Proceedings of the KIEE Conference (대한전기학회:학술대회논문집)
- 1993.11a
- /
- Pages.317-319
- /
- 1993
Redundant Sensor Signal Validation of Nuclear Power Plants Using the Simplified Parity Space Method
단순화된 패리티 공간기법을 이용한 원전 다중센서 신호검증
-
Oh, S.H.
(Korea Institute of Nuclear Safety)
;
- Kim, D.I. (Korea Institute of Nuclear Safety) ;
-
Zoo, O.P.
(Korea Institute of Nuclear Safety)
;
-
Chung, Y.H.
(Korea Institute of Nuclear Safety)
;
- Ryu, B.H. (Korea Institute of Nuclear Safety) ;
- Lim, C.H. (Korea Institute of Nuclear Safety) ;
- Kim, K.J. (Chung Nam National Univ.)
-
오성헌
(한국원자력안전기술원)
;
- 김대일 (한국원자력안전기술원) ;
-
주운표
(한국원자력안전기술원)
;
-
정윤형
(한국원자력안전기술원)
;
- 류부형 (한국원자력안전기술원) ;
- 임장현 (한국원자력안전기술원) ;
- 김건중 (충남대학교)
- Published : 1993.11.26
Abstract
The function estimation characteristics of neural networks can be used for sensor signal validation of a system. In case of applying the neural networks to signal validation, it is a important problem that the redundant sensor signals used as a input signal of neural networks should be validated. In this paper, we simplify the conventional parity space method in order to input the validated signal to the neural networks and also propose the sensor signal validation method, which estimates the reliable sensor output combining neural networks with the simplified parity space method. The acceptability of the proposed signal validation method is demonstrated by using the simulation data in safety injection accident of nuclear power plants.
Keywords