhanced Coalbed Methane and CO2, Sequestration Projects , 2005 .

[20]  John Heaviside,et al.  Fundamentals of Relative Permeability: Experimental and Theoretical Considerations , 1983 .

[21]  A. Skauge,et al.  Rate Effects on Centrifuge Drainage Relative Permeability , 2000 .

[22]  Muhammad Sahimi,et al.  Flow and Transport in Porous Media and Fractured Rock: From Classical Methods to Modern Approaches , 1995 .

[23]  F H Luis Ayala,et al.  Neuro-simulation analysis of pressure maintenance operations in gas condensate reservoirs , 2007 .

[24]  J. Hagoort,et al.  Oil Recovery by Gravity Drainage , 1980 .

[25]  R. P. Sutton.  Compressibility Factors for High-Molecular-Weight Reservoir Gases , 1985 .

[26]  Artificial-Intelligence Technology Predicts Relative Permeability of Giant Carbonate Reservoirs , 2009 .

[27]  Parul Parashar,et al.  Neural Networks in Machine Learning , 2014 .

[28]  Zhenzihao Zhang.  Predicting Petrophysical Properties From Rate-Transient Data: An Artificial Intelligence Application , 2017 .

[29]  Qian Sun,et al.  Development and Application of an Artificial-Neural-Network Based Expert System for Screening and Optimization of Polymer Flooding Projects , 2018 .

[30]  H. Sarma,et al.  A Laboratory Investigation of the Pseudo Relative Permeability Characteristics of Unstable Immiscible Displacements , 1994 .

[31]  T. Ertekin,et al.  An Effective Coupling of Type Curves and Expert Systems for Evaluating Multi-stage Hydraulically Fractured Horizontal Wells in Composite Dual-porosity Shale Gas Reservoirs , 2014 .

[32]  H. L. Stone.  Probability Model for Estimating Three-Phase Relative Permeability , 1970 .

[33]  Farad Kamyabi,et al.  Multiphase Flow in Porous Media , 2014 .

[34]  Thomas Alwin Blasingame,et al.  Decline Curve Analysis for Variable Pressure Drop/Variable Flowrate Systems , 1991 .

[35]  P. M. Dranchuk,et al.  Calculation of Z Factors For Natural Gases Using Equations of State , 1975 .

[36]  Torleif Holt,et al.  Gravity Stable Displacement of Oil by Hydrocarbon Gas After Waterflooding , 1992 .

[37]  Turgay Ertekin,et al.  An Artificial Neural Network Based Relative Permeability Predictor , 2003 .

[38]  S. Skjaeveland,et al.  Three-Phase Relative Permeabilities from Displacement Experiments with Full Account for Capillary Pressure , 1998 .

[39]  R. W. Watson,et al.  Development of universal proxy models for screening and optimization of cyclic pressure pulsing in naturally fractured reservoirs , 2011 .

[40]  Luis F. Ayala,et al.  Study of Gas/Condensate Reservoir Exploitation Using Neurosimulation , 2007 .

[41]  G. Jerauld.  General Three-Phase Relative Permeability Model for Prudhoe Bay , 1997 .

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

[43]  S. E. Buckley,et al.  Mechanism of Fluid Displacement in Sands , 1942 .

[44]  M. R. Islam,et al.  A Dynamic Method For Measuring Relative Permeability , 1986 .

[45]  Ahmed H. El-Banbi,et al.  Production Analysis of Linear Flow Into Fractured Tight Gas Wells , 1998 .

[46]  E. C. Donaldson,et al.  Two- and three-phase relative permeability studies , 1965 .

[47]  A. M. Sarem.  Three-Phase Relative Permeability Measurements by Unsteady-State Method , 1966 .

[48]  Turgay Ertekin,et al.  A New Screening Tool for Improved Oil Recovery Methods Using Artificial Neural Networks , 2012 .

[49]  A. Grader,et al.  Development and Testing of Two-Phase Relative Permeability Predictors Using Artificial Neural Networks , 2002 .

[50]  W. McCain.  Reservoir-fluid property correlations; State of the art , 1991 .

[51]  H. L. Stone.  Estimation of Three-Phase Relative Permeability And Residual Oil Data , 1973 .

[52]  F. Civan,et al.  Direct Determination of Relative Permeability from Nonsteady-State Constant Pressure and Rate Displacements , 2001 .

[53]  B. B. Maini,et al.  Measurements and Correlations of Three-Phase Relative Permeability at Elevated Temperatures and Pressures , 1989 .

[54]  Turgay Ertekin,et al.  The Development of an Artificial Neural Network as a Pressure Transient Analysis Tool for Applications in Double-Porosity Reservoirs , 2007 .

[55]  Qian Sun,et al.  Structuring an artificial intelligence based decision making tool for cyclic steam stimulation processes , 2017 .

[56]  Prasanna Chidambaram.  Development and testing of an artificial neural network based history matching protocol to characterize reservoir properties , 2009 .

[57]  Donald L. Katz,et al.  Density of Natural Gases , 1942 .

[58]  Martin J. Blunt,et al.  Theoretical Analysis of Three Phase Flow Experiments in Porous Media , 1996 .

[59]  L. Ayala H.,et al.  Decline curve analysis using a pseudo-pressure-based interporosity flow equation for naturally fractured gas reservoirs , 2017, Journal of Petroleum Exploration and Production Technology.

[60]  W. R. Purcell,et al.  Capillary Pressures - Their Measurement Using Mercury and the Calculation of Permeability Therefrom , 1949 .

[61]  Tao Gang,et al.  A More General Capillary Pressure Curve and Its Estimation From Production Data , 2007 .

[62]  Engel Van Spronsen.  Three-phase relative permeability measurements using the centrifuge method , 1982 .

[63]  Farshid Torabi,et al.  IMPLEMENTING ARTIFICIAL NEURAL NETWORK FOR PREDICTING CAPILLARY PRESSURE IN RESERVOIR ROCKS , 2013 .

[64]  K. Aziz,et al.  Analysis and correlation of nitrogen and lean gas miscibility pressure , 1985 .

[65]  H. J. Welge,et al.  A Simplified Method for Computing Oil Recovery by Gas or Water Drive , 1952 .

[66]  D. J. O'Meara,et al.  Multiphase Relative Permeability Measurements Using an Automated Centrifuge , 1983 .

[67]  Luis F. Ayala,et al.  Analysis of Gas-Cycling Performance in Gas/Condensate Reservoirs Using Neuro-Simulation , 2005 .

[68]  Farshid Torabi,et al.  The Development of an Artificial Neural Network Model for Prediction of Crude Oil Viscosities , 2011 .

[69]  Djebbar Tiab,et al.  Petrophysics: Theory and Practice of Measuring Reservoir Rock and Fluid Transport Properties , 1996 .

[70]  S. C. Jones,et al.  Graphical Techniques for Determining Relative Permeability From Displacement Experiments , 1978 .

[71]  Qiang Sun,et al.  Forecasting Well Performance in a Discontinuous Tight Oil Reservoir Using Artificial Neural Networks , 2013 .

[72]  Turgay Ertekin,et al.  An Artificial Neural Network Utility for the Optimization of History Matching Process , 2007 .