Characterization of used nuclear fuel with multivariate analysis for process monitoring

This paper presents initial development of a reactor-type classifier that is used to select a reactor-specific partial least squares model to predict used nuclear fuel burnup. Nuclide activities for prototypic used fuel samples were generated in ORIGEN-ARP and used to investigate techniques to chara...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Nuclear instruments & methods in physics research. Section A, Accelerators, spectrometers, detectors and associated equipment Accelerators, spectrometers, detectors and associated equipment, 2014, Vol.735, p.624-632
Hauptverfasser: Dayman, Kenneth J., Coble, Jamie B., Orton, Christopher R., Schwantes, Jon M.
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 632
container_issue
container_start_page 624
container_title Nuclear instruments & methods in physics research. Section A, Accelerators, spectrometers, detectors and associated equipment
container_volume 735
creator Dayman, Kenneth J.
Coble, Jamie B.
Orton, Christopher R.
Schwantes, Jon M.
description This paper presents initial development of a reactor-type classifier that is used to select a reactor-specific partial least squares model to predict used nuclear fuel burnup. Nuclide activities for prototypic used fuel samples were generated in ORIGEN-ARP and used to investigate techniques to characterize used nuclear fuel in terms of reactor type (pressurized or boiling water reactor) and burnup. A variety of reactor type classification algorithms, including k-nearest neighbors, linear and quadratic discriminant analyses, and support vector machines, were evaluated to differentiate used fuel from pressurized and boiling water reactors. Then, reactor type-specific partial least squares models were developed to predict the burnup of the fuel. Using these reactor type-specific models instead of a model trained for all light water reactors improved the accuracy of burnup predictions. The developed classification and prediction models were combined and applied to a large dataset that included eight fuel assembly designs, two of which were not used in training the models, and spanned the range of the initial 235U enrichment, cooling time, and burnup values expected of future commercial used fuel for reprocessing. Error rates were consistent across the range of considered enrichment, cooling time, and burnup values. Average absolute relative errors in burnup predictions for validation data both within and outside the training space were 0.0574% and 0.0597%, respectively. The errors seen in this work are artificially low, because the models were trained, optimized, and tested on simulated, noise-free data. However, these results indicate that the developed models may generalize well to new data and that the proposed approach constitutes a viable first step in developing a fuel characterization algorithm based on gamma spectra.
doi_str_mv 10.1016/j.nima.2013.09.056
format Article
fullrecord <record><control><sourceid>proquest_osti_</sourceid><recordid>TN_cdi_osti_scitechconnect_1130185</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>1530991614</sourcerecordid><originalsourceid>FETCH-LOGICAL-c307t-ff88c1fabf292ce61164d217960485f6e1fc1bd321c34ccfc2caf4b2c632ffe63</originalsourceid><addsrcrecordid>eNot0E1LAzEQgOEgCtbqH_AUPHnZNZPsZjdHKX6B4EXxGNJpYlO2iSZZpf56t9S5zOVlGB5CLoHVwEDebOrgt6bmDETNVM1aeURm0He8Um0nj8lsivpKMcZPyVnOGzaN6voZeV-sTTJYbPK_pvgYaHR0zHZFw4iDNYm60Q70x5c13Y5D8d8meVMsNcEMu-wzdTHRzxTR5ky3MfgSkw8f5-TEmSHbi_89J2_3d6-Lx-r55eFpcftcoWBdqZzrewRnlo4rjlYCyGbFoVOSNX3rpAWHsFwJDigaRIccjWuWHKXgzlkp5uTqcDfm4nVGXyyuMYZgsWgAwaBvp-j6EE1_fo02F731Ge0wmGDjmDW0gikFEpop5YcUU8w5Wac_0ySbdhqY3lPrjd5T6z21ZkpP1OIP0od1Hw</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>1530991614</pqid></control><display><type>article</type><title>Characterization of used nuclear fuel with multivariate analysis for process monitoring</title><source>Access via ScienceDirect (Elsevier)</source><creator>Dayman, Kenneth J. ; Coble, Jamie B. ; Orton, Christopher R. ; Schwantes, Jon M.