Prediction of critical heat flux for narrow rectangular channels in a steady state condition using machine learning

The subchannel of a research reactor used to generate high power density is designed to be narrow and rectangular and comprises plate-type fuels operating under downward flow conditions. Critical heat flux (CHF) is a crucial parameter for estimating the safety of a nuclear fuel; hence, this paramete...

Full description

Saved in:
Bibliographic Details
Published in:Nuclear engineering and technology 2021, Vol.53 (6), p.1796-1809
Main Authors: Kim, Huiyung, Moon, Jeongmin, Hong, Dongjin, Cha, Euiyoung, Yun, Byongjo
Format: Article
Language:Korean
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page 1809
container_issue 6
container_start_page 1796
container_title Nuclear engineering and technology
container_volume 53
creator Kim, Huiyung
Moon, Jeongmin
Hong, Dongjin
Cha, Euiyoung
Yun, Byongjo
description The subchannel of a research reactor used to generate high power density is designed to be narrow and rectangular and comprises plate-type fuels operating under downward flow conditions. Critical heat flux (CHF) is a crucial parameter for estimating the safety of a nuclear fuel; hence, this parameter should be accurately predicted. Here, machine learning is applied for the prediction of CHF in a narrow rectangular channel. Although machine learning can effectively analyze large amounts of complex data, its application to CHF, particularly for narrow rectangular channels, remains challenging because of the limited flow conditions available in existing experimental databases. To resolve this problem, we used four CHF correlations to generate pseudo-data for training an artificial neural network. We also propose a network architecture that includes pre-training and prediction stages to predict and analyze the CHF. The trained neural network predicted the CHF with an average error of 3.65% and a root-mean-square error of 17.17% for the test pseudo-data; the respective errors of 0.9% and 26.4% for the experimental data were not considered during training. Finally, machine learning was applied to quantitatively investigate the parametric effect on the CHF in narrow rectangular channels under downward flow conditions.
format article
fullrecord <record><control><sourceid>kisti</sourceid><recordid>TN_cdi_kisti_ndsl_JAKO202124452890566</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>JAKO202124452890566</sourcerecordid><originalsourceid>FETCH-kisti_ndsl_JAKO2021244528905663</originalsourceid><addsrcrecordid>eNqNjMFKxDAQQIMoWHT_YS4eC03S7HaPIoroQQ978LaM6XQ7bJxAJkX9exfxAzw9eDzemWmc833rw_B2bhq78UMbNt5fmpUqv3e9s7YLg22MvhYaOVbOAnmCWLhyxAQzYYUpLV8w5QKCpeRPKBQrymFJWCDOKEJJgQUQtBKO3ydgJYhZRv49LspygA-MMwtBIixyEtfmYsKktPrjlbl5uN_dPbZH1sp7GTXtn26fX1znrOv74IZtF9Zr_9_uBwjGTNs</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Prediction of critical heat flux for narrow rectangular channels in a steady state condition using machine learning</title><source>BACON - Elsevier - GLOBAL_SCIENCEDIRECT-OPENACCESS</source><creator>Kim, Huiyung ; Moon, Jeongmin ; Hong, Dongjin ; Cha, Euiyoung ; Yun, Byongjo</creator><creatorcontrib>Kim, Huiyung ; Moon, Jeongmin ; Hong, Dongjin ; Cha, Euiyoung ; Yun, Byongjo</creatorcontrib><description>The subchannel of a research reactor used to generate high power density is designed to be narrow and rectangular and comprises plate-type fuels operating under downward flow conditions. Critical heat flux (CHF) is a crucial parameter for estimating the safety of a nuclear fuel; hence, this parameter should be accurately predicted. Here, machine learning is applied for the prediction of CHF in a narrow rectangular channel. Although machine learning can effectively analyze large amounts of complex data, its application to CHF, particularly for narrow rectangular channels, remains challenging because of the limited flow conditions available in existing experimental databases. To resolve this problem, we used four CHF correlations to generate pseudo-data for training an artificial neural network. We also propose a network architecture that includes pre-training and prediction stages to predict and analyze the CHF. The trained neural network predicted the CHF with an average error of 3.65% and a root-mean-square error of 17.17% for the test pseudo-data; the respective errors of 0.9% and 26.4% for the experimental data were not considered during training. Finally, machine learning was applied to quantitatively investigate the parametric effect on the CHF in narrow rectangular channels under downward flow conditions.</description><identifier>ISSN: 1738-5733</identifier><identifier>EISSN: 2234-358X</identifier><language>kor</language><ispartof>Nuclear engineering and technology, 2021, Vol.53 (6), p.1796-1809</ispartof><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>230,315,786,790,891,4043</link.rule.ids></links><search><creatorcontrib>Kim, Huiyung</creatorcontrib><creatorcontrib>Moon, Jeongmin</creatorcontrib><creatorcontrib>Hong, Dongjin</creatorcontrib><creatorcontrib>Cha, Euiyoung</creatorcontrib><creatorcontrib>Yun, Byongjo</creatorcontrib><title>Prediction of critical heat flux for narrow rectangular channels in a steady state condition using machine learning</title><title>Nuclear engineering and technology</title><addtitle>Nuclear engineering and technology : an international journal of the Korean Nuclear Society</addtitle><description>The subchannel of a research reactor used to generate high power density is designed to be narrow and rectangular and comprises plate-type fuels operating under downward flow conditions. Critical heat flux (CHF) is a crucial parameter