Korbicz, Józef - red. ; Patton, Ronald J. - red.
A fault diagnosis scheme for unknown nonlinear dynamic systems with modules of residual generation and residual evaluation is considered. Main emphasis is placed upon designing a bank of neural networks with dynamic neurons that model a system diagnosed at normal and faulty operating points. ; To improve the quality of neural modelling, two optimization problems are included in the construction of such dynamic networks: searching for an optimal network architecture and the network training algorithm. To find a good solution, the effective well-known cascade-correlation algorithm is adapted here. ; The residuals generated by a bank of neural models are then evaluated by means of pattern classification. To illustrate the effectiveness of our approach, two applications are presented: a neural model of Narendra's system and a fault detection and identification system for the two-tank process.
Zielona Góra: Uniwersytet Zielonogórski
AMCS, volume 9, number 3 (1999) ; kliknij tutaj, żeby przejść
Biblioteka Uniwersytetu Zielonogórskiego
2021-09-03
2021-01-22
93
https://zbc.uz.zgora.pl/publication/64801
Nazwa wydania | Data |
---|---|
Dynamic neural networks for process modelling in fault detection and isolation systems | 2021-09-03 |
Patan, Krzysztof Witczak, Marcin Korbicz, Józef Korbicz, Józef - ed. Sauter, Dominique - ed.
Dalton, Tracy Klotzek, Petra Frank, Paul M. Korbicz, Józef - red. Patton, Ronald J. - red.
Korbicz, Józef Patan, Krzysztof Korbicz, Józef - red. Uciński, Dariusz - red.
Yasui, Syozo Rutkowska, Danuta - ed. Zadeh, Lotfi A. - ed.
Marcu, Teodor Mirea, Letitia Frank, Paul M. Korbicz, Józef - red. Patton, Ronald J. - red.
Nowicki, Adam Grochowski, Michał Duzinkiewicz, Kazimierz Cordón, Oskar - ed. Kazienko, Przemysław - ed.
Chen, Wei Khan, Abdul Q. Abid, Muhammmad Ding, Steven X. Korbicz, Józef - red. Uciński, Dariusz - red.
Maksimov, Vyacheslav Pandolfi, Luciano Triggiani, Roberto- ed. Maksimov, Vyacheslav I. - ed.