Machine-learning informed prediction of high-entropy solid solution formation: Beyond the Hume-Rothery rules
The empirical rules for the prediction of solid solution formation proposed so far in the literature usually have very compromised predictability. Some rules with seemingly good predictability were, however, tested using small data sets. Based on an unprecedented large dataset containing 1252 multic...
Gespeichert in:
Veröffentlicht in: | npj computational materials 2020-05, Vol.6 (1), Article 50 |
---|---|
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 | npj computational materials |
container_volume | 6 |
creator | Pei, Zongrui Yin, Junqi Hawk, Jeffrey A. Alman, David E. Gao, Michael C. |
description | The empirical rules for the prediction of solid solution formation proposed so far in the literature usually have very compromised predictability. Some rules with seemingly good predictability were, however, tested using small data sets. Based on an unprecedented large dataset containing 1252 multicomponent alloys, machine-learning methods showed that the formation of solid solutions can be very accurately predicted (93%). The machine-learning results help identify the most important features, such as molar volume, bulk modulus, and melting temperature. As such a new thermodynamics-based rule was developed to predict solid–solution alloys. The new rule is nonetheless slightly less accurate (73%) but has roots in the physical nature of the problem. The new rule is employed to predict solid solutions existing in the three blocks, each of which consists of 9 elements. The predictions encompass face-centered cubic (FCC), body-centered cubic (BCC), and hexagonal closest packed (HCP) structures in a high throughput manner. The validity of the prediction is further confirmed by CALculations of PHAse Diagram (CALPHAD) calculations with high consistency (94%). Since the new thermodynamics-based rule employs only elemental properties, applicability in screening for solid solution high-entropy alloys is straightforward and efficient. |
doi_str_mv | 10.1038/s41524-020-0308-7 |
format | Article |
fullrecord | <record><control><sourceid>proquest_osti_</sourceid><recordid>TN_cdi_osti_scitechconnect_1617776</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2399787836</sourcerecordid><originalsourceid>FETCH-LOGICAL-c452t-11932996119a2829baad5e39f8b0af32696bee3971b9e5893f1a200b354e2c3c3</originalsourceid><addsrcrecordid>eNp1kE9LxDAQxYsoKLofwFvQczR_2qbxpqKuoAii55Cm022km9SkPey3N7WCXrzMvGF-bxhelp1SckEJry5jTguWY8IIJpxUWOxlR4wUAnNZkv0_-jBbxfhBCKGSVSwnR1n_rE1nHeAedHDWbZB1rQ9baNAQoLFmtN4h36LObjoMbgx-2KHoe9vMdfpezwY9qyt0AzvvGjR2gNbTFvCrTzLsUJh6iCfZQav7CKuffpy939-93a7x08vD4-31EzZ5wUZMqeRMyjJ1nd6UtdZNAVy2VU10y1kpyxrSLGgtoagkb6lmhNS8yIEZbvhxdrbc9XG0Kho7gumMdw7MqGhJhRBlgs4XaAj-c4I4qg8_BZf-UoxLKSpR8ZmiC2WCjzFAq4ZgtzrsFCVqDl8t4asUvprDVyJ52OKJiXUbCL-X_zd9AX1shx8</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2399787836</pqid></control><display><type>article</type><title>Machine-learning informed prediction of high-entropy solid solution formation: Beyond the Hume-Rothery rules</title><source>DOAJ Directory of Open Access Journals</source><source>Springer Nature OA Free Journals</source><source>Nature Free</source><source>EZB-FREE-00999 freely available EZB journals</source><creator>Pei, Zongrui ; Yin, Junqi ; Hawk, Jeffrey A. ; Alman, David E. ; Gao, Michael C.</creator><creatorcontrib>Pei, Zongrui ; Yin, Junqi ; Hawk, Jeffrey A. ; Alman, David E. ; Gao, Michael C. ; Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States) ; National Energy Technology Laboratory (NETL), Pittsburgh, PA, Morgantown, WV, and Albany, OR (United States)</creatorcontrib><description>The empirical rules for the prediction of solid solution formation proposed so far in the literature usually have very compromised predictability. Some rules with seemingly good predictability were, however, tested using small data sets. Based on an unprecedented large dataset containing 1252 multicomponent