A new correlation based on artificial neural networks for predicting the natural gas compressibility factor

In this study a new correlation of natural gas compressibility factor based on theory of Mohammadikhah-Mohebbi-Abolghasemi’s equation of state (MMA EOS) is developed using an artificial neural network. In MMA EOS, the compressibility factor as a function of M-factor (BP/RT) is expressed. An artificial neural network (ANN) is designed in which the M-factor, reduced temperature, and reduced pressure are selected as input variables, whereas the natural gas compressibility factor is selected as output. Then, a new correlation based on the weights of ANN is obtained. Results of this correlation are compared with some other equations and experimental data. Proposed correlation for 597 data points has an average absolute deviation (AAD%) of 0.6% and a correlation coefficient (R2 value) of 0.9999.

[1]  T. Guo,et al.  A study on the supercompressibility and compressibility factors of natural gas mixtures , 1991 .

[2]  C. Tsonopoulos,et al.  Second virial coefficients of polar haloalkanes , 1975 .

[3]  Soteris A. Kalogirou,et al.  Artificial intelligence for the modeling and control of combustion processes: a review , 2003 .

[4]  Masoud Rahimi,et al.  New correlations to predict natural gas viscosity and compressibility factor , 2010 .

[5]  Mohammad Bagher Menhaj,et al.  Training feedforward networks with the Marquardt algorithm , 1994, IEEE Trans. Neural Networks.

[6]  Y. Duan,et al.  Correlations for second and third virial coefficients of pure fluids , 2004 .

[7]  Mohamed Mohandes,et al.  Estimation of global solar radiation using artificial neural networks , 1998 .

[8]  D. Henderson,et al.  Third virial coefficients of Ar Kr and Kr Xe mixtures , 1975 .

[9]  T. Boublı́k,et al.  The second virial coefficient of polar rod-like molecules , 2003 .

[10]  H. L. Johnston,et al.  Low Pressure Data of State of Nitric Oxide and of Nitrous Oxide between their Boiling Points and Room Temperature , 1934 .

[11]  Adolfo P. Pires,et al.  An equation of state for property prediction of alcohol–hydrocarbon and water–hydrocarbon systems , 2001 .

[12]  M. Moosavian,et al.  A novel equation of state (EOS) for prediction of solute solubility in supercritical carbon dioxide: Experimental determination and correlation , 2009 .

[13]  Joe W. Magee,et al.  Isochoric (p, ρ,T) measurements for five natural gas mixtures fromT=(225 to 350) K at pressures to 35 MPa , 1997 .

[14]  Roberto Battiti,et al.  First- and Second-Order Methods for Learning: Between Steepest Descent and Newton's Method , 1992, Neural Computation.

[15]  A. Vetere.  An improved method to predict the second virial coefficients of pure compounds , 1999 .

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

[17]  G. Cardini,et al.  Analytical approximations to virial coefficients for pure and mixed systems , 1986 .

[18]  Robert F. Curl,et al.  The Volumetric and Thermodynamic Properties of Fluids. III. Empirical Equation for the Second Virial Coefficient1 , 1957 .