Modélisation des propriétés thermodynamique et de transport de l’eau aux états liquide et vapeur

B. Mohammedi, S. Hanini, N. Mellel, M. Boumaza


Abstract: In this work, we are interested in the modeling of thermodynamic and transport properties of the water and steam with a wide range of pressure, temperature, enthalpy and entropy using artificial neural networks (ANN). These networks enable us to reproduce, as faithfully as possible, the properties concerned by the study, namely 21 properties in the saturation state, 17 properties for the superheated steam and for the subcooled liquid. These properties are expressed according to pressure and enthalpy or pressure and temperature, a formulation linking otherwise the temperature and enthalpy. The interest of these functions is to allow cover a wide area of use, single and two phase, thermodynamic properties with a single formulation.

Several networks are developed; the average relative error for the least estimated property does not exceed 2%. We then compiled all the networks in a visual application developed under Borland Delphi with an intuitive graphical user interface for greatest ease of use for calculation of water properties.

Résumé : Dans ce travail, nous nous sommes intéressés à la modélisation des propriétés thermodynamique et de transport de l’eau aux états liquide et vapeur avec une large gamme de pression, de température, d’enthalpie et d’entropie au moyen des réseaux de neurones artificiels ANN (Artificial Neural Network). Ces réseaux permettent de reproduire, le plus fidèlement possible, les propriétés concernées par l’étude, à savoir 21 propriétés à l’état de saturation, 17 propriétés pour la vapeur surchauffée et pour le liquide sous-refroidi. Ces propriétés sont exprimées en fonction de la pression et de l’enthalpie ou de la pression et de la température, une formulation reliant par ailleurs la température et l’enthalpie. L’intérêt de ces fonctions est de permettre de couvrir un large domaine d’utilisation, simple et double phase, des propriétés thermodynamiques avec une seule formulation.

Plusieurs réseaux sont développés, dont l’erreur relative moyenne pour la propriété la moins estimée n’excède pas 2 %. Nous avons, ensuite, compilé tous les réseaux dans une application visuelle élaborée sous Borland Delphi avec une interface graphique utilisateur intuitive pour une plus grande facilité d'utilisation pour le calcul des propriétés de l’eau.

Full Text:



Wagner, W.; Kretzschmar H.J. International Steam Tables. Second edition; Springer-Verlag Berlin Heidelberg (2008).

Si-Moussa, C.; Hanini, S.; Derriche, R.; Bouhedda, M.; Bouzidi A. Prediction of high-pressure vapor liquid equilibrium of six binary systems; carbon dioxide with six esters; using an artificial neural network model. Brazilian Journal of Chemical Engineering 25:01(2008) 183-199.

Yaws C.L. Chemical properties handbook. McGRAW-HILL (2006).

Stowe K. An introduction to thermodynamics and statistical mechanics. Cambridge University Press second edition (2007).

Dreyfus, G.; Martinez, J.M.; Samuelides, M.; Gordon, M. B.; Badran F.; Thiria S. Réseaux de Neurones Méthodologie et Applications. Editions Eyrolles. Paris (2002).

Lee, Y.; Oh, S.H.; Kim M.W. The Effect of Initial Weights on Premature Saturation in Back-Propagation Learning. International Joint Conference on Neural Networks. 1(1991) 765-770.

Demuth, H.; Beale, M.; Hagan M. Matlab, Neural Network Toolbox 6. User’s Guide MathWorks Inc. (2009).

Lu, M.L.; McGreavy, C.; Kam E.K.T. Prediction of Thermal Conductivity of Pure Liquids and Mixtures Using Neural Network. Journal of Chemical Engineering of Japan 30:3(1997).

Lee, M.J.; Hwang, S.M.; Chen J.T. Density and Viscosity Calculations for Polar Solutions via Neural Networks. Journal of Chemical Engineering of Japan 27:6(1994).

Homer, J.; Generalis, S.; Robson J.H. Artificial Neural Networks for Prediction of Liquids Viscosity; Density; Heat of Vaporization; Boiling Point and Pitzer’s Acentric Factor Part I: Hydrocarbons. Physical Chemistry Chemical Physics. 1:17(1999) 4075-4081. DOI: 10.1039/a904096j.

