Inverse analysis of friction coefficient in discrete element method using powder properties by support vector regression
This study demonstrates the inverse prediction of the discrete-element method (DEM) input friction coefficient from the DEM output powder properties such as the outflow rate, aerated bulk density, and repose angle. Support vector (SV) regression can reasonably reproduce the friction coefficient from...
Gespeichert in:
| Veröffentlicht in: | Journal of the Ceramic Society of Japan 2024/04/01, Vol.132(4), pp.189-192 |
|---|---|
| Hauptverfasser: | , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 192 |
|---|---|
| container_issue | 4 |
| container_start_page | 189 |
| container_title | Journal of the Ceramic Society of Japan |
| container_volume | 132 |
| creator | Murata, Hidenobu Yamanoi, Mikio Suzuki, Yoshihiro |
| description | This study demonstrates the inverse prediction of the discrete-element method (DEM) input friction coefficient from the DEM output powder properties such as the outflow rate, aerated bulk density, and repose angle. Support vector (SV) regression can reasonably reproduce the friction coefficient from the DEM output powder properties. Among the powder properties considered in this study, the outflow rate is found to be the most effective for predicting the friction coefficient. Other powder properties also contribute to improving the prediction accuracy. The accuracy of the SV model depends on the number of cases used for the inverse regression of the friction coefficient, and models with practical accuracy can be obtained for 100–200 cases. These results will lead to further use of machine learning in DEM simulations. |
| doi_str_mv | 10.2109/jcersj2.23135 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_3054726284</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>3054726284</sourcerecordid><originalsourceid>FETCH-LOGICAL-c489t-67be0b5019c7281c95608e38e737e4fef9ad7f618db3124d2e98b9ab9b0fd7893</originalsourceid><addsrcrecordid>eNo9kE1PwzAMhisEEp9H7pE4F_LVNjkiNGDSJC5wjtLUGam2psTZYP-esqFdbMt-_Mp-i-KW0XvOqH7oHSTs-T0XTFQnxQUTUpV1JarTqVaKl7SR4ry4ROwprbkU6qL4mQ_baQuIHexqhwFJ9MSn4HKIA3ERvA8uwJBJGEgX0CXIQGAF67_eGvJn7MgGw7AkY_zuIJExxRFSDoCk3RHcjGNMmWzB5ZhIgmUCxEn7ujjzdoVw85-vio_n2fvTa7l4e5k_PS5KJ5XOZd20QNuKMu0arpjTVU0VCAWNaEB68Np2ja-Z6lrBuOw4aNVq2-qW-q5RWlwVdwfd6a6vDWA2fdyk6Vk0glay4TVXcqLKA-VSREzgzZjC2qadYdT8mWv-zTV7cyd-duB7zHYJR9pOj7sVHGkmuJH7uN87zt2nTQYG8QutD4oG</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3054726284</pqid></control><display><type>article</type><title>Inverse analysis of friction coefficient in discrete element method using powder properties by support vector regression</title><source>J-STAGE Free</source><creator>Murata, Hidenobu ; Yamanoi, Mikio ; Suzuki, Yoshihiro</creator><creatorcontrib>Murata, Hidenobu ; Yamanoi, Mikio ; Suzuki, Yoshihiro</creatorcontrib><description>This study demonstrates the inverse prediction of the discrete-element method (DEM) input friction coefficient from the DEM output powder properties such as the outflow rate, aerated bulk density, and repose angle. Support vector (SV) regression can reasonably reproduce the friction coefficient from the DEM output powder properties. Among the powder properties considered in this study, the outflow rate is found to be the most effective for predicting the friction coefficient. Other powder properties also contribute to improving the prediction accuracy. The accuracy of the SV model depends on the number of cases used for the inverse regression of the friction coefficient, and models with practical accuracy can be obtained for 100–200 cases. These results will lead to further use of machine learning in DEM simulations.