Modeling of correlation between heat treatment and mechanical properties of Ti-6Al-4V alloy using feed forward back propagation neural network

Junaidi Syarif, Yan Pratama Detak, Rizauddin Ramli

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

A model for predicting mechanical properties of Ti-6Al-4V alloy has been developed and the Feed Forward Back Propagation (FFBP) as one type of algorithm of the Artificial Neural Network has been applied as the prediction system. Hardness, ultimate tensile strength (UTS), yield strength (YS) and elongation that are basic mechanical properties of Ti-6AL-4V alloy are predicted as a function of heat treatment process. Other tensile testing parameter, i.e. strain rate, is also considered in the model because increase of strain rate will increase UTS and YS, but will decrease elongation. Since the FFBP is a supervised system, it requires a lot of input and output data pairs for training process. The data are acquired from literatures and preprocessed before training. Performance of the model are evaluated by the Normalized Root Mean Square Error (NRMSE) and the Coefficient Correlation (R). The NRMSE and the R values of both training and validation parts show almost excellent values. Therefore, the model using the FFBP is appropriate to predict the mechanical properties of Ti-6Al-4V alloy.

Original languageEnglish
Pages (from-to)1689-1694
Number of pages6
JournalISIJ International
Volume50
Issue number11
DOIs
Publication statusPublished - 2010

Fingerprint

Backpropagation
Heat treatment
Neural networks
Mechanical properties
Mean square error
Yield stress
Strain rate
Elongation
Tensile strength
Tensile testing
Hardness
titanium alloy (TiAl6V4)

Keywords

  • Feed forward backpropagation neural network
  • Mechanical properties
  • Prediction system
  • Themal and mechanical treatment
  • Ti-6Al-4V alloy

ASJC Scopus subject areas

  • Mechanical Engineering
  • Mechanics of Materials
  • Materials Chemistry
  • Metals and Alloys

Cite this

Modeling of correlation between heat treatment and mechanical properties of Ti-6Al-4V alloy using feed forward back propagation neural network. / Syarif, Junaidi; Detak, Yan Pratama; Ramli, Rizauddin.

In: ISIJ International, Vol. 50, No. 11, 2010, p. 1689-1694.

Research output: Contribution to journalArticle

@article{b9e6249cca204168997461eaf28f43c3,
title = "Modeling of correlation between heat treatment and mechanical properties of Ti-6Al-4V alloy using feed forward back propagation neural network",
abstract = "A model for predicting mechanical properties of Ti-6Al-4V alloy has been developed and the Feed Forward Back Propagation (FFBP) as one type of algorithm of the Artificial Neural Network has been applied as the prediction system. Hardness, ultimate tensile strength (UTS), yield strength (YS) and elongation that are basic mechanical properties of Ti-6AL-4V alloy are predicted as a function of heat treatment process. Other tensile testing parameter, i.e. strain rate, is also considered in the model because increase of strain rate will increase UTS and YS, but will decrease elongation. Since the FFBP is a supervised system, it requires a lot of input and output data pairs for training process. The data are acquired from literatures and preprocessed before training. Performance of the model are evaluated by the Normalized Root Mean Square Error (NRMSE) and the Coefficient Correlation (R). The NRMSE and the R values of both training and validation parts show almost excellent values. Therefore, the model using the FFBP is appropriate to predict the mechanical properties of Ti-6Al-4V alloy.",
keywords = "Feed forward backpropagation neural network, Mechanical properties, Prediction system, Themal and mechanical treatment, Ti-6Al-4V alloy",
author = "Junaidi Syarif and Detak, {Yan Pratama} and Rizauddin Ramli",
year = "2010",
doi = "10.2355/isijinternational.50.1689",
language = "English",
volume = "50",
pages = "1689--1694",
journal = "ISIJ International",
issn = "0915-1559",
publisher = "Iron and Steel Institute of Japan",
number = "11",

}

TY - JOUR

T1 - Modeling of correlation between heat treatment and mechanical properties of Ti-6Al-4V alloy using feed forward back propagation neural network

AU - Syarif, Junaidi

AU - Detak, Yan Pratama

AU - Ramli, Rizauddin

PY - 2010

Y1 - 2010

N2 - A model for predicting mechanical properties of Ti-6Al-4V alloy has been developed and the Feed Forward Back Propagation (FFBP) as one type of algorithm of the Artificial Neural Network has been applied as the prediction system. Hardness, ultimate tensile strength (UTS), yield strength (YS) and elongation that are basic mechanical properties of Ti-6AL-4V alloy are predicted as a function of heat treatment process. Other tensile testing parameter, i.e. strain rate, is also considered in the model because increase of strain rate will increase UTS and YS, but will decrease elongation. Since the FFBP is a supervised system, it requires a lot of input and output data pairs for training process. The data are acquired from literatures and preprocessed before training. Performance of the model are evaluated by the Normalized Root Mean Square Error (NRMSE) and the Coefficient Correlation (R). The NRMSE and the R values of both training and validation parts show almost excellent values. Therefore, the model using the FFBP is appropriate to predict the mechanical properties of Ti-6Al-4V alloy.

AB - A model for predicting mechanical properties of Ti-6Al-4V alloy has been developed and the Feed Forward Back Propagation (FFBP) as one type of algorithm of the Artificial Neural Network has been applied as the prediction system. Hardness, ultimate tensile strength (UTS), yield strength (YS) and elongation that are basic mechanical properties of Ti-6AL-4V alloy are predicted as a function of heat treatment process. Other tensile testing parameter, i.e. strain rate, is also considered in the model because increase of strain rate will increase UTS and YS, but will decrease elongation. Since the FFBP is a supervised system, it requires a lot of input and output data pairs for training process. The data are acquired from literatures and preprocessed before training. Performance of the model are evaluated by the Normalized Root Mean Square Error (NRMSE) and the Coefficient Correlation (R). The NRMSE and the R values of both training and validation parts show almost excellent values. Therefore, the model using the FFBP is appropriate to predict the mechanical properties of Ti-6Al-4V alloy.

KW - Feed forward backpropagation neural network

KW - Mechanical properties

KW - Prediction system

KW - Themal and mechanical treatment

KW - Ti-6Al-4V alloy

UR - http://www.scopus.com/inward/record.url?scp=79551577262&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79551577262&partnerID=8YFLogxK

U2 - 10.2355/isijinternational.50.1689

DO - 10.2355/isijinternational.50.1689

M3 - Article

AN - SCOPUS:79551577262

VL - 50

SP - 1689

EP - 1694

JO - ISIJ International

JF - ISIJ International

SN - 0915-1559

IS - 11

ER -