Share

IIR document

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

Author(s) : SHOUREHDELI S. A., GHOLIPOUR H.

Type of article: IJR article

Summary

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.

Available documents

Format PDF

Pages: 395-409

Available

  • Public price

    20 €

  • Member price*

    Free

* Best rate depending on membership category (see the detailed benefits of individual and corporate memberships).

Details

  • Original title: Evaluating the generality of machine learning-based universal models used for prediction of condensation heat transfer coefficient in mini/macro channels.
  • Record ID : 30032238
  • Languages: English
  • Subject: Technology
  • Source: International Journal of Refrigeration - Revue Internationale du Froid - vol. 159
  • Publication date: 2024/03
  • DOI: http://dx.doi.org/10.1016/j.ijrefrig.2024.01.009

Links


See other articles in this issue (32)
See the source

Indexing