Estimation of thermophysical properties of dimethyl ether as a commercial refrigerant based on artificial neural networks

In this research, the ability of Multilayer Perceptron Artificial Neural Networks based on back-propagation algorithm has been investigated to estimate dimethyl ether (RE 170) densities and vapor pressures. The best network configuration for this case was determined as a three layers network including 12, 15, 1 neurons in its layers, respectively, using Levenberg-Marquardt training algorithm. The comparisons between results show that there is a good agreement between experimental data and network predictions. As the uncertainties in the presented network for prediction of and saturated liquid, densities are less than 0.04% and 0.16%, respectively. Comparisons among the ANN predictions, several equations of state, and experimental data sets show that the ANN results are in good agreement with the experimental data better than EoSs. Another network for estimation of vapor pressure has been trained with uncertainty less than 0.85%. Results prove that artificial neural network can be a successful tool to represent thermophysical properties effectively, if develops efficiently.

[1]  Mehmet Bilgin.  Isobaric vapour-liquid equilibrium calculations of binary systems using a neural network , 2004 .

[2]  Mohammad Reza Dehghani,et al.  Modeling and prediction of activity coefficient ratio of electrolytes in aqueous electrolyte solution containing amino acids using artificial neural network , 2006 .

[3]  Jiangtao Wu,et al.  Vapor Pressure Measurements of Dimethyl Ether from (233 to 399) K , 2004 .

[4]  Adnan Sözen,et al.  Formulation based on artificial neural network of thermodynamic properties of ozone friendly refrigerant/absorbent couples , 2005 .

[5]  Somenath Ganguly,et al.  Prediction of VLE data using radial basis function network , 2003, Comput. Chem. Eng..

[6]  Mohammad Ali Moosavian,et al.  Characterization of basic properties for pure substances and petroleum fractions by neural network , 2005 .

[7]  P. Griffiths,et al.  Comparison of methods for calculating thermodynamic properties of binary mixtures in the sub and super critical state: Lee-Kesler and cubic equations of state for binary mixtures containing either CO2 or H2S , 2003 .

[8]  Jiangtao Wu,et al.  Vapor Pressure Measurements of Dimethyl Ether from (213 to 393) K , 2008 .

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

[10]  Alfredo Antonio,et al.  Development of neural network models for the prediction of dewpoint pressure of retrograde gases and saturated oil viscosity of black oil systems , 2002 .

[11]  Fengkun Wang,et al.  Surface Tension of Dimethyl Ether from (213 to 368) K , 2003 .

[12]  L. Fedele,et al.  Hydrogen-bonding of HFCs with dimethyl ether: evaluation by isothermal VLE measurements , 2002 .

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

[14]  Jorge C. G. Calado,et al.  Vapor-liquid equilibrium in the system dimethyl ether/methanol from 0 to 180.degree.C and at pressures to 6.7 MPa , 1982 .

[15]  M. Scattolini,et al.  Compressed Liquid Densities and Saturated Liquid Densities of Dimethyl Ether (RE170) , 2005 .

[16]  L. Fedele,et al.  Isothermal VLE Measurements for Difluoromethane + Dimethyl Ether and an Evaluation of Hydrogen Bonding , 2005 .

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

[18]  Jiangtao Wu,et al.  Measurement of the Critical Parameters and the Saturation Densities of Dimethyl Ether , 2004 .

[19]  L. Fedele,et al.  Isothermal vapour + liquid equilibrium measurements and correlation for the dimethyl ether + 1,1,1,2,3,3,3-heptafluoropropane and the propane + 1,1,1,2,3,3,3-heptafluoropropane systems , 2004 .

[20]  Eric W. Lemmon,et al.  Experimental densities, vapor pressures, and critical point, and a fundamental equation of state for dimethyl ether , 2007 .

[21]  Dominique Richon,et al.  Vapour–liquid equilibrium data for the 1,1,1,2 tetrafluoroethane (R134a) + dimethyl ether (DME) system at temperatures from 293.18 to 358.15 K and pressures up to about 3 MPa , 2005 .

[22]  M. Mohsennia,et al.  A three-parameter cubic equation of state for prediction of thermodynamic properties of fluids , 2008 .

[23]  R. Camporese,et al.  Vapor−Liquid Equilibrium for Dimethyl Ether and 2-Methylpropane , 2000 .

[24]  G. M. Wilson,et al.  Phase equilibria on seven binary mixtures , 2000 .

[25]  C. Peters,et al.  Phase behavior of the binary system near-critical dimethylether and tripalmitin: measurements and thermodynamic modeling , 2002 .

[26]  A. Fredenslund,et al.  High Pressure Solubility of Carbon Dioxide and Carbon Monoxide in Dimethyl Ether , 1995 .