The performance of system identification methods based on multi-layer artificial neural network (ANN) models is analyzed. The state of the system is monitored by multiple ANNs which act as individual neuro agents. An algorithm based on fuzzy logics is applied to combine information from ANNs. In this paper, we elaborate a method which can make a distinction between the occurrence of unexperienced events and any inconsistency in the judgments of agents caused by statistical uncertainties in the actual data. The results are illustrated by analyzing signals of numerical experiments and also actual measurements in a nuclear reactor.
|出版ステータス||Published - 1994|
|イベント||Proceedings of the Artificial Neural Networks in Engineering Conference (ANNIE'94) - St. Louis, MO, USA|
継続期間: 1994 11 13 → 1994 11 16
|Conference||Proceedings of the Artificial Neural Networks in Engineering Conference (ANNIE'94)|
|City||St. Louis, MO, USA|
|Period||94/11/13 → 94/11/16|
ASJC Scopus subject areas