Hybrid approach to predict the effective properties of heterogeneous materials using artificial neural networks and micromechanical models
In this article, an investigation was carried out to verify hybrid models capabilities to predict the effective properties of heterogeneous materials. A hybrid model ANN−φ is developed by combining artificial neural networks and micromechanical modeling. The homogenization approach used in this stud...
Gespeichert in:
| Veröffentlicht in: | International journal for numerical methods in engineering 2022-02, Vol.123 (3), p.794-819 |
|---|---|
| Hauptverfasser: | , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 819 |
|---|---|
| container_issue | 3 |
| container_start_page | 794 |
| container_title | International journal for numerical methods in engineering |
| container_volume | 123 |
| creator | Danoun, Aymen Pruliére, Etienne Chemisky, Yves |
| description | In this article, an investigation was carried out to verify hybrid models capabilities to predict the effective properties of heterogeneous materials. A hybrid model ANN−φ is developed by combining artificial neural networks and micromechanical modeling. The homogenization approach used in this study is mainly based on Eshelby's inclusion problem. The ANN−φ model, once trained on an Eshelby's tensors database, showed an excellent predictive capabilities of the effective mechanical behavior and local stresses in heterogeneous materials. The obtained results with ANN−φ are compared to numerical estimations which are often costly in terms of computational time. The results presented in this work show that the developed hybrid model can provide a significant computational time saving by a factor up to 2000 for 104 phases while maintaining its accuracy and reliability. |
| doi_str_mv | 10.1002/nme.6877 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_hal_p</sourceid><recordid>TN_cdi_hal_primary_oai_HAL_hal_03498851v1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2620242423</sourcerecordid><originalsourceid>FETCH-LOGICAL-c3277-af30f1d7470483d53106b47665fc5ca480e0fde17384352a827c117f55a44ffa3</originalsourceid><addsrcrecordid>eNp1kcFqGzEQhkVpoE5S6CMIcmkPm45W0mp9DCGpC05zSc9C1o68cr2rjbRr41foU1e2Q25lDsP88_Ezw0_IFwa3DKD83nd4W9VKfSAzBnNVQAnqI5nl1byQ85p9IpcpbQAYk8Bn5O_isIq-oWYYYjC2pWOgQ8TG25GOLVJ0Du3od5jVMGAcPSYaHG1xxBjW2GOYEu1MnrzZJjol36-pyZzzNiu0xyme2rgP8U-ipm9o520MHdrW9N7mZRca3KZrcuGyBX5-61fk9-PDy_2iWD7_-Hl_tywsL5UqjOPgWKOEAlHzRnIG1UqoqpLOSmtEDQiuQaZ4LbgsTV0qy5hyUhohnDP8inw7-7Zmq4foOxMPOhivF3dLfdSAi3ldS7Zjmb05s_n71wnTqDdhin0-T5dVCaXIxTP19Uzlt1KK6N5tGehjKjqnoo-pZLQ4o3u_xcN_Of3r6eHE_wMbHY_L</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2620242423</pqid></control><display><type>article</type><title>Hybrid approach to predict the effective properties of heterogeneous materials using artificial neural networks and micromechanical models</title><source>Wiley Online Library Journals Frontfile Complete</source><creator>Danoun, Aymen ; Pruliére, Etienne ; Chemisky, Yves</creator><creatorcontrib>Danoun, Aymen ; Pruliére, Etienne ; Chemisky, Yves</creatorcontrib><description>In this article, an investigation was carried out to verify hybrid models capabilities to predict the effective properties of heterogeneous materials. A hybrid model ANN−φ is developed by combining artificial neural networks and micromechanical modeling. The homogenization approach used in this study is mainly based on Eshelby's inclusion problem. The ANN−φ model, once trained on an Eshelby's tensors database, showed an excellent predictive capabilities of the effective mechanical behavior and local stresses in heterogeneous materials. The obtained results with ANN−φ are compared to numerical estimations which are often costly in terms of computational time. The results presented in this work show that the developed hybrid model can provide a significant computational time saving by a factor up to 2000 for 104 phases while maintaining its accuracy and reliability.</description><identifier>ISSN: 0029-5981</identifier><identifier>EISSN: 1097-0207</identifier><identifier>DOI: 10.1002/nme.6877</identifier><language>eng</language><publisher>Hoboken, USA: John Wiley & Sons, Inc</publisher><subject>artificial neural network ; Artificial neural networks ; Computational efficiency ; Computing time ; effective properties ; Engineering Sciences ; Eshelby tensor ; heterogeneous materials ; homogenization ; inclusion problems ; Materials ; Mechanical properties ; Neural networks ; Tensors</subject><ispartof>International journal for numerical methods in engineering, 2022-02, Vol.123 (3), p.794-819</ispartof><rights>2021 John Wiley & Sons Ltd.