• DocumentCode
    288840
  • Title

    Engineering and manufacturing applications of ART-1 neural networks

  • Author

    Smith, Scott D G ; Escobedo, Richard A.

  • Author_Institution
    Boeing Comput. Services, Seattle, WA, USA
  • Volume
    6
  • fYear
    1994
  • fDate
    27 Jun- 2 Jul 1994
  • Firstpage
    3780
  • Abstract
    Adaptive resonance theory (ART) neural networks offer many attractive properties for applications to engineering and manufacturing problems. In this paper we discuss some of these properties and then describe some important applications. The applications discussed include retrieval of engineering designs, clustering of machines for cellular manufacturing, detection of novel events in complex data or signals, and monitoring of factory machines. The applications are described in terms of their importance, how ART-1 neural networks are utilized, and the methods used to process the input data. Techniques described include using macro-circuits of ART-1 modules to provide enhanced functionality, monitoring network activations to detect novelty, and coupling multiple ART-1 modules together to provide supervised learning
  • Keywords
    ART neural nets; information retrieval; manufacturing data processing; monitoring; pattern recognition; production engineering computing; ART-1 neural networks; adaptive resonance theory; cellular manufacturing; engineering designs retrieval; functionality; machines clustering; machines monitoring; macro-circuits; network activations; novel events detection; supervised learning; Adaptive systems; Cellular manufacturing; Data engineering; Design engineering; Event detection; Information retrieval; Neural networks; Resonance; Signal design; Subspace constraints;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on
  • Conference_Location
    Orlando, FL
  • Print_ISBN
    0-7803-1901-X
  • Type

    conf

  • DOI
    10.1109/ICNN.1994.374812
  • Filename
    374812