Publication detail
FUZZY NEURAL NETWORK AS A LIFETIME PREDICTOR OF INSULATIVE MATERIAL
HAMMER, M. ŘÍHA, Z. LATINA, P.
Czech title
FUZZY NEURONOVÁ SÍŤ JAKO PREDIKTOR ZBYTKOVÉ ŹIVOTNOSTI IZOLAČNÍHO MATERIÁLU
English title
FUZZY NEURAL NETWORK AS A LIFETIME PREDICTOR OF INSULATIVE MATERIAL
Type
conference paper
Language
en
Original abstract
When researching electro-insulating materials, searching for new methods of diagnostics and prediction of the lifetime of those insulating materials assumes more and more importance. We are concerned with degradation process of insulating material Relanex used for insulation systems of electric rotary machines windings. Our research is focused to residual lifetime prediction of this insulation systém bhy artificial intelligence. Most usable methods of artificial intelligence are neural networks and fuzzy systems. In this contribution we are especially focused to use hybrid systems like fuzzy-neural networks. The first part of the paper describes the use of fuzzy neural networks which forecast the life of insulating material for windings in electric rotary machine. The second part shows the simulation of insulating material behavior with fuzzy neural networks. Tables evaluate the application of this tool for the solution of the problems investigated. We have used the above-mentioned fuzzy neural networks for the prediction of insulating materials that were programmed in Matlab 6.5 environment.
Czech abstract
Článek pojednává o řešení problematiky diagnostiky izolačního materiálu Relanex, pomocí metod umělé inteligence. Jako nástroj pro simulaci materiálu byly použity hybridní systémy. Hybridním systémem může být fuzzy neuronová síť, která spojuje výhody fuzzy systémů a neuronových sítí. Fuzzy neuronové sítě byly naprogramovány v prostředí Matlab 6.5, stejně tak výsledky simulací byly získány tímto produktem. Vstupní veličiny jsou tvořeny koeficienty Ba (aktivační energie polarizačního děje), Bv (aktivační energie vodivostního děje) a Uk (parametr určující kritické napětí). Na základě změn vnitřní struktury neuronové sítě, použitím různých učících algoritmů, různých metod deffuzyfikace a kombinacemi jednotlivých vstupních veličin pak byl ovlivňován výsledek simulace materiálu.
English abstract
When researching electro-insulating materials, searching for new methods of diagnostics and prediction of the lifetime of those insulating materials assumes more and more importance. We are concerned with degradation process of insulating material Relanex used for insulation systems of electric rotary machines windings. Our research is focused to residual lifetime prediction of this insulation systém bhy artificial intelligence. Most usable methods of artificial intelligence are neural networks and fuzzy systems. In this contribution we are especially focused to use hybrid systems like fuzzy-neural networks. The first part of the paper describes the use of fuzzy neural networks which forecast the life of insulating material for windings in electric rotary machine. The second part shows the simulation of insulating material behavior with fuzzy neural networks. Tables evaluate the application of this tool for the solution of the problems investigated. We have used the above-mentioned fuzzy neural networks for the prediction of insulating materials that were programmed in Matlab 6.5 environment.
Keywords in Czech
izolační Material; Fuzzy Neural síť; Fuzzy System; Diagnostika
Keywords in English
Insulative Material; Fuzzy Neural Network; Fuzzy Systems; Diagnostic
RIV year
2005
Released
09.06.2005
Location
Sibiu, Romania
ISBN
973-718-259-6
Book
UBR-CORR Study and Control of Corroslon in the Perspective of Sustalnable Development of Urban Distribution Grids
Pages from–to
146–148
Pages count
3
BIBTEX
@inproceedings{BUT20454,
author="Miloš {Hammer} and Zbyněk {Říha} and Petr {Latina},
title="FUZZY NEURAL NETWORK AS A LIFETIME PREDICTOR OF INSULATIVE MATERIAL",
booktitle="UBR-CORR Study and Control of Corroslon in the Perspective of Sustalnable Development of Urban Distribution Grids",
year="2005",
month="June",
pages="146--148",
address="Sibiu, Romania",
isbn="973-718-259-6"
}