</creator><creatorcontrib>Dayman, Kenneth J. ; Coble, Jamie B. ; Orton, Christopher R. ; Schwantes, Jon M. ; Pacific Northwest National Lab. (PNNL), Richland, WA (United States)</creatorcontrib><description>This paper presents initial development of a reactor-type classifier that is used to select a reactor-specific partial least squares model to predict used nuclear fuel burnup. Nuclide activities for prototypic used fuel samples were generated in ORIGEN-ARP and used to investigate techniques to characterize used nuclear fuel in terms of reactor type (pressurized or boiling water reactor) and burnup. A variety of reactor type classification algorithms, including k-nearest neighbors, linear and quadratic discriminant analyses, and support vector machines, were evaluated to differentiate used fuel from pressurized and boiling water reactors. Then, reactor type-specific partial least squares models were developed to predict the burnup of the fuel. Using these reactor type-specific models instead of a model trained for all light water reactors improved the accuracy of burnup predictions. The developed classification and prediction models were combined and applied to a large dataset that included eight fuel assembly designs, two of which were not used in training the models, and spanned the range of the initial 235U enrichment, cooling time, and burnup values expected of future commercial used fuel for reprocessing. Error rates were consistent across the range of considered enrichment, cooling time, and burnup values. Average absolute relative errors in burnup predictions for validation data both within and outside the training space were 0.0574% and 0.0597%, respectively. The errors seen in this work are artificially low, because the models were trained, optimized, and tested on simulated, noise-free data. However, these results indicate that the developed models may generalize well to new data and that the proposed approach constitutes a viable first step in developing a fuel characterization algorithm based on gamma spectra.</description><identifier>ISSN: 0168-9002</identifier><identifier>EISSN: 1872-9576</identifier><identifier>DOI: 10.1016/j.nima.2013.09.056</identifier><language>eng</language><publisher>United States: Elsevier</publisher><subject>Algorithms ; Errors ; Fuel Reprocessing ; Fuels ; Mathematical models ; Multi-Isotope Process Monitor ; Nuclear engineering ; NUCLEAR FUEL CYCLE AND FUEL MATERIALS ; Nuclear power generation ; Nuclear reactor components ; Nuclear reactors ; Process Monitoring ; Safeguards</subject><ispartof>Nuclear instruments &amp; methods in physics research. Section A, Accelerators, spectrometers, detectors and associated equipment, 2014, Vol.735, p.624-632</ispartof><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c307t-ff88c1fabf292ce61164d217960485f6e1fc1bd321c34ccfc2caf4b2c632ffe63</citedby><cites>FETCH-LOGICAL-c307t-ff88c1fabf292ce61164d217960485f6e1fc1bd321c34ccfc2caf4b2c632ffe63</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>230,314,780,784,885,4024,27923,27924,27925</link.rule.ids><backlink>$$Uhttps://www.osti.gov/biblio/1130185$$D View this record in Osti.gov$$Hfree_for_read</backlink></links><search><creatorcontrib>Dayman, Kenneth J.</creatorcontrib><creatorcontrib>Coble, Jamie B.</creatorcontrib><creatorcontrib>Orton, Christopher R.</creatorcontrib><creatorcontrib>Schwantes, Jon M.</creatorcontrib><creatorcontrib>Pacific Northwest National Lab. (PNNL), Richland, WA (United States)</creatorcontrib><title>Characterization of used nuclear fuel with multivariate analysis for process monitoring</title><title>Nuclear instruments &amp; methods in physics research. Section A, Accelerators, spectrometers, detectors and associated equipment</title><description>This paper presents initial development of a reactor-type classifier that is used to select a reactor-specific partial least squares model to predict used nuclear fuel burnup. Nuclide activities for prototypic used fuel samples were generated in ORIGEN-ARP and used to investigate techniques to characterize used nuclear fuel in terms of reactor type (pressurized or boiling water reactor) and burnup. A variety of reactor type classification algorithms, including k-nearest neighbors, linear and quadratic discriminant analyses, and support vector machines, were evaluated to differentiate used fuel from pressurized and boiling water reactors. Then, reactor type-specific partial least squares models