Partager

Document IIF

Évaluation de la généralité de modèles universels basés sur l'apprentissage automatique utilisés pour la prédiction du coefficient de transfert de chaleur par condensation dans les mini/macro-canaux.

Evaluating the generality of machine learning-based universal models used for prediction of condensation heat transfer coefficient in mini/macro channels.

Auteurs : SHOUREHDELI S. A., GHOLIPOUR H.

Type d'article : Article de la RIF

Résumé

This research concerns the development of universal models founded on machine learning to predict the condensation heat transfer coefficient. In this regard, a consolidated database has been employed encompassing 8340 data points which belong to the flow condensation inside mini/macro channels. The database consists of 25 working fluids with hydraulic diameters ranging from 0.42 to 20.8 mm, mass velocities ranging from 13.1 to 1400 Kg m−2 s− 1 and reduced pressures ranging from 0.03 to 0.9. Four machine learning regression models namely artificial neural network (ANN), gradient-boosted regression (GBR), random forest regression (RFR) and support vector regression (SVR) are trained utilizing the database, and subsequently their accuracy and generality are compared. A multitude of dimensionless parameters are regarded as features, while three parameters specifically the heat transfer coefficient, Nusselt number and Nusselt number correction factor are each considered individually as targets. Within each model, the optimal values of the important hyper-parameters are tuned through appropriate search methods. In order to evaluate the generality of the models, the idea is to sequentially exclude each individual database from the consolidated database. The comparison of accuracy and generality of the models reveals that the RFR model using Nusselt number correction factor as target with a mean absolute relative deviation (MARD) of 3.01 % exhibits the highest level of accuracy, whereas the RFR model employing Nusselt number as target with a MARD for the predicted excluded values equal to 19.49 % demonstrates the superior generality.

Documents disponibles

Format PDF

Pages : 395-409

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 : Evaluating the generality of machine learning-based universal models used for prediction of condensation heat transfer coefficient in mini/macro channels.
  • Identifiant de la fiche : 30032238
  • Langues : Anglais
  • Sujet : Technologie
  • Source : International Journal of Refrigeration - Revue Internationale du Froid - vol. 159
  • Date d'édition : 03/2024
  • DOI : http://dx.doi.org/10.1016/j.ijrefrig.2024.01.009

Liens


Voir d'autres articles du même numéro (32)
Voir la source

Indexation