</rights><rights>2022 John Wiley & Sons, Ltd.</rights><rights>Distributed under a Creative Commons Attribution 4.0 International License</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c3277-af30f1d7470483d53106b47665fc5ca480e0fde17384352a827c117f55a44ffa3</citedby><cites>FETCH-LOGICAL-c3277-af30f1d7470483d53106b47665fc5ca480e0fde17384352a827c117f55a44ffa3</cites><orcidid>0000-0001-6872-6842 ; 0000-0003-2238-2081 ; 0000-0002-8725-9554</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://onlinelibrary.wiley.com/doi/pdf/10.1002%2Fnme.6877$$EPDF$$P50$$Gwiley$$H</linktopdf><linktohtml>$$Uhttps://onlinelibrary.wiley.com/doi/full/10.1002%2Fnme.6877$$EHTML$$P50$$Gwiley$$H</linktohtml><link.rule.ids>230,314,780,784,885,1416,27923,27924,45573,45574</link.rule.ids><backlink>$$Uhttps://hal.science/hal-03498851$$DView record in HAL$$Hfree_for_read</backlink></links><search><creatorcontrib>Danoun, Aymen</creatorcontrib><creatorcontrib>Pruliére, Etienne</creatorcontrib><creatorcontrib>Chemisky, Yves</creatorcontrib><title>Hybrid approach to predict the effective properties of heterogeneous materials using artificial neural networks and micromechanical models</title><title>International journal for numerical methods in engineering</title><description>In this article, an investigation was carried out to verify hybrid models capabilities to predict the effective properties of heterogeneous materials. A hybrid model ANN−φ is developed by combining artificial neural networks and micromechanical modeling. The homogenization approach used in this study is mainly based on Eshelby's inclusion problem. The ANN−φ model, once trained on an Eshelby's tensors database, showed an excellent predictive capabilities of the effective mechanical behavior and local stresses in heterogeneous materials. The obtained results with ANN−φ are compared to numerical estimations which are often costly in terms of computational time. The results presented in this work show that the developed hybrid model can provide a significant computational time saving by a factor up to 2000 for 104 phases while maintaining its accuracy and reliability.</description><subject>artificial neural network</subject><subject>Artificial neural networks</subject><subject>Computational efficiency</subject><subject>Computing time</subject><subject>effective properties</subject><subject>Engineering Sciences</subject><subject>Eshelby tensor</subject><subject>heterogeneous materials</subject><subject>homogenization</subject><subject>inclusion problems</subject><subject>Materials</subject><subject>Mechanical properties</subject><subject>Neural networks</subject><subject>Tensors</subject><issn>0029-5981</issn><issn>1097-0207</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><recordid>eNp1kcFqGzEQhkVpoE5S6CMIcmkPm45W0mp9DCGpC05zSc9C1o68cr2rjbRr41foU1e2Q25lDsP88_Ezw0_IFwa3DKD83nd4W9VKfSAzBnNVQAnqI5nl1byQ85p9IpcpbQAYk8Bn5O_isIq-oWYYYjC2pWOgQ8TG25GOLVJ0Du3od5jVMGAcPSYaHG1xxBjW2GOYEu1MnrzZJjol36-pyZzzNiu0xyme2rgP8U-ipm9o520MHdrW9N7mZRca3KZrcuGyBX5-61fk9-PDy_2iWD7_-Hl_tywsL5UqjOPgWKOEAlHzRnIG1UqoqpLOSmtEDQiuQaZ4LbgsTV0qy5hyUhohnDP8inw7-7Zmq4foOxMPOhivF3dLfdSAi3ldS7Zjmb05s_n71wnTqDdhin0-T5dVCaXIxTP19Uzlt1KK6N5tGehjKjqnoo-pZLQ4o3u_xcN_Of3r6eHE_wMbHY_L</recordid><startdate>20220215</startdate><enddate>20220215</enddate><creator>Danoun, Aymen</creator><creator>Pruliére, Etienne</creator><creator>Chemisky, Yves</creator><general>John Wiley & Sons, Inc</general><general>Wiley Subscription Services, Inc</general><general>Wiley</general><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7TB</scope><scope>8FD</scope><scope>FR3</scope><scope>JQ2</scope><scope>KR7</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><scope>1XC</scope><orcidid>https://orcid.org/0000-0001-6872-6842</orcidid><orcidid>https://orcid.org/0000-0003-2238-2081</orcidid><orcidid>https://orcid.org/0000-0002-8725-9554</orcidid></search><sort><creationdate>20220215</creationdate><title>Hybrid approach to predict the effective properties of heterogeneous materials using artificial neural networks and micromechanical models</title><author>Danoun, Aymen ; Pruliére, Etienne ; Chemisky, Yves</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c3277-af30f1d7470483d53106b47665fc5ca480e0fde17384352a827c117f55a44ffa3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>artificial neural network</topic><topic>Artificial neural networks</topic><topic>Computational efficiency</topic><topic>Computing time</topic><topic>effective properties</topic><topic>Engineering Sciences</topic><topic>Eshelby tensor</topic><topic>heterogeneous materials</topic><topic>homogenization</topic><topic>inclusion problems</topic><topic>Materials</topic><topic>Mechanical properties</topic><topic>Neural networks</topic><topic>Tensors</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Danoun, Aymen</creatorcontrib><creatorcontrib>Pruliére, Etienne</creatorcontrib><creatorcontrib>Chemisky, Yves</creatorcontrib><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Mechanical & Transportation Engineering Abstracts</collection><collection>Technology Research Database</collection><collection>Engineering Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Civil Engineering Abstracts</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><collection>Hyper Article en Ligne (HAL)</collection><jtitle>International journal for numerical methods in engineering</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Danoun, Aymen</au><au>Pruliére, Etienne</au><au>Chemisky, Yves</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Hybrid approach to predict the effective properties of heterogeneous materials using artificial neural networks and micromechanical models</atitle><jtitle>International journal for numerical methods in engineering</jtitle><date>2022-02-15</date><risdate>2022</risdate><volume>123</volume><issue>3</issue><spage>794</spage><epage>819</epage><pages>794-819</pages><issn>0029-5981</issn><eissn>1097-0207</eissn><abstract>In this article, an investigation was carried out to verify hybrid models capabilities to predict the effective properties of heterogeneous materials. A hybrid model ANN−φ is developed by combining artificial neural networks and micromechanical modeling. The homogenization approach used in this study is mainly based on Eshelby's inclusion problem. The ANN−φ model, once trained on an Eshelby's tensors database, showed an excellent predictive capabilities of the effective mechanical behavior and local stresses in heterogeneous materials. The obtained results with ANN−φ are compared to numerical estimations which are often costly in terms of computational time. The results presented in this work show that the developed hybrid model can provide a significant computational time saving by a factor up to 2000 for 104 phases while maintaining its accuracy and reliability.</abstract><cop>Hoboken, USA</cop><pub>John Wiley & Sons, Inc</pub><doi>10.1002/nme.6877</doi><tpages>26</tpages><orcidid>https://orcid.org/0000-0001-6872-6842</orcidid><orcidid>https://orcid.org/0000-0003-2238-2081</orcidid><orcidid>https://orcid.org/0000-0002-8725-9554</orcidid></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 0029-5981 |
| ispartof | International journal for numerical methods in engineering, 2022-02, Vol.123 (3), p.794-819 |
| issn | 0029-5981 1097-0207 |
| language | eng |
| recordid | cdi_hal_primary_oai_HAL_hal_03498851v1 |
| source | Wiley Online Library Journals Frontfile Complete |
| subjects | artificial neural network Artificial neural networks Computational efficiency Computing time effective properties Engineering Sciences Eshelby tensor heterogeneous materials homogenization inclusion problems Materials Mechanical properties Neural networks Tensors |
| title | Hybrid approach to predict the effective properties of heterogeneous materials using artificial neural networks and micromechanical models |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-10T22%3A32%3A20IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_hal_p&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Hybrid%20approach%20to%20predict%20the%20effective%20properties%20of%20heterogeneous%20materials%20using%20artificial%20neural%20networks%20and%20micromechanical%20models&rft.jtitle=International%20journal%20for%20numerical%20methods%20in%20engineering&rft.au=Danoun,%20Aymen&rft.date=2022-02-15&rft.volume=123&rft.issue=3&rft.spage=794&rft.epage=819&rft.pages=794-819&rft.issn=0029-5981&rft.eissn=1097-0207&rft_id=info:doi/10.1002/nme.6877&rft_dat=%3Cproquest_hal_p%3E2620242423%3C/proquest_hal_p%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2620242423&rft_id=info:pmid/&rfr_iscdi=true |