Evolving an accurate model based on machine learning approach for prediction of dew-point pressure in gas condensate reservoirs

Abstract Over the years, accurate prediction of dew-point pressure of gas condensate has been a vital importance in reservoir evaluation. Although various scientists and researchers have proposed correlations for this purpose since 1942, but most of these models fail to provide the desired accuracy in prediction of dew-point pressure. Therefore, further improvement is still needed. The objective of this study is to present an improved artificial neural network (ANN) method to predict dew-point pressures in gas condensate reservoirs. The model was developed and tested using a total set of 562 experimental data point from different gas condensate fluids covering a wide range of variables. After a series of optimization processes by monitoring the networks performance, the best network structure was selected. This study also presents a detailed comparison between the results predicted by this ANN model and those of other universal empirical correlations for estimation dew-point pressure. The results showed that the developed model outperforms all the existing methods and provides predictions in acceptable agreement with experimental data. Also it is shown that the improved ANN model is capable of simulating the actual physical trend of the dew-point pressure versus temperature between the cricondenbar and cricondenterm on the phase envelope. Finally, an outlier diagnosis was performed on the whole data set to detect the erroneous measurements from experimental data.

[1]  Harvey T. Kennedy,et al.  A Correlation of Dewpoint Pressure With Fluid Composition and Temperature , 1967 .

[2]  Ali Elkamel,et al.  Reservoir permeability prediction by neural networks combined with hybrid genetic algorithm and particle swarm optimization , 2013 .

[3]  Robert J. Schalkoff,et al.  Artificial neural networks , 1997 .

[4]  Farhad Gharagheizi,et al.  Intelligent model for prediction of CO2 – Reservoir oil minimum miscibility pressure , 2013 .

[5]  Sohrab Zendehboudi,et al.  Prediction of Condensate-to-Gas Ratio for Retrograde Gas Condensate Reservoirs Using Artificial Neural Network with Particle Swarm Optimization , 2012 .

[6]  E. Rój,et al.  Simulation of an absorption column performance using feed-forward neural networks in nitric acid production , 1998 .

[7]  Kenneth Levenberg.  A METHOD FOR THE SOLUTION OF CERTAIN NON – LINEAR PROBLEMS IN LEAST SQUARES , 1944 .

[8]  Payam Setoodeh,et al.  Artificial Neural Network Modeling of Surface Tension for Pure Organic Compounds , 2012 .

[9]  M. A. Al-Marhoun,et al.  A New Correlation for Gas-condensate Dewpoint Pressure Prediction , 2001 .

[10]  Farhad Gharagheizi,et al.  Toward an intelligent approach for determination of saturation pressure of crude oil , 2013 .

[11]  Ali Danesh,et al.  Phase behavior modeling of gas-condensate fluids using an equation of state , 1991 .

[12]  Adel M. Elsharkawy,et al.  Predicting the dew point pressure for gas condensate reservoirs: empirical models and equations of state , 2002 .

[14]  Colin R. Goodall,et al.  13 Computation using the QR decomposition , 1993, Computational Statistics.

[15]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[16]  K. S. Pedersen,et al.  Characterization of gas condensate mixtures , 1988 .

[17]  B. H. Sage,et al.  Volumetric and Viscosity Studies of Oil and Gas from a San Joaquin Valley Field , 1949 .

[18]  Joseph J. Martin.  Cubic Equations of State-Which? , 1979 .

[19]  Arne Crogh.  Improved correlations for retrograde gases , 1996 .

[20]  B. H. Sage,et al.  Volumetric and Phase Behavior of Oil and Gas from Paloma Field , 1945 .

[21]  Mohammad R. Riazi,et al.  Estimation of properties distribution of C7+ by using artificial neural networks , 2011 .

[22]  Celso Kazuyuki Morooka,et al.  Development of intelligent systems for well drilling and petroleum production , 2001 .

[23]  A. Mohammadi,et al.  Use of Artificial Neural Networks for Estimating Water Content of Natural Gases , 2007 .

[24]  E. I. Organick,et al.  Prediction of Saturation Pressures for Condensate-Gas and Volatile-Oil Mixtures , 1952 .

[25]  G. Soave.  Equilibrium constants from a modified Redlich-Kwong equation of state , 1972 .

[26]  D. Richon,et al.  Modeling of thermodynamic properties using neural networks: Application to refrigerants , 2002 .

[27]  Okan Ozgonenel,et al.  The use of artificial neural networks (ANN) for modeling of adsorption of Cu(II) from industrial leachate by pumice , 2011 .

[28]  Amin Shokrollahi,et al.  Evolving artificial neural network and imperialist competitive algorithm for prediction oil flow rate of the reservoir , 2013, Appl. Soft Comput..

[29]  D. Zudkevitch,et al.  Correlation and prediction of vapor‐liquid equilibria with the redlich‐kwong equation of state , 1970 .

[30]  Reza Chamkalani,et al.  SOFT COMPUTING METHOD FOR PREDICTION OF CO2 CORROSION IN FLOW LINES BASED ON NEURAL NETWORK APPROACH , 2013 .

[31]  Mahmood Amani,et al.  Implementation of SVM framework to estimate PVT properties of reservoir oil , 2013 .

[32]  K. Vasanth Kumar,et al.  Neural Network Prediction of Interfacial Tension at Crystal/Solution Interface , 2009 .

[33]  Peter J. Rousseeuw,et al.  Robust regression and outlier detection , 1987 .

[34]  Farhad Gharagheizi,et al.  Toward a predictive model for estimating dew point pressure in gas condensate systems , 2013 .

[35]  D. Marquardt.  An Algorithm for Least-Squares Estimation of Nonlinear Parameters , 1963 .

[36]  B. H. Sage,et al.  Volumetric Behavior of Oil and Gas From a Louisiana Field I , 1950 .

[37]  Paola Gramatica,et al.  Principles of QSAR models validation: internal and external , 2007 .

[38]  Ali Naseri,et al.  Reservoir oil viscosity determination using a rigorous approach , 2014 .