Understanding oxidation of Fe-Cr-Al alloys through explainable artificial intelligence
Abstract The oxidation resistance of FeCrAl based on alloying composition and oxidizing conditions is predicted using a combinatorial experimental and artificial intelligence approach. A neural network (NN) classification model was trained on the experimental FeCrAl dataset produced at GE Research....
Gespeichert in:
| Veröffentlicht in: | MRS communications 2023-01, Vol.13 (1) |
|---|---|
| Hauptverfasser: | , , , , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | |
|---|---|
| container_issue | 1 |
| container_start_page | |
| container_title | MRS communications |
| container_volume | 13 |
| creator | Roy, Indranil Feng, Bojun Roychowdhury, Subhrajit Ravi, Sandipp Krishnan Umretiya, Rajnikant V. Reynolds, Christopher Ghosh, Sayan Rebak, Raul B. Hoffman, Andrew |
| description | Abstract The oxidation resistance of FeCrAl based on alloying composition and oxidizing conditions is predicted using a combinatorial experimental and artificial intelligence approach. A neural network (NN) classification model was trained on the experimental FeCrAl dataset produced at GE Research. Furthermore, using the SHapley Additive exPlanations (SHAP) explainable artificial intelligence (XAI) tool, we explore how the NN can showcase further material insights that are unavailable directly from a black-box model. We report that high Al and Cr content forms protective oxide layer, while Mo in FeCrAl creates thick unprotective oxide scale that is vulnerable to spallation due to thermal expansion. Graphical abstract |
| format | Article |
| fullrecord | <record><control><sourceid>osti</sourceid><recordid>TN_cdi_osti_scitechconnect_2418376</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2418376</sourcerecordid><originalsourceid>FETCH-osti_scitechconnect_24183763</originalsourceid><addsrcrecordid>eNqNykEOgjAQQNEuNJEod2jcNxEQiktDJB5A3ZJaBhgzmZq2Jnh7XXgA_-Zt_kIkeVYeVFVXeiXSEB67b2WVa10m4nblHnyIhnvkUboZexPRsXSDbEE1Xh1JGiL3DjJO3r3GScL8JINs7gTS-IgDWjQkkSMQ4QhsYSOWg6EA6c-12LanS3NWLkTsgsUIdrKOGWzs8n1WF7oq_po-37RByg</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Understanding oxidation of Fe-Cr-Al alloys through explainable artificial intelligence</title><source>SpringerLink Journals</source><creator>Roy, Indranil ; Feng, Bojun ; Roychowdhury, Subhrajit ; Ravi, Sandipp Krishnan ; Umretiya, Rajnikant V. ; Reynolds, Christopher ; Ghosh, Sayan ; Rebak, Raul B. ; Hoffman, Andrew</creator><creatorcontrib>Roy, Indranil ; Feng, Bojun ; Roychowdhury, Subhrajit ; Ravi, Sandipp Krishnan ; Umretiya, Rajnikant V. ; Reynolds, Christopher ; Ghosh, Sayan ; Rebak, Raul B. ; Hoffman, Andrew ; GE Packaged Power, LLC, Houston, TX (United States)</creatorcontrib><description>Abstract The oxidation resistance of FeCrAl based on alloying composition and oxidizing conditions is predicted using a combinatorial experimental and artificial intelligence approach. A neural network (NN) classification model was trained on the experimental FeCrAl dataset produced at GE Research. Furthermore, using the SHapley Additive exPlanations (SHAP) explainable artificial intelligence (XAI) tool, we explore how the NN can showcase further material insights that are unavailable directly from a black-box model. We report that high Al and Cr content forms protective oxide layer, while Mo in FeCrAl creates thick unprotective oxide scale that is vulnerable to spallation due to thermal expansion. Graphical abstract</description><identifier>ISSN: 2159-6867</identifier><language>eng</language><publisher>United States: Springer Nature</publisher><subject>Materials Science</subject><ispartof>MRS communications, 2023-01, Vol.13 (1)</ispartof><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><orcidid>0000000336124323</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>230,314,780,784,885</link.rule.ids><backlink>$$Uhttps://www.osti.gov/biblio/2418376$$D View this record in Osti.gov$$Hfree_for_read</backlink></links><search><creatorcontrib>Roy, Indranil</creatorcontrib><creatorcontrib>Feng, Bojun</creatorcontrib><creatorcontrib>Roychowdhury, Subhrajit</creatorcontrib><creatorcontrib>Ravi, Sandipp Krishnan</creatorcontrib><creatorcontrib>Umretiya, Rajnikant V.</creatorcontrib><creatorcontrib>Reynolds, Christopher</creatorcontrib><creatorcontrib>Ghosh, Sayan</creatorcontrib><creatorcontrib>Rebak, Raul B.