Inference of mixing rules for thermodynamic equations of state using neural 
networks

Bravo-Sánchez, Ulises Iván; Rico-Martínez, Ramiro; Alvarado, Javier F. J.; Iglesias-Silva, G.A.

Item

ITEM ACTIONSEXPORT

Add to Basket

Local TagsRelease HistoryDetailsSummary

Released

Journal Article

Inference of mixing rules for thermodynamic equations of state using neural networks

MPS-Authors

/persons/resource/persons22003

Rico-Martínez, Ramiro
Physical Chemistry, Fritz Haber Institute, Max Planck Society;

External Resource

No external resources are shared

Fulltext (restricted access)

There are currently no full texts shared for your IP range.

Fulltext (public)

There are no public fulltexts stored in PuRe

Supplementary Material (public)

There is no public supplementary material available

Citation

Bravo-Sánchez, U. I., Rico-Martínez, R., Alvarado, J. F. J., & Iglesias-Silva, G. (1998). Inference of mixing rules for thermodynamic equations of state using neural networks. Latin American Applied Research, 32(32), 97-104.

Cite as: https://hdl.handle.net/21.11116/0000-0008-1EF7-1

Abstract

The Artificial Neural Networks (ANNs) have proven to be a valuable tool for many applications. For modeling, the ANNs can be used to extract ad-hoc models that substitute for the lack of a first-principles formulation. The ANN is expected to capture the underlying characteristics of the system and thus can be used to predict, for example, the evolution of the dynamical response of a system. In this contribution we illustrate the use of ANNs for the construction of "gray-box" models: The purpose is not to replace the need for a fundamental model, but rather complement it. The illustration is based in the ANN-inference of mixing rules for a thermodynamic equation of state (EOS). The application of the ANNs within the framework of an EOS substantially increases the potential for applications allowing the estimation of thermodynamic properties different that the ones used for the training of the ANN.