A new approach for estimation of PVT properties of pure gases based on artificial neural network model

Equations of state are useful for description of fluid properties such as pressure-volume-temperature (PVT). However, the success estimation of such correlations depends mainly on the range of data which have originated. Therefore new models are highly required. In this work a new method is proposed based on Artificial Neural Network (ANN) for estimation of PVT properties of compounds. The data sets were collected from Perry's Chemical Engineers' Handbook. Different training schemes for the back-propagation learning algorithm, such as; Scaled Conjugate Gradient (SCG), Levenberg-Marquardt (LM) and Resilient back Propagation (RP) methods were used. The accuracy and trend stability of the trained networks were tested against unseen data. The LM algorithm with sixty neurons in the hidden layer has proved to be the best suitable algorithm with the minimum Mean Square Error (MSE) of 0.000606. The ANN's capability to estimate the PVT properties is one of the best estimating method with high performance.

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

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

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

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

[5]  M. A. Al-Marhoun,et al.  Using Artificial Neural Networks to Develop New PVT Correlations for Saudi Crude Oils , 2002 .

[6]  Harry Rodríguez-Vallés,et al.  A neural networks method to predict activity coefficients for binary systems based on molecular functional group contribution , 2006 .

[7]  Adnan Sözen,et al.  Investigation of thermodynamic properties of refrigerant/absorbent couples using artificial neural networks , 2004 .

[8]  Karen Schou Pedersen,et al.  Phase Behavior of Petroleum Reservoir Fluids , 2006 .

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

[10]  P. Perrot,et al.  A To Z Of Thermodynamics , 1998 .

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

[12]  R. Lang,et al.  A Future for Dynamic Neural Networks , 2000 .

[13]  A. Danesh.  PVT and Phase Behaviour of Petroleum Reservoir Fluids , 1998 .

[14]  G. Padmavathi,et al.  Neural modelling of Mooney viscosity of polybutadiene rubber , 2005, Comput. Chem. Eng..

[15]  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 .

[16]  Dominique Richon,et al.  Use of artificial neural networks for calculating derived thermodynamic quantities from volumetric property data , 2003 .

[17]  Don W. Green,et al.  Perry's Chemical Engineers' Handbook , 2007 .

[18]  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 .

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

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