Calcul des propriétés thermodynamiques d'un frigorigène de remplacement (R-508B) grâce à un réseau neuronal artificiel.

Calculation for the thermodynamic properties of an alternative refrigerant (R-508B) using artificial neural network.

Auteurs : SÖZEN A., ÖZALP M., ARCAKLIOGLU E.

Type d'article : Article

Résumé

This study proposes a alternative approach based on artificial neural networks (ANNs) to determine the thermodynamic properties - specific volume, enthalpy and entropy - of an alternative refrigerant (R-508B) for both saturated liquid-vapour region (wet vapour) and superheated vapour region. In the ANN, the back-propagation learning algorithm with two different variants, namely scaled conjugate gradient (SCG) and Levenberg-Marquardt (LM), and Logistic Sigmoid transfer function were used to determine the best approach. The most suitable algorithm and with appropriate number of neurons in the hidden layer is found to be the LM algorithm which has provided the minimum error. [Reprinted with permission from Elsevier. Copyright, 2006].

Détails

  • Titre original : Calculation for the thermodynamic properties of an alternative refrigerant (R-508B) using artificial neural network.
  • Identifiant de la fiche : 2007-0967
  • Langues : Anglais
  • Source : Applied Thermal Engineering - vol. 27 - n. 2-3
  • Date d'édition : 02/2007

Liens


Voir d'autres articles du même numéro (10)
Voir la source