Critical heat flux prediction using genetic programming for water flow in vertical round tubes

https://doi.org/10.1016/S0735-1933(97)00078-XGet rights and content

Abstract

The genetic programming method is used to develop critical heat flux (CHF) correlations for upward water flow in vertical round tubes under low pressure and low flow conditions. The genetic programming, as a symbolic regression tool, finds both the functional form and fitting coefficients of a correlation without any initial assumptions. Inlet and local condition type correlations are developed based on 414 and 314 CHF data from KAIST CHF data bank, respectively. The inlet condition type correlation shows the rms error of 15.2% and the local condition type one shows the rms errors of 32.7% and 13.2% by the direct substitution method and the heat balance method, respectively. Prediction errors are smaller than or comparable to those for other existing correlations.

References (15)

  • P. Hejzlar et al.

    Nucl. Eng. Des.

    (1996)
  • D.C. Groeneveld

    Nucl. Eng. Des.

    (1996)
  • S.K. Moon et al.

    Nucl. Eng. Des.

    (1996)
  • Y. Katto et al.

    Int. J. Heat and Mass Transfer

    (1984)
  • F. Inasaka et al.

    Nucl. Eng. Des.

    (1996)
  • R.W. Bowring

    A Simple But Accurate Round Tube, Uniform Heat Flux, Dryout Correlation Over the Pressure Range 0.7 – 17 MN/m2 (100–2500 psia)

    AEEW-R789

    (1972)
  • L. Biasi

    Energia Nucleare

    (1967)
There are more references available in the full text version of this article.

Cited by (19)

  • Particle swarm optimization-based least squares support vector regression for critical heat flux prediction

    2013, Annals of Nuclear Energy
    Citation Excerpt :

    There are several hybrid methods that combine ANN and other techniques for prediction of CHF (Kim et al., 2000b; Zaferanlouei et al., 2010). In addition to ANN, genetic algorithm (GA), one of the evolutionary algorithm (EA) methods, is also used alone (Lee et al., 1997) or in combination with ANN to predict the CHF (Kwon et al., 2005; Wei et al., 2010). However, ANN has its own disadvantages, such as having difficulty in determining the number of hidden layers and hidden neurons per layer and may get stuck in local minima and overfitting.

  • Combination of support vector regression and artificial neural networks for prediction of critical heat flux

    2013, International Journal of Heat and Mass Transfer
    Citation Excerpt :

    Most of them were summarized in Table 4 of [10] and the others were reported in the references [11,12]. Besides, genetic algorithm (GA), as one of the optimization techniques, has also been used to predict CHF [13]. Generally, these above studies can be divided into two categories: one is that ANNs alone were used to predict CHF and the other is that ANNs were combined with other techniques to predict CHF.

  • Applications of genetic neural network for prediction of critical heat flux

    2010, International Journal of Thermal Sciences
    Citation Excerpt :

    It tries to find an optimal transformation of variables and then simple regression analysis is performed for the transformed variables. In reference [8], genetic programming was used to find a mathematical expression in a symbolic form between dependent and independent variables. Hundreds of different models and correlations on the prediction of CHF exist in the open literature and enormous amounts of experimental data are available at present.

  • Heat transfer correlations by symbolic regression

    2006, International Journal of Heat and Mass Transfer
View all citing articles on Scopus

Fax: +82-42-869-3810

View full text