A surrogate machine learning model for advanced gas-cooled reactor graphite core safety analysis

[Display omitted] •A machine learning model was developed to predict seismic core displacements from crack configurations for the advanced gas-cooled reactor.•The model was trained on a dataset from software which simulates a severe earthquake.•The aim was to increase the computational efficiency of...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Nuclear engineering and design 2022-08, Vol.395, p.111842, Article 111842
Hauptverfasser: Jones, H. Rhys, Mu, Tingting, Kudawoo, Dzifa, Brown, Gavin, Martinuzzi, Philippe, McLachlan, Neil
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page 111842
container_title Nuclear engineering and design
container_volume 395
creator Jones, H. Rhys
Mu, Tingting
Kudawoo, Dzifa
Brown, Gavin
Martinuzzi, Philippe
McLachlan, Neil
description [Display omitted] •A machine learning model was developed to predict seismic core displacements from crack configurations for the advanced gas-cooled reactor.•The model was trained on a dataset from software which simulates a severe earthquake.•The aim was to increase the computational efficiency of data generation. A surrogate machine learning model was developed with the aim of predicting seismic graphite core displacements from crack configurations for the advanced gas-cooled reactor. The model was trained on a dataset generated by a software package which simulates the behaviour of the graphite core during a severe earthquake. Several machine learning techniques, such as the use of convolutional neural networks, were identified as highly applicable to this particular problem. Through the development of the model, several observations and insights were garnered which may be of interest from a graphite core analysis and safety perspective. The best performing model was capable of making 95% of test set predictions within a 20 percentage point margin of the ground truth.
doi_str_mv 10.1016/j.nucengdes.2022.111842
format Article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_2762942340</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S0029549322001960</els_id><sourcerecordid>2762942340</sourcerecordid><originalsourceid>FETCH-LOGICAL-c392t-46aa247fb5aa029097d05238e13959503704867b4b618fea774b47007ae04a7c3</originalsourceid><addsrcrecordid>eNqFkE9LxDAQxYMouK5-BgOeW5M0bZrjsvgPBC8K3uJsOu1m6TZr0i7stzfLilfnMgPz3vDmR8gtZzlnvLrf5MNkcegajLlgQuSc81qKMzLjtRKZKvXnOZkxJnRWSl1ckqsYN-xYWszI14LGKQTfwYh0C3btBqQ9Qhjc0NGtb7CnrQ8Umj0MFhvaQcys930aA4Id064LsFu75Lc-II3Q4nigMEB_iC5ek4sW-og3v31OPh4f3pfP2evb08ty8ZrZQosxkxWAkKpdlQApKtOqYaUoauSFLnXJCsVkXamVXFW8bhGUkiupGFOATIKyxZzcne7ugv-eMI5m46eQQkQjVCW0FIVkSaVOKht8jAFbswtuC-FgODNHnGZj_nCaI05zwpmci5MT0xN7h8FE6_CIxAW0o2m8-_fGD9ecgjM</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2762942340</pqid></control><display><type>article</type><title>A surrogate machine learning model for advanced gas-cooled reactor graphite core safety analysis</title><source>Access via ScienceDirect (Elsevier)</source><creator>Jones, H. Rhys ; Mu, Tingting ; Kudawoo, Dzifa ; Brown, Gavin ; Martinuzzi, Philippe ; McLachlan, Neil</creator><creatorcontrib>Jones, H. Rhys ; Mu, Tingting ; Kudawoo, Dzifa ; Brown, Gavin ; Martinuzzi, Philippe ; McLachlan, Neil</creatorcontrib><description>[Display omitted] •A machine learning model was developed to predict seismic core displacements from crack configurations for the advanced gas-cooled reactor.•The model was trained on a dataset from software which simulates a severe earthquake.•The aim was to increase the computational efficiency of data generation. A surrogate machine learning model was developed with the aim of predicting seismic graphite core displacements from crack configurations for the advanced gas-cooled reactor. The model was trained on a dataset generated by a software package which simulates the behaviour of the graphite core during a severe earthquake. Several machine learning techniques, such as the use of convolutional neural networks, were identified as highly applicable to this particular problem. Through the development of the model, several observations and insights were garnered which may be of interest from a graphite core analysis and safety perspective. The best performing model was capable of making 95% of test set predictions within a 20 percentage point margin of the ground truth.