DC Field | Value | Language |
---|---|---|
dc.contributor.author | Park, Donggeun | ko |
dc.contributor.author | Jung, Jiyoung | ko |
dc.contributor.author | Ryu, Seunghwa | ko |
dc.date.accessioned | 2023-06-27T02:00:13Z | - |
dc.date.available | 2023-06-27T02:00:13Z | - |
dc.date.created | 2023-06-26 | - |
dc.date.issued | 2023-09 | - |
dc.identifier.citation | COMPOSITE STRUCTURES, v.319 | - |
dc.identifier.issn | 0263-8223 | - |
dc.identifier.uri | http://hdl.handle.net/10203/310043 | - |
dc.description.abstract | Deep learning's fast and accurate inference between material configurations and properties has been used to design digital composites with superior mechanical properties. However, initial training sets cannot explore a vast design space with astronomical numbers of possible combinations, and most DL methods cannot guarantee predictive power in unobserved domains that may contain optimal configurations. Active learning-based gradual DNN model update schemes were implemented, but this increased computational costs. We propose a single-shot training pipeline to predict stress/strain distribution and stiffness over configuration space far from the initial training set. Predicting a composite's load response requires predicting its stress/strain field. Two autoencoders and a cGAN predict high-resolution stress/strain fields from grid-averaged local fields inferred from binary digital composite configurations. Our pipeline accurately predicts the high-resolution stress/strain field distri-bution in the unseen volume fraction (VF) domain or for composites with configurations very different from the initial training set. The framework can predict high-resolution fields in many physical phenomena and design composite materials for engineering applications. | - |
dc.language | English | - |
dc.publisher | ELSEVIER SCI LTD | - |
dc.title | Double generative network (DGNet) pipeline for structure-property relation of digital composites | - |
dc.type | Article | - |
dc.identifier.wosid | 001007451700001 | - |
dc.identifier.scopusid | 2-s2.0-85160010824 | - |
dc.type.rims | ART | - |
dc.citation.volume | 319 | - |
dc.citation.publicationname | COMPOSITE STRUCTURES | - |
dc.identifier.doi | 10.1016/j.compstruct.2023.117131 | - |
dc.contributor.localauthor | Ryu, Seunghwa | - |
dc.description.isOpenAccess | N | - |
dc.type.journalArticle | Article | - |
dc.subject.keywordAuthor | Deep learning | - |
dc.subject.keywordAuthor | Composite design | - |
dc.subject.keywordAuthor | Design space | - |
dc.subject.keywordAuthor | Stress field | - |
dc.subject.keywordAuthor | Super-resolution | - |
dc.subject.keywordAuthor | U-Net | - |
dc.subject.keywordPlus | DEEP | - |
dc.subject.keywordPlus | MICROSCOPY | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.