Application of adaptive neuro-fuzzy inference system for estimation of vapor+ liquid equuilibria of binary systems, carbon dioxide–ethyl caproate, ethyl caprylate and ethyl caprate

Vapor–liquid equilibria (VLE) play a vital role in designing and modelling of process equipments. Since it is not always possible to carry out experiments at all possible temperatures and pressures, generally thermodynamic models based on equations of state are used for estimation of VLE. In this paper, an alternate tool, i.e. adaptive neuro-fuzzy inference system (ANFIS) is presented for the simultaneous estimation of vapor liquid equilibria (VLE) of three binary systems viz. carbon dioxide–ethyl caproate, ethyl caprylate and ethyl caprate which are of importance in supercritical extraction. The root mean square errors (RMSE) and determination coefficient (R2) performance functions are used to evaluate the adequacy of the models. The results obtained in this work indicate that ANFIS have better agreement with experimental data than the thermodynamics models.

کلیدواژه ها:

Equilibrium ، Liquid-vapor ، Adaptive neuro-fuzzy inference system ، binary mixture