Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | 이승환 | - |
dc.date.accessioned | 2020-11-11T02:04:51Z | - |
dc.date.available | 2020-11-11T02:04:51Z | - |
dc.date.issued | 2019-11 | - |
dc.identifier.citation | SCIENCE AND TECHNOLOGY OF WELDING AND JOINING, v. 25, no. 4, Page. 282-289 | en_US |
dc.identifier.issn | 1362-1718 | - |
dc.identifier.issn | 1743-2936 | - |
dc.identifier.uri | https://www.tandfonline.com/doi/full/10.1080/13621718.2019.1687635 | - |
dc.identifier.uri | https://repository.hanyang.ac.kr/handle/20.500.11754/155363 | - |
dc.description.abstract | In this study, microstructures of weldment produced using carbon steel A516 grade 60 were analysed via a deep learning approach to measure the fraction of acicular ferrite which considerably influences on mechanical properties of carbon steel. The fully convolutional network was used to conduct the image segmentation. Submerged arc welding was used for welding, and the dataset was constructed using optical microscope. The model was compiled with ResNet, which is the state-of-the-art classifier used as an encoder. The model is trained to distinguish acicular ferrite from microstructures of dataset images and then estimate its accuracy. As a result, the mean intersection over union, which is a metric commonly used to evaluate image segmentation, was shown to be higher than 85%. | en_US |
dc.description.sponsorship | This work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) [No. 2017R1C1B5018334] and by Korea Institute of Energy Technology Evaluation and Planning (KETEP) and the Ministry of Trade, Industry & Energy (MOTIE) of the Republic of Korea [No. 201810102360] and Korea Aerospace University, [No. 2019-01-006]. | en_US |
dc.language.iso | en | en_US |
dc.publisher | TAYLOR & FRANCIS LTD | en_US |
dc.subject | Submerged arc welding | en_US |
dc.subject | carbon steel | en_US |
dc.subject | acicular ferrite | en_US |
dc.subject | fraction | en_US |
dc.subject | segmentation | en_US |
dc.subject | deep learning | en_US |
dc.subject | fully convolutional network | en_US |
dc.subject | ResNet | en_US |
dc.title | Residual neural network-based fully convolutional network for microstructure segmentation | en_US |
dc.type | Article | en_US |
dc.identifier.doi | 10.1080/13621718.2019.1687635 | - |
dc.relation.journal | SCIENCE AND TECHNOLOGY OF WELDING AND JOINING | - |
dc.contributor.googleauthor | Jang, Junmyoung | - |
dc.contributor.googleauthor | Van, Donghyun | - |
dc.contributor.googleauthor | Jang, Hyojin | - |
dc.contributor.googleauthor | Baik, Dae Hyun | - |
dc.contributor.googleauthor | Yoo, Sang Duk | - |
dc.contributor.googleauthor | Park, Jaewoong | - |
dc.contributor.googleauthor | Mhin, Sungwook | - |
dc.contributor.googleauthor | Mazumder, Jyoti | - |
dc.contributor.googleauthor | Lee, Seung Hwan | - |
dc.relation.code | 2019036767 | - |
dc.sector.campus | S | - |
dc.sector.daehak | COLLEGE OF ENGINEERING[S] | - |
dc.sector.department | DIVISION OF MECHANICAL ENGINEERING | - |
dc.identifier.pid | seunghlee | - |
dc.identifier.orcid | https://orcid.org/0000-0002-1509-3348 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.