Partager

Document IIF

Prévisions du point normal d’ébullition et de la température critique des frigorigènes par réseau neuronal de graphes (GNN) et apprentissage par transfert (TL).

Prediction of normal boiling point and critical temperature of refrigerants by graph neural network and transfer learning.

Auteurs : WANG G., HU P.

Type d'article : Article de la RIF

Résumé

Normal boiling point () and critical temperature () are two major thermodynamic properties of refrigerants. In this study, a dataset with 742 data points for and 166 data points for was collected from references, and then prediction models of and for refrigerants were established by graph neural network and transfer learning. Graph neural network is applied to correlate the and of refrigerants with their corresponding molecular structure, while transfer learning is used to further improve the prediction accuracy on . Compared with the data in references, the average absolute deviation for is 1.20%, and for , it is reduced from 1.91% to 1.05% with the help of transfer learning, which is lower than the group contribution methods. The results indicate that the graph neural network is a powerful approach to estimating refrigerant properties, and transfer learning can improve the prediction accuracy for the case of insufficient training data.

Documents disponibles

Format PDF

Pages : 97-104

Disponible

  • Prix public

    20 €

  • Prix membre*

    Gratuit

* meilleur tarif applicable selon le type d'adhésion (voir le détail des avantages des adhésions individuelles et collectives)

Détails

  • Titre original : Prediction of normal boiling point and critical temperature of refrigerants by graph neural network and transfer learning.
  • Identifiant de la fiche : 30031762
  • Langues : Anglais
  • Sujet : Technologie
  • Source : International Journal of Refrigeration - Revue Internationale du Froid - vol. 151
  • Date d'édition : 07/2023
  • DOI : http://dx.doi.org/10.1016/j.ijrefrig.2023.04.006

Liens


Voir d'autres articles du même numéro (33)
Voir la source

Indexation