DC Field | Value | Language |
---|---|---|
dc.contributor.author | Kim, Taewan | ko |
dc.contributor.author | Lee, Seungchul | ko |
dc.date.accessioned | 2023-09-13T09:00:08Z | - |
dc.date.available | 2023-09-13T09:00:08Z | - |
dc.date.created | 2023-09-13 | - |
dc.date.created | 2023-09-13 | - |
dc.date.issued | 2023-09 | - |
dc.identifier.citation | IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, v.19, no.9, pp.9404 - 9412 | - |
dc.identifier.issn | 1551-3203 | - |
dc.identifier.uri | http://hdl.handle.net/10203/312601 | - |
dc.description.abstract | Deep-learning-based fault diagnosis methods require a large number of labeled datasets. However, considering the changing operating conditions, it is impractical to obtain labeled datasets for all cases. Therefore, this article proposes a new unsupervised clustering and domain adaptation framework to circumvent data deficiency and domain issues. The proposed framework comprises two steps: unsupervised clustering and domain adaptation. In the unsupervised clustering, an expectation-maximization adversarial autoencoder, which combines an expectation-maximization algorithm with an adversarial autoencoder, is used for feature extraction and subspace mapping. Subsequently, the mapped features are clustered using a Gaussian mixture model. In the domain adaptation, a domain synchronization that is based on the symmetric Kullback-Leibler divergence metric is used to infer the relationship between the source and target domain clusters. The experiments on two rolling-element-bearing datasets validate the effectiveness of our method. Specifically, our method performs domain adaptation without retraining, which is promising for real industrial applications. | - |
dc.language | English | - |
dc.publisher | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC | - |
dc.title | A Novel Unsupervised Clustering and Domain Adaptation Framework for Rotating Machinery Fault Diagnosis | - |
dc.type | Article | - |
dc.identifier.wosid | 001037910900014 | - |
dc.identifier.scopusid | 2-s2.0-85144754238 | - |
dc.type.rims | ART | - |
dc.citation.volume | 19 | - |
dc.citation.issue | 9 | - |
dc.citation.beginningpage | 9404 | - |
dc.citation.endingpage | 9412 | - |
dc.citation.publicationname | IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS | - |
dc.identifier.doi | 10.1109/TII.2022.3228395 | - |
dc.contributor.localauthor | Lee, Seungchul | - |
dc.contributor.nonIdAuthor | Kim, Taewan | - |
dc.description.isOpenAccess | N | - |
dc.type.journalArticle | Article | - |
dc.subject.keywordAuthor | Domain adaptation | - |
dc.subject.keywordAuthor | domain synchronization | - |
dc.subject.keywordAuthor | expectation-maximization adversarial autoencoder (EM-AAE) | - |
dc.subject.keywordAuthor | unsupervised fault clustering | - |
dc.subject.keywordAuthor | unsupervised | - |
dc.subject.keywordPlus | CLASSIFICATION | - |
dc.subject.keywordPlus | MODEL | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.