alloys, machine-learning methods showed that the formation of solid solutions can be very accurately predicted (93%). The machine-learning results help identify the most important features, such as molar volume, bulk modulus, and melting temperature. As such a new thermodynamics-based rule was developed to predict solid–solution alloys. The new rule is nonetheless slightly less accurate (73%) but has roots in the physical nature of the problem. The new rule is employed to predict solid solutions existing in the three blocks, each of which consists of 9 elements. The predictions encompass face-centered cubic (FCC), body-centered cubic (BCC), and hexagonal closest packed (HCP) structures in a high throughput manner. The validity of the prediction is further confirmed by CALculations of PHAse Diagram (CALPHAD) calculations with high consistency (94%). Since the new thermodynamics-based rule employs only elemental properties, applicability in screening for solid solution high-entropy alloys is straightforward and efficient.</description><identifier>ISSN: 2057-3960</identifier><identifier>EISSN: 2057-3960</identifier><identifier>DOI: 10.1038/s41524-020-0308-7</identifier><language>eng</language><publisher>London: Nature Publishing Group UK</publisher><subject>639/301/1023/1026 ; 639/301/1034 ; 639/766/25 ; Alloy development ; Alloys ; Body centered cubic lattice ; Bulk modulus ; Characterization and Evaluation of Materials ; Chemistry and Materials Science ; Computational Intelligence ; Computer simulation ; Entropy of formation ; Entropy of solution ; Face centered cubic lattice ; High entropy alloys ; Learning algorithms ; Machine learning ; MATERIALS SCIENCE ; Mathematical analysis ; Mathematical and Computational Engineering ; Mathematical and Computational Physics ; Mathematical Modeling and Industrial Mathematics ; Melt temperature ; Molar volume ; Phase diagrams ; Predictions ; Solid solutions ; Theoretical ; Thermodynamics</subject><ispartof>npj computational materials, 2020-05, Vol.6 (1), Article 50</ispartof><rights>This is a U.S. government work and not under copyright protection in the U.S.; foreign copyright protection may apply 2020</rights><rights>This is a U.S. government work and not under copyright protection in the U.S.; foreign copyright protection may apply 2020. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c452t-11932996119a2829baad5e39f8b0af32696bee3971b9e5893f1a200b354e2c3c3</citedby><cites>FETCH-LOGICAL-c452t-11932996119a2829baad5e39f8b0af32696bee3971b9e5893f1a200b354e2c3c3</cites><orcidid>0000-0003-0748-4629 ; 0000-0002-0515-846X ; 0000000307484629 ; 000000020515846X ; 0000000338435520</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://link.springer.com/content/pdf/10.1038/s41524-020-0308-7$$EPDF$$P50$$Gspringer$$Hfree_for_read</linktopdf><linktohtml>$$Uhttps://doi.org/10.1038/s41524-020-0308-7$$EHTML$$P50$$Gspringer$$Hfree_for_read</linktohtml><link.rule.ids>230,314,780,784,864,885,27924,27925,41120,42189,51576</link.rule.ids><backlink>$$Uhttps://www.osti.gov/servlets/purl/1617776$$D View this record in Osti.gov$$Hfree_for_read</backlink></links><search><creatorcontrib>Pei, Zongrui</creatorcontrib><creatorcontrib>Yin, Junqi</creatorcontrib><creatorcontrib>Hawk, Jeffrey A.</creatorcontrib><creatorcontrib>Alman, David E.</creatorcontrib><creatorcontrib>Gao, Michael C.</creatorcontrib><creatorcontrib>Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)</creatorcontrib><creatorcontrib>National Energy Technology Laboratory (NETL), Pittsburgh, PA, Morgantown, WV, and Albany, OR (United States)</creatorcontrib><title>Machine-learning informed prediction of high-entropy solid solution formation: Beyond the Hume-Rothery rules</title><title>npj computational materials</title><addtitle>npj Comput Mater</addtitle><description>The empirical rules for the prediction of solid solution formation proposed so far in the literature usually have very compromised predictability. Some rules with seemingly good predictability