for estimating the safety of a nuclear fuel; hence, this parameter should be accurately predicted. Here, machine learning is applied for the prediction of CHF in a narrow rectangular channel. Although machine learning can effectively analyze large amounts of complex data, its application to CHF, particularly for narrow rectangular channels, remains challenging because of the limited flow conditions available in existing experimental databases. To resolve this problem, we used four CHF correlations to generate pseudo-data for training an artificial neural network. We also propose a network architecture that includes pre-training and prediction stages to predict and analyze the CHF. The trained neural network predicted the CHF with an average error of 3.65% and a root-mean-square error of 17.17% for the test pseudo-data; the respective errors of 0.9% and 26.4% for the experimental data were not considered during training. Finally, machine learning was applied to quantitatively investigate the parametric effect on the CHF in narrow rectangular channels under downward flow conditions.</description><issn>1738-5733</issn><issn>2234-358X</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><recordid>eNqNjMFKxDAQQIMoWHT_YS4eC03S7HaPIoroQQ978LaM6XQ7bJxAJkX9exfxAzw9eDzemWmc833rw_B2bhq78UMbNt5fmpUqv3e9s7YLg22MvhYaOVbOAnmCWLhyxAQzYYUpLV8w5QKCpeRPKBQrymFJWCDOKEJJgQUQtBKO3ydgJYhZRv49LspygA-MMwtBIixyEtfmYsKktPrjlbl5uN_dPbZH1sp7GTXtn26fX1znrOv74IZtF9Zr_9_uBwjGTNs</recordid><startdate>2021</startdate><enddate>2021</enddate><creator>Kim, Huiyung</creator><creator>Moon, Jeongmin</creator><creator>Hong, Dongjin</creator><creator>Cha, Euiyoung</creator><creator>Yun, Byongjo</creator><scope>JDI</scope></search><sort><creationdate>2021</creationdate><title>Prediction of critical heat flux for narrow rectangular channels in a steady state condition using machine learning</title><author>Kim, Huiyung ; Moon, Jeongmin ; Hong, Dongjin ; Cha, Euiyoung ; Yun, Byongjo</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-kisti_ndsl_JAKO2021244528905663</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>kor</language><creationdate>2021</creationdate><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Kim, Huiyung</creatorcontrib><creatorcontrib>Moon, Jeongmin</creatorcontrib><creatorcontrib>Hong, Dongjin</creatorcontrib><creatorcontrib>Cha, Euiyoung</creatorcontrib><creatorcontrib>Yun, Byongjo</creatorcontrib><collection>KoreaScience</collection><jtitle>Nuclear engineering and technology</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Kim, Huiyung</au><au>Moon, Jeongmin</au><au>Hong, Dongjin</au><au>Cha, Euiyoung</au><au>Yun, Byongjo</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Prediction of critical heat flux for narrow rectangular channels in a steady state condition using machine learning</atitle><jtitle>Nuclear engineering and technology</jtitle><addtitle>Nuclear engineering and technology : an international journal of the Korean Nuclear Society</addtitle><date>2021</date><risdate>2021</risdate><volume>53</volume><issue>6</issue><spage>1796</spage><epage>1809</epage><pages>1796-1809</pages><issn>1738-5733</issn><eissn>2234-358X</eissn><notes>KISTI1.1003/JNL.JAKO202124452890566</notes><abstract>The subchannel of a research reactor used to generate high power density is designed to be narrow and rectangular and comprises plate-type fuels operating under downward flow conditions. Critical heat flux (CHF) is a crucial parameter for estimating the safety of a nuclear fuel; hence, this parameter should be accurately predicted. Here, machine learning is applied for the prediction of CHF in a narrow rectangular channel. Although machine learning can effectively analyze large amounts of complex data, its application to CHF, particularly for narrow rectangular channels, remains challenging because of the limited flow conditions available in existing experimental databases. To resolve this problem, we used four CHF correlations to generate pseudo-data for training an artificial neural network. We also propose a network architecture that includes pre-training and prediction stages to predict and analyze the CHF. The trained neural network predicted the CHF with an average error of 3.65% and a root-mean-square error of 17.17% for the test pseudo-data; the respective errors of 0.9% and 26.4% for the experimental data were not considered during training. Finally, machine learning was applied to quantitatively investigate the parametric effect on the CHF in narrow rectangular channels under downward flow conditions.</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 1738-5733
ispartof Nuclear engineering and technology, 2021, Vol.53 (6), p.1796-1809
issn 1738-5733
2234-358X
language kor
recordid cdi_kisti_ndsl_JAKO202124452890566
source BACON - Elsevier - GLOBAL_SCIENCEDIRECT-OPENACCESS
title Prediction of critical heat flux for narrow rectangular channels in a steady state condition using machine learning
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-09-23T02%3A24%3A58IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-kisti&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Prediction%20of%20critical%20heat%20flux%20for%20narrow%20rectangular%20channels%20in%20a%20steady%20state%20condition%20using%20machine%20learning&rft.jtitle=Nuclear%20engineering%20and%20technology&rft.au=Kim,%20Huiyung&rft.date=2021&rft.volume=53&rft.issue=6&rft.spage=1796&rft.epage=1809&rft.pages=1796-1809&rft.issn=1738-5733&rft.eissn=2234-358X&rft_id=info:doi/&rft_dat=%3Ckisti%3EJAKO202124452890566%3C/kisti%3E%3Cgrp_id%3Ecdi_FETCH-kisti_ndsl_JAKO2021244528905663%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true