Gibbs–Duhem-informed neural networks for binary activity coefficient prediction

Digital Discovery, vol. 2, pp. 1752–1767

Abstract

Gibbs–Duhem-informed neural networks provide a flexible hybrid approach to predicting binary activity coefficients with both high accuracy and thermodynamic consistency.

Authors 4

1. Jan G. Rittig Aachen Process Systems Engineering (AVT.SVT)

   RWTH Aachen University

   Affiliation as printed

   Process Systems Engineering (AVT.SVT), RWTH Aachen University, Forckenbeckstraße 51, 52074 Aachen, Germany

2. Kobi Felton

   University of Cambridge

   Affiliation as printed

   Department of Chemical Engineering and Biotechnology, University of Cambridge, Philippa Fawcett Dr, Cambridge CB3 0AS, UK

3. Alexei A. Lapkin

   University of Cambridge

   Affiliation as printed

   Department of Chemical Engineering and Biotechnology, University of Cambridge, Philippa Fawcett Dr, Cambridge CB3 0AS, UK

4. Alexander Mitsos corresponding Aachen Process Systems Engineering (AVT.SVT)

   Forschungszentrum Jülich · Jülich Aachen Research Alliance · RWTH Aachen University

   Affiliation as printed

   Institute of Energy and Climate Research: Energy Systems Engineering (IEK-10), Forschungszentrum Jülich GmbH, Wilhelm-Johnen-Straße, 52425 Jülich, Germany

   JARA-ENERGY, Templergraben 55, 52056 Aachen, Germany

   Process Systems Engineering (AVT.SVT), RWTH Aachen University, Forckenbeckstraße 51, 52074 Aachen, Germany