Publication detail

INFLUENCE OF FUZZY NEURAL NETWORK INPUT PARAMETERS ON MODELING PROCESS OF INSULATIVE MATERIAL

HAMMER, M. ŘÍHA, Z. LATINA, P.

Original Title

INFLUENCE OF FUZZY NEURAL NETWORK INPUT PARAMETERS ON MODELING PROCESS OF INSULATIVE MATERIAL

English Title

INFLUENCE OF FUZZY NEURAL NETWORK INPUT PARAMETERS ON MODELING PROCESS OF INSULATIVE MATERIAL

Type

conference paper

Language

en

Original Abstract

Well timed diagnostics of functional state of production machines is still very important in this time. We are focused on problem of degradation procedure inside insulative systems. The paper deals with the the effect of the input values on the result of modeling process of insulating material. The input data consist of coefficients Ba (activation energy of a polarization action), Bv (activation energy of a conduction action) and Uk, being a parameter that determines critical voltage. The input data was obtained by non-destructive measurement method on insulating material samples in laboratory environment. They are the main prerequisites for the modeling of coefficient Up (break-down voltage) that characterizes the lifetime of the insulating material and, therefore, the whole motor. The fuzzy neural networks were programmed in the Matlab 6.5 environment and the results of simulations were obtained using the same product.

English abstract

Well timed diagnostics of functional state of production machines is still very important in this time. We are focused on problem of degradation procedure inside insulative systems. The paper deals with the the effect of the input values on the result of modeling process of insulating material. The input data consist of coefficients Ba (activation energy of a polarization action), Bv (activation energy of a conduction action) and Uk, being a parameter that determines critical voltage. The input data was obtained by non-destructive measurement method on insulating material samples in laboratory environment. They are the main prerequisites for the modeling of coefficient Up (break-down voltage) that characterizes the lifetime of the insulating material and, therefore, the whole motor. The fuzzy neural networks were programmed in the Matlab 6.5 environment and the results of simulations were obtained using the same product.

Keywords

Fuzzy Neural Network; Diagnostics; Simulation; Lifetime Insulating Material

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

153

Pages to

155

Pages count

3

BibTex


@inproceedings{BUT18417,
  author="Miloš {Hammer} and Zbyněk {Říha} and Petr {Latina}",
  title="INFLUENCE OF FUZZY NEURAL NETWORK INPUT PARAMETERS ON MODELING PROCESS OF INSULATIVE MATERIAL",
  annote="Well timed diagnostics of functional state of production machines is still very important in this time. We are focused on problem of degradation procedure inside insulative systems.
The paper deals with the the effect of the input values on the result of modeling process of insulating material. The input data consist of coefficients Ba (activation energy of a polarization action), Bv (activation energy of a conduction action) and Uk, being a parameter that determines critical voltage. The input data was obtained by non-destructive measurement method on insulating material samples in laboratory environment. They are the main prerequisites for the modeling of coefficient Up (break-down voltage) that characterizes the lifetime of the insulating material and, therefore, the whole motor. The fuzzy neural networks were programmed in the Matlab 6.5 environment and the results of simulations were obtained using the same product.",
  booktitle="UBR-CORR Study and Control of Corroslon in the Perspective of Sustalnable Development of Urban Distribution Grids",
  chapter="18417",
  howpublished="print",
  year="2005",
  month="june",
  pages="153--155",
  type="conference paper"
}