DC Field | Value | Language |
---|---|---|
dc.contributor.author | Jung, Jaimyun | - |
dc.contributor.author | Yoon, Jae Ik | - |
dc.contributor.author | Park, Hyung Keun | - |
dc.contributor.author | Kim, Jin You | - |
dc.contributor.author | Kim, Hyoung Seop | - |
dc.date.accessioned | 2019-04-07T15:03:08Z | - |
dc.date.available | 2019-04-07T15:03:08Z | - |
dc.date.created | 2018-12-04 | - |
dc.date.issued | 2019-01 | - |
dc.identifier.issn | 0927-0256 | - |
dc.identifier.uri | https://oasis.postech.ac.kr/handle/2014.oak/95334 | - |
dc.description.abstract | Full-field simulations with synthetic microstructure offer unique opportunities in predicting and understanding the linkage between microstructural variables and properties of a material prior to or in conjunction with experimental efforts. Nevertheless, the computational cost restrains the application of full-field simulations in optimizing materials microstructures or in establishing comprehensive structure-property linkages. To address this issue, we propose the use of machine learning technique, namely Gaussian process regression, with a small number of full-field simulation results to construct structure-property linkages that are accurate over a wide range of microstructures. Furthermore, we demonstrate that with the implementation of expected improvement algorithm, microstructures that exhibit most desirable properties can be identified using even smaller number of full-field simulations. | - |
dc.language | English | - |
dc.publisher | ELSEVIER SCIENCE BV | - |
dc.relation.isPartOf | COMPUTATIONAL MATERIALS SCIENCE | - |
dc.title | An efficient machine learning approach to establish structure-property linkages | - |
dc.type | Article | - |
dc.identifier.doi | 10.1016/j.commatsci.2018.09.034 | - |
dc.type.rims | ART | - |
dc.identifier.bibliographicCitation | COMPUTATIONAL MATERIALS SCIENCE, v.156, pp.17 - 25 | - |
dc.identifier.wosid | 000449375500003 | - |
dc.citation.endPage | 25 | - |
dc.citation.startPage | 17 | - |
dc.citation.title | COMPUTATIONAL MATERIALS SCIENCE | - |
dc.citation.volume | 156 | - |
dc.contributor.affiliatedAuthor | Kim, Hyoung Seop | - |
dc.identifier.scopusid | 2-s2.0-85053511571 | - |
dc.description.journalClass | 1 | - |
dc.description.journalClass | 1 | - |
dc.description.isOpenAccess | N | - |
dc.type.docType | Article | - |
dc.subject.keywordPlus | FEATURE-SELECTION METHODS | - |
dc.subject.keywordPlus | CRYSTAL PLASTICITY | - |
dc.subject.keywordPlus | 2-POINT STATISTICS | - |
dc.subject.keywordPlus | OPTIMIZATION | - |
dc.subject.keywordPlus | MICROSTRUCTURES | - |
dc.subject.keywordPlus | DEFORMATION | - |
dc.subject.keywordPlus | COMPOSITES | - |
dc.subject.keywordPlus | MODELS | - |
dc.subject.keywordPlus | CLASSIFICATION | - |
dc.subject.keywordPlus | SIMULATIONS | - |
dc.subject.keywordAuthor | Microstructure | - |
dc.subject.keywordAuthor | Machine learning | - |
dc.subject.keywordAuthor | Gaussian process regression | - |
dc.subject.keywordAuthor | Optimization | - |
dc.relation.journalWebOfScienceCategory | Materials Science, Multidisciplinary | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.relation.journalResearchArea | Materials Science | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.
library@postech.ac.kr Tel: 054-279-2548
Copyrights © by 2017 Pohang University of Science ad Technology All right reserved.