Artificial neural networks for real-time estimation of basic waveforms of voltages and currents

Author

Cichocki, A. ; Lobos, T.

Author_Institution

Tech. Univ. Warsaw, Poland

fYear

1993

fDate

4-7 May 1993

Firstpage

357

Lastpage

363

Abstract

New parallel algorithms for estimation of parameters of sinewaves contaminated by noise are proposed. The problem of estimation is formulated as an optimization problem and solved by using the gradient descent method. Algorithms based on the least absolute value, the least-squares and the minimax (Chebyshev) criteria are developed and compared. The implementation of the algorithms by an appropriate neural network is also given. Illustrative computer simulation results confirm validity and high performance of the proposed solution

Keywords

digital simulation; least squares approximations; minimax techniques; neural nets; parameter estimation; power system analysis computing; Chebyshev criteria; algorithms; artificial neural networks; computer simulation; current waveforms estimation; gradient descent method; minimax criteria; noise; power system control; power system protection; real-time estimation; sinewaves; voltage waveforms estimation; Artificial neural networks; Distortion measurement; Harmonic distortion; Neural networks; Noise measurement; Parameter estimation; Power system protection; Signal processing; Signal processing algorithms; Voltage;

fLanguage

English

Publisher

ieee

Conference_Titel

Power Industry Computer Application Conference, 1993. Conference Proceedings

Conference_Location

Scottsdale, AZ

Print_ISBN

0-7803-1301-1

Type

conf

DOI

10.1109/PICA.1993.290995

Filename

290995