DC Field | Value | Language |
---|---|---|
dc.contributor.author | Yu, Yonggyun | ko |
dc.contributor.author | Hur, Taeil | ko |
dc.contributor.author | Jung, Jaeho | ko |
dc.contributor.author | Jang, In Gwun | ko |
dc.date.accessioned | 2019-04-15T14:31:30Z | - |
dc.date.available | 2019-04-15T14:31:30Z | - |
dc.date.created | 2018-09-19 | - |
dc.date.issued | 2019-03 | - |
dc.identifier.citation | STRUCTURAL AND MULTIDISCIPLINARY OPTIMIZATION, v.59, no.3, pp.787 - 799 | - |
dc.identifier.issn | 1615-147X | - |
dc.identifier.uri | http://hdl.handle.net/10203/254134 | - |
dc.description.abstract | In this study, we propose a novel deep learning-based method to predict an optimized structure for a given boundary condition and optimization setting without using any iterative scheme. For this purpose, first, using open-source topology optimization code, datasets of the optimized structures paired with the corresponding information on boundary conditions and optimization settings are generated at low (32 x 32) and high (128 x 128) resolutions. To construct the artificial neural network for the proposed method, a convolutional neural network (CNN)-based encoder and decoder network is trained using the training dataset generated at low resolution. Then, as a two-stage refinement, the conditional generative adversarial network (cGAN) is trained with the optimized structures paired at both low and high resolutions and is connected to the trained CNN-based encoder and decoder network. The performance evaluation results of the integrated network demonstrate that the proposed method can determine a near-optimal structure in terms of pixel values and compliance with negligible computational time. | - |
dc.language | English | - |
dc.publisher | SPRINGER | - |
dc.title | Deep learning for determining a near-optimal topological design without any iteration | - |
dc.type | Article | - |
dc.identifier.wosid | 000461581600007 | - |
dc.identifier.scopusid | 2-s2.0-85055943134 | - |
dc.type.rims | ART | - |
dc.citation.volume | 59 | - |
dc.citation.issue | 3 | - |
dc.citation.beginningpage | 787 | - |
dc.citation.endingpage | 799 | - |
dc.citation.publicationname | STRUCTURAL AND MULTIDISCIPLINARY OPTIMIZATION | - |
dc.identifier.doi | 10.1007/s00158-018-2101-5 | - |
dc.contributor.localauthor | Jang, In Gwun | - |
dc.contributor.nonIdAuthor | Yu, Yonggyun | - |
dc.contributor.nonIdAuthor | Hur, Taeil | - |
dc.contributor.nonIdAuthor | Jung, Jaeho | - |
dc.description.isOpenAccess | N | - |
dc.type.journalArticle | Article | - |
dc.subject.keywordAuthor | Deep learning | - |
dc.subject.keywordAuthor | Machine learning | - |
dc.subject.keywordAuthor | Topology optimization | - |
dc.subject.keywordAuthor | Generative model | - |
dc.subject.keywordAuthor | Generative adversarial network | - |
dc.subject.keywordAuthor | Convolutional neural network | - |
dc.subject.keywordPlus | SPACE ADJUSTMENT | - |
dc.subject.keywordPlus | OPTIMIZATION | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.