Global Nuclear Safety
National Research Nuclear University "MEPhI"
online version: ISSN 2499-9733
print version: ISSN 2305-414Х
2016-4(21)
Design, manufacturing and commissioning of nuclear industry equipment
| Article Name | System Adaptation of the Accepting and Radiating Objects Synchronized on the Phase in the Conditions of Selection Phase Distortion Using of Artificial Neural Networks |
|---|---|
| Authors | Nguyen Dang Thao |
| Address | Moscow Institute of physics and technology (State University) |
| Abstract | The paper discusses the adaptation of the system synchronized on the phase of the accepting and radiating objects by comparison with the reference signal in terms of phase distortion of the reference signal. Representation of system in the form of artificial neural network, with the subsequent training, is used for compensation of distortion of standard phase. Representation of systems and devices in the form of artificial neural networks is used for the solution of various tasks. Such representation enables the application of optimization methods of parameters used in artificial neural networks for parameter optimization are presented in the form of systems or devices. The composition of the optimized parameters is determined by selecting the configuration of the artificial neural network. It is shown that the system can adapt by method of comparison with a standard in the conditions of phase distortion of the training selections, due to application as a standard only of the module of a reference signal at representation of system of the accepting and radiating objects synchronized on a phase in the form of artificial neural network with the nonlinearity corresponding to complex number module definition. |
| Keywords | system of the accepting and radiating objects, adaptation by last mean square, adaptive array, artificial neural network |
| Language | Russian |
| References | [1] Adaptivnye antennye reshetki: uchebnoe posobie v 2-kh chastyakh [Adaptive antenna array. The education guidance in 2 parts]. Edited by V.A. Grigoreva. Sankt-Peterburg: Pub. ITMO university, 2016. (in Russian) [2] Galushkin A.I. Sintez mnogosloynykh sistem raspoznavaniya obrazov [Synthesis of multilayered systems of recognition of images]. M. Pub. «Energiya» [Energy], 1974. (in Russian) [3] Sazonov D.M. Mnogoelementnye antennye sistemy [Multielement antenna systems]. M. Pub. «Radiotekhnika» [Radio Engineering], 2015. ISBN 978-5-93-108-093-2, 144 p. (in Russian) [4] Seydl P., Taufer I. Model korotkozamknutoy shchelevoy linii v vide iskusstvennoy neyronnoy seti [Model of the short-circuited slot-hole line in the form of artificial neural network]. Neyrokompyutery: razrabotka, primenenie [Neurocomputers: development, application]. 2009. №5. ISSN 1999-8554, pp. 57–61. (in Russian) [5] Tarkhov D.A. Neyrosetevye modeli i algoritmy [Neural network models and algorithms]. M. Pub. «Radiotekhnika» [Radio Engineering], 2014. ISBN 978-5-88070-376-0, 355 p. (in Russian) [6] Tatuzov A.L. Neyronnye seti v zadachakh radiolokatsii [Neural networks in problems of a radar-location]. M. Pub. «Radiotekhnika» [Radio Engineering], 2009, ISBN 978-5-88070-244-243-2, 432 p. (in Russian) [7] Khabarov A.V. Objedinenie antenn s neizvestnymi koordinatami v antennuyu reshetku [Combination of antennas with unknown coordinates in an antenna array]. Antennas [перевод], 2006, №11, ISSN 0320-9601, pp. 7–11. (in Russian) |
| Papers | 32 - 42 |
| URL Article | URL Article |
| Open Article |