</description><identifier>ISSN: 0029-5493</identifier><identifier>EISSN: 1872-759X</identifier><identifier>DOI: 10.1016/j.nucengdes.2022.111842</identifier><language>eng</language><publisher>Amsterdam: Elsevier B.V</publisher><subject>Advanced gas-cooled reactor ; Artificial neural networks ; Convolutional neural network ; Core analysis ; Data analysis ; Data science ; Earthquakes ; Gas cooled reactors ; Graphite ; Learning algorithms ; Machine learning ; Neural networks ; Nuclear ; Nuclear safety ; Reactors ; Regression ; Seismic activity ; Shaker table ; Supervised learning ; Surrogate model</subject><ispartof>Nuclear engineering and design, 2022-08, Vol.395, p.111842, Article 111842</ispartof><rights>2022 The Author(s)</rights><rights>Copyright Elsevier BV Aug 15, 2022</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c392t-46aa247fb5aa029097d05238e13959503704867b4b618fea774b47007ae04a7c3</citedby><cites>FETCH-LOGICAL-c392t-46aa247fb5aa029097d05238e13959503704867b4b618fea774b47007ae04a7c3</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://dx.doi.org/10.1016/j.nucengdes.2022.111842$$EHTML$$P50$$Gelsevier$$Hfree_for_read</linktohtml><link.rule.ids>314,780,784,3550,27924,27925,45995</link.rule.ids></links><search><creatorcontrib>Jones, H. Rhys</creatorcontrib><creatorcontrib>Mu, Tingting</creatorcontrib><creatorcontrib>Kudawoo, Dzifa</creatorcontrib><creatorcontrib>Brown, Gavin</creatorcontrib><creatorcontrib>Martinuzzi, Philippe</creatorcontrib><creatorcontrib>McLachlan, Neil</creatorcontrib><title>A surrogate machine learning model for advanced gas-cooled reactor graphite core safety analysis</title><title>Nuclear engineering and design</title><description>[Display omitted] •A machine learning model was developed to predict seismic core displacements from crack configurations for the advanced gas-cooled reactor.•The model was trained on a dataset from software which simulates a severe earthquake.•The aim was to increase the computational efficiency of data generation. A surrogate machine learning model was developed with the aim of predicting seismic graphite core displacements from crack configurations for the advanced gas-cooled reactor. The model was trained on a dataset generated by a software package which simulates the behaviour of the graphite core during a severe earthquake. Several machine learning techniques, such as the use of convolutional neural networks, were identified as highly applicable to this particular problem. Through the development of the model, several observations and insights were garnered which may be of interest from a graphite core analysis and safety perspective. The best performing model was capable of making 95% of test set predictions within a 20 percentage point margin of the ground truth.</description><subject>Advanced gas-cooled reactor</subject><subject>Artificial neural networks</subject><subject>Convolutional neural network</subject><subject>Core analysis</subject><subject>Data analysis</subject><subject>Data science</subject><subject>Earthquakes</subject><subject>Gas cooled reactors</subject><subject>Graphite</subject><subject>Learning algorithms</subject><subject>Machine learning</subject><subject>Neural networks</subject><subject>Nuclear</subject><subject>Nuclear safety</subject><subject>Reactors</subject><subject>Regression</subject><subject>Seismic activity</subject><subject>Shaker table</subject><subject>Supervised learning</subject><subject>Surrogate model</subject><issn>0029-5493</issn><issn>1872-759X</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><recordid>eNqFkE9LxDAQxYMouK5-BgOeW5M0bZrjsvgPBC8K3uJsOu1m6TZr0i7stzfLilfnMgPz3vDmR8gtZzlnvLrf5MNkcegajLlgQuSc81qKMzLjtRKZKvXnOZkxJnRWSl1ckqsYN-xYWszI14LGKQTfwYh0C3btBqQ9Qhjc0NGtb7CnrQ8Umj0MFhvaQcys930aA4Id064LsFu75Lc-II3Q4nigMEB_iC5ek4sW-og3v31OPh4f3pfP2evb08ty8ZrZQosxkxWAkKpdlQApKtOqYaUoauSFLnXJCsVkXamVXFW8bhGUkiupGFOATIKyxZzcne7ugv-eMI5m46eQQkQjVCW0FIVkSaVOKht8jAFbswtuC-FgODNHnGZj_nCaI05zwpmci5MT0xN7h8FE6_CIxAW0o2m8-_fGD9ecgjM</recordid><startdate>20220815</startdate><enddate>20220815</enddate><creator>Jones, H. Rhys</creator><creator>Mu, Tingting</creator><creator>Kudawoo, Dzifa</creator><creator>Brown, Gavin</creator><creator>Martinuzzi, Philippe</creator><creator>McLachlan, Neil</creator><general>Elsevier B.V</general><general>Elsevier BV</general><scope>6I.