• JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
 
  Bookmark and Share
 
 
Master's Dissertation
DOI
https://doi.org/10.11606/D.3.2020.tde-13042021-091422
Document
Author
Full name
Vitor Annecchini Schimid
E-mail
Institute/School/College
Knowledge Area
Date of Defense
Published
São Paulo, 2020
Supervisor
Committee
Nabeta, Silvio Ikuyo (President)
Pereira, Fabio Henrique
Teixeira, Julio Carlos
Title in Portuguese
Identificação de parâmetros de máquinas síncronas pelo ensaio de resposta em frequência utilizando rede neural LSTM.
Keywords in Portuguese
Ajuste de curva
Ensaio de resposta em frequência
Máquina síncronas
Redes neurais
Abstract in Portuguese
O presente trabalho visa o desenvolvimento de um método numérico para o ajuste da curva de indutância de uma máquina síncrona, proveniente do ensaio de resposta em frequência com a utilização de um inversor de frequência. Este método baseia-se na utilização da rede neural LSTM, bem como os métodos numéricos Simplex de Nelder e Mead e Média Móvel, para previsão de pontos nos extremos das altas e baixas frequências da curva de indutância, tendo em vista que as limitações do inversor impedem a obtenção destes pontos diretamente do arranjo em bancada. Desta forma, os parâmetros da máquina síncrona puderam ser obtidos com margem de erro máxima de 13%.
Title in English
Identification of synchronous machine parameters by frequency response test using neural LSTM network.
Keywords in English
Frequency response test
LSTM
Neural network
Abstract in English
This work aims to develop a numerical method for adjusting the inductance curve of a synchronous machine from the frequency response test using a frequency inverter. This method is based on the use of the LSTM neural network, as well as the Simplex and Moving Average methods, to predict points at the ends of the high and low frequencies of the inductance curve, since the inverter limitations prevent the obtaining of these points directly from the bench arrangement. In this way, the parameters of the synchronous machine could be obtained with a maximum error margin of 13%.
 
WARNING - Viewing this document is conditioned on your acceptance of the following terms of use:
This document is only for private use for research and teaching activities. Reproduction for commercial use is forbidden. This rights cover the whole data about this document as well as its contents. Any uses or copies of this document in whole or in part must include the author's name.
Publishing Date
2021-04-14
 
WARNING: Learn what derived works are clicking here.
All rights of the thesis/dissertation are from the authors
CeTI-SC/STI
Digital Library of Theses and Dissertations of USP. Copyright © 2001-2024. All rights reserved.