were, however, tested using small data sets. Based on an unprecedented large dataset containing 1252 multicomponent alloys, machine-learning methods showed that the formation of solid solutions can be very accurately predicted (93%). The machine-learning results help identify the most important features, such as molar volume, bulk modulus, and melting temperature. As such a new thermodynamics-based rule was developed to predict solid–solution alloys. The new rule is nonetheless slightly less accurate (73%) but has roots in the physical nature of the problem. The new rule is employed to predict solid solutions existing in the three blocks, each of which consists of 9 elements. The predictions encompass face-centered cubic (FCC), body-centered cubic (BCC), and hexagonal closest packed (HCP) structures in a high throughput manner. The validity of the prediction is further confirmed by CALculations of PHAse Diagram (CALPHAD) calculations with high consistency (94%). Since the new thermodynamics-based rule employs only elemental properties, applicability in screening for solid solution high-entropy alloys is straightforward and efficient.</description><subject>639/301/1023/1026</subject><subject>639/301/1034</subject><subject>639/766/25</subject><subject>Alloy development</subject><subject>Alloys</subject><subject>Body centered cubic lattice</subject><subject>Bulk modulus</subject><subject>Characterization and Evaluation of Materials</subject><subject>Chemistry and Materials Science</subject><subject>Computational Intelligence</subject><subject>Computer simulation</subject><subject>Entropy of formation</subject><subject>Entropy of solution</subject><subject>Face centered cubic lattice</subject><subject>High entropy alloys</subject><subject>Learning algorithms</subject><subject>Machine learning</subject><subject>MATERIALS SCIENCE</subject><subject>Mathematical analysis</subject><subject>Mathematical and Computational Engineering</subject><subject>Mathematical and Computational Physics</subject><subject>Mathematical Modeling and Industrial Mathematics</subject><subject>Melt temperature</subject><subject>Molar volume</subject><subject>Phase diagrams</subject><subject>Predictions</subject><subject>Solid solutions</subject><subject>Theoretical</subject><subject>Thermodynamics</subject><issn>2057-3960</issn><issn>2057-3960</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><sourceid>C6C</sourceid><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><sourceid>GNUQQ</sourceid><recordid>eNp1kE9LxDAQxYsoKLofwFvQczR_2qbxpqKuoAii55Cm022km9SkPey3N7WCXrzMvGF-bxhelp1SckEJry5jTguWY8IIJpxUWOxlR4wUAnNZkv0_-jBbxfhBCKGSVSwnR1n_rE1nHeAedHDWbZB1rQ9baNAQoLFmtN4h36LObjoMbgx-2KHoe9vMdfpezwY9qyt0AzvvGjR2gNbTFvCrTzLsUJh6iCfZQav7CKuffpy939-93a7x08vD4-31EzZ5wUZMqeRMyjJ1nd6UtdZNAVy2VU10y1kpyxrSLGgtoagkb6lmhNS8yIEZbvhxdrbc9XG0Kho7gumMdw7MqGhJhRBlgs4XaAj-c4I4qg8_BZf-UoxLKSpR8ZmiC2WCjzFAq4ZgtzrsFCVqDl8t4asUvprDVyJ52OKJiXUbCL-X_zd9AX1shx8</recordid><startdate>20200507</startdate><enddate>20200507</enddate><creator>Pei, Zongrui</creator><creator>Yin, Junqi</creator><creator>Hawk, Jeffrey A.</creator><creator>Alman, David E.</creator><creator>Gao, Michael C.</creator><general>Nature Publishing Group UK</general><general>Nature Publishing Group</general><scope>C6C</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>3V.</scope><scope>7X7</scope><scope>7XB</scope><scope>8FE</scope><scope>8FG</scope><scope>8FH</scope><scope>8FI</scope><scope>8FJ</scope><scope>8FK</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BBNVY</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>BHPHI</scope><scope>CCPQU</scope><scope>D1I</scope><scope>DWQXO</scope><scope>FYUFA</scope><scope>GHDGH</scope><scope>GNUQQ</scope><scope>HCIFZ</scope><scope>K9.</scope><scope>KB.