Support Vector Regression and Functional Networks for viscosity and Gas/Oil Ratio Curves Estimation

In oil and gas industry, prior prediction of certain properties is needed ahead of exploration and facility design. Viscosity and gas/oil ratio (GOR) are among those properties described through curves with their values varying over a specific range of reservoir pressures. However, the usual single point prediction approach could result into curves that are inconsistent, exhibiting scattered behavior as compared to the real curves. Support Vector Regressors and Functional Networks are explored in this paper to solve this problem. Inputs into the developed models include hydrocarbon and non-hydrocarbon crude oil compositions and other strongly correlating reservoir parameters. Graphical plots and statistical error measures, including root mean square error and average absolute percent relative error, have been used to evaluate the performance of the models. A comparative study is performed between the two techniques and with the conventional feed forward artificial neural networks. Most importantly, the predicted curves are consistent with the shapes of the physical curves of the mentioned oil properties, preserving the need of such curves for interpolation and ensuring conformity of the predicted curves with the conventional properties.

[1]  Mohd Saberi Mohamad,et al.  A Hybrid of Genetic Algorithm and Support Vector Machine for Features Selection and Classification of Gene Expression Microarray , 2005, Int. J. Comput. Intell. Appl..

[2]  Adel M. Elsharkawy.  Modeling the Properties of Crude Oil and Gas Systems Using RBF Network , 1998 .

[3]  H. D. Beggs,et al.  Correlations for Fluid Physical Property Prediction , 1980 .

[4]  Jai P. Gupta,et al.  PVT Correlations of Indian Crude Using Support Vector Regression , 2009 .

[5]  Munirudeen A. Oloso,et al.  Prediction of Crude Oil Viscosity and Gas/Oil Ratio Curves Using Recent Advances to Neural Networks , 2009 .

[6]  S. A. Kahn.  Development Of Viscosity Correlations For Crude Oils , 1987 .

[7]  M N Hemmati,et al.  Evaluation of Empirically Derived PVT Properties for Middle East Crude Oils , 2007 .

[8]  J. P. Holman,et al.  Experimental methods for engineers , 1971 .

[9]  Yasin Hajizadeh,et al.  Viscosity prediction of crude oils with genetic algorithms , 2007 .

[10]  Weida Zhou,et al.  Support Vector Machines Based on the Orthogonal Projection Kernel of Father Wavelet , 2005, Int. J. Comput. Intell. Appl..

[11]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[12]  Enrique Castillo,et al.  Functional Networks , 1998, Neural Processing Letters.

[13]  M. A. Al-Marhoun,et al.  Evaluation Of Below Bubble Point Viscosity Correlations & Construction of a New Neural Network Model , 2007 .

[14]  F. Frashad,et al.  Empirical PVT Correlations For Colombian Crude Oils , 1996 .

[15]  Reyadh A. Almehaideb.  Improved PVT correlations for UAE crude oils , 1997 .

[16]  M. A. Al-Marhoun.  Evaluation of empirically derived PVT properties for Middle East crude oils , 2004 .

[17]  Carlton Beal,et al.  The Viscosity of Air, Water, Natural Gas, Crude Oil and Its Associated Gases at Oil Field Temperatures and Pressures , 1946 .

[18]  Ju-Nam Chew,et al.  A Viscosity Correlation for Gas-Saturated Crude Oils , 1959 .

[19]  Anthony Widjaja,et al.  Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond , 2003, IEEE Transactions on Neural Networks.

[20]  J.T.H. Ng,et al.  An Improved Temperature-Viscosity Correlation For Crude Oil Systems , 1983 .

[21]  O. Glaso,et al.  Generalized Pressure-Volume-Temperature Correlations , 1980 .

[22]  Adel M. Elsharkawy,et al.  Universal Neural Network Based Model for Estimating The PVT Properties of Crude Oil Systems , 1997 .

[23]  Amar Khoukhi,et al.  PVT properties prediction using hybrid genetic-neuro-fuzzy systems , 2011 .

[24]  H. D. Beggs,et al.  Correlations for Fluid Physical Property Prediction , 1980 .

[25]  F. F. Farshad,et al.  Pressure-Volume-Temperature Correlations for Gulf of Mexico Crude Oils , 1993 .

[26]  Vassilis Gaganis,et al.  A Novel Non-Iterative Method for the Prediction of the PVT Behavior of Reservoir Fluids , 1999 .

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

[28]  Amar Khoukhi,et al.  Viscosity and gas/oil ratio curves estimation using advances to neural networks , 2011, International Workshop on Systems, Signal Processing and their Applications, WOSSPA.

[29]  E. Castillo,et al.  Functional Networks: A New Network‐Based Methodology , 2000 .

[30]  Munirudeen A. Oloso,et al.  Evolutionary Neural Networks for Estimating Viscosity and Gas/Oil Ratio Curves , 2010 .

[31]  Rafa Labedi,et al.  Improved correlations for predicting the viscosity of light crudes , 1992 .

[32]  Mansour Karkoub,et al.  Universal neural-network-based model for estimating the PVT properties of crude oil systems , 1999 .

[33]  F. F. Farshad,et al.  Viscosity Correlations for Gulf of Mexico Crude Oils , 1995 .

[34]  M. A. Al-Marhoun,et al.  Artificial Neural Networks Models for Predicting PVT Properties of Oil Field Brines , 2005 .

[35]  A. A. Al-Shammasi.  Bubble Point Pressure and Oil Formation Volume Factor Correlations , 1999 .

[36]  A. A. Al-Shammasi.  A Review of Bubblepoint Pressure and Oil Formation Volume Factor Correlations , 2001 .

[37]  Birol Dindoruk,et al.  PVT Properties and Viscosity Correlations for Gulf of Mexico Oils , 2004 .

[38]  S. S. Ikiensikimama,et al.  Black Oil Empirical PVT Correlations Screening for the Niger Delta Crude , 2006 .

[39]  Dustin Boswell,et al.  Introduction to Support Vector Machines , 2002 .

[40]  Abdul Azeez Abdul Raheem,et al.  Prediction of crude oil viscosity curve using artificial intelligence techniques , 2012 .