Ebullition en écoulement de mélanges : modélisation du transfert de chaleur grâce à des réseaux neuronaux artificiels.
Mixtures flow boiling: modelling heat transfer through artificial neural networks.
Auteurs : SCALABRIN G., CONDOSTA M., MARCHI P.
Type d'article : Article
Résumé
The flow boiling inside horizontal smooth tubes is studied for mixtures and a new modelling technique is proposed for the heat transfer. In a former work, the flow boiling of pure fluids inside smooth tubes was studied with artificial neural networks (ANN), obtaining individual heat transfer equations in a totally heuristic mode from the direct regression of experimental data. In the present work the method is extended to mixtures. Also in this case the correlation architectures considered for the ANN functions were based on the directly-accessible physical quantities controlling the phenomenon. Two modelling architectures are set up: a first one with the controlling physical quantities as independent variables and a second one where the inputs are the individual heat transfer values of the pure components and the mixture composition. The validation of both the obtained models demonstrate an accurate and substantially equivalent representation of the available heat transfer data with a considerable increase of prediction capability with respect to the conventional methods. The multilayer feed forward neural network equations both in terms of physical variables and in terms of components heat transfer models and composition have obtained very satisfactory accuracies. The modelling technique allows to avoid the need for any thermodynamic and transport property model for the target mixture and, moreover, the method can be used to check the consistency of new data sets before using them for processing. [Reprinted with permission from Elsevier. Copyright, 2006].
Détails
- Titre original : Mixtures flow boiling: modelling heat transfer through artificial neural networks.
- Identifiant de la fiche : 2006-2258
- Langues : Anglais
- Source : International Journal of thermal Sciences - vol. 45 - n. 7
- Date d'édition : 07/2006
Liens
Voir d'autres articles du même numéro (2)
Voir la source
Indexation
-
Modelling flow boiling heat transfer of pure fl...
- Auteurs : SCALABRIN G., CONDOSTA M., MARCHI P.
- Date : 07/2006
- Langues : Anglais
- Source : International Journal of thermal Sciences - vol. 45 - n. 7
Voir la fiche
-
Generalized neural network correlation for flow...
- Auteurs : WANG W. J., ZHAO L. X., ZHANG C. L.
- Date : 07/2006
- Langues : Anglais
- Source : International Journal of Heat and Mass Transfer - vol. 49 - n. 15-16
Voir la fiche
-
Flow boiling of pure fluids: local heat transfe...
- Auteurs : SCALABRIN G., CONDOSTA M., MARCHI P.
- Date : 08/2006
- Langues : Anglais
- Source : International Journal of thermal Sciences - vol. 45 - n. 8
Voir la fiche
-
Neural network analysis of boiling heat transfe...
- Auteurs : LIU T., SUN X., LI X., et al.
- Date : 12/2002
- Langues : Anglais
- Source : International Journal of Heat and Mass Transfer - vol. 45 - n. 25
Voir la fiche
-
Analysis of forced convection heat transfer to ...
- Auteurs : SCALABRIN G., PIAZZA L.
- Date : 03/2003
- Langues : Anglais
- Source : International Journal of Heat and Mass Transfer - vol. 46 - n. 7
Voir la fiche