Prediction of crude oil refractive index through optimized support vector regression: a competition between optimization techniques

Refractive index (RI) provides valuable information about various reservoir engineering calculations, making it a key parameter for characterizing crude oils. Determination of this index through experiment is capital-intensive, time consuming, and also toil. Hence, it is essential to search for an efficient and accurate estimation of crude oil RI. In this study, an intelligent approach, based on optimized support vector regression (SVR), is introduced to find a quantitative correlation between crude oil RI and SARA (saturate, aromatic, resin, and asphaltene) fraction data. Optimization of SVR is implemented through three searching approaches, viz. hybrid of grid and pattern search (HGP), genetic algorithm (GA), and imperialist competitive algorithm (ICA). Using these approaches, three models are constructed and tested on experimental data gathered from open source literature. To evaluate the performance of these models, their outputs are compared with corresponding experimental data in terms of statistical criteria. The comparative study clearly shows the advantage of ICA over its rivals (GA and HGP) in optimizing the SVR parameters. ICA optimized support vector regression results in an R2 of 0.9971 and MSE of 1.48548e−05 demonstrating its efficacy in obtaining crude oil refractive index form SARA data.

[1]  Benito E. Flores,et al.  A pragmatic view of accuracy measurement in forecasting , 1986 .

[2]  Amin Gholami,et al.  How committee machine with SVR and ACE estimates bubble point pressure of crudes , 2014 .

[3]  Caro Lucas,et al.  Imperialist competitive algorithm: An algorithm for optimization inspired by imperialistic competition , 2007, 2007 IEEE Congress on Evolutionary Computation.

[4]  J. Buckley,et al.  Crude oil and asphaltene characterization for prediction of wetting alteration , 2002 .

[5]  Ardeshir Hezarkhani,et al.  A new approach to improve permeability prediction of petroleum reservoirs using neural network adaptive wavelet (wavenet) , 2015 .

[6]  Hossein Safari,et al.  A hybrid intelligent computational scheme for determination of refractive index of crude oil using SARA fraction analysis , 2015 .

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

[8]  Jill S. Buckley,et al.  Evaluating Crude Oils by SARA Analysis , 2002 .

[9]  Javad Alikhani,et al.  An Optimization Problem for Evaluation of Image Segmentation Methods , 2010 .

[10]  Amin Gholami,et al.  Asphaltene precipitation of titration data modeling through committee machine with stochastically optimized fuzzy logic and optimized neural network , 2014 .

[11]  Amin Gholami,et al.  Support vector regression based determination of shear wave velocity , 2015 .

[12]  Amir H. Mohammadi,et al.  Hybrid of Two Heuristic Optimizations with LSSVM to Predict Refractive Index as Asphaltene Stability Identifier , 2014 .

[13]  Ali Naseri,et al.  Toward reservoir oil viscosity correlation , 2013 .

[14]  E. Hegazi,et al.  Measuring the refractive index of crude oil using a capillary tube interferometer , 2003 .

[15]  Andreas Christmann,et al.  Support vector machines , 2008, Data Mining and Knowledge Discovery Handbook.

[16]  Mohammad R. Riazi,et al.  Estimation of viscosity of liquid hydrocarbon systems , 2001 .

[17]  Farhad Gharagheizi,et al.  Diagnosis of asphaltene stability in crude oil through “two parameters” SVM model , 2012 .

[18]  M. Khishvand,et al.  Nonlinear Risk Optimization Approach to Gas Lift Allocation Optimization , 2012 .

[19]  Ali Chamkalani,et al.  Correlations between SARA Fractions, Density, and RI to Investigate the Stability of Asphaltene , 2012 .

[20]  Bernhard Schölkopf,et al.  Kernel Methods in Computational Biology , 2005 .

[21]  Amin Gholami,et al.  Oil-CO2 MMP Determination in Competition of Neural Network, Support Vector Regression, and Committee Machine , 2014 .

[22]  Amin Gholami,et al.  PSO-Fuzzy eliminates deficiency of neuro-fuzzy in assessment of asphaltene stability , 2015 .

[23]  Amin Gholami,et al.  Robust method based on optimized support vector regression for modeling of asphaltene precipitation , 2015 .

[24]  V. Vapnik.  Estimation of Dependences Based on Empirical Data , 2006 .

[25]  I. D. Gates,et al.  Support vector regression for porosity prediction in a heterogeneous reservoir: A comparative study , 2010, Comput. Geosci..

[26]  Amin Gholami,et al.  Genetic optimization of neural network and fuzzy logic for oil bubble point pressure modeling , 2014, Korean Journal of Chemical Engineering.

[27]  Caro Lucas,et al.  Imperialist competitive algorithm for minimum bit error rate beamforming , 2009, Int. J. Bio Inspired Comput..

[28]  A. M. Sarem,et al.  New Analytic Techniques for Petroleum Fluid Characterization Using Molar Refraction , 1997 .

[29]  Shahab D. Mohaghegh,et al.  Virtual-Intelligence Applications in Petroleum Engineering: Part 2—Evolutionary Computing , 2000 .

[30]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[31]  Caro Lucas,et al.  Colonial Competitive Algorithm as a Tool for Nash Equilibrium Point Achievement , 2008, ICCSA.

[32]  N. Morrow,et al.  WETTABILITY AND IMBIBITION: MICROSCOPIC DISTRIBUTION OF WETTING AND ITS CONSEQUENCES AT THE CORE AND FIELD SCALES , 2003 .

[33]  Walter G Chapman,et al.  Application of the One-Third rule in hydrocarbon and crude oil systems , 2010, Fluid Phase Equilibria.

[34]  Amin Gholami,et al.  Smart Determination of Difference Index for Asphaltene Stability Evaluation , 2014 .

[35]  Amin Gholami,et al.  An improved support vector regression model for estimation of saturation pressure of crude oils , 2015 .

[36]  Amin Gholami,et al.  Fuzzy Assessment of Asphaltene Stability in Crude Oils , 2014 .

[37]  Hamid Reza Ansari,et al.  Use seismic colored inversion and power law committee machine based on imperial competitive algorithm for improving porosity prediction in a heterogeneous reservoir , 2014 .

[38]  Amin Gholami,et al.  Smart correlation of compositional data to saturation pressure , 2015 .

[39]  Ardeshir Hezarkhani,et al.  Comparison of WAVENET and ANN for predicting the porosity obtained from well log data , 2014 .

[40]  Caro Lucas,et al.  Colonial competitive algorithm: A novel approach for PID controller design in MIMO distillation column process , 2008, Int. J. Intell. Comput. Cybern..

[41]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[42]  I. D. Gates,et al.  Support vector regression to predict porosity and permeability: Effect of sample size , 2012, Comput. Geosci..

[43]  A. Ghanbarzadeh,et al.  Application of PSO (particle swarm optimization) and GA (genetic algorithm) techniques on demand est , 2010 .

[44]  Ali Naseri,et al.  A Correlations Approach for Prediction of PVT Properties of Reservoir Oils , 2014 .

[45]  Ali Naseri,et al.  An artificial neural network approach to predict asphaltene deposition test result , 2012 .

[46]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .