Prediction of vapor–liquid equilibrium data for ternary systems using artificial neural networks

Abstract Most solvents used in the semiconductor industry are toxic and costly. Thus, the solvents should be recovered for re-use in these processes by distillation methods, and vapor–liquid equilibrium data are necessary for the design and operation of distillation columns. These data can be estimated using activity coefficient models. In this work, artificial neural networks were applied to predict and estimate vapor–liquid equilibrium data for ternary systems saturated with salt. The databases taken from literature were split into training, validating and testing data and the best architecture was an 8–6–7–4 network. The absolute mean errors for the whole database were 0.0166, 0.0177, 0.0151 for the vapor mole fraction of components ( y 1 , y 2 , y 3 ) and 0.74 °C for the bubble point temperature. The artificial neural network predictions showed better agreement with experimental data than the thermodynamic model predictions.

[1]  Alberto Arce,et al.  VLE for water + ethanol + 1-octanol mixtures. Experimental measurements and correlations , 1996 .

[2]  J. Gmehling,et al.  Vapor-liquid equilibrium data collection. Aqueous-organic systems , 1977 .

[3]  K. W. Ho,et al.  Prediction and experimental verification of the salt effect on the vapour–liquid equilibrium of water–ethanol–2-propanol mixture , 2004 .

[4]  T. C. Tan,et al.  Prediction and experimental verification of the effect of salt on the vapour–liquid equilibrium of ethanol/1-propanol/water mixture , 2005 .

[5]  H. C. Ti,et al.  Isobaric vapour—liquid equilibria of ethanol—toluene—sodium acetate mixtures at various system pressures , 1988 .

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

[7]  Akira Takada,et al.  Prediction of vapor–liquid equilibrium for binary systems containing HFEs by using artificial neural network , 2002 .

[8]  Faïçal Larachi,et al.  Vapour–liquid equilibrium data analysis for mixed solvent–electrolyte systems using neural network models , 2000 .

[9]  Robert J. Schalkoff,et al.  Artificial neural networks , 1997 .

[10]  K. Asadpour‐Zeynali,et al.  Solubility prediction of anthracene in binary and ternary solvents by artificial neural networks (ANNs) , 2004 .

[11]  D. R. Baughman,et al.  Neural Networks in Bioprocessing and Chemical Engineering , 1992 .

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

[13]  Swati Mohanty,et al.  Estimation of vapour liquid equilibria of binary systems, carbon dioxide–ethyl caproate, ethyl caprylate and ethyl caprate using artificial neural networks , 2005 .

[14]  H. Renon.  Vapour-liquid equilibrium data collection: Aqueous organic systems : by J. Gmehling and U. Onken, Chemistry Data Series, Vol. I, Part 1, Dechema, Frankfurt/Main, 1977 , 1977 .

[15]  Malcolm H. I. Baird,et al.  Handbook of Solvent Extraction , 1991 .

[16]  M. Iliuta,et al.  Salt effect of LiCl on vapor–liquid equilibrium of the acetone–methanol system , 1998 .

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

[18]  R. Reid,et al.  The Properties of Gases and Liquids , 1977 .

[19]  Ernesto Vercher,et al.  Isobaric Vapor−Liquid Equilibrium for Ethanol + Water + Potassium Nitrate , 1996 .

[20]  Ashish Dwivedi,et al.  Potential applications of artificial neural networks to thermodynamics: vapor–liquid equilibrium predictions , 1999 .

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

[22]  M. Iliuta,et al.  Effect of Calcium Chloride on the Isobaric Vapor−Liquid Equilibrium of 1-Propanol + Water , 1996 .

[23]  J. Smith,et al.  Introduction to chemical engineering thermodynamics , 1949 .

[24]  Aage Fredenslund,et al.  Artificial neural networks as a predictive tool for vapor-liquid equilibrium , 1994 .

[25]  Sheng H. Lin,et al.  Recovery of isopropyl alcohol from waste solvent of a semiconductor plant. , 2004, Journal of hazardous materials.