Machine learning aided phase field method for fracture mechanics
A machine learning aided non-deterministic damage prediction framework against both 2D and 3D fracture problems is presented in this paper. By introducing a newly developed extended support vector regression (X-SVR) with generalized Dirichlet feature mapping into the phase field crack growth model,...
Gespeichert in:
| Veröffentlicht in: | International journal of engineering science 2021-12, Vol.169, p.103587, Article 103587 |
|---|---|
| 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 | |
| container_start_page | 103587 |
| container_title | International journal of engineering science |
| container_volume | 169 |
| creator | Feng, Yuan Wang, Qihan Wu, Di Luo, Zhen Chen, Xiaojun Zhang, Tianyu Gao, Wei |
| description | A machine learning aided non-deterministic damage prediction framework against both 2D and 3D fracture problems is presented in this paper. By introducing a newly developed extended support vector regression (X-SVR) with generalized Dirichlet feature mapping into the phase field crack growth model, a damage assessment method that contains both crack diagnosis and prognosis is designed. Within the proposed analysis framework, the intricate fracture mechanism of practical engineering system can be learnt by the X-SVR model so a continuous damage diagnosis-prognosis loop can be established to assess the latest working condition of the structure. The proposed framework is applicable not only for quantifying and then assessing the current working conditions, but also for predicting the potentially crack propagation against the future forecasted information. Compared with the established experimental records and numerical result, the accuracy, effectiveness, and computational efficiency of the proposed framework are fully verified. |
| doi_str_mv | 10.1016/j.ijengsci.2021.103587 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_2600350510</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S0020722521001294</els_id><sourcerecordid>2600350510</sourcerecordid><originalsourceid>FETCH-LOGICAL-c406t-5dfdbc03159423b436bf1e87701003c20b8df2e481d4c0f454580ae6765764c73</originalsourceid><addsrcrecordid>eNqFkEtLAzEUhYMoWKt_QQZcT73J5DGzq4gvqLjRdcgkN50M7UxNpoL_3pTq2tWFwznncj5CriksKFB52y9Cj8M62bBgwGgWK1GrEzKjtWpKRht1SmYADErFmDgnFyn1ACCqppmR5auxXRiw2KCJQxjWhQkOXbHrTMLCB9y4YotTN7rCj7Hw0dhpHzFrtjNDsOmSnHmzSXj1e-fk4_Hh_f65XL09vdzfrUrLQU6lcN61FioqGs6qlley9RRrpYACVJZBWzvPkNfUcQueCy5qMCiVFEpyq6o5uTn27uL4ucc06X7cxyG_1EzmCgEiD58TeXTZOKYU0etdDFsTvzUFfaCle_1HSx9o6SOtHFweg5g3fAWMOjtwsOhCRDtpN4b_Kn4AvWZ0zA</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2600350510</pqid></control><display><type>article</type><title>Machine learning aided phase field method for fracture mechanics</title><source>ScienceDirect Journals (5 years ago - present)</source><creator>Feng, Yuan ; Wang, Qihan ; Wu, Di ; Luo, Zhen ; Chen, Xiaojun ; Zhang, Tianyu ; Gao, Wei</creator><creatorcontrib>Feng, Yuan ; Wang, Qihan ; Wu, Di ; Luo, Zhen ; Chen, Xiaojun ; Zhang, Tianyu ; Gao, Wei</creatorcontrib><description>A machine learning aided non-deterministic damage prediction framework against both 2D and 3D fracture problems is presented in this paper. By introducing a newly developed extended support vector regression (X-SVR) with generalized Dirichlet feature mapping into the phase field crack growth model, a damage assessment method that contains both crack diagnosis and prognosis is designed. Within the proposed analysis framework, the intricate fracture mechanism of practical engineering system can be learnt by the X-SVR model so a continuous damage diagnosis-prognosis loop can be established to assess the latest working condition of the structure. The proposed framework is applicable not only for quantifying and then assessing the current working conditions, but also for predicting the potentially crack propagation against the future forecasted information. Compared with the established experimental records and numerical result, the accuracy, effectiveness, and computational efficiency of the proposed framework are fully verified.