An artificial neural network-based NRTL model for simulating liquid-liquid equilibria of systems present in biofuels production

• Published in: Fluid phase equilibria Vol. 483; pp. 153 - 164
• Main Authors: Reynel-Ávila, H.E., Bonilla-Petriciolet, A., Tapia-Picazo, J.C.
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 15.03.2019
• Subjects: Artificial neural network; Biofuels; Liquid-liquid equilibria; NRTL model; NRTL model; Artificial neural network; Biofuels; Liquid-liquid equilibria
• ISSN: 0378-3812; 1879-0224
• DOI: 10.1016/j.fluid.2018.11.009

A new hybrid local composition model was developed for simulating the liquid-liquid equilibria of systems involved in biofuels production. This model was based on the hybridization of the NRTL equation and an artificial neural network. Numerical performance of this hybrid model was tested with experimental phase equilibria data of biofuels-based ternary systems. Results showed that this hybrid thermodynamic model has improved data fitting properties than those obtained for the original NRTL equation. This model can be utilized to improve the estimation of liquid-liquid equilibria in biofuel process simulations. •New hybrid NRTL model was developed for liquid-liquid equilibria modeling of biofuels systems.•Performance of new model was tested with experimental phase equilibria data of biofuels systems.•ANNs-NRTL outperformed the original version of NRTL for tested cases of study.