Running Multiple Neural Networks for Process Trend Interpretation

JOURNAL OF CHEMICAL ENGINEERING OF JAPAN

Yoshiyuki Yamashita¹  Mutsumi Suzuki¹  Hiroshi Komori¹ 

[1] Department of Chemical Engineering, Tohoku University

关键词: Neural Networks;    Fault Detection;    Process Monitoring;    Adaptive Resonance;    Pattern Recognition;   

DOI  :  10.1252/jcej.32.552

来源: Maruzen Company Ltd

【 摘 要 】

References(10)Cited-By(2)An architecture for running multiple ART2 neural networks in parallel is presented. Each of the networks can treat different sizes of clusters. As the result, these multiple networks can show higher performance for detecting new classes. A proposed method is demonstrated for the detection of model changes for time-series models.

【 授权许可】

Unknown