were developed to predict the burnup of the fuel. Using these reactor type-specific models instead of a model trained for all light water reactors improved the accuracy of burnup predictions. The developed classification and prediction models were combined and applied to a large dataset that included eight fuel assembly designs, two of which were not used in training the models, and spanned the range of the initial 235U enrichment, cooling time, and burnup values expected of future commercial used fuel for reprocessing. Error rates were consistent across the range of considered enrichment, cooling time, and burnup values. Average absolute relative errors in burnup predictions for validation data both within and outside the training space were 0.0574% and 0.0597%, respectively. The errors seen in this work are artificially low, because the models were trained, optimized, and tested on simulated, noise-free data. However, these results indicate that the developed models may generalize well to new data and that the proposed approach constitutes a viable first step in developing a fuel characterization algorithm based on gamma spectra.</description><subject>Algorithms</subject><subject>Errors</subject><subject>Fuel Reprocessing</subject><subject>Fuels</subject><subject>Mathematical models</subject><subject>Multi-Isotope Process Monitor</subject><subject>Nuclear engineering</subject><subject>NUCLEAR FUEL CYCLE AND FUEL MATERIALS</subject><subject>Nuclear power generation</subject><subject>Nuclear reactor components</subject><subject>Nuclear reactors</subject><subject>Process Monitoring</subject><subject>Safeguards</subject><issn>0168-9002</issn><issn>1872-9576</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2014</creationdate><recordtype>article</recordtype><recordid>eNot0E1LAzEQgOEgCtbqH_AUPHnZNZPsZjdHKX6B4EXxGNJpYlO2iSZZpf56t9S5zOVlGB5CLoHVwEDebOrgt6bmDETNVM1aeURm0He8Um0nj8lsivpKMcZPyVnOGzaN6voZeV-sTTJYbPK_pvgYaHR0zHZFw4iDNYm60Q70x5c13Y5D8d8meVMsNcEMu-wzdTHRzxTR5ky3MfgSkw8f5-TEmSHbi_89J2_3d6-Lx-r55eFpcftcoWBdqZzrewRnlo4rjlYCyGbFoVOSNX3rpAWHsFwJDigaRIccjWuWHKXgzlkp5uTqcDfm4nVGXyyuMYZgsWgAwaBvp-j6EE1_fo02F731Ge0wmGDjmDW0gikFEpop5YcUU8w5Wac_0ySbdhqY3lPrjd5T6z21ZkpP1OIP0od1Hw</recordid><startdate>2014</startdate><enddate>2014</enddate><creator>Dayman, Kenneth J.</creator><creator>Coble, Jamie B.</creator><creator>Orton, Christopher R.</creator><creator>Schwantes, Jon M.</creator><general>Elsevier</general><scope>AAYXX</scope><scope>CITATION</scope><scope>7U5</scope><scope>8FD</scope><scope>FR3</scope><scope>H8D</scope><scope>KR7</scope><scope>L7M</scope><scope>OTOTI</scope></search><sort><creationdate>2014</creationdate><title>Characterization of used nuclear fuel with multivariate analysis for process monitoring</title><author>Dayman, Kenneth J. ; Coble, Jamie B. ; Orton, Christopher R. ; Schwantes, Jon M.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c307t-ff88c1fabf292ce61164d217960485f6e1fc1bd321c34ccfc2caf4b2c632ffe63</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2014</creationdate><topic>Algorithms</topic><topic>Errors</topic><topic>Fuel Reprocessing</topic><topic>Fuels</topic><topic>Mathematical models</topic><topic>Multi-Isotope Process Monitor</topic><topic>Nuclear engineering</topic><topic>NUCLEAR FUEL CYCLE AND FUEL MATERIALS</topic><topic>Nuclear power generation</topic><topic>Nuclear reactor components</topic><topic>Nuclear reactors</topic><topic>Process Monitoring</topic><topic>Safeguards</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Dayman, Kenneth J.</creatorcontrib><creatorcontrib>Coble, Jamie B.</creatorcontrib><creatorcontrib>Orton, Christopher R.</creatorcontrib><creatorcontrib>Schwantes, Jon M.</creatorcontrib><creatorcontrib>Pacific Northwest National Lab. (PNNL), Richland, WA (United States)</creatorcontrib><collection>CrossRef</collection><collection>Solid State and Superconductivity Abstracts</collection><collection>Technology Research Database</collection><collection>Engineering Research Database</collection><collection>Aerospace Database</collection><collection>Civil Engineering Abstracts</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>OSTI.GOV</collection><jtitle>Nuclear instruments &amp; methods in physics research. Section A, Accelerators, spectrometers, detectors and associated equipment</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Dayman, Kenneth J.