Prediction of tool life in end milling of Ti-6Al-4V alloy using artificial neural network and multiple regression models

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

Tool life of the cutting tools is considered as one of the factors which has effects on machining costs and the quality of machined parts. The topic of tool life prediction has been an interesting and important research topic attracting the attention of a wide number of researchers in this particular area. In terms of the suitable methods used in this research topic, it is stated that both statistical and artificial intelligence (AI) approaches can be employed to model tool life. For further justifying the capability of the ANN model in predicting tool life, the current study was based on conducting experimental work for collecting the experimental data. After carrying out the experiment, 17 data sets were collected and they were divided into two subsets; the first one for training and the second for testing. Since the data sets seemed to be lower than the number of data sets used in previous studies, we attempted to make verification of the ability of the ANN model in learning and adapting with low training and testing data. Diverse topologies accompanied with single and two hidden layers were created for modeling the tool life. For choosing the best and most effective network, the study adopted the mean square error function as criteria for the evaluation of the network selection. Thus, based on the data generated from the same experiment, a regression model (RM) was constructed employing the SPSS software. A comparison between the ANN model and RMs in terms of their accuracy was carried out and the findings revealed that the accuracy of the ANN was higher than that of the RM.

Original languageEnglish
Pages (from-to)1735-1741
Number of pages7
JournalSains Malaysiana
Volume42
Issue number12
Publication statusPublished - Dec 2013

Fingerprint

Neural networks
Testing
Cutting tools
Mean square error
Artificial intelligence
Machining
Experiments
Topology
Costs

Keywords

  • Artificial neural network
  • Prediction
  • Tool life
  • Uncoated carbide

ASJC Scopus subject areas

  • General

Cite this

Prediction of tool life in end milling of Ti-6Al-4V alloy using artificial neural network and multiple regression models. / Al-Zubaidi, Salah; A Ghani, Jaharah; Che Haron, Che Hassan.

In: Sains Malaysiana, Vol. 42, No. 12, 12.2013, p. 1735-1741.

Research output: Contribution to journalArticle

@article{e854fa54e5454b7f893440b2af14d591,
title = "Prediction of tool life in end milling of Ti-6Al-4V alloy using artificial neural network and multiple regression models",
abstract = "Tool life of the cutting tools is considered as one of the factors which has effects on machining costs and the quality of machined parts. The topic of tool life prediction has been an interesting and important research topic attracting the attention of a wide number of researchers in this particular area. In terms of the suitable methods used in this research topic, it is stated that both statistical and artificial intelligence (AI) approaches can be employed to model tool life. For further justifying the capability of the ANN model in predicting tool life, the current study was based on conducting experimental work for collecting the experimental data. After carrying out the experiment, 17 data sets were collected and they were divided into two subsets; the first one for training and the second for testing. Since the data sets seemed to be lower than the number of data sets used in previous studies, we attempted to make verification of the ability of the ANN model in learning and adapting with low training and testing data. Diverse topologies accompanied with single and two hidden layers were created for modeling the tool life. For choosing the best and most effective network, the study adopted the mean square error function as criteria for the evaluation of the network selection. Thus, based on the data generated from the same experiment, a regression model (RM) was constructed employing the SPSS software. A comparison between the ANN model and RMs in terms of their accuracy was carried out and the findings revealed that the accuracy of the ANN was higher than that of the RM.",
keywords = "Artificial neural network, Prediction, Tool life, Uncoated carbide",
author = "Salah Al-Zubaidi and {A Ghani}, Jaharah and {Che Haron}, {Che Hassan}",
year = "2013",
month = "12",
language = "English",
volume = "42",
pages = "1735--1741",
journal = "Sains Malaysiana",
issn = "0126-6039",
publisher = "Penerbit Universiti Kebangsaan Malaysia",
number = "12",

}

TY - JOUR

T1 - Prediction of tool life in end milling of Ti-6Al-4V alloy using artificial neural network and multiple regression models

AU - Al-Zubaidi, Salah

AU - A Ghani, Jaharah

AU - Che Haron, Che Hassan

PY - 2013/12

Y1 - 2013/12

N2 - Tool life of the cutting tools is considered as one of the factors which has effects on machining costs and the quality of machined parts. The topic of tool life prediction has been an interesting and important research topic attracting the attention of a wide number of researchers in this particular area. In terms of the suitable methods used in this research topic, it is stated that both statistical and artificial intelligence (AI) approaches can be employed to model tool life. For further justifying the capability of the ANN model in predicting tool life, the current study was based on conducting experimental work for collecting the experimental data. After carrying out the experiment, 17 data sets were collected and they were divided into two subsets; the first one for training and the second for testing. Since the data sets seemed to be lower than the number of data sets used in previous studies, we attempted to make verification of the ability of the ANN model in learning and adapting with low training and testing data. Diverse topologies accompanied with single and two hidden layers were created for modeling the tool life. For choosing the best and most effective network, the study adopted the mean square error function as criteria for the evaluation of the network selection. Thus, based on the data generated from the same experiment, a regression model (RM) was constructed employing the SPSS software. A comparison between the ANN model and RMs in terms of their accuracy was carried out and the findings revealed that the accuracy of the ANN was higher than that of the RM.

AB - Tool life of the cutting tools is considered as one of the factors which has effects on machining costs and the quality of machined parts. The topic of tool life prediction has been an interesting and important research topic attracting the attention of a wide number of researchers in this particular area. In terms of the suitable methods used in this research topic, it is stated that both statistical and artificial intelligence (AI) approaches can be employed to model tool life. For further justifying the capability of the ANN model in predicting tool life, the current study was based on conducting experimental work for collecting the experimental data. After carrying out the experiment, 17 data sets were collected and they were divided into two subsets; the first one for training and the second for testing. Since the data sets seemed to be lower than the number of data sets used in previous studies, we attempted to make verification of the ability of the ANN model in learning and adapting with low training and testing data. Diverse topologies accompanied with single and two hidden layers were created for modeling the tool life. For choosing the best and most effective network, the study adopted the mean square error function as criteria for the evaluation of the network selection. Thus, based on the data generated from the same experiment, a regression model (RM) was constructed employing the SPSS software. A comparison between the ANN model and RMs in terms of their accuracy was carried out and the findings revealed that the accuracy of the ANN was higher than that of the RM.

KW - Artificial neural network

KW - Prediction

KW - Tool life

KW - Uncoated carbide

UR - http://www.scopus.com/inward/record.url?scp=84892178210&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84892178210&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:84892178210

VL - 42

SP - 1735

EP - 1741

JO - Sains Malaysiana

JF - Sains Malaysiana

SN - 0126-6039

IS - 12

ER -