</description><identifier>ISSN: 1882-0743</identifier><identifier>EISSN: 1348-6535</identifier><identifier>DOI: 10.2109/jcersj2.23135</identifier><language>eng</language><publisher>Tokyo: The Ceramic Society of Japan</publisher><subject>Accuracy ; Aerated bulk density ; Aeration ; Angle of repose ; Bulk density ; Coefficient of friction ; Discrete element method ; Friction coefficient ; Machine learning ; Outflow ; Outflow rate ; Regression ; Repose angle ; Support vector machines</subject><ispartof>Journal of the Ceramic Society of Japan, 2024/04/01, Vol.132(4), pp.189-192</ispartof><rights>2024 The Ceramic Society of Japan</rights><rights>2024. This work is published under https://creativecommons.org/licenses/by/4.0/deed.ja (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-c489t-67be0b5019c7281c95608e38e737e4fef9ad7f618db3124d2e98b9ab9b0fd7893</citedby><cites>FETCH-LOGICAL-c489t-67be0b5019c7281c95608e38e737e4fef9ad7f618db3124d2e98b9ab9b0fd7893</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,1883,27924,27925</link.rule.ids></links><search><creatorcontrib>Murata, Hidenobu</creatorcontrib><creatorcontrib>Yamanoi, Mikio</creatorcontrib><creatorcontrib>Suzuki, Yoshihiro</creatorcontrib><title>Inverse analysis of friction coefficient in discrete element method using powder properties by support vector regression</title><title>Journal of the Ceramic Society of Japan</title><addtitle>J. Ceram. Soc. Japan</addtitle><description>This study demonstrates the inverse prediction of the discrete-element method (DEM) input friction coefficient from the DEM output powder properties such as the outflow rate, aerated bulk density, and repose angle. Support vector (SV) regression can reasonably reproduce the friction coefficient from the DEM output powder properties. Among the powder properties considered in this study, the outflow rate is found to be the most effective for predicting the friction coefficient. Other powder properties also contribute to improving the prediction accuracy. The accuracy of the SV model depends on the number of cases used for the inverse regression of the friction coefficient, and models with practical accuracy can be obtained for 100–200 cases. These results will lead to further use of machine learning in DEM simulations.</description><subject>Accuracy</subject><subject>Aerated bulk density</subject><subject>Aeration</subject><subject>Angle of repose</subject><subject>Bulk density</subject><subject>Coefficient of friction</subject><subject>Discrete element method</subject><subject>Friction coefficient</subject><subject>Machine learning</subject><subject>Outflow</subject><subject>Outflow rate</subject><subject>Regression</subject><subject>Repose angle</subject><subject>Support vector machines</subject><issn>1882-0743</issn><issn>1348-6535</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><recordid>eNo9kE1PwzAMhisEEp9H7pE4F_LVNjkiNGDSJC5wjtLUGam2psTZYP-esqFdbMt-_Mp-i-KW0XvOqH7oHSTs-T0XTFQnxQUTUpV1JarTqVaKl7SR4ry4ROwprbkU6qL4mQ_baQuIHexqhwFJ9MSn4HKIA3ERvA8uwJBJGEgX0CXIQGAF67_eGvJn7MgGw7AkY_zuIJExxRFSDoCk3RHcjGNMmWzB5ZhIgmUCxEn7ujjzdoVw85-vio_n2fvTa7l4e5k_PS5KJ5XOZd20QNuKMu0arpjTVU0VCAWNaEB68Np2ja-Z6lrBuOw4aNVq2-qW-q5RWlwVdwfd6a6vDWA2fdyk6Vk0glay4TVXcqLKA-VSREzgzZjC2qadYdT8mWv-zTV7cyd-duB7zHYJR9pOj7sVHGkmuJH7uN87zt2nTQYG8QutD4oG</recordid><startdate>20240401</startdate><enddate>20240401</enddate><creator>Murata, Hidenobu</creator><creator>Yamanoi, Mikio</creator><creator>Suzuki, Yoshihiro</creator><general>The Ceramic Society of Japan</general><general>Japan Science and Technology Agency</general><scope>AAYXX</scope><scope>CITATION</scope><scope>7QQ</scope><scope>7SR</scope><scope>8FD</scope><scope>JG9</scope></search><sort><creationdate>20240401</creationdate><title>Inverse analysis of friction coefficient in discrete element method using powder properties by support vector regression</title><author>Murata, Hidenobu ; Yamanoi, Mikio ; Suzuki, Yoshihiro</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c489t-67be0b5019c7281c95608e38e737e4fef9ad7f618db3124d2e98b9ab9b0fd7893</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Accuracy</topic><topic>Aerated bulk density</topic><topic>Aeration</topic><topic>Angle of repose</topic><topic>Bulk density</topic><topic>Coefficient of friction</topic><topic>Discrete element method</topic><topic>Friction coefficient</topic><topic>Machine learning</topic><topic>Outflow</topic><topic>Outflow rate</topic><topic>Regression</topic><topic>Repose angle</topic><topic>Support vector machines</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Murata, Hidenobu</creatorcontrib><creatorcontrib>Yamanoi, Mikio</creatorcontrib><creatorcontrib>Suzuki, Yoshihiro</creatorcontrib><collection>CrossRef</collection><collection>Ceramic Abstracts</collection><collection>Engineered Materials Abstracts</collection><collection>Technology Research Database</collection><collection>Materials Research Database</collection><jtitle>Journal of the Ceramic Society of Japan</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Murata, Hidenobu</au><au>Yamanoi, Mikio</au><au>Suzuki, Yoshihiro</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Inverse analysis of friction coefficient in discrete element method using powder properties by support vector regression</atitle><jtitle>Journal of the Ceramic Society of Japan</jtitle><addtitle>J. Ceram. Soc. Japan</addtitle><date>2024-04-01</date><risdate>2024</risdate><volume>132</volume><issue>4</issue><spage>189</spage><epage>192</epage><pages>189-192</pages><artnum>23135</artnum><issn>1882-0743</issn><eissn>1348-6535</eissn><abstract>This study demonstrates the inverse prediction of the discrete-element method (DEM) input friction coefficient from the DEM output powder properties such as the outflow rate, aerated bulk density, and repose angle. Support vector (SV) regression can reasonably reproduce the friction coefficient from the DEM output powder properties. Among the powder properties considered in this study, the outflow rate is found to be the most effective for predicting the friction coefficient. Other powder properties also contribute to improving the prediction accuracy. The accuracy of the SV model depends on the number of cases used for the inverse regression of the friction coefficient, and models with practical accuracy can be obtained for 100–200 cases. These results will lead to further use of machine learning in DEM simulations.</abstract><cop>Tokyo</cop><pub>The Ceramic Society of Japan</pub><doi>10.2109/jcersj2.23135</doi><tpages>4</tpages><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 1882-0743 |
| ispartof | Journal of the Ceramic Society of Japan, 2024/04/01, Vol.132(4), pp.189-192 |
| issn | 1882-0743 1348-6535 |
| language | eng |
| recordid | cdi_proquest_journals_3054726284 |
| source | J-STAGE Free |
| subjects | Accuracy Aerated bulk density Aeration Angle of repose Bulk density Coefficient of friction Discrete element method Friction coefficient Machine learning Outflow Outflow rate Regression Repose angle Support vector machines |
| title | Inverse analysis of friction coefficient in discrete element method using powder properties by support vector regression |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-28T04%3A27%3A11IST&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=Inverse%20analysis%20of%20friction%20coefficient%20in%20discrete%20element%20method%20using%20powder%20properties%20by%20support%20vector%20regression&rft.jtitle=Journal%20of%20the%20Ceramic%20Society%20of%20Japan&rft.au=Murata,%20Hidenobu&rft.date=2024-04-01&rft.volume=132&rft.issue=4&rft.spage=189&rft.epage=192&rft.pages=189-192&rft.artnum=23135&rft.issn=1882-0743&rft.eissn=1348-6535&rft_id=info:doi/10.2109/jcersj2.23135&rft_dat=%3Cproquest_cross%3E3054726284%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=3054726284&rft_id=info:pmid/&rfr_iscdi=true |