</au><au>Coble, Jamie B.</au><au>Orton, Christopher R.</au><au>Schwantes, Jon M.</au><aucorp>Pacific Northwest National Lab. (PNNL), Richland, WA (United States)</aucorp><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Characterization of used nuclear fuel with multivariate analysis for process monitoring</atitle><jtitle>Nuclear instruments &amp; methods in physics research. Section A, Accelerators, spectrometers, detectors and associated equipment</jtitle><date>2014</date><risdate>2014</risdate><volume>735</volume><spage>624</spage><epage>632</epage><pages>624-632</pages><issn>0168-9002</issn><eissn>1872-9576</eissn><abstract>This paper presents initial development of a reactor-type classifier that is used to select a reactor-specific partial least squares model to predict used nuclear fuel burnup. Nuclide activities for prototypic used fuel samples were generated in ORIGEN-ARP and used to investigate techniques to characterize used nuclear fuel in terms of reactor type (pressurized or boiling water reactor) and burnup. A variety of reactor type classification algorithms, including k-nearest neighbors, linear and quadratic discriminant analyses, and support vector machines, were evaluated to differentiate used fuel from pressurized and boiling water reactors. Then, reactor type-specific partial least squares models were developed to predict the burnup of the fuel. Using these reactor type-specific models instead of a model trained for all light water reactors improved the accuracy of burnup predictions. The developed classification and prediction models were combined and applied to a large dataset that included eight fuel assembly designs, two of which were not used in training the models, and spanned the range of the initial 235U enrichment, cooling time, and burnup values expected of future commercial used fuel for reprocessing. Error rates were consistent across the range of considered enrichment, cooling time, and burnup values. Average absolute relative errors in burnup predictions for validation data both within and outside the training space were 0.0574% and 0.0597%, respectively. The errors seen in this work are artificially low, because the models were trained, optimized, and tested on simulated, noise-free data. However, these results indicate that the developed models may generalize well to new data and that the proposed approach constitutes a viable first step in developing a fuel characterization algorithm based on gamma spectra.</abstract><cop>United States</cop><pub>Elsevier</pub><doi>10.1016/j.nima.2013.09.056</doi><tpages>9</tpages></addata></record>
fulltext fulltext
identifier ISSN: 0168-9002
ispartof Nuclear instruments & methods in physics research. Section A, Accelerators, spectrometers, detectors and associated equipment, 2014, Vol.735, p.624-632
issn 0168-9002
1872-9576
language eng
recordid cdi_osti_scitechconnect_1130185
source Access via ScienceDirect (Elsevier)
subjects Algorithms
Errors
Fuel Reprocessing
Fuels
Mathematical models
Multi-Isotope Process Monitor
Nuclear engineering
NUCLEAR FUEL CYCLE AND FUEL MATERIALS
Nuclear power generation
Nuclear reactor components
Nuclear reactors
Process Monitoring
Safeguards
title Characterization of used nuclear fuel with multivariate analysis for process monitoring
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-23T15%3A03%3A45IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_osti_&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Characterization%20of%20used%20nuclear%20fuel%20with%20multivariate%20analysis%20for%20process%20monitoring&rft.jtitle=Nuclear%20instruments%20&%20methods%20in%20physics%20research.%20Section%20A,%20Accelerators,%20spectrometers,%20detectors%20and%20associated%20equipment&rft.au=Dayman,%20Kenneth%20J.&rft.aucorp=Pacific%20Northwest%20National%20Lab.%20(PNNL),%20Richland,%20WA%20(United%20States)&rft.date=2014&rft.volume=735&rft.spage=624&rft.epage=632&rft.pages=624-632&rft.issn=0168-9002&rft.eissn=1872-9576&rft_id=info:doi/10.1016/j.nima.2013.09.056&rft_dat=%3Cproquest_osti_%3E1530991614%3C/proquest_osti_%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=1530991614&rft_id=info:pmid/&rfr_iscdi=true