메뉴 건너뛰기
.. 내서재 .. 알림
소속 기관/학교 인증
인증하면 논문, 학술자료 등을  무료로 열람할 수 있어요.
한국대학교, 누리자동차, 시립도서관 등 나의 기관을 확인해보세요
(국내 대학 90% 이상 구독 중)
로그인 회원가입 고객센터 ENG
주제분류

추천
검색
질문

논문 기본 정보

자료유형
학술대회자료
저자정보
진익재 (울산과학기술원) 임도영 (울산과학기술원) 방인철 (울산과학기술원)
저널정보
한국유체기계학회 한국유체기계학회 학술대회 논문집 2022년 한국유체기계학회 하계학술대회
발행연도
2022.6
수록면
249 - 255 (7page)

이용수

표지
📌
연구주제
📖
연구배경
🔬
연구방법
🏆
연구결과
AI에게 요청하기
추천
검색
질문

초록· 키워드

오류제보하기
Diagnosis of the multiple components with fault detection is related to the safety of various industries, including power plants. A nuclear power plant is composed of numerous components with a significant scale than other power plants. Therefore, methods of components inspection for several industries have been suggested to enhance safety. Recently, interest in the deep learning-based infrared (IR) inspection method has been growing by demonstrating high performance with intuitive non-contact inspection than other methods. However, deep learning-based IR component inspection methods suggested previously used high-resolution IR cameras accompanying limitations of complex installation and high cost. Due to the limitations, the application of this technique is difficult. This study proposes IR based multi-components inspection method that could diagnose the conditions efficiently with reduced cost by applying a compact IR sensor. The UNIST reactor innovation loop (URI-LO), an integral effect test facility based on APR-1400, was utilized to conduct this study. Classification algorithms based on the convolutional neural network (CNN) were compared for applications with high performance. ResNet 34 shows that the overall performance is outstanding than other algorithms. ResNet 34 could conduct the multi-components inspection with 93% of the lowest accuracy in less than 1 sec. This IR-based multi-component inspection method is considered to enhance the safety of various industries with the reduced cost and human error, including nuclear power plants.

목차

ABSTRACT
1. 서론
2. 모델링 및 방법론
3. 결과 및 논의
4. 결론
참고문헌(Reference)

참고문헌 (0)

참고문헌 신청

함께 읽어보면 좋을 논문

논문 유사도에 따라 DBpia 가 추천하는 논문입니다. 함께 보면 좋을 연관 논문을 확인해보세요!

이 논문의 저자 정보

이 논문과 함께 이용한 논문

최근 본 자료

전체보기

댓글(0)

0