抄録
This paper present a new method for trend diagnosis system using neural networks. Most of dynamical systems are not easy to analyze and detect faults because the observed parameters are not directly expressing the state of the system. We have to measure the temporal tendencies of the parameters, which is not easy not only for testing machine but also for human work. Here, the effectiveness of the trend fault diagnosis system using recurrent neural networks is examined for the air-conditioning system. The network was trained with the fault and correct data sequences obtained from the system simulation. The experimental fault detection results by using actual data proved that the proposed method is effective to perform the trend diagnosis of dynamic system.
本文言語 | English |
---|---|
ホスト出版物のタイトル | Proceedings of the IEEE International Conference on Systems, Man and Cybernetics |
出版社 | IEEE |
ページ | 1186-1191 |
ページ数 | 6 |
巻 | 2 |
出版ステータス | Published - 2000 |
イベント | 2000 IEEE Interantional Conference on Systems, Man and Cybernetics - Nashville, TN, USA 継続期間: 2000 10月 8 → 2000 10月 11 |
Other
Other | 2000 IEEE Interantional Conference on Systems, Man and Cybernetics |
---|---|
City | Nashville, TN, USA |
Period | 00/10/8 → 00/10/11 |
ASJC Scopus subject areas
- ハードウェアとアーキテクチャ
- 制御およびシステム工学