• 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
 
 
Doctoral Thesis
DOI
https://doi.org/10.11606/T.3.1998.tde-24072024-111839
Document
Author
Full name
Marcelo Massarani
Institute/School/College
Knowledge Area
Date of Defense
Published
São Paulo, 1998
Supervisor
Committee
Salvagni, Ronaldo de Breyne (President)
Júnior, Vicente Lopes
Kaminski, Paulo Carlos
Nascimento, Cláudio Augusto Oller do
Pavanello, Renato
Title in Portuguese
Uso de redes neurais artificiais para representar o comportamento viscoelástico de materiais.
Keywords in Portuguese
Engenharia mecânica
Materiais
Redes neurais
Abstract in Portuguese
O comportamento viscoelástico não linear de materiais ainda é representado de forma rudimentar por modelos constitutivos analíticos. É proposto o uso de redes neurais artificiais para representar o comportamento viscoelástico de materiais sob carregamentos uniaxiais. Alguns exemplos são desenvolvidos usando redes neurais que geram sua própria arquitetura e também redes neurais recorrentes para representar o comportamento viscoelástico de materiais. Os resultados obtidos podem ser considerados animadores. As vantagens observadas no uso de redes neurais artificiais para representar o comportamento de materiais são as seguintes: nenhuma hipótese a respeito do comportamento do material é necessária; o comportamento do material é apreendido diretamente dos dados de ensaios; e não é necessário nenhuma aproximação numérica para usar uma rede neural artificial já treinada.
Title in English
Untitled in english
Keywords in English
Materials
Mechanical engineering
Neural networks
Abstract in English
The non linear viscoelastic material behavior is poorly represented by constitutive equations. The present5 study proposes a neural network approach for non linear viscoelastic behavior under uniaxial loading. Some examples were done using self-growing neural networks and recurrent neural networks modeling non linear viscoelastic behavior. The results were encouraging. The main beneficts of neural network approach are: no assumptions about the material behavior are required; the material behavior can be represented directly from experimental data; once trained no numerical approximations are required when using the neural network.
 
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
2024-07-24
 
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.