</scope><scope>LK8</scope><scope>M0S</scope><scope>M7P</scope><scope>PDBOC</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>OIOZB</scope><scope>OTOTI</scope><orcidid>https://orcid.org/0000-0003-0748-4629</orcidid><orcidid>https://orcid.org/0000-0002-0515-846X</orcidid><orcidid>https://orcid.org/0000000307484629</orcidid><orcidid>https://orcid.org/000000020515846X</orcidid><orcidid>https://orcid.org/0000000338435520</orcidid></search><sort><creationdate>20200507</creationdate><title>Machine-learning informed prediction of high-entropy solid solution formation: Beyond the Hume-Rothery rules</title><author>Pei, Zongrui ; Yin, Junqi ; Hawk, Jeffrey A. ; Alman, David E. ; Gao, Michael C.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c452t-11932996119a2829baad5e39f8b0af32696bee3971b9e5893f1a200b354e2c3c3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>639/301/1023/1026</topic><topic>639/301/1034</topic><topic>639/766/25</topic><topic>Alloy development</topic><topic>Alloys</topic><topic>Body centered cubic lattice</topic><topic>Bulk modulus</topic><topic>Characterization and Evaluation of Materials</topic><topic>Chemistry and Materials Science</topic><topic>Computational Intelligence</topic><topic>Computer simulation</topic><topic>Entropy of formation</topic><topic>Entropy of solution</topic><topic>Face centered cubic lattice</topic><topic>High entropy alloys</topic><topic>Learning algorithms</topic><topic>Machine learning</topic><topic>MATERIALS SCIENCE</topic><topic>Mathematical analysis</topic><topic>Mathematical and Computational Engineering</topic><topic>Mathematical and Computational Physics</topic><topic>Mathematical Modeling and Industrial Mathematics</topic><topic>Melt temperature</topic><topic>Molar volume</topic><topic>Phase diagrams</topic><topic>Predictions</topic><topic>Solid solutions</topic><topic>Theoretical</topic><topic>Thermodynamics</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Pei, Zongrui</creatorcontrib><creatorcontrib>Yin, Junqi</creatorcontrib><creatorcontrib>Hawk, Jeffrey A.</creatorcontrib><creatorcontrib>Alman, David E.</creatorcontrib><creatorcontrib>Gao, Michael C.</creatorcontrib><creatorcontrib>Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)</creatorcontrib><creatorcontrib>National Energy Technology Laboratory (NETL), Pittsburgh, PA, Morgantown, WV, and Albany, OR (United States)</creatorcontrib><collection>Springer Nature OA Free Journals</collection><collection>CrossRef</collection><collection>ProQuest Central (Corporate)</collection><collection>Health & Medical Collection</collection><collection>ProQuest Central (purchase pre-March 2016)</collection><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>ProQuest Natural Science Collection</collection><collection>Hospital Premium Collection</collection><collection>Hospital Premium Collection (Alumni Edition)</collection><collection>ProQuest Central (Alumni) (purchase pre-March 2016)</collection><collection>Materials Science & Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>Biological Science Collection</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>Natural Science Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Materials Science Collection</collection><collection>ProQuest Central Korea</collection><collection>Health Research Premium Collection</collection><collection>Health Research Premium Collection (Alumni)</collection><collection>ProQuest Central Student</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Health & Medical Complete (Alumni)</collection><collection>Materials Science Database</collection><collection>ProQuest Biological Science Collection</collection><collection>Health & Medical Collection (Alumni Edition)</collection><collection>Biological Science Database</collection><collection>Materials Science Collection</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>OSTI.GOV - Hybrid</collection><collection>OSTI.GOV</collection><jtitle>npj computational materials</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Pei, Zongrui</au><au>Yin, Junqi</au><au>Hawk, Jeffrey A.</au><au>Alman, David E.</au><au>Gao, Michael C.