Incorporating feedforward neural network within finite element analysis for L-bending springback prediction

Research output: Contribution to journalArticle

16 Citations (Scopus)

Abstract

The use of the latest nonlinear recovery in finite element (FE) analysis for obtaining an accurate springback prediction has become more complicated and requires complex computational programming in order to develop a constitutive model. Thus, the purpose of this paper is to apply an alternative method that is capable of facilitating the modelling of nonlinear recovery with acceptable accuracy. By using the artificial neural network (ANN), the experimental results of monotonic loading, unloading, and reloading can be processed through a back propagation network that is able to detect a pattern and do a direct mapping of elastically-driven change after the plastic forming. FE analysis procedures were carried out for the springback prediction of sheet metal based on an L-bending experiment. The findings of the FE analysis show an improvement in the accuracy of the predictions when compared to the measured data.

Original languageEnglish
Pages (from-to)2604-2614
Number of pages11
JournalExpert Systems with Applications
Volume42
Issue number5
DOIs
Publication statusPublished - 1 Apr 2015

Fingerprint

Feedforward neural networks
Finite element method
Plastics forming
Recovery
Sheet metal
Constitutive models
Unloading
Backpropagation
Neural networks
Experiments

Keywords

  • Finite element
  • L-bending
  • Neural network
  • Springback prediction

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Engineering(all)

Cite this

@article{1f48ef4981f1442d90f4df020538b7d1,
title = "Incorporating feedforward neural network within finite element analysis for L-bending springback prediction",
abstract = "The use of the latest nonlinear recovery in finite element (FE) analysis for obtaining an accurate springback prediction has become more complicated and requires complex computational programming in order to develop a constitutive model. Thus, the purpose of this paper is to apply an alternative method that is capable of facilitating the modelling of nonlinear recovery with acceptable accuracy. By using the artificial neural network (ANN), the experimental results of monotonic loading, unloading, and reloading can be processed through a back propagation network that is able to detect a pattern and do a direct mapping of elastically-driven change after the plastic forming. FE analysis procedures were carried out for the springback prediction of sheet metal based on an L-bending experiment. The findings of the FE analysis show an improvement in the accuracy of the predictions when compared to the measured data.",
keywords = "Finite element, L-bending, Neural network, Springback prediction",
author = "Jamli, {M. R.} and {Mohd Ihsan}, {Ahmad Kamal Ariffin} and {Abd. Wahab}, Dzuraidah",
year = "2015",
month = "4",
day = "1",
doi = "10.1016/j.eswa.2014.11.005",
language = "English",
volume = "42",
pages = "2604--2614",
journal = "Expert Systems with Applications",
issn = "0957-4174",
publisher = "Elsevier Limited",
number = "5",

}

TY - JOUR

T1 - Incorporating feedforward neural network within finite element analysis for L-bending springback prediction

AU - Jamli, M. R.

AU - Mohd Ihsan, Ahmad Kamal Ariffin

AU - Abd. Wahab, Dzuraidah

PY - 2015/4/1

Y1 - 2015/4/1

N2 - The use of the latest nonlinear recovery in finite element (FE) analysis for obtaining an accurate springback prediction has become more complicated and requires complex computational programming in order to develop a constitutive model. Thus, the purpose of this paper is to apply an alternative method that is capable of facilitating the modelling of nonlinear recovery with acceptable accuracy. By using the artificial neural network (ANN), the experimental results of monotonic loading, unloading, and reloading can be processed through a back propagation network that is able to detect a pattern and do a direct mapping of elastically-driven change after the plastic forming. FE analysis procedures were carried out for the springback prediction of sheet metal based on an L-bending experiment. The findings of the FE analysis show an improvement in the accuracy of the predictions when compared to the measured data.

AB - The use of the latest nonlinear recovery in finite element (FE) analysis for obtaining an accurate springback prediction has become more complicated and requires complex computational programming in order to develop a constitutive model. Thus, the purpose of this paper is to apply an alternative method that is capable of facilitating the modelling of nonlinear recovery with acceptable accuracy. By using the artificial neural network (ANN), the experimental results of monotonic loading, unloading, and reloading can be processed through a back propagation network that is able to detect a pattern and do a direct mapping of elastically-driven change after the plastic forming. FE analysis procedures were carried out for the springback prediction of sheet metal based on an L-bending experiment. The findings of the FE analysis show an improvement in the accuracy of the predictions when compared to the measured data.

KW - Finite element

KW - L-bending

KW - Neural network

KW - Springback prediction

UR - http://www.scopus.com/inward/record.url?scp=84912535699&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84912535699&partnerID=8YFLogxK

U2 - 10.1016/j.eswa.2014.11.005

DO - 10.1016/j.eswa.2014.11.005

M3 - Article

AN - SCOPUS:84912535699

VL - 42

SP - 2604

EP - 2614

JO - Expert Systems with Applications

JF - Expert Systems with Applications

SN - 0957-4174

IS - 5

ER -