Rai, P.; Majumdar ,G.C.; DasGupta, S.; De S. Prediction of Viscosity of Clarified Fruit Juice Using Artificial Neural Network: A Combined Effect of Concentration and Temperature. Journal of Food Engineering 68(2005) 527-533. DOI: 10.1016/j.jfoodeng.2004.07.003.

Scalabrin, G.; Critofoli G. The Viscosity Surface of Propane in the Form of Multilayer Feed Forward Neural networks. International Journal of Thermophysics 24:5(2003).

Scalabrin, G.; Corbetti, C.; Cristofoli G. A. Viscosity Equation of State for R123 in the Form of Multilayer Feed Forward Neural networks. International Journal of Thermophysics 22:5(2001).

Scalabrin, G.; Cristofoli G. The Viscosity Surfaces of R152a in the Form a Multilayer Feed Forward Neural Networks. International Journal of Refrigeration 26(2003) 302-314.

Cristofoli, G.; Piazza, L.; Scalabrin G. A. Viscosity Equation of State For R134a Through a Multilayer Feed Forward Neural Networks. Fluid Phase Equilibria 199(2002) 223-236.

Beladel, B.; Mohammedi, B.; Guesmia, A.; Benamar M.E.A. Neural network prediction of K and L-shell X-ray production cross sections. Radiochimica Acta 106:12(2018); DOI: 10.1515/ract-2018-2990.

Gheziel, A.; Hanini, S.; Mohammedi, B.; Ararem, A.; Mellel N. Particle dispersion modeling in ventilated room using artificial neural network. Nuclear Science and Techniques 28:5(2017). DOI: 10.1007/s41365-016-0159-6.

Wagner, W.; Prub A. The IAPWS Formulation 1995 for the Thermodynamic Properties of Ordinary Water Substance for General and Scientific Use. Journal of Physical Chemistry 31(2002) 387-535.

Harvey A.H. Thermodynamic Properties of Water: Tabulation from the IAPWS Formulation 1995 for the Thermodynamic Properties of Ordinary Water Substance for General and Scientific Use. NISTIR 5078, National Institute of Standards and Technology (1998).

Washburn E.W. International Critical Tables of Numerical Data, Physics, Chemistry and Technology. National Academies Press Washington DC (1930). DOI: 10.17226/20230.

Chase M.W. JANAF Thermochemical Tables. Journal of Physical and Chemical Reference Data 14:1(1985).

Yaws C.L. Yaws Handbook of thermodynamic and physical properties of chemical compounds. Norwich New York, Knovel (2004).

Goodwin, A.R.H.; Marsh, K.N.; Wakeham W.A. Measurement of the thermodynamic properties of single phases (Experimental thermodynamics) volume vi. International Union of Pure and Applied Chemistry; Elsevier Science B.V.(2003).

Rogers, G.F.C.; Mayhew Y.R. Thermodynamic and Transport Properties of Fluids: SI Units. Blackwell Publishing Ltd (2004).

Gicquel R. Diagrammes interactifs des vapeurs, Manuel d’utilisation. Thermoptim Version V1.3 (2000).

Alberty R.A. Biochemical Thermodynamics: Applications of Mathernatica. John Wiley & Sons (2006).

Andyc Creation and Katmar Software; WASP for Windows; Version 2.0.36 (2004).

Ciftcioglu, Ö.; Türkcan E. SMORN-VII : Report neural network benchmark; analysis results & follow-up’96. A symposium on Nuclear Reactor Surveillance and Diagnostics (1996) Avignon (FRANCE) revised (1998).

Wu C. Thermodynamic Cycles: Computer-aided design and optimization. Marcel Dekker Inc. (2004).

Barrachin, M.; Cheynet, B.; Fischer E. NUCLEA : Une base de données thermodynamiques pour les applications nucléaires. Journée sur la coopération scientifique CNRS/IRSN (2008).


  • There are currently no refbacks.