Detailed Information

Cited 0 time in webofscience Cited 0 time in scopus
Metadata Downloads

Hierarchical Deep Neural Network for Fire Detection in Wind Turbine Nacelles

Full metadata record
DC Field Value Language
dc.contributor.authorDo, Eun Chan-
dc.contributor.authorPark, Su Hyun-
dc.contributor.authorOh, Ki-Yong-
dc.date.accessioned2024-11-28T08:36:11Z-
dc.date.available2024-11-28T08:36:11Z-
dc.date.issued2024-08-
dc.identifier.issn1225-7842-
dc.identifier.issn2287-402X-
dc.identifier.urihttps://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/195377-
dc.description.abstractAs global demand for renewable energy continues to rise, the number of installed wind turbines is rapidly increasing, leading to a higher incidence of fire accidents in wind turbines. However, conventional fire-detection methods, such as smoke and flame detectors, suffer from low detection accuracy and long response times. To address these limitations, several fire detection methods based on artificial intelligence have been proposed. However, these approaches often rely on object-detection neural networks, that result in high false-alarm rates for pseudo-fire images. In this study, a hierarchical deep neural network for fire-condition monitoring is proposed, which reduces the false alarm rate and accurately identifies the locations of smoke and fire. The proposed neural network initially employs a fire-classification neural network to classify situations into three categories: fire, smoke or normal. By analyzing the overall image information, false alarms are effectively reduced. Based on the classification results, an object-detection neural network specializing in smoke and fire detection is then activated to identify their locations. The inferred information on fire locations can be utilized to operate autonomous targeted fire-suppression systems. Fire image sets are constructed to train and validate the proposed neural network. The performance of the proposed neural network is verified by comparing its classification accuracy, object-detection accuracy, and false-alarm rates with those of other neural networks. The proposed approach can be applicable to the nacelles of wind turbines and also various industrial environments requiring condition monitoring.-
dc.description.abstract최근 풍력 터빈의 설치가 증가하여 화재 사고 또한 빈번해지면서, 기존 자동화재탐지 설비의 낮은감지 정확도와 긴 감지 시간이 문제가 되고 있다. 이를 해결하기 위해 다양한 인공지능 기반 화재 감지 기법이 제안되었으나, 여전히 비화재보가 높다는 한계가 존재한다. 본 연구에서는 이러한 문제 해결을 위한 계층적 화재 감지 심층 신경망을 제안한다. 제안 심층 신경망은 먼저 분류 심층 신경망을 통해 오경보율을 효과적으로 낮추고, 추론 결과에 따라 연기 및 화재 위치 추론에 특화된 객체 탐지 심층 신경망을 작동하여 화원의 정확한 위치를 탐지한다. 이러한 화원 위치 추론 결과를 바탕으로 자율형 조준 소화 시스템에 적용할 수 있다. 제안 심층 신경망의 학습 및 검증을 위해 화재 이미지 세트를 구축하였으며 여타 다른 심층 신경망과 분류 정확도, 객체 탐지 정확도, 오경보율을 비교하여 검증하였다. 향후 나셀 뿐만 아니라 상태 감시가 필요한 다양한 산업 환경에도 확장 적용이 가능할 것으로 사료된다.-
dc.format.extent10-
dc.language한국어-
dc.language.isoKOR-
dc.publisher한국비파괴검사학회-
dc.titleHierarchical Deep Neural Network for Fire Detection in Wind Turbine Nacelles-
dc.title.alternative풍력 터빈 나셀의 화재 감지를 위한 계층적 심층 신경망-
dc.typeArticle-
dc.publisher.location대한민국-
dc.identifier.doi10.7779/JKSNT.2024.44.4.268-
dc.identifier.wosid001314563200005-
dc.identifier.bibliographicCitation비파괴검사학회지, v.44, no.4, pp 268 - 277-
dc.citation.title비파괴검사학회지-
dc.citation.volume44-
dc.citation.number4-
dc.citation.startPage268-
dc.citation.endPage277-
dc.type.docTypeArticle-
dc.identifier.kciidART003114586-
dc.description.isOpenAccessN-
dc.description.journalRegisteredClassesci-
dc.description.journalRegisteredClasskci-
dc.relation.journalResearchAreaMaterials Science-
dc.relation.journalWebOfScienceCategoryMaterials Science, Characterization & Testing-
dc.subject.keywordAuthorFire Detection-
dc.subject.keywordAuthorHierarchical Deep Neural Network-
dc.subject.keywordAuthorWind Turbine Nacelle-
dc.subject.keywordAuthorCondition Monitoring System (CMS)-
dc.subject.keywordAuthor화재 감지-
dc.subject.keywordAuthor계층적 심층 신경망-
dc.subject.keywordAuthor풍력 터빈 나셀-
dc.subject.keywordAuthor상태 감시 시스템-
dc.identifier.urlhttps://www.dbpia.co.kr/journal/articleDetail?nodeId=NODE11915357&language=ko_KR&hasTopBanner=true-
Files in This Item
Go to Link
Appears in
Collections
서울 공과대학 > 서울 기계공학부 > 1. Journal Articles

qrcode

Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.

Related Researcher

Researcher Oh, Ki-Yong photo

Oh, Ki-Yong
COLLEGE OF ENGINEERING (SCHOOL OF MECHANICAL ENGINEERING)
Read more

Altmetrics

Total Views & Downloads

BROWSE