Prediction of powder injection molding process parameters using artificial neural networks

Javad Rajabi, Norhamidi Muhamad, Maryam Rajabi, Jamal Rajabi

Research output: Contribution to journalArticle

Abstract

The parameters of Powder Injection Molding (PIM) process were modeled by artificial neural networks (ANNs). The feed-forward multilayer perceptron was utilized and trained by back-propagation algorithm. Particle size, particle morphology, debinding time, and sintering temperature were taken into account and regarded as inputs of the ANN model. The outputs included relative density, wax loss, shrinkage, and hardness. The results obtained using the ANN model were in good agreement with the experimental data. In fact, they displayed an average R-value of 0.95 versus the experimental values. The optimum architecture of ANN was 7-4-1, in which the network was trained with Levenberg-Marquardt training algorithm. Thus, the ANN model can be used to evaluate, calculate, and forecast PIM process parameters.

Original languageEnglish
Pages (from-to)183-186
Number of pages4
JournalJurnal Teknologi (Sciences and Engineering)
Volume59
Issue numberSUPPL.2
Publication statusPublished - 2012

Fingerprint

Injection molding
Neural networks
Powders
Backpropagation algorithms
Waxes
Multilayer neural networks
Sintering
Hardness
Particle size
Temperature

Keywords

  • Artificial neural network
  • Back propagation algorithm
  • Debinding
  • Powder injection molding
  • Sintering

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Prediction of powder injection molding process parameters using artificial neural networks. / Rajabi, Javad; Muhamad, Norhamidi; Rajabi, Maryam; Rajabi, Jamal.

In: Jurnal Teknologi (Sciences and Engineering), Vol. 59, No. SUPPL.2, 2012, p. 183-186.

Research output: Contribution to journalArticle

@article{aeb99666721c4cd9b646e0ce81e39a82,
title = "Prediction of powder injection molding process parameters using artificial neural networks",
abstract = "The parameters of Powder Injection Molding (PIM) process were modeled by artificial neural networks (ANNs). The feed-forward multilayer perceptron was utilized and trained by back-propagation algorithm. Particle size, particle morphology, debinding time, and sintering temperature were taken into account and regarded as inputs of the ANN model. The outputs included relative density, wax loss, shrinkage, and hardness. The results obtained using the ANN model were in good agreement with the experimental data. In fact, they displayed an average R-value of 0.95 versus the experimental values. The optimum architecture of ANN was 7-4-1, in which the network was trained with Levenberg-Marquardt training algorithm. Thus, the ANN model can be used to evaluate, calculate, and forecast PIM process parameters.",
keywords = "Artificial neural network, Back propagation algorithm, Debinding, Powder injection molding, Sintering",
author = "Javad Rajabi and Norhamidi Muhamad and Maryam Rajabi and Jamal Rajabi",
year = "2012",
language = "English",
volume = "59",
pages = "183--186",
journal = "Jurnal Teknologi",
issn = "0127-9696",
publisher = "Penerbit Universiti Teknologi Malaysia",
number = "SUPPL.2",

}

TY - JOUR

T1 - Prediction of powder injection molding process parameters using artificial neural networks

AU - Rajabi, Javad

AU - Muhamad, Norhamidi

AU - Rajabi, Maryam

AU - Rajabi, Jamal

PY - 2012

Y1 - 2012

N2 - The parameters of Powder Injection Molding (PIM) process were modeled by artificial neural networks (ANNs). The feed-forward multilayer perceptron was utilized and trained by back-propagation algorithm. Particle size, particle morphology, debinding time, and sintering temperature were taken into account and regarded as inputs of the ANN model. The outputs included relative density, wax loss, shrinkage, and hardness. The results obtained using the ANN model were in good agreement with the experimental data. In fact, they displayed an average R-value of 0.95 versus the experimental values. The optimum architecture of ANN was 7-4-1, in which the network was trained with Levenberg-Marquardt training algorithm. Thus, the ANN model can be used to evaluate, calculate, and forecast PIM process parameters.

AB - The parameters of Powder Injection Molding (PIM) process were modeled by artificial neural networks (ANNs). The feed-forward multilayer perceptron was utilized and trained by back-propagation algorithm. Particle size, particle morphology, debinding time, and sintering temperature were taken into account and regarded as inputs of the ANN model. The outputs included relative density, wax loss, shrinkage, and hardness. The results obtained using the ANN model were in good agreement with the experimental data. In fact, they displayed an average R-value of 0.95 versus the experimental values. The optimum architecture of ANN was 7-4-1, in which the network was trained with Levenberg-Marquardt training algorithm. Thus, the ANN model can be used to evaluate, calculate, and forecast PIM process parameters.

KW - Artificial neural network

KW - Back propagation algorithm

KW - Debinding

KW - Powder injection molding

KW - Sintering

UR - http://www.scopus.com/inward/record.url?scp=84872691816&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84872691816&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:84872691816

VL - 59

SP - 183

EP - 186

JO - Jurnal Teknologi

JF - Jurnal Teknologi

SN - 0127-9696

IS - SUPPL.2

ER -