Modelling of the superplastic deformation of the near-a titanium alloy (Ti-2.5AL-1.8MN) using arrhenius-type constitutive model and artificial neural network

Ahmed Mosleh, Anastasia Mikhaylovskaya, Anton Kotov, Theo Pourcelot, Sergey Aksenov, James Kwame, Vladimir Portnoy

Research output: Contribution to journalArticle

18 Citations (Scopus)

Abstract

The paper focuses on developing constitutive models for superplastic deformation behaviour of near-α titanium alloy (Ti-2.5Al-1.8Mn) at elevated temperatures in a range from 840 to 890 °C and in a strain rate range from 2 × 10−4 to 8 × 10−4 s−1. Stress–strain experimental tensile tests data were used to develop the mathematical models. Both, hyperbolic sine Arrhenius-type constitutive model and artificial neural-network model were constructed. A comparative study on the competence of the developed models to predict the superplastic deformation behaviour of this alloy was made. The fitting results suggest that the artificial neural-network model has higher accuracy and is more efficient in fitting the superplastic deformation flow behaviour of near-αTitanium alloy (Ti-2.5Al-1.8Mn) at superplastic forming than the Arrhenius-type constitutive model. However, the tested results revealed that the error for the artificial neural-network is higher than the case of Arrhenius-type constitutive model for predicting the unmodelled conditions.

LanguageEnglish
Article number568
Number of pages15
JournalMetals
Volume7
Issue number12
DOIs
Publication statusPublished - 15 Dec 2017

Fingerprint

Superplastic deformation
titanium alloys
Constitutive models
Titanium alloys
Neural networks
Strain rate
superplastic forming
Mathematical models
tensile tests
strain rate
mathematical models
Temperature

Keywords

  • activation energy
  • arrhenius-type constitutive equation
  • artificial neural network
  • constitutive modelling
  • superplasticity
  • titanium alloy

Cite this

Mosleh, Ahmed ; Mikhaylovskaya, Anastasia ; Kotov, Anton ; Pourcelot, Theo ; Aksenov, Sergey ; Kwame, James ; Portnoy, Vladimir. / Modelling of the superplastic deformation of the near-a titanium alloy (Ti-2.5AL-1.8MN) using arrhenius-type constitutive model and artificial neural network. In: Metals. 2017 ; Vol. 7, No. 12.
@article{a141af9eb68c435ea1e0ebd36e4c3527,
title = "Modelling of the superplastic deformation of the near-a titanium alloy (Ti-2.5AL-1.8MN) using arrhenius-type constitutive model and artificial neural network",
abstract = "The paper focuses on developing constitutive models for superplastic deformation behaviour of near-α titanium alloy (Ti-2.5Al-1.8Mn) at elevated temperatures in a range from 840 to 890 °C and in a strain rate range from 2 × 10−4 to 8 × 10−4 s−1. Stress–strain experimental tensile tests data were used to develop the mathematical models. Both, hyperbolic sine Arrhenius-type constitutive model and artificial neural-network model were constructed. A comparative study on the competence of the developed models to predict the superplastic deformation behaviour of this alloy was made. The fitting results suggest that the artificial neural-network model has higher accuracy and is more efficient in fitting the superplastic deformation flow behaviour of near-αTitanium alloy (Ti-2.5Al-1.8Mn) at superplastic forming than the Arrhenius-type constitutive model. However, the tested results revealed that the error for the artificial neural-network is higher than the case of Arrhenius-type constitutive model for predicting the unmodelled conditions.",
keywords = "activation energy, arrhenius-type constitutive equation, artificial neural network, constitutive modelling, superplasticity, titanium alloy",
author = "Ahmed Mosleh and Anastasia Mikhaylovskaya and Anton Kotov and Theo Pourcelot and Sergey Aksenov and James Kwame and Vladimir Portnoy",
year = "2017",
month = "12",
day = "15",
doi = "10.3390/met7120568",
language = "English",
volume = "7",
journal = "Synthetic Metals",
issn = "0379-6779",
number = "12",

}

Modelling of the superplastic deformation of the near-a titanium alloy (Ti-2.5AL-1.8MN) using arrhenius-type constitutive model and artificial neural network. / Mosleh, Ahmed; Mikhaylovskaya, Anastasia; Kotov, Anton; Pourcelot, Theo; Aksenov, Sergey; Kwame, James; Portnoy, Vladimir.

In: Metals, Vol. 7, No. 12, 568, 15.12.2017.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Modelling of the superplastic deformation of the near-a titanium alloy (Ti-2.5AL-1.8MN) using arrhenius-type constitutive model and artificial neural network

AU - Mosleh, Ahmed

AU - Mikhaylovskaya, Anastasia

AU - Kotov, Anton

AU - Pourcelot, Theo

AU - Aksenov, Sergey

AU - Kwame, James

AU - Portnoy, Vladimir

PY - 2017/12/15

Y1 - 2017/12/15

N2 - The paper focuses on developing constitutive models for superplastic deformation behaviour of near-α titanium alloy (Ti-2.5Al-1.8Mn) at elevated temperatures in a range from 840 to 890 °C and in a strain rate range from 2 × 10−4 to 8 × 10−4 s−1. Stress–strain experimental tensile tests data were used to develop the mathematical models. Both, hyperbolic sine Arrhenius-type constitutive model and artificial neural-network model were constructed. A comparative study on the competence of the developed models to predict the superplastic deformation behaviour of this alloy was made. The fitting results suggest that the artificial neural-network model has higher accuracy and is more efficient in fitting the superplastic deformation flow behaviour of near-αTitanium alloy (Ti-2.5Al-1.8Mn) at superplastic forming than the Arrhenius-type constitutive model. However, the tested results revealed that the error for the artificial neural-network is higher than the case of Arrhenius-type constitutive model for predicting the unmodelled conditions.

AB - The paper focuses on developing constitutive models for superplastic deformation behaviour of near-α titanium alloy (Ti-2.5Al-1.8Mn) at elevated temperatures in a range from 840 to 890 °C and in a strain rate range from 2 × 10−4 to 8 × 10−4 s−1. Stress–strain experimental tensile tests data were used to develop the mathematical models. Both, hyperbolic sine Arrhenius-type constitutive model and artificial neural-network model were constructed. A comparative study on the competence of the developed models to predict the superplastic deformation behaviour of this alloy was made. The fitting results suggest that the artificial neural-network model has higher accuracy and is more efficient in fitting the superplastic deformation flow behaviour of near-αTitanium alloy (Ti-2.5Al-1.8Mn) at superplastic forming than the Arrhenius-type constitutive model. However, the tested results revealed that the error for the artificial neural-network is higher than the case of Arrhenius-type constitutive model for predicting the unmodelled conditions.

KW - activation energy

KW - arrhenius-type constitutive equation

KW - artificial neural network

KW - constitutive modelling

KW - superplasticity

KW - titanium alloy

UR - http://www.scopus.com/inward/record.url?scp=85038438509&partnerID=8YFLogxK

U2 - 10.3390/met7120568

DO - 10.3390/met7120568

M3 - Article

VL - 7

JO - Synthetic Metals

T2 - Synthetic Metals

JF - Synthetic Metals

SN - 0379-6779

IS - 12

M1 - 568

ER -