There are no files associated with this item.
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.citation.endPage | 2362 | - |
dc.citation.number | 5 | - |
dc.citation.startPage | 2353 | - |
dc.citation.title | JOURNAL OF MECHANICAL SCIENCE AND TECHNOLOGY | - |
dc.citation.volume | 37 | - |
dc.contributor.author | Park, Jae Phil | - |
dc.contributor.author | Ham, Junhyuk | - |
dc.contributor.author | Kim, Ji Hyun | - |
dc.contributor.author | Oh, Young-Jin | - |
dc.contributor.author | Bahn, Chi Bum | - |
dc.date.accessioned | 2023-12-21T12:39:09Z | - |
dc.date.available | 2023-12-21T12:39:09Z | - |
dc.date.created | 2023-06-13 | - |
dc.date.issued | 2023-05 | - |
dc.description.abstract | We developed a fatigue residual useful life (RUL) prediction model using the available time-series fatigue data of Ni-base alloy welds via a long short-term memory (LSTM) network. The effects of some LSTM network hyperparameters on model performance were investigated through sensitivity studies. The LSTM network model outperformed multiple regression models when the LSTM model hyperparameters were appropriately tuned. However, the additional gain was insignificant, considering that the LSTM network was much more complex than multiple regression models. The best performance of the LSTM network model was achieved when the number of hidden units, input window size, and batch size were small and the number of LSTM layers was large. | - |
dc.identifier.bibliographicCitation | JOURNAL OF MECHANICAL SCIENCE AND TECHNOLOGY, v.37, no.5, pp.2353 - 2362 | - |
dc.identifier.doi | 10.1007/s12206-023-0412-y | - |
dc.identifier.issn | 1738-494X | - |
dc.identifier.scopusid | 2-s2.0-85156264051 | - |
dc.identifier.uri | https://scholarworks.unist.ac.kr/handle/201301/64492 | - |
dc.identifier.wosid | 000980381600002 | - |
dc.language | 영어 | - |
dc.publisher | KOREAN SOC MECHANICAL ENGINEERS | - |
dc.title | Fatigue residual useful life estimation of Ni-base alloy weld with time-series data | - |
dc.type | Article | - |
dc.description.isOpenAccess | FALSE | - |
dc.relation.journalWebOfScienceCategory | Engineering, Mechanical | - |
dc.relation.journalResearchArea | Engineering | - |
dc.type.docType | Article; Early Access | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.description.journalRegisteredClass | kci | - |
dc.subject.keywordAuthor | Fatigue | - |
dc.subject.keywordAuthor | Long short-term memory network | - |
dc.subject.keywordAuthor | Multiple regression | - |
dc.subject.keywordAuthor | Ni-base alloy weld | - |
dc.subject.keywordAuthor | Residual useful life | - |
dc.subject.keywordAuthor | Time-series data | - |
dc.subject.keywordPlus | NEURAL-NETWORKS | - |
dc.subject.keywordPlus | LSTM | - |
dc.subject.keywordPlus | PREDICTION | - |
Items in Repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Tel : 052-217-1404 / Email : scholarworks@unist.ac.kr
Copyright (c) 2023 by UNIST LIBRARY. All rights reserved.
ScholarWorks@UNIST was established as an OAK Project for the National Library of Korea.