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
- 학위논문
- 저자정보
- 지도교수
- 최병근
- 발행연도
- 2019
- 저작권
- 경상대학교 논문은 저작권에 의해 보호받습니다.
이용수10
이 논문의 연구 히스토리 (2)
- 이 논문의 후속연구가 궁금하신가요?
- 연관 학술논문 또는 학술발표를 통해 보다 발전된 연구결과를 확인하실 수 있습니다.
- 이 논문의 연구 히스토리 확인하기
초록· 키워드
오류제보하기
The need for condition monitoring and fault diagnosis is expanding to ensure the reliability and safety of machinery. Condition monitoring is confirmed the status of the machine in real time, minimizing losses for the failure. And fault diagnosis is enabled planned maintenance by finding fault early. The pipe is widely used in industrial fields such as power plants, large ships, automobiles and aviation. Also reliability and stability are required. As technology advances, researches on predictive maintenance based on machine learning are under way. However, there is no research related to monitoring and diagnosis using machine learning algorithms in pipe. In particular, pipe involves a lot of noise, so signal processing is also needed.
Therefore, in this paper, the signal processing and the machine learning algorithm is applied for pipe condition monitoring and fault diagnosis. And classification performance is calculated. Through this process, signal processing and machine learning algorithms are analyzed that are suitable for pipe. The experiment is carried out according to the operation conditions(temperature and flow rate) and fault(fault and form) of the pipe. Before applying signal processing and machine learning algorithms, reliability is verified through comparison of experimental and analysis values. Signal processing is performed to minimize the noise signal of the pipe. And the classification performance is evaluated using the machine learning algorithm.
Through this, the purpose is to study signal processing & machine learning suitable for pipe condition monitoring and fault diagnosis.
Therefore, in this paper, the signal processing and the machine learning algorithm is applied for pipe condition monitoring and fault diagnosis. And classification performance is calculated. Through this process, signal processing and machine learning algorithms are analyzed that are suitable for pipe. The experiment is carried out according to the operation conditions(temperature and flow rate) and fault(fault and form) of the pipe. Before applying signal processing and machine learning algorithms, reliability is verified through comparison of experimental and analysis values. Signal processing is performed to minimize the noise signal of the pipe. And the classification performance is evaluated using the machine learning algorithm.
Through this, the purpose is to study signal processing & machine learning suitable for pipe condition monitoring and fault diagnosis.
목차
Ⅰ. 서론 11. 연구 배경 및 현황 12. 연구 절차 및 목적 3Ⅱ. 이론적 배경 51. 음향방출 52. 신호처리 73. 기계학습 13Ⅲ. 실험 및 해석 251. 상태 및 결함에 따른 배관 실험 252. 배관 수치해석 30Ⅳ. 신호처리 및 기계학습 341. 운전 조건에 따른 분류 342. 결함에 따른 분류 403. 운전 및 결함에 따른 복합분류 46Ⅴ. 결론 52
최근 본 자료
댓글(0)
0