Estimation of natural gas compressibility factors using artificial neural network approach

Abstract Prediction of compressibility factor of natural gas is an important key in many gas and petroleum engineering calculations. In this study compressibility factors of different compositions of natural gas are modeled by using an artificial neural network (ANN) based on back-propagation method. A reliable database including more than 5500 experimental data of compressibility factors is used for testing and training of ANN. The designed neural network can predict the natural gas compressibility factors using pseudo-reduced pressure and pseudo reduced temperature with average absolute relative deviation percent of 0.593. The accuracy of designed ANN has been compared to the mostly used empirical models as well as equations of state of Peng–Robinson and statistical association fluid theory. The comparison indicates that the proposed method provide more accurate results relative to other methods used in this work.

[1]  P. Buryan,et al.  Isothermal pVTmeasurements on gas hydrocarbon mixtures using a vibrating-tube apparatus , 2002 .

[2]  Ridha Gharbi.  Estimating the Isothermal Compressibility Coefficient of Undersaturated Middle East Crudes Using Neural Networks , 1997 .

[3]  W. Wagner,et al.  Refractive index and density isotherms for methane from 273 to 373 K and at pressures up to 34 MPa , 1992 .

[4]  E. Vogel,et al.  Viscosity Measurements and Predictions for Natural Gas , 2004 .

[5]  Anthony R. H. Goodwin,et al.  A MEMS Vibrating Edge Supported Plate for the Simultaneous Measurement of Density and Viscosity: Results for Argon, Nitrogen, and Methane at Temperatures from (297 to 373) K and Pressures between (1 and 62) MPa † , 2009 .

[6]  A. B. Bulsari,et al.  Neural Networks for Chemical Engineers , 1995 .

[7]  J. Trusler,et al.  Measurement of the (pressure, density, temperature) relation of two (methane + nitrogen) gas mixtures at temperatures between 240 and 400 K and pressures up to 20 MPa using an accurate single-sinker densimeter , 2006 .

[8]  Reid C. Miller,et al.  Densities and Dew Points of Vapor Mixtures of Methane + Propane and Methane + Propane + Hexane Using a Dual-Sinker Densimeter , 2001 .

[9]  Marc J. Assael,et al.  Viscosity of Natural-Gas Mixtures: Measurements and Prediction , 2001 .

[10]  Martin T. Hagan,et al.  Neural network design , 1995 .

[11]  P. S. Chappelear,et al.  Viscosity of methane, hydrogen, and four mixtures of methane and hydrogen from -100.degree.C to 0.degree.C at high pressures , 1976 .

[12]  Sayed Mohsen Hosseini,et al.  A new approach for estimation of PVT properties of pure gases based on artificial neural network model , 2009 .

[13]  B. Sage,et al.  Phase Equilibria in Hydrocarbon Systems The Methane-Ethane System in the Gaseous Region , 1939 .

[14]  A. Goodwin,et al.  Dielectric constants and molar polarizabilities for vapor mixtures of methane + propane and methane + propane + hexane obtained with a radio frequency reentrant cavity , 2002 .

[15]  B. Sage,et al.  Phase Equilibrium in Hydrocarbon Systems.Methane–Carbon Dioxide System in the Gaseous Region , 1944 .

[16]  D. R. Douslin,et al.  P-V-T Relations for Methane , 1964 .

[17]  C. Williamson,et al.  Second and third virial coefficients for (methane + nitrogen) , 2001 .

[18]  James G. Blencoe,et al.  Volumetric properties for {(1 –x)CO2+xCH4},{(1 −x)CO2+xN2}, and {(1 −x)CH4+xN2} at the preessures (19.94, 29.94, 39.94, 59.93, 79.93, and 99.93) MPa and the temperature 673.15 K , 1996 .

[19]  K. Hall,et al.  Accurate density measurements for a 91% methane natural gas-like mixture , 2007 .

[20]  D. Peng,et al.  A New Two-Constant Equation of State , 1976 .

[21]  G. Pazuki,et al.  The Prediction of the Compressibility Factor of Sour and Natural Gas by an Artificial Neural Network System , 2011 .

[22]  W. Wakeham,et al.  Densities of (water + methane) in the temperature range 430 K to 699 K and at pressures up to 30 MPa , 1996 .

[23]  Farhad Qanbari,et al.  Using artificial neural networks to estimate the z-factor for natural hydrocarbon gases , 2010 .

[24]  B. E. Gammon,et al.  Second and Third Virial Coefficients for Methane + Ethane and Methane + Ethane + Carbon Dioxide at (300 and 320) K , 1996 .

[25]  James G. Blencoe,et al.  Volumetric properties for {x1CO2+x2CH4+ (1 −x1−x2)N2} at the pressures (19.94, 39.94, 59.93, and 99.93) MPa and temperatures (323.15, 373.15, 473.15, and 573.15) K , 1996 .

[26]  Marc J. Assael,et al.  Dynamic Viscosity Measurements of Three Natural Gas Mixtures—Comparison against Prediction Models , 2007 .

[27]  N. Smaoui,et al.  Application of Artificial Neural Network for Estimating Tight Gas Sand Intrinsic Permeability , 1996 .

[28]  N. Kahraman,et al.  Internal combustion engines fueled by natural gas—hydrogen mixtures , 2004 .

[29]  S. Sumathi,et al.  Introduction to neural networks using MATLAB 6.0 , 2006 .

[30]  Stanley H. Huang,et al.  Equation of state for small, large, polydisperse, and associating molecules , 1990 .

[31]  Yasuhiko Arai,et al.  THE COMPRESSIBILITY FACTORS OF HYDROGEN METHANE, HYDROGEN-ETHANE AND HYDROGEN-PROPANE GASEOUS MIXTURES , 1977 .

[32]  K. Hall,et al.  (p, Vm, T) and phase equilibrium measurements for a natural gas-like mixture using an automated isochoric apparatus , 2006 .

[33]  J. C. Seitz,et al.  Volumetric properties for {(1 −x)CO2+xCH4}, {(1 −x)CO2+xN2}, and {(1 −x)CH4+xN2} at the pressures (9.94, 19.94, 29.94, 39.94, 59.93, 79.93, and 99.93) MPa and temperatures (323.15, 373.15, 473.15, and 573.15) K , 1996 .

[34]  W. Wakeham,et al.  Phase behaviour and density of (methane+n-butane) , 1999 .

[35]  J. Ely,et al.  Thermophysical Properties of Fluids. II. Methane, Ethane, Propane, Isobutane, and Normal Butane , 1987 .

[36]  Ehsan Heidaryan,et al.  A NOVEL CORRELATION APPROACH FOR PREDICTION OF NATURAL GAS COMPRESSIBILITY FACTOR , 2010 .