Publication result detail

Fuzzy model optimization by a genetic algorithm

HAMMER, M.

Original Title

Fuzzy model optimization by a genetic algorithm

English Title

Fuzzy model optimization by a genetic algorithm

Type

Paper in proceedings (conference paper)

Original Abstract

The life of the insulating systems of electric rotary machines is strongly dependent upon electrical and thermal features of the insulating material used. The subject of the diagnostics is to specify the condition of insulation used. At present days, the most popular diagnostic tools are the methods of artificial intelligence, and one method is the fuzzy modelling. However, this tool has many variable parameters, and the resulting effect depends upon the suitable setting. This paper is concentrated on the use of genetic algorithms for the optimization of variable parameters in the fuzzy model that is used as a diagnostic tool for winding insulation of electric rotary machines. In this case, the optimization of fuzzy model means to minimize the absolute mean error for the diagnostics of winding insulation. The first section of the paper describes the architecture and the setting of the genetic algorithm, the fuzzy model optimization and the input/output data. The second section presents the optimization curves, and the calculated values that were specified by the genetic algorithm as the optimized ones are shown in tables. The use of the diagnostic tool to solve the problems investigated is assessed in tables. The optimization method, the genetic algorithm and the fuzzy model were programmed in Matlab 6 environment. Also, all simulations and the calculated values were obtained by means of this product.

English abstract

The life of the insulating systems of electric rotary machines is strongly dependent upon electrical and thermal features of the insulating material used. The subject of the diagnostics is to specify the condition of insulation used. At present days, the most popular diagnostic tools are the methods of artificial intelligence, and one method is the fuzzy modelling. However, this tool has many variable parameters, and the resulting effect depends upon the suitable setting. This paper is concentrated on the use of genetic algorithms for the optimization of variable parameters in the fuzzy model that is used as a diagnostic tool for winding insulation of electric rotary machines. In this case, the optimization of fuzzy model means to minimize the absolute mean error for the diagnostics of winding insulation. The first section of the paper describes the architecture and the setting of the genetic algorithm, the fuzzy model optimization and the input/output data. The second section presents the optimization curves, and the calculated values that were specified by the genetic algorithm as the optimized ones are shown in tables. The use of the diagnostic tool to solve the problems investigated is assessed in tables. The optimization method, the genetic algorithm and the fuzzy model were programmed in Matlab 6 environment. Also, all simulations and the calculated values were obtained by means of this product.

Key words in English

Genetic algorithm, System optimization, Neural network, Artificial intelligence, Diagnostics, Insulation and fuzzy

Authors

HAMMER, M.

Released

01.01.2002

Publisher

S.C.ICPE

Location

Constanta, Rumunsko

ISBN

973-95041-3-2

Book

Study and control of corrosion in the perspective of suistanable development of urban distribution grids

Pages from

58

Pages count

5

BibTex

@inproceedings{BUT5349,
  author="Miloš {Hammer}",
  title="Fuzzy model optimization by a genetic algorithm",
  booktitle="Study and control of corrosion in the perspective of suistanable development of urban distribution grids",
  year="2002",
  pages="5",
  publisher="S.C.ICPE",
  address="Constanta, Rumunsko",
  isbn="973-95041-3-2"
}