Prediction of CHF in concentric-tube open thermosiphon using artificial neural network and genetic algorithm

R. H. Chen, G. H. Su, S. Z. Qiu, Kenji Fukuda

Research output: Contribution to journalArticlepeer-review

19 Citations (Scopus)

Abstract

In this paper, an artificial neural network (ANN) for predicting critical heat flux (CHF) of concentric-tube open thermosiphon has been trained successfully based on the experimental data from the literature. The dimensionless input parameters of the ANN are density ratio, ρ lv; the ratio of the heated tube length to the inner diameter of the outer tube, L/D i; the ratio of frictional area, d i/(D i + d o); and the ratio of equivalent heated diameter to characteristic bubble size, D he/ [σ/g(ρ lv)]0.5, the output is Kutateladze number, Ku. The predicted values of ANN are found to be in reasonable agreement with the actual values from the experiments with a mean relative error (MRE) of 8.46%. New correlations for predicting CHF were also proposed by using genetic algorithm (GA) and succeeded to correlate the existing CHF data with better accuracy than the existing empirical correlations.

Original languageEnglish
Pages (from-to)345-353
Number of pages9
JournalHeat and Mass Transfer/Waerme- und Stoffuebertragung
Volume46
Issue number3
DOIs
Publication statusPublished - 2010 Mar

ASJC Scopus subject areas

  • Condensed Matter Physics
  • Fluid Flow and Transfer Processes

Fingerprint

Dive into the research topics of 'Prediction of CHF in concentric-tube open thermosiphon using artificial neural network and genetic algorithm'. Together they form a unique fingerprint.

Cite this