Analysis of the critical heat flux in round vertical tubes under low pressure and flow oscillation conditions

Applications of artificial neural network

Su. Guanghui (Corresponding Author), K. Morita, K. Fukuda, Mark Pidduck, Jia Dounan, Jaakko Miettinen

Research output: Contribution to journalReview ArticleScientificpeer-review

54 Citations (Scopus)

Abstract

Artificial neural networks (ANNs) for predicting critical heat flux (CHF) under low pressure and oscillation conditions have been trained successfully for either natural circulation or forced circulation (FC) in the present study. The input parameters of the ANN are pressure, mean mass flow rate, relative amplitude, inlet subcooling, oscillation period and the ratio of the heated length to the diameter of the tube, L/D. The output is a nondimensionalized factor F, which expresses the relative CHF under oscillation conditions. Based on the trained ANN, the influences of principal parameters on F for FC were analyzed. The parametric trends of the CHF under oscillation obtained by the trained ANN are as follows: the effects of pressure below 500 kPa are complex due to the influence of other parameters. F will increase with increasing mean mass flow rate under any conditions, and will decrease generally with an increase in relative amplitude. F will decrease initially and then increase with increasing inlet subcooling. The influence curves of mean mass flow rate on F will be almost the same when the period is shorter than 5.0 s or longer than 15 s. The influence of L/D will be negligible if L/D>200. It is found that the minimum number of neurons in the hidden layer is a product of the number of neurons in the input layer and in the output layer.
Original languageEnglish
Pages (from-to)17-35
Number of pages19
JournalNuclear Engineering and Design
Volume220
Issue number1
DOIs
Publication statusPublished - 2003
MoE publication typeA2 Review article in a scientific journal

Fingerprint

pressure oscillations
low flow
artificial neural network
heat flux
low pressure
Heat flux
mass flow rate
oscillation
tubes
Neural networks
oscillations
Flow rate
neurons
Neurons
output
trends
analysis
curves
products
rate

Keywords

  • turbulent flow
  • boiling water reactors
  • nuclear reactors
  • mass flow
  • critical heat flux
  • artificial neural networks
  • neural networks

Cite this

Guanghui, Su. ; Morita, K. ; Fukuda, K. ; Pidduck, Mark ; Dounan, Jia ; Miettinen, Jaakko. / Analysis of the critical heat flux in round vertical tubes under low pressure and flow oscillation conditions : Applications of artificial neural network. In: Nuclear Engineering and Design. 2003 ; Vol. 220, No. 1. pp. 17-35.
@article{593a73c0df95425c8d540eb487b5e540,
title = "Analysis of the critical heat flux in round vertical tubes under low pressure and flow oscillation conditions: Applications of artificial neural network",
abstract = "Artificial neural networks (ANNs) for predicting critical heat flux (CHF) under low pressure and oscillation conditions have been trained successfully for either natural circulation or forced circulation (FC) in the present study. The input parameters of the ANN are pressure, mean mass flow rate, relative amplitude, inlet subcooling, oscillation period and the ratio of the heated length to the diameter of the tube, L/D. The output is a nondimensionalized factor F, which expresses the relative CHF under oscillation conditions. Based on the trained ANN, the influences of principal parameters on F for FC were analyzed. The parametric trends of the CHF under oscillation obtained by the trained ANN are as follows: the effects of pressure below 500 kPa are complex due to the influence of other parameters. F will increase with increasing mean mass flow rate under any conditions, and will decrease generally with an increase in relative amplitude. F will decrease initially and then increase with increasing inlet subcooling. The influence curves of mean mass flow rate on F will be almost the same when the period is shorter than 5.0 s or longer than 15 s. The influence of L/D will be negligible if L/D>200. It is found that the minimum number of neurons in the hidden layer is a product of the number of neurons in the input layer and in the output layer.",
keywords = "turbulent flow, boiling water reactors, nuclear reactors, mass flow, critical heat flux, artificial neural networks, neural networks",
author = "Su. Guanghui and K. Morita and K. Fukuda and Mark Pidduck and Jia Dounan and Jaakko Miettinen",
year = "2003",
doi = "10.1016/S0029-5493(02)00304-7",
language = "English",
volume = "220",
pages = "17--35",
journal = "Nuclear Engineering and Design",
issn = "0029-5493",
publisher = "Elsevier",
number = "1",

