Please use this identifier to cite or link to this item: https://hdl.handle.net/10216/98237
Author(s): Catarina Castro
Carlos Alberto Conceição António
Luísa Costa Sousa
Title: Artificial neural networks and metal forming optimization using genetic algorithms
Issue Date: 2006
Abstract: Nowadays computer simulations of metal forming processes using the finite element methodare considered an essential tool, avoiding the use of costly trial-and-error methods. Given aset of input data, the computation of metal forming process evolution and its final results isdefined as a direct problem. Optimization problems can be formulated as inverse problems.The aim of an inverse problem is to determine one or more of the direct problem input data,leading to a given desired result. Evolutionary genetic algorithms have been proposed aimingto solve optimization problems. These evolutionary methods can be computer time consumingdue to the large number of necessary simulations with different input parameters. Introducingan Artificial Neural Network (ANN) the computer time spent on metal forming simulationscan be significantly reduced. In this paper, we intend firstly to present an ANN model that canbe trained using computer simulations of metal forming processes and the results stored; laterthe stored results can be used for predicting metal forming simulation outputs. Secondly,considering the ANN results, a genetic algorithm will be implemented in order to optimize ametal forming process example.
Subject: Ciências Tecnológicas
Technological sciences
URI: https://repositorio-aberto.up.pt/handle/10216/98237
Source: Mechanics and materials in design
Document Type: Artigo em Livro de Atas de Conferência Internacional
Rights: restrictedAccess
Appears in Collections:FEUP - Artigo em Livro de Atas de Conferência Internacional

Files in This Item:
File Description SizeFormat 
55838.pdf
  Restricted Access
Artificial Neural Networks and Metal Forming Optimization Using Genetic Algorithms, artigo completo em CD18.62 kBAdobe PDF    Request a copy from the Author(s)


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.