Full Content is available to subscribers

Subscribe/Learn More  >

A Brief Review of Computational Intelligence Techniques for Critical Heat Flux Prediction

[+] Author Affiliations
B. T. Jiang

Xi'an Polytechnic University, Xi'an, China

Y. N. Liu

Xi'an Jiaotong University, Xi'an, China

Paper No. ICONE26-82325, pp. V06BT08A050; 7 pages
  • 2018 26th International Conference on Nuclear Engineering
  • Volume 6B: Thermal-Hydraulics and Safety Analyses
  • London, England, July 22–26, 2018
  • Conference Sponsors: Nuclear Engineering Division
  • ISBN: 978-0-7918-5149-4
  • Copyright © 2018 by ASME


Critical heat flux (CHF) is one of the important design criteria of water cooled nuclear reactors and plays a key role for the safety and economics of nuclear power plants (NPPs). One of the goals of nuclear reactor design is to receive maximum efficiency under full power and its efficiency would be improved when the core exit temperature increases. From this perspective, the design of a nuclear reactor needs to take into account the appropriate thermal margin to ensure that the fuel design limits are within acceptable limits for any normal operating conditions. However, in general, CHF limits the heat flux from the fuel rods and the power capacity of the nuclear reactor. CHF refers to the transition from nucleate boiling to film boiling and causes an abrupt rise of the fuel rod surface temperature. Therefore, prediction of CHF is vital to the design and safety analysis of water cooled nuclear reactors. During the last five decades, large efforts have been carried out on the CHF prediction by many researchers. Generally, CHF prediction can be achieved in three main ways: empirical correlations, look-up tables and phenomenological models. Due to the complex nature of CHF, there is no deterministic theory for the prediction of CHF. Even the look-up tables and the empirical correlations have their own application ranges and limitations. To overcome these limitations, some computational intelligence (CI) techniques have been developed for the prediction of CHF by many researchers in the last two decades. This paper provides a brief overview of CI techniques for prediction of CHF. In this paper, the reviewed CI techniques mainly include artificial neural networks (ANNs), genetic algorithms (GAs), support vector machines (SVMs), and their hybrid models. This review also compares the strengths and weaknesses of several CI techniques and provides basic technical support for future selection of appropriate methods by those involved in the field.

Copyright © 2018 by ASME



Interactive Graphics


Country-Specific Mortality and Growth Failure in Infancy and Yound Children and Association With Material Stature

Use interactive graphics and maps to view and sort country-specific infant and early dhildhood mortality and growth failure data and their association with maternal

Citing articles are presented as examples only. In non-demo SCM6 implementation, integration with CrossRef’s "Cited By" API will populate this tab (http://www.crossref.org/citedby.html).

Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In