}

Analysis of the critical heat flux in round vertical tubes under low pressure and flow oscillation conditions : Applications of artificial neural network. / Guanghui, Su. (Corresponding Author); Morita, K.; Fukuda, K.; Pidduck, Mark; Dounan, Jia; Miettinen, Jaakko.

In: Nuclear Engineering and Design, Vol. 220, No. 1, 2003, p. 17-35.

Research output: Contribution to journalReview ArticleScientificpeer-review

TY - JOUR

T1 - Analysis of the critical heat flux in round vertical tubes under low pressure and flow oscillation conditions

T2 - Applications of artificial neural network

AU - Guanghui, Su.

AU - Morita, K.

AU - Fukuda, K.

AU - Pidduck, Mark

AU - Dounan, Jia

AU - Miettinen, Jaakko

PY - 2003

Y1 - 2003

N2 - Artificial neural networks (ANNs) for predicting critical heat flux (CHF) under low pressure and oscillation conditions have been trained successfully for either natural circulation or forced circulation (FC) in the present study. The input parameters of the ANN are pressure, mean mass flow rate, relative amplitude, inlet subcooling, oscillation period and the ratio of the heated length to the diameter of the tube, L/D. The output is a nondimensionalized factor F, which expresses the relative CHF under oscillation conditions. Based on the trained ANN, the influences of principal parameters on F for FC were analyzed. The parametric trends of the CHF under oscillation obtained by the trained ANN are as follows: the effects of pressure below 500 kPa are complex due to the influence of other parameters. F will increase with increasing mean mass flow rate under any conditions, and will decrease generally with an increase in relative amplitude. F will decrease initially and then increase with increasing inlet subcooling. The influence curves of mean mass flow rate on F will be almost the same when the period is shorter than 5.0 s or longer than 15 s. The influence of L/D will be negligible if L/D>200. It is found that the minimum number of neurons in the hidden layer is a product of the number of neurons in the input layer and in the output layer.

AB - Artificial neural networks (ANNs) for predicting critical heat flux (CHF) under low pressure and oscillation conditions have been trained successfully for either natural circulation or forced circulation (FC) in the present study. The input parameters of the ANN are pressure, mean mass flow rate, relative amplitude, inlet subcooling, oscillation period and the ratio of the heated length to the diameter of the tube, L/D. The output is a nondimensionalized factor F, which expresses the relative CHF under oscillation conditions. Based on the trained ANN, the influences of principal parameters on F for FC were analyzed. The parametric trends of the CHF under oscillation obtained by the trained ANN are as follows: the effects of pressure below 500 kPa are complex due to the influence of other parameters. F will increase with increasing mean mass flow rate under any conditions, and will decrease generally with an increase in relative amplitude. F will decrease initially and then increase with increasing inlet subcooling. The influence curves of mean mass flow rate on F will be almost the same when the period is shorter than 5.0 s or longer than 15 s. The influence of L/D will be negligible if L/D>200. It is found that the minimum number of neurons in the hidden layer is a product of the number of neurons in the input layer and in the output layer.

KW - turbulent flow

KW - boiling water reactors

KW - nuclear reactors

KW - mass flow

KW - critical heat flux

KW - artificial neural networks

KW - neural networks

U2 - 10.1016/S0029-5493(02)00304-7

DO - 10.1016/S0029-5493(02)00304-7

M3 - Review Article

VL - 220

SP - 17

EP - 35

JO - Nuclear Engineering and Design

JF - Nuclear Engineering and Design

SN - 0029-5493

IS - 1

ER -