인문학
사회과학
자연과학
공학
의약학
농수해양학
예술체육학
복합학
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
- 1999.10
- 수록면
- 139 - 147 (9page)
이용수
초록· 키워드
Detection, identification, and accommodation of sensor failures can be a challenging task for complex dynamic systems such as aircraft. Classic state estimation tools based on observers and/or Kalman filters as well as alternative methods using on-line learning estimators have been proposed in the technical literature to address this problem. This paper presents the results of a neural network based scheme to provide fault tolerance following sensor failures. Results from the application of the methodology to actual flight data of the B737 aircraft are presented. Particularly, the paper compares the performance of two different detection schemes within the SFDIA architecture applied to failures of different aircraft sensors. The overall results confirm the interesting capabilities of neural estimators for this application and show the improvements achievable with the refined scheme in dealing with the most conservative case of soft failure.
상세정보 수정요청해당 페이지 내 제목·저자·목차·페이지정보가 잘못된 경우 알려주세요!
목차
- ABSTRACT
- 초록
- Ⅰ. Introduction
- Ⅱ. Issues in sensor failure tolerance and NN-based SFDIA scheme
- Ⅲ. SFDIA for simulated failures using B-737 data
- Ⅳ. Results of the SFDIA applied to the B-737 data
- Ⅴ. Conclusions
- References