CHOOSING A NEURAL NETWORK STRUCTURE FOR SIGNAL PROCESSING AS AN EXPERIMENT PLANNING-Reference-Cited by-同舟云学术

CHOOSING A NEURAL NETWORK STRUCTURE FOR SIGNAL PROCESSING AS AN EXPERIMENT PLANNING

Published:2021-09-29 Issue:3 Volume: Page:123-132
ISSN:1810-1909
Container-title:Vestnik Chuvashskogo universiteta
language:
Short-container-title:Vestn. Čuv. univ.

Author:

Slavutskii Leonid A.¹^ORCID,Slavutskaya Elena V.²^ORCID

Affiliation:

1. Chuvash State University

2. I.Ya. Yakovlev Chuvash State Pedagogical University

Abstract

The paper is devoted to the use of artificial neural networks for signal processing in electrical engineering and electric power industry. Direct propagation neural network (perceptron) is considered as an object in the theory of experiment planning. The variants of the neural network structure empirical choice, the quality criteria of its training and testing are analyzed. It is shown that the perceptron structure choice, the training sample, and the training algorithms require planning. Variables and parameters of neuro algorithm that can act as factors, state parameters, and disturbing influences in the framework of the experimental planning theory are discussed. The proposed approach is demonstrated by the example of neural network analysis of the industrial frequency signal of 50 Hz nonlinear distortions. The possibility of using an elementary perceptron with one hidden layer and a minimum number of neurons to correct the transformer saturation current is analyzed. The conditions under which the neuro algorithm allows one to restore the values of the main harmonic amplitude, frequency and phase with an error of no more than one percent are revealed. The signal processing in a «sliding window» with a duration of a fraction of the fundamental frequency period is proposed, and the neuro algorithm accuracy characteristics are estimated. The possibility to automate the neural network structure choosing for signal processing is discussed.

Publisher

I.N. Ulianov Chuvash State University

Link

https://www.chuvsu.ru/wp-content/uploads/2021/09/vchu_2021_3_123-132.pdf

Reference30 articles.

1. Korol E.G. Analiz metodov modelirovaniya magnitnykh kharakteristik elektromagnitov dlya kompensatsii magnitnogo polya elektrooborudovaniya [Analysis of methods for modeling the magnetic characteristics of electromagnets for compensating the magnetic field of electrical equipment]. Elektrotekhnika i Elektromekhanika, 2007, no. 2, pp. 31–34.

2. Kruglov V.V., Borisov V.V. Iskusstvennye neironnye seti. Teoriya i praktika [Neural networks. Theory and practice] Moscow, Goryachaya liniya Telekom Publ., 2001, 382 p.

3. Kuzhekov S.L., Nudel’man G.S. Obespecheniye pravil’noy raboty mikroprotsessornykh ustroystv differentsial’noy zashchity pri nasyshchenii transformatorov toka [Ensuring the correct operation of microprocessor devices of differential protection during saturation of current transformers]. Elektromekhanika, 2009, no. 4, pp. 12–17.

4. Lyamets Yu.Ya., Nudel’man G.S., Pavlov A.O., Efimov E.B., Zakon’shek Ya. Raspoznavaemost’ povrezhdenii elektroperedachi, ch. 1,2,3 [Detectability of power transmission damage]. Elektrichestvo, 2001, no. 2, pp. 16–23; no. 3, pp. 16–24; no. 12, pp. 9–22.

5. Slavutskaya E., Slavutskiy L. On choosing the artificial neural networks structure and the algorithms for psycho diagnostic data analyzing [O vybore struktury iskusstvennykh neyrosetey i algoritmov analiza psikhodiagnosticheskikh dannykh]. Kazan pedagogical journal, 2020, no. 5(142), рp. 202–210. DOI:34772/KPJ.2020.142.5.026.