</au><aucorp>Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)</aucorp><aucorp>National Energy Technology Laboratory (NETL), Pittsburgh, PA, Morgantown, WV, and Albany, OR (United States)</aucorp><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Machine-learning informed prediction of high-entropy solid solution formation: Beyond the Hume-Rothery rules</atitle><jtitle>npj computational materials</jtitle><stitle>npj Comput Mater</stitle><date>2020-05-07</date><risdate>2020</risdate><volume>6</volume><issue>1</issue><artnum>50</artnum><issn>2057-3960</issn><eissn>2057-3960</eissn><abstract>The empirical rules for the prediction of solid solution formation proposed so far in the literature usually have very compromised predictability. Some rules with seemingly good predictability were, however, tested using small data sets. Based on an unprecedented large dataset containing 1252 multicomponent alloys, machine-learning methods showed that the formation of solid solutions can be very accurately predicted (93%). The machine-learning results help identify the most important features, such as molar volume, bulk modulus, and melting temperature. As such a new thermodynamics-based rule was developed to predict solid–solution alloys. The new rule is nonetheless slightly less accurate (73%) but has roots in the physical nature of the problem. The new rule is employed to predict solid solutions existing in the three blocks, each of which consists of 9 elements. The predictions encompass face-centered cubic (FCC), body-centered cubic (BCC), and hexagonal closest packed (HCP) structures in a high throughput manner. The validity of the prediction is further confirmed by CALculations of PHAse Diagram (CALPHAD) calculations with high consistency (94%). Since the new thermodynamics-based rule employs only elemental properties, applicability in screening for solid solution high-entropy alloys is straightforward and efficient.</abstract><cop>London</cop><pub>Nature Publishing Group UK</pub><doi>10.1038/s41524-020-0308-7</doi><orcidid>https://orcid.org/0000-0003-0748-4629</orcidid><orcidid>https://orcid.org/0000-0002-0515-846X</orcidid><orcidid>https://orcid.org/0000000307484629</orcidid><orcidid>https://orcid.org/000000020515846X</orcidid><orcidid>https://orcid.org/0000000338435520</orcidid><oa>free_for_read</oa></addata></record> |
fulltext | fulltext |
identifier | ISSN: 2057-3960 |
ispartof | npj computational materials, 2020-05, Vol.6 (1), Article 50 |
issn | 2057-3960 2057-3960 |
language | eng |
recordid | cdi_osti_scitechconnect_1617776 |
source | DOAJ Directory of Open Access Journals; Springer Nature OA Free Journals; Nature Free; EZB-FREE-00999 freely available EZB journals |
subjects | 639/301/1023/1026 639/301/1034 639/766/25 Alloy development Alloys Body centered cubic lattice Bulk modulus Characterization and Evaluation of Materials Chemistry and Materials Science Computational Intelligence Computer simulation Entropy of formation Entropy of solution Face centered cubic lattice High entropy alloys Learning algorithms Machine learning MATERIALS SCIENCE Mathematical analysis Mathematical and Computational Engineering Mathematical and Computational Physics Mathematical Modeling and Industrial Mathematics Melt temperature Molar volume Phase diagrams Predictions Solid solutions Theoretical Thermodynamics |
title | Machine-learning informed prediction of high-entropy solid solution formation: Beyond the Hume-Rothery rules |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-03T12%3A23%3A10IST&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=Machine-learning%20informed%20prediction%20of%20high-entropy%20solid%20solution%20formation:%20Beyond%20the%20Hume-Rothery%20rules&rft.jtitle=npj%20computational%20materials&rft.au=Pei,%20Zongrui&rft.aucorp=Oak%20Ridge%20National%20Lab.%20(ORNL),%20Oak%20Ridge,%20TN%20(United%20States)&rft.date=2020-05-07&rft.volume=6&rft.issue=1&rft.artnum=50&rft.issn=2057-3960&rft.eissn=2057-3960&rft_id=info:doi/10.1038/s41524-020-0308-7&rft_dat=%3Cproquest_osti_%3E2399787836%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=2399787836&rft_id=info:pmid/&rfr_iscdi=true |