Analysis of CHF in saturated forced convective boiling on a heated surface with impinging jets using artificial neural network and genetic algorithm

Tenglong Cong, Ronghua Chen, Guanghui Su, Suizheng Qiu, Wenxi Tian

Research output: Contribution to journalArticle

16 Citations (Scopus)

Abstract

In this paper, a three-layer Back Propagation (BP) algorithm artificial neural network (ANN) for predicting critical heat flux (CHF) in saturated forced convective boiling on a heated surface with impinging jets was trained successfully with a root mean square (RMS) error of 17.39%. The input parameters of the ANN are liquid-to-vapor density ratio, ρl/ ρv, the ratio of characteristic dimension of the heated surface to the diameter of the impinging jet, L/d, reciprocal of the Weber number, 2σ/ρlu2(L - d), and the number of impinging jets, Nj. The output is dimensionless heat flux, qco/ ρvHfgu. Based on the trained ANN, the influence of principal parameters on CHF has been analyzed as follows. CHF increases with an increase in jet velocity and decreases with an increase in L/d and N j. CHF increases with an increase in pressure at first and then decreases. Besides, a new correlation was generalized using genetic algorithm (GA) as a comparison with ANN to confirm the advantage of ANN.

Original languageEnglish
Pages (from-to)3945-3951
Number of pages7
JournalNuclear Engineering and Design
Volume241
Issue number9
DOIs
Publication statusPublished - 2011 Sep

Fingerprint

genetic algorithms
genetic algorithm
boiling
artificial neural network
Boiling liquids
heat flux
Heat flux
Genetic algorithms
Neural networks
Density of gases
Backpropagation algorithms
root-mean-square errors
back propagation
Mean square error
analysis
vapors
liquid
output
Liquids
liquids

ASJC Scopus subject areas

  • Nuclear Energy and Engineering
  • Mechanical Engineering
  • Safety, Risk, Reliability and Quality
  • Materials Science(all)
  • Nuclear and High Energy Physics
  • Waste Management and Disposal

Cite this

Analysis of CHF in saturated forced convective boiling on a heated surface with impinging jets using artificial neural network and genetic algorithm. / Cong, Tenglong; Chen, Ronghua; Su, Guanghui; Qiu, Suizheng; Tian, Wenxi.

In: Nuclear Engineering and Design, Vol. 241, No. 9, 09.2011, p. 3945-3951.

Research output: Contribution to journalArticle

Cong, Tenglong ; Chen, Ronghua ; Su, Guanghui ; Qiu, Suizheng ; Tian, Wenxi. / Analysis of CHF in saturated forced convective boiling on a heated surface with impinging jets using artificial neural network and genetic algorithm. In: Nuclear Engineering and Design. 2011 ; Vol. 241, No. 9. pp. 3945-3951.
@article{0d0c00c2db2442e8a3838f4ad8a48801,
title = "Analysis of CHF in saturated forced convective boiling on a heated surface with impinging jets using artificial neural network and genetic algorithm",
abstract = "In this paper, a three-layer Back Propagation (BP) algorithm artificial neural network (ANN) for predicting critical heat flux (CHF) in saturated forced convective boiling on a heated surface with impinging jets was trained successfully with a root mean square (RMS) error of 17.39{\%}. The input parameters of the ANN are liquid-to-vapor density ratio, ρl/ ρv, the ratio of characteristic dimension of the heated surface to the diameter of the impinging jet, L/d, reciprocal of the Weber number, 2σ/ρlu2(L - d), and the number of impinging jets, Nj. The output is dimensionless heat flux, qco/ ρvHfgu. Based on the trained ANN, the influence of principal parameters on CHF has been analyzed as follows. CHF increases with an increase in jet velocity and decreases with an increase in L/d and N j. CHF increases with an increase in pressure at first and then decreases. Besides, a new correlation was generalized using genetic algorithm (GA) as a comparison with ANN to confirm the advantage of ANN.",
author = "Tenglong Cong and Ronghua Chen and Guanghui Su and Suizheng Qiu and Wenxi Tian",
year = "2011",
month = "9",
doi = "10.1016/j.nucengdes.2011.07.029",
language = "English",
volume = "241",
pages = "3945--3951",
journal = "Nuclear Engineering and Design",
issn = "0029-5493",
publisher = "Elsevier BV",
number = "9",

}

TY - JOUR

T1 - Analysis of CHF in saturated forced convective boiling on a heated surface with impinging jets using artificial neural network and genetic algorithm

AU - Cong, Tenglong

AU - Chen, Ronghua

AU - Su, Guanghui

AU - Qiu, Suizheng

AU - Tian, Wenxi

PY - 2011/9

Y1 - 2011/9

N2 - In this paper, a three-layer Back Propagation (BP) algorithm artificial neural network (ANN) for predicting critical heat flux (CHF) in saturated forced convective boiling on a heated surface with impinging jets was trained successfully with a root mean square (RMS) error of 17.39%. The input parameters of the ANN are liquid-to-vapor density ratio, ρl/ ρv, the ratio of characteristic dimension of the heated surface to the diameter of the impinging jet, L/d, reciprocal of the Weber number, 2σ/ρlu2(L - d), and the number of impinging jets, Nj. The output is dimensionless heat flux, qco/ ρvHfgu. Based on the trained ANN, the influence of principal parameters on CHF has been analyzed as follows. CHF increases with an increase in jet velocity and decreases with an increase in L/d and N j. CHF increases with an increase in pressure at first and then decreases. Besides, a new correlation was generalized using genetic algorithm (GA) as a comparison with ANN to confirm the advantage of ANN.

AB - In this paper, a three-layer Back Propagation (BP) algorithm artificial neural network (ANN) for predicting critical heat flux (CHF) in saturated forced convective boiling on a heated surface with impinging jets was trained successfully with a root mean square (RMS) error of 17.39%. The input parameters of the ANN are liquid-to-vapor density ratio, ρl/ ρv, the ratio of characteristic dimension of the heated surface to the diameter of the impinging jet, L/d, reciprocal of the Weber number, 2σ/ρlu2(L - d), and the number of impinging jets, Nj. The output is dimensionless heat flux, qco/ ρvHfgu. Based on the trained ANN, the influence of principal parameters on CHF has been analyzed as follows. CHF increases with an increase in jet velocity and decreases with an increase in L/d and N j. CHF increases with an increase in pressure at first and then decreases. Besides, a new correlation was generalized using genetic algorithm (GA) as a comparison with ANN to confirm the advantage of ANN.

UR - http://www.scopus.com/inward/record.url?scp=80052565752&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80052565752&partnerID=8YFLogxK

U2 - 10.1016/j.nucengdes.2011.07.029

DO - 10.1016/j.nucengdes.2011.07.029

M3 - Article

VL - 241

SP - 3945

EP - 3951

JO - Nuclear Engineering and Design

JF - Nuclear Engineering and Design

SN - 0029-5493

IS - 9

ER -