Applications of machine learning methods for boiling modeling and prediction: A comprehensive review

M. M. Rashidi, M. Alhuyi Nazari, C. Harley, E. Momoniat, I. Mahariq, N. Ali

Research output: Contribution to journalArticlepeer-review

9 Citations (Scopus)

Abstract

Boiling refers to the heat transfer mechanism that occurs due to the phase transition from liquid to vapor. In comparison with single phase heat transfer, this mechanism has several advantages such as much higher rate at lower temperature differences. Regarding the complexities of two phase heat transfer simulation, due to the involvement of various parameters in this phenomenon, applying intelligent methods such as artificial neural networks could be useful for modeling this type of heat transfer mechanism. In the present article, studies on the modeling of pool boiling heat transfer utilizing machine learning methods have been reviewed, and their findings are reflected. According to the outcomes of the reviewed works, it can be concluded that using intelligent methods can provide accurate predictions of pool boiling heat transfer with a R2 of around 0.99 in some cases. In addition, by applying these methods it would be possible to predict the heat transfer in cases of utilizing nanofluids or porous media. The exactness and applicability range of these models is influenced by several elements such as the considered inputs, applied methods and employed functions. Using an appropriate method with optimal parameter values for the relevant intelligent method would lead to higher precision in modeling.

Original languageEnglish
Article number100081
JournalChemical Thermodynamics and Thermal Analysis
Volume8
DOIs
Publication statusPublished - Dec 2022

Keywords

  • Artificial neural network
  • Machine learning
  • Nanofluid
  • Pool boiling

ASJC Scopus subject areas

  • Physical and Theoretical Chemistry

Fingerprint

Dive into the research topics of 'Applications of machine learning methods for boiling modeling and prediction: A comprehensive review'. Together they form a unique fingerprint.

Cite this