</creatorcontrib><creatorcontrib>Hoffman, Andrew</creatorcontrib><creatorcontrib>GE Packaged Power, LLC, Houston, TX (United States)</creatorcontrib><title>Understanding oxidation of Fe-Cr-Al alloys through explainable artificial intelligence</title><title>MRS communications</title><description>Abstract The oxidation resistance of FeCrAl based on alloying composition and oxidizing conditions is predicted using a combinatorial experimental and artificial intelligence approach. A neural network (NN) classification model was trained on the experimental FeCrAl dataset produced at GE Research. Furthermore, using the SHapley Additive exPlanations (SHAP) explainable artificial intelligence (XAI) tool, we explore how the NN can showcase further material insights that are unavailable directly from a black-box model. We report that high Al and Cr content forms protective oxide layer, while Mo in FeCrAl creates thick unprotective oxide scale that is vulnerable to spallation due to thermal expansion. Graphical abstract</description><subject>Materials Science</subject><issn>2159-6867</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><recordid>eNqNykEOgjAQQNEuNJEod2jcNxEQiktDJB5A3ZJaBhgzmZq2Jnh7XXgA_-Zt_kIkeVYeVFVXeiXSEB67b2WVa10m4nblHnyIhnvkUboZexPRsXSDbEE1Xh1JGiL3DjJO3r3GScL8JINs7gTS-IgDWjQkkSMQ4QhsYSOWg6EA6c-12LanS3NWLkTsgsUIdrKOGWzs8n1WF7oq_po-37RByg</recordid><startdate>20230109</startdate><enddate>20230109</enddate><creator>Roy, Indranil</creator><creator>Feng, Bojun</creator><creator>Roychowdhury, Subhrajit</creator><creator>Ravi, Sandipp Krishnan</creator><creator>Umretiya, Rajnikant V.</creator><creator>Reynolds, Christopher</creator><creator>Ghosh, Sayan</creator><creator>Rebak, Raul B.</creator><creator>Hoffman, Andrew</creator><general>Springer Nature</general><scope>OTOTI</scope><orcidid>https://orcid.org/0000000336124323</orcidid></search><sort><creationdate>20230109</creationdate><title>Understanding oxidation of Fe-Cr-Al alloys through explainable artificial intelligence</title><author>Roy, Indranil ; Feng, Bojun ; Roychowdhury, Subhrajit ; Ravi, Sandipp Krishnan ; Umretiya, Rajnikant V. ; Reynolds, Christopher ; Ghosh, Sayan ; Rebak, Raul B. ; Hoffman, Andrew</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-osti_scitechconnect_24183763</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Materials Science</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Roy, Indranil</creatorcontrib><creatorcontrib>Feng, Bojun</creatorcontrib><creatorcontrib>Roychowdhury, Subhrajit</creatorcontrib><creatorcontrib>Ravi, Sandipp Krishnan</creatorcontrib><creatorcontrib>Umretiya, Rajnikant V.</creatorcontrib><creatorcontrib>Reynolds, Christopher</creatorcontrib><creatorcontrib>Ghosh, Sayan</creatorcontrib><creatorcontrib>Rebak, Raul B.</creatorcontrib><creatorcontrib>Hoffman, Andrew</creatorcontrib><creatorcontrib>GE Packaged Power, LLC, Houston, TX (United States)</creatorcontrib><collection>OSTI.GOV</collection><jtitle>MRS communications</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Roy, Indranil</au><au>Feng, Bojun</au><au>Roychowdhury, Subhrajit</au><au>Ravi, Sandipp Krishnan</au><au>Umretiya, Rajnikant V.</au><au>Reynolds, Christopher</au><au>Ghosh, Sayan</au><au>Rebak, Raul B.</au><au>Hoffman, Andrew</au><aucorp>GE Packaged Power, LLC, Houston, TX (United States)</aucorp><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Understanding oxidation of Fe-Cr-Al alloys through explainable artificial intelligence</atitle><jtitle>MRS communications</jtitle><date>2023-01-09</date><risdate>2023</risdate><volume>13</volume><issue>1</issue><issn>2159-6867</issn><abstract>Abstract The oxidation resistance of FeCrAl based on alloying composition and oxidizing conditions is predicted using a combinatorial experimental and artificial intelligence approach. A neural network (NN) classification model was trained on the experimental FeCrAl dataset produced at GE Research. Furthermore, using the SHapley Additive exPlanations (SHAP) explainable artificial intelligence (XAI) tool, we explore how the NN can showcase further material insights that are unavailable directly from a black-box model. We report that high Al and Cr content forms protective oxide layer, while Mo in FeCrAl creates thick unprotective oxide scale that is vulnerable to spallation due to thermal expansion. Graphical abstract</abstract><cop>United States</cop><pub>Springer Nature</pub><orcidid>https://orcid.org/0000000336124323</orcidid></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 2159-6867 |
| ispartof | MRS communications, 2023-01, Vol.13 (1) |
| issn | 2159-6867 |
| language | eng |
| recordid | cdi_osti_scitechconnect_2418376 |
| source | SpringerLink Journals |
| subjects | Materials Science |
| title | Understanding oxidation of Fe-Cr-Al alloys through explainable artificial intelligence |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-04T06%3A29%3A58IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-osti&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Understanding%20oxidation%20of%20Fe-Cr-Al%20alloys%20through%20explainable%20artificial%20intelligence&rft.jtitle=MRS%20communications&rft.au=Roy,%20Indranil&rft.aucorp=GE%20Packaged%20Power,%20LLC,%20Houston,%20TX%20(United%20States)&rft.date=2023-01-09&rft.volume=13&rft.issue=1&rft.issn=2159-6867&rft_id=info:doi/&rft_dat=%3Costi%3E2418376%3C/osti%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true |