Korean Journal of Chemical Engineering, Vol.30, No.9, 1681-1686, 2013
Application of artificial neural network for vapor liquid equilibrium calculation of ternary system including ionic liquid: Water, ethanol and 1-butyl-3-methylimidazolium acetate
A feed forward three-layer artificial neural network (ANN) model was developed for VLE prediction of ternary systems including ionic liquid (IL) (water+ethanol+1-butyl-3- methyl-imidazolium acetate), in a relatively wide range of IL mass fractions up to 0.8, with the mole fractions of ethanol on IL-free basis fixed separately at 0.1, 0.2, 0.4, 0.6, 0.8, and 0.98. The output results of the ANN were the mole fraction of ethanol in vapor phase and the equilibrium temperature. The validity of the model was evaluated through a test data set, which were not employed in the training case of the network. The performance of the ANN model for estimating the mole fraction and temperature in the ternary system including IL was compared with the non-random-two-liquid (NRTL) and electrolyte non-randomtwo-liquid (eNRTL) models. The results of this comparison show that the ANN model has a superior performance in predicting the VLE of ternary systems including ionic liquid.
Haykin S, Neural networks: A comprehensive foundation, Prentice Hall, Upper Saddle River, NJ, 1999
Hassibi B, Stork DG, in Advances in Neural Information Processing Systems, Hanson SJ, Cowan JD, Giles CL Eds., volume 5, pp. 164-171. Morgan Kaufmann, San Mateo, CA, 1993
Le Cun Y, Denker JS, Solla SA, Optimal Brain Damage, In Touretzky DS (Ed.), Advances in Neural Information Processing Systems 2, Proceedings of the 1989 Conference, San Mateo, California, Morgan Kaufmann Publishers, 1990