DocumentCode :
2331786
Title :
Fault classification using time variable ART2-A networks
Author :
Benitez-Perez, Hector
Author_Institution :
Departamento de Ingenieria de Sistemas Computacionales y Automatizacion, UNAM, Obregon
Volume :
2
fYear :
2002
fDate :
2002
Firstpage :
832
Abstract :
Increasingly, there is a move towards in-built intelligence for sensors and actuators to integrate "smart" peripheral elements as part of a distributed control system. The utilisation of local intelligence to provide local fault detection and fault tolerance facilitates the incorporation of new variables into the structure of these peripheral elements. How on-line fault classification overcomes the time varying situation is studied here. The main idea is to integrate three ART2-A networks in order to produce a fault classification capable of managing the situation.
Keywords :
ART neural nets; control engineering computing; distributed control; fault diagnosis; intelligent control; neural net architecture; pattern classification; time-varying systems; actuators; distributed control system; fault classification; in-built intelligence; local fault detection; local fault tolerance; local intelligence; pattern recognition; sensors; smart peripheral elements; time variable ART2-A networks; Distributed control; Fault detection; Fault diagnosis; Fault tolerant systems; Intelligent actuators; Intelligent sensors; Intelligent structures; Neural networks; Pattern recognition; Sensor systems;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Control Applications, 2002. Proceedings of the 2002 International Conference on
Print_ISBN :
0-7803-7386-3
Type :
conf
DOI :
10.1109/CCA.2002.1038709
Filename :
1038709
Link To Document :
بازگشت