Show simple item record

dc.contributor.authorHu, Chao
dc.contributor.authorYoun, Byeng D.
dc.contributor.authorKim, Taejin
dc.contributor.authorWang, Pingfeng
dc.date.accessioned2015-06-25T18:06:43Z
dc.date.available2015-06-25T18:06:43Z
dc.date.issued2015-10
dc.identifier.citationHu, Chao; Youn, Byeng D.; Kim, Taejin; Wang, Pingfeng. 2015. A co-training-based approach for prediction of remaining useful life utilizing both failure and suspension data. Mechanical Systems and Signal Processing, vol. 62–63, October 2015:pp 75–90en_US
dc.identifier.issn0888-3270
dc.identifier.otherWOS:000355354300005
dc.identifier.urihttp://dx.doi.org/10.1016/j.ymssp.2015.03.004
dc.identifier.urihttp://hdl.handle.net/10057/11299
dc.descriptionClick on the DOI link to access the article (may not be free).en_US
dc.description.abstractTraditional data-driven prognostics often requires some amount of failure data for the offline training in order to achieve good accuracy for the online prediction. Failure data refer to condition monitoring data collected from the very beginning of an engineered system's lifetime till the occurrence of its failure. However, in many engineered systems, failure data are fairly expensive and time-consuming to obtain while suspension data are readily available. Suspension data refer to condition monitoring data acquired from the very beginning of an engineered system's lifetime till planned inspection or maintenance when the system is taken out of service. In such cases, it becomes essentially critical to utilize suspension data which may carry rich information regarding the degradation trend and help achieve more accurate remaining useful life (RUL) prediction. To this end, this paper proposes a co-training-based data-driven prognostic approach, denoted by COPROG, which uses two data-driven algorithms with each predicting RULs of suspension units for the other. After a suspension unit is chosen and its RUL is predicted by an individual algorithm, it becomes a virtual failure unit that is added to the training data set of the other individual algorithm. Results obtained from two case studies suggest that COPROG gives more accurate RUL prediction, as compared to any individual algorithm with no use of suspension data, and that COPROG can effectively exploit suspension data to improve the prognostic accuracy.en_US
dc.description.sponsorshipMid-Career Researcher Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Science, ICT and Future Planning (2013R1A2A2A01068627), and the Technology Innovation Program (10050980, System Reliability Improvement and Validation for New Growth Power Industry Equipment) funded by the Ministry of Trade, Industry & Energy (MI, Korea).en_US
dc.language.isoen_USen_US
dc.publisherElsevier B.V.en_US
dc.relation.ispartofseriesMechanical Systems and Signal Processing;v.62-63
dc.subjectCo-trainingen_US
dc.subjectSemi-supervised learningen_US
dc.subjectSuspension dataen_US
dc.subjectData-driven prognosticsen_US
dc.subjectRUL predictionen_US
dc.titleA co-training-based approach for prediction of remaining useful life utilizing both failure and suspension dataen_US
dc.typeArticleen_US
dc.rights.holder(C) 2015 Elsevier Ltd. All rights reserved.


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record