</description><identifier>ISSN: 0020-7225</identifier><identifier>EISSN: 1879-2197</identifier><identifier>DOI: 10.1016/j.ijengsci.2021.103587</identifier><language>eng</language><publisher>Oxford: Elsevier Ltd</publisher><subject>Crack propagation ; Damage assessment ; Diagnosis ; Dirichlet problem ; Engineering ; Fracture mechanics ; Fractures ; Information update ; Machine learning ; Non-deterministic damage prediction ; Phase field analysis ; Prognosis ; Support vector machines</subject><ispartof>International journal of engineering science, 2021-12, Vol.169, p.103587, Article 103587</ispartof><rights>2021 Elsevier Ltd</rights><rights>Copyright Elsevier BV Dec 1, 2021</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c406t-5dfdbc03159423b436bf1e87701003c20b8df2e481d4c0f454580ae6765764c73</citedby><cites>FETCH-LOGICAL-c406t-5dfdbc03159423b436bf1e87701003c20b8df2e481d4c0f454580ae6765764c73</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://dx.doi.org/10.1016/j.ijengsci.2021.103587$$EHTML$$P50$$Gelsevier$$H</linktohtml><link.rule.ids>314,780,784,3548,27923,27924,45994</link.rule.ids></links><search><creatorcontrib>Feng, Yuan</creatorcontrib><creatorcontrib>Wang, Qihan</creatorcontrib><creatorcontrib>Wu, Di</creatorcontrib><creatorcontrib>Luo, Zhen</creatorcontrib><creatorcontrib>Chen, Xiaojun</creatorcontrib><creatorcontrib>Zhang, Tianyu</creatorcontrib><creatorcontrib>Gao, Wei</creatorcontrib><title>Machine learning aided phase field method for fracture mechanics</title><title>International journal of engineering science</title><description>A machine learning aided non-deterministic damage prediction framework against both 2D and 3D fracture problems is presented in this paper. By introducing a newly developed extended support vector regression (X-SVR) with generalized Dirichlet feature mapping into the phase field crack growth model, a damage assessment method that contains both crack diagnosis and prognosis is designed. Within the proposed analysis framework, the intricate fracture mechanism of practical engineering system can be learnt by the X-SVR model so a continuous damage diagnosis-prognosis loop can be established to assess the latest working condition of the structure. The proposed framework is applicable not only for quantifying and then assessing the current working conditions, but also for predicting the potentially crack propagation against the future forecasted information. Compared with the established experimental records and numerical result, the accuracy, effectiveness, and computational efficiency of the proposed framework are fully verified.</description><subject>Crack propagation</subject><subject>Damage assessment</subject><subject>Diagnosis</subject><subject>Dirichlet problem</subject><subject>Engineering</subject><subject>Fracture mechanics</subject><subject>Fractures</subject><subject>Information update</subject><subject>Machine learning</subject><subject>Non-deterministic damage prediction</subject><subject>Phase field analysis</subject><subject>Prognosis</subject><subject>Support vector machines</subject><issn>0020-7225</issn><issn>1879-2197</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><recordid>eNqFkEtLAzEUhYMoWKt_QQZcT73J5DGzq4gvqLjRdcgkN50M7UxNpoL_3pTq2tWFwznncj5CriksKFB52y9Cj8M62bBgwGgWK1GrEzKjtWpKRht1SmYADErFmDgnFyn1ACCqppmR5auxXRiw2KCJQxjWhQkOXbHrTMLCB9y4YotTN7rCj7Hw0dhpHzFrtjNDsOmSnHmzSXj1e-fk4_Hh_f65XL09vdzfrUrLQU6lcN61FioqGs6qlley9RRrpYACVJZBWzvPkNfUcQueCy5qMCiVFEpyq6o5uTn27uL4ucc06X7cxyG_1EzmCgEiD58TeXTZOKYU0etdDFsTvzUFfaCle_1HSx9o6SOtHFweg5g3fAWMOjtwsOhCRDtpN4b_Kn4AvWZ0zA</recordid><startdate>20211201</startdate><enddate>20211201</enddate><creator>Feng, Yuan</creator><creator>Wang, Qihan</creator><creator>Wu, Di</creator><creator>Luo, Zhen</creator><creator>Chen, Xiaojun</creator><creator>Zhang, Tianyu</creator><creator>Gao, Wei</creator><general>Elsevier Ltd</general><general>Elsevier BV</general><scope>AAYXX</scope><scope>CITATION</scope><scope>7TB</scope><scope>8FD</scope><scope>FR3</scope><scope>KR7</scope></search><sort><creationdate>20211201</creationdate><title>Machine learning aided phase field method for fracture mechanics</title><author>Feng, Yuan ; Wang, Qihan ; Wu, Di ; Luo, Zhen ; Chen, Xiaojun ; Zhang, Tianyu ; Gao, Wei</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c406t-5dfdbc03159423b436bf1e87701003c20b8df2e481d4c0f454580ae6765764c73</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Crack propagation</topic><topic>Damage assessment</topic><topic>Diagnosis</topic><topic>Dirichlet problem</topic><topic>Engineering</topic><topic>Fracture mechanics</topic><topic>Fractures</topic><topic>Information update</topic><topic>Machine learning</topic><topic>Non-deterministic damage prediction</topic><topic>Phase field analysis</topic><topic>Prognosis</topic><topic>Support vector machines</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Feng, Yuan</creatorcontrib><creatorcontrib>Wang, Qihan</creatorcontrib><creatorcontrib>Wu, Di</creatorcontrib><creatorcontrib>Luo, Zhen</creatorcontrib><creatorcontrib>Chen, Xiaojun</creatorcontrib><creatorcontrib>Zhang, Tianyu</creatorcontrib><creatorcontrib>Gao, Wei</creatorcontrib><collection>CrossRef</collection><collection>Mechanical & Transportation Engineering Abstracts</collection><collection>Technology Research Database</collection><collection>Engineering Research Database</collection><collection>Civil Engineering Abstracts</collection><jtitle>International journal of engineering science</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Feng, Yuan</au><au>Wang, Qihan</au><au>Wu, Di</au><au>Luo, Zhen</au><au>Chen, Xiaojun</au><au>Zhang, Tianyu</au><au>Gao, Wei</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Machine learning aided phase field method for fracture mechanics</atitle><jtitle>International journal of engineering science</jtitle><date>2021-12-01</date><risdate>2021</risdate><volume>169</volume><spage>103587</spage><pages>103587-</pages><artnum>103587</artnum><issn>0020-7225</issn><eissn>1879-2197</eissn><abstract>A machine learning aided non-deterministic damage prediction framework against both 2D and 3D fracture problems is presented in this paper. By introducing a newly developed extended support vector regression (X-SVR) with generalized Dirichlet feature mapping into the phase field crack growth model, a damage assessment method that contains both crack diagnosis and prognosis is designed. Within the proposed analysis framework, the intricate fracture mechanism of practical engineering system can be learnt by the X-SVR model so a continuous damage diagnosis-prognosis loop can be established to assess the latest working condition of the structure. The proposed framework is applicable not only for quantifying and then assessing the current working conditions, but also for predicting the potentially crack propagation against the future forecasted information. Compared with the established experimental records and numerical result, the accuracy, effectiveness, and computational efficiency of the proposed framework are fully verified.</abstract><cop>Oxford</cop><pub>Elsevier Ltd</pub><doi>10.1016/j.ijengsci.2021.103587</doi></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 0020-7225 |
| ispartof | International journal of engineering science, 2021-12, Vol.169, p.103587, Article 103587 |
| issn | 0020-7225 1879-2197 |
| language | eng |
| recordid | cdi_proquest_journals_2600350510 |
| source | ScienceDirect Journals (5 years ago - present) |
| subjects | Crack propagation Damage assessment Diagnosis Dirichlet problem Engineering Fracture mechanics Fractures Information update Machine learning Non-deterministic damage prediction Phase field analysis Prognosis Support vector machines |
| title | Machine learning aided phase field method for fracture mechanics |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-12T01%3A21%3A22IST&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=Machine%20learning%20aided%20phase%20field%20method%20for%20fracture%20mechanics&rft.jtitle=International%20journal%20of%20engineering%20science&rft.au=Feng,%20Yuan&rft.date=2021-12-01&rft.volume=169&rft.spage=103587&rft.pages=103587-&rft.artnum=103587&rft.issn=0020-7225&rft.eissn=1879-2197&rft_id=info:doi/10.1016/j.ijengsci.2021.103587&rft_dat=%3Cproquest_cross%3E2600350510%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=2600350510&rft_id=info:pmid/&rft_els_id=S0020722521001294&rfr_iscdi=true |