Application of artificial neural networks in prediction tool life of PVD coated carbide when end milling of TI6aL4v alloy

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Nowadays, the application of artificial neural networks (ANN) is often utilized in solving numerous problems in machining processes. There has been evidence of the significance of a tool life prediction of coated and uncoated cutting tools. The current study aims at applying ANN in the prediction of the tool life of PVD cutting tools using low experimental data sets. It used a feed forward back propagation neural network with a Levenberg-Marquard (L-M) training algorithm is used in modeling the tool life of a PVD insert cutting tool when end milling of Ti6Al4V under dry cutting conditions. One hundred and ten (110) models were designed, trained and tested using Matlab neural network tool box. Based on the same experimental data, a regression model (RM) has been constructed employing SPSS software, and based on the mean square error of ANN and RM models, the two models were compared. The findings revealed that the ANN model resulted into minimum mean square error compared with RM model.

Original languageEnglish
Pages (from-to)179-186
Number of pages8
JournalInternational Journal of Mechanics
Volume6
Issue number3
Publication statusPublished - 2012

Fingerprint

Physical vapor deposition
carbides
Carbides
Neural networks
predictions
Cutting tools
regression analysis
Mean square error
Milling (machining)
problem solving
inserts
Backpropagation
machining
boxes
Machining
education
computer programs

Keywords

  • Artificial neural network
  • Coated carbide
  • End milling
  • Prediction
  • Ti6al4v alloy
  • Tool life

ASJC Scopus subject areas

  • Physics and Astronomy(all)
  • Electrical and Electronic Engineering

Cite this

@article{f892aa96874e4d82bdc99a79a01b065c,
title = "Application of artificial neural networks in prediction tool life of PVD coated carbide when end milling of TI6aL4v alloy",
abstract = "Nowadays, the application of artificial neural networks (ANN) is often utilized in solving numerous problems in machining processes. There has been evidence of the significance of a tool life prediction of coated and uncoated cutting tools. The current study aims at applying ANN in the prediction of the tool life of PVD cutting tools using low experimental data sets. It used a feed forward back propagation neural network with a Levenberg-Marquard (L-M) training algorithm is used in modeling the tool life of a PVD insert cutting tool when end milling of Ti6Al4V under dry cutting conditions. One hundred and ten (110) models were designed, trained and tested using Matlab neural network tool box. Based on the same experimental data, a regression model (RM) has been constructed employing SPSS software, and based on the mean square error of ANN and RM models, the two models were compared. The findings revealed that the ANN model resulted into minimum mean square error compared with RM model.",
keywords = "Artificial neural network, Coated carbide, End milling, Prediction, Ti6al4v alloy, Tool life",
author = "Salah Al-Zubaidi and {A Ghani}, Jaharah and {Che Haron}, {Che Hassan}",
year = "2012",
language = "English",
volume = "6",
pages = "179--186",
journal = "International Journal of Mechanics",
issn = "1998-4448",
publisher = "North Atlantic University Union NAUN",
number = "3",

}

TY - JOUR

T1 - Application of artificial neural networks in prediction tool life of PVD coated carbide when end milling of TI6aL4v alloy

AU - Al-Zubaidi, Salah

AU - A Ghani, Jaharah

AU - Che Haron, Che Hassan

PY - 2012

Y1 - 2012

N2 - Nowadays, the application of artificial neural networks (ANN) is often utilized in solving numerous problems in machining processes. There has been evidence of the significance of a tool life prediction of coated and uncoated cutting tools. The current study aims at applying ANN in the prediction of the tool life of PVD cutting tools using low experimental data sets. It used a feed forward back propagation neural network with a Levenberg-Marquard (L-M) training algorithm is used in modeling the tool life of a PVD insert cutting tool when end milling of Ti6Al4V under dry cutting conditions. One hundred and ten (110) models were designed, trained and tested using Matlab neural network tool box. Based on the same experimental data, a regression model (RM) has been constructed employing SPSS software, and based on the mean square error of ANN and RM models, the two models were compared. The findings revealed that the ANN model resulted into minimum mean square error compared with RM model.

AB - Nowadays, the application of artificial neural networks (ANN) is often utilized in solving numerous problems in machining processes. There has been evidence of the significance of a tool life prediction of coated and uncoated cutting tools. The current study aims at applying ANN in the prediction of the tool life of PVD cutting tools using low experimental data sets. It used a feed forward back propagation neural network with a Levenberg-Marquard (L-M) training algorithm is used in modeling the tool life of a PVD insert cutting tool when end milling of Ti6Al4V under dry cutting conditions. One hundred and ten (110) models were designed, trained and tested using Matlab neural network tool box. Based on the same experimental data, a regression model (RM) has been constructed employing SPSS software, and based on the mean square error of ANN and RM models, the two models were compared. The findings revealed that the ANN model resulted into minimum mean square error compared with RM model.

KW - Artificial neural network

KW - Coated carbide

KW - End milling

KW - Prediction

KW - Ti6al4v alloy

KW - Tool life

UR - http://www.scopus.com/inward/record.url?scp=84871351361&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84871351361&partnerID=8YFLogxK

M3 - Article

VL - 6

SP - 179

EP - 186

JO - International Journal of Mechanics

JF - International Journal of Mechanics

SN - 1998-4448

IS - 3

ER -