Surrogate modelling of VLE: Integrating machine learning with thermodynamic constraints

An easy-to-implement methodology to develop accurate, fast and thermodynamically consistent surrogate machine learning (ML) models for multicomponent phase equilibria is proposed. The methodology is successfully applied to predict the vapour-liquid equilibrium (VLE) behavior of a mixture containing...

Full description

Bibliographic Details
Main Authors: Andres Carranza-Abaid, Hallvard F. Svendsen, Jana P. Jakobsen
Format: Article
Language:English
Published: Elsevier 2020-11-01
Series:Chemical Engineering Science: X
Subjects:
CO2
MEA
Online Access:http://www.sciencedirect.com/science/article/pii/S2590140020300265