ETRI-Knowledge Sharing Plaform

ENGLISH

성과물

논문 검색
구분 SCI
연도 ~ 키워드

상세정보

학술대회 Health Management Technology for Estimating the Remaining Useful Life of Household Appliances
Cited 2 time in scopus Download 0 time Share share facebook twitter linkedin kakaostory
저자
김낙우, 이현용, 이준기, 이병탁
발행일
202111
출처
International Conference on Consumer Electronics (ICCE) 2021 : Asia, pp.1-3
DOI
https://dx.doi.org/10.1109/ICCE-Asia53811.2021.9642012
초록
In this paper, we propose a new time series-based domain adaptation technique for health management in home devices. Because it is based on domain adversarial neural network technology, it can learn labeled domain data and utilize it in unlabeled domains. In addition, by modifying the domain adaptation network to process time series data, it supports prediction of remaining useful life of time series data for home devices. We confirmed that the proposed method shows much better prediction performance compared to other network models.
KSP 제안 키워드
Home Devices, Household appliances, Network model, Network technology, Time series data, domain adaptation, health management, neural network, prediction performance, process time, remaining useful life