Prediction of hydroforming characteristics using random neural networks

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

In recent years, hydroforming has become the topic of a lot of active research. Researchers have been looking for better procedures and prediction tools to improve the quality of the product and reduce the prototyping cost. Similar to any other metal forming process, hydroforming leads to non-homogeneous plastic deformations of the workpiece. In this paper, a model is developed to predict the amount of deformation caused by hydroforming using random neural networks (RNNs). RNNs learn the behavior of a system from the provided input/output data in a manner similar to the way the human brain does. This is different from the usual connectionist neural network (NN) models which are based on simple functional analyses. Experimental data is collected and used in training as well as testing the RNNs. The RNN models have feedforward architectures and use a generalized learning algorithm in the training process. Multi-layer RNNs with as few as six neurons were used to capture the nonlinear correlations between the input and output data collected from an experimental setup. The RNN models were able to predict the center deflection, the thickness variation, as well as the deformed shape of circular plate specimens with good accuracy.

Original languageEnglish
Pages (from-to)321-330
Number of pages10
JournalJournal of Intelligent Manufacturing
Volume17
Issue number3
DOIs
Publication statusPublished - Jun 2006
Externally publishedYes

Fingerprint

Neural networks
Metal forming
Learning algorithms
Neurons
Plastic deformation
Brain
Testing
Costs

Keywords

  • Circular plate
  • Hydroforming
  • Plastic deformation
  • Random neural networks

ASJC Scopus subject areas

  • Artificial Intelligence
  • Industrial and Manufacturing Engineering

Cite this

Prediction of hydroforming characteristics using random neural networks. / Karkoub, Mansour.

In: Journal of Intelligent Manufacturing, Vol. 17, No. 3, 06.2006, p. 321-330.

Research output: Contribution to journalArticle

@article{9a103f97cbb9435891ded82a90b98744,
title = "Prediction of hydroforming characteristics using random neural networks",
abstract = "In recent years, hydroforming has become the topic of a lot of active research. Researchers have been looking for better procedures and prediction tools to improve the quality of the product and reduce the prototyping cost. Similar to any other metal forming process, hydroforming leads to non-homogeneous plastic deformations of the workpiece. In this paper, a model is developed to predict the amount of deformation caused by hydroforming using random neural networks (RNNs). RNNs learn the behavior of a system from the provided input/output data in a manner similar to the way the human brain does. This is different from the usual connectionist neural network (NN) models which are based on simple functional analyses. Experimental data is collected and used in training as well as testing the RNNs. The RNN models have feedforward architectures and use a generalized learning algorithm in the training process. Multi-layer RNNs with as few as six neurons were used to capture the nonlinear correlations between the input and output data collected from an experimental setup. The RNN models were able to predict the center deflection, the thickness variation, as well as the deformed shape of circular plate specimens with good accuracy.",
keywords = "Circular plate, Hydroforming, Plastic deformation, Random neural networks",
author = "Mansour Karkoub",
year = "2006",
month = "6",
doi = "10.1007/s10845-005-0002-0",
language = "English",
volume = "17",
pages = "321--330",
journal = "Journal of Intelligent Manufacturing",
issn = "0956-5515",
publisher = "Springer Netherlands",
number = "3",

}

TY - JOUR

T1 - Prediction of hydroforming characteristics using random neural networks

AU - Karkoub, Mansour

PY - 2006/6

Y1 - 2006/6

N2 - In recent years, hydroforming has become the topic of a lot of active research. Researchers have been looking for better procedures and prediction tools to improve the quality of the product and reduce the prototyping cost. Similar to any other metal forming process, hydroforming leads to non-homogeneous plastic deformations of the workpiece. In this paper, a model is developed to predict the amount of deformation caused by hydroforming using random neural networks (RNNs). RNNs learn the behavior of a system from the provided input/output data in a manner similar to the way the human brain does. This is different from the usual connectionist neural network (NN) models which are based on simple functional analyses. Experimental data is collected and used in training as well as testing the RNNs. The RNN models have feedforward architectures and use a generalized learning algorithm in the training process. Multi-layer RNNs with as few as six neurons were used to capture the nonlinear correlations between the input and output data collected from an experimental setup. The RNN models were able to predict the center deflection, the thickness variation, as well as the deformed shape of circular plate specimens with good accuracy.

AB - In recent years, hydroforming has become the topic of a lot of active research. Researchers have been looking for better procedures and prediction tools to improve the quality of the product and reduce the prototyping cost. Similar to any other metal forming process, hydroforming leads to non-homogeneous plastic deformations of the workpiece. In this paper, a model is developed to predict the amount of deformation caused by hydroforming using random neural networks (RNNs). RNNs learn the behavior of a system from the provided input/output data in a manner similar to the way the human brain does. This is different from the usual connectionist neural network (NN) models which are based on simple functional analyses. Experimental data is collected and used in training as well as testing the RNNs. The RNN models have feedforward architectures and use a generalized learning algorithm in the training process. Multi-layer RNNs with as few as six neurons were used to capture the nonlinear correlations between the input and output data collected from an experimental setup. The RNN models were able to predict the center deflection, the thickness variation, as well as the deformed shape of circular plate specimens with good accuracy.

KW - Circular plate

KW - Hydroforming

KW - Plastic deformation

KW - Random neural networks

UR - http://www.scopus.com/inward/record.url?scp=33646400549&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33646400549&partnerID=8YFLogxK

U2 - 10.1007/s10845-005-0002-0

DO - 10.1007/s10845-005-0002-0

M3 - Article

VL - 17

SP - 321

EP - 330

JO - Journal of Intelligent Manufacturing

JF - Journal of Intelligent Manufacturing

SN - 0956-5515

IS - 3

ER -