Automated trend diagnosis using neural networks

Herath K U Samarasinghe*, Shuji Hashimoto


    研究成果: Conference contribution

    3 被引用数 (Scopus)


    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.

    ホスト出版物のタイトルProceedings of the IEEE International Conference on Systems, Man and Cybernetics
    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 82000 10月 11


    Other2000 IEEE Interantional Conference on Systems, Man and Cybernetics
    CityNashville, TN, USA

    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


    「Automated trend diagnosis using neural networks」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。