인문학
사회과학
자연과학
공학
의약학
농수해양학
예술체육학
복합학
DBpia AI
AI 에이전트
AI 아이디어
AI 리더
AI 뷰어
Citeasy
크롬 서지관리 다운로드
지원사업
학술연구/단체지원/교육 등 연구자 활동을 지속하도록 DBpia가 지원하고 있어요.
커뮤니티
연구자들이 자신의 연구와 전문성을 널리 알리고, 새로운 협력의 기회를 만들 수 있는 네트워킹 공간이에요.
논문 기본 정보
- 자료유형
- 학술저널
- 저자정보
- 발행연도
- 2024.9
- 수록면
- 280 - 287 (8page)
- DOI
- 10.7315/CDE.2024.280
이용수
초록· 키워드
Cooling systems are essential in both residential and industrial environments, where failures can reduce production efficiency and pose safety risks. Ensuring the reliability and continuous operation through predictive maintenance is increasingly important. This study aims to provide efficient and high-performance maintenance by developing a comprehensive 3-stage algorithm that combines classifiers and predictors. Utilizing data from the ASHRAE RP-1043 project, we validated and compared the performance of various machine learning models. Our findings indicate that Support Vector Machine (SVM), XGBoost, and RandomForest models exhibit the highest performance. Consequently, we propose a fault classifier based on SVM and XGBoost, along with a remaining useful life (RUL) predictor utilizing RandomForest. By leveraging these insights, we developed a three-stage predictive maintenance algorithm that effectively combines fault classification and RUL prediction. This integrated approach enhances the ability to predict and prevent cooling system failures, ensuring their continuous and reliable operation. Our research contributes significantly to the field of predictive maintenance, providing a practical solution for maintaining the efficiency and safety of cooling systems, thereby supporting their critical role in various settings.
#Cooling system
#Fault classifier
#Hybrid application
#Machine learning
#Predictive maintenance
#Remaining useful life
상세정보 수정요청해당 페이지 내 제목·저자·목차·페이지정보가 잘못된 경우 알려주세요!
목차
- ABSTRACT
- 1. 서론
- 2. 관련 연구 동향
- 3. 분류기와 예측기의 혼합적용
- 4. 혼합 적용을 통한 예지보전
- 5. 결론
- References
참고문헌
참고문헌 신청최근 본 자료
UCI(KEPA) : I410-151-24-02-090657233