</scope><scope>AAFTH</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SP</scope><scope>7ST</scope><scope>7TB</scope><scope>8FD</scope><scope>C1K</scope><scope>FR3</scope><scope>KR7</scope><scope>L7M</scope><scope>SOI</scope></search><sort><creationdate>20220815</creationdate><title>A surrogate machine learning model for advanced gas-cooled reactor graphite core safety analysis</title><author>Jones, H. Rhys ; Mu, Tingting ; Kudawoo, Dzifa ; Brown, Gavin ; Martinuzzi, Philippe ; McLachlan, Neil</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c392t-46aa247fb5aa029097d05238e13959503704867b4b618fea774b47007ae04a7c3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Advanced gas-cooled reactor</topic><topic>Artificial neural networks</topic><topic>Convolutional neural network</topic><topic>Core analysis</topic><topic>Data analysis</topic><topic>Data science</topic><topic>Earthquakes</topic><topic>Gas cooled reactors</topic><topic>Graphite</topic><topic>Learning algorithms</topic><topic>Machine learning</topic><topic>Neural networks</topic><topic>Nuclear</topic><topic>Nuclear safety</topic><topic>Reactors</topic><topic>Regression</topic><topic>Seismic activity</topic><topic>Shaker table</topic><topic>Supervised learning</topic><topic>Surrogate model</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Jones, H. Rhys</creatorcontrib><creatorcontrib>Mu, Tingting</creatorcontrib><creatorcontrib>Kudawoo, Dzifa</creatorcontrib><creatorcontrib>Brown, Gavin</creatorcontrib><creatorcontrib>Martinuzzi, Philippe</creatorcontrib><creatorcontrib>McLachlan, Neil</creatorcontrib><collection>ScienceDirect Open Access Titles</collection><collection>Elsevier:ScienceDirect:Open Access</collection><collection>CrossRef</collection><collection>Electronics &amp; Communications Abstracts</collection><collection>Environment Abstracts</collection><collection>Mechanical &amp; Transportation Engineering Abstracts</collection><collection>Technology Research Database</collection><collection>Environmental Sciences and Pollution Management</collection><collection>Engineering Research Database</collection><collection>Civil Engineering Abstracts</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Environment Abstracts</collection><jtitle>Nuclear engineering and design</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Jones, H. Rhys</au><au>Mu, Tingting</au><au>Kudawoo, Dzifa</au><au>Brown, Gavin</au><au>Martinuzzi, Philippe</au><au>McLachlan, Neil</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>A surrogate machine learning model for advanced gas-cooled reactor graphite core safety analysis</atitle><jtitle>Nuclear engineering and design</jtitle><date>2022-08-15</date><risdate>2022</risdate><volume>395</volume><spage>111842</spage><pages>111842-</pages><artnum>111842</artnum><issn>0029-5493</issn><eissn>1872-759X</eissn><abstract>[Display omitted] •A machine learning model was developed to predict seismic core displacements from crack configurations for the advanced gas-cooled reactor.•The model was trained on a dataset from software which simulates a severe earthquake.•The aim was to increase the computational efficiency of data generation. A surrogate machine learning model was developed with the aim of predicting seismic graphite core displacements from crack configurations for the advanced gas-cooled reactor. The model was trained on a dataset generated by a software package which simulates the behaviour of the graphite core during a severe earthquake. Several machine learning techniques, such as the use of convolutional neural networks, were identified as highly applicable to this particular problem. Through the development of the model, several observations and insights were garnered which may be of interest from a graphite core analysis and safety perspective. The best performing model was capable of making 95% of test set predictions within a 20 percentage point margin of the ground truth.</abstract><cop>Amsterdam</cop><pub>Elsevier B.V</pub><doi>10.1016/j.nucengdes.2022.111842</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 0029-5493
ispartof Nuclear engineering and design, 2022-08, Vol.395, p.111842, Article 111842
issn 0029-5493
1872-759X
language eng
recordid cdi_proquest_journals_2762942340
source Access via ScienceDirect (Elsevier)
subjects Advanced gas-cooled reactor
Artificial neural networks
Convolutional neural network
Core analysis
Data analysis
Data science
Earthquakes
Gas cooled reactors
Graphite
Learning algorithms
Machine learning
Neural networks
Nuclear
Nuclear safety
Reactors
Regression
Seismic activity
Shaker table
Supervised learning
Surrogate model
title A surrogate machine learning model for advanced gas-cooled reactor graphite core safety analysis
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T17%3A47%3A57IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=A%20surrogate%20machine%20learning%20model%20for%20advanced%20gas-cooled%20reactor%20graphite%20core%20safety%20analysis&rft.jtitle=Nuclear%20engineering%20and%20design&rft.au=Jones,%20H.%20Rhys&rft.date=2022-08-15&rft.volume=395&rft.spage=111842&rft.pages=111842-&rft.artnum=111842&rft.issn=0029-5493&rft.eissn=1872-759X&rft_id=info:doi/10.1016/j.nucengdes.2022.111842&rft_dat=%3Cproquest_cross%3E2762942340%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2762942340&rft_id=info:pmid/&rft_els_id=S0029549322001960&rfr_iscdi=true