Geodesic
Dynamic Neural Networks for Process Modelling in Fault Detection and Isolation Systems
International Journal of Applied Mathematics and Computer Science, Tome 9 (1999) no. 3, pp. 519-546.

Voir la notice de l'article provenant de la source Library of Science

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.
Keywords: fault detection, dynamic neural networks, non-linear modelling, learning algorithms, FL-classifier, two-tank system
Mots-clés : wykrywanie błędu, sieć neuronowa dynamiczna, modelowanie nieliniowe, algorytm inteligentny 
@article{IJAMCS_1999_9_3_a1,
     author = {Korbicz, J. and Patan, K. and Obuchowicz, A.},
     title = {Dynamic {Neural} {Networks} for {Process} {Modelling} in {Fault} {Detection} and {Isolation} {Systems}},
     journal = {International Journal of Applied Mathematics and Computer Science},
     pages = {519--546},
     publisher = {mathdoc},
     volume = {9},
     number = {3},
     year = {1999},
     language = {en},
     url = {http://geodesic.mathdoc.fr/item/IJAMCS_1999_9_3_a1/}
}
TY  - JOUR
AU  - Korbicz, J.
AU  - Patan, K.
AU  - Obuchowicz, A.
TI  - Dynamic Neural Networks for Process Modelling in Fault Detection and Isolation Systems
JO  - International Journal of Applied Mathematics and Computer Science
PY  - 1999
SP  - 519
EP  - 546
VL  - 9
IS  - 3
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/item/IJAMCS_1999_9_3_a1/
LA  - en
ID  - IJAMCS_1999_9_3_a1
ER  - 
%0 Journal Article
%A Korbicz, J.
%A Patan, K.
%A Obuchowicz, A.
%T Dynamic Neural Networks for Process Modelling in Fault Detection and Isolation Systems
%J International Journal of Applied Mathematics and Computer Science
%D 1999
%P 519-546
%V 9
%N 3
%I mathdoc
%U http://geodesic.mathdoc.fr/item/IJAMCS_1999_9_3_a1/
%G en
%F IJAMCS_1999_9_3_a1
Korbicz, J.; Patan, K.; Obuchowicz, A. Dynamic Neural Networks for Process Modelling in Fault Detection and Isolation Systems. International Journal of Applied Mathematics and Computer Science, Tome 9 (1999) no. 3, pp. 519-546. http://geodesic.mathdoc.fr/item/IJAMCS_1999_9_3_a1/