Artificial neural network modeling of phase volume fraction of Ti alloy under isothermal and non-isothermal hot forging conditions

  • J. H. Kim
  • N. S. Reddy
  • J. T. Yeom
  • C. S. Lee
  • N. K. Park
Article

Abstract

An artificial neural network (ANN) model was applied to simulate the phase volume fraction of titanium alloy under isothermal and non-isothermal hot forging condition. For isothermal hot forging process, equilibrium phase volume fraction at specific temperature was predicted. For this purpose, chemical composition of six alloy elements (i.e. Al, V, Fe, O, N, and C) and specimen temperature were chosen as input parameter. After that, phase volume fraction under non-isothermal condition was simulated again. Input parameters consist of initial phase volume fraction, equilibrium phase volume fraction at specific temperature, cooling rate, and temperature. The ANN model was coupled with the FE simulation in order to predict the variation of phase volume fraction during non-isothermal forging. Ti−6A1−4V alloy was forged under isothermal and non-isothermal condition and then, the resulting microstructures were compared with simulated data.

Keywords

Artificial neural network Ti alloy Phase volume fraction Forging 

References

  1. [1]
    E. W. Collings, The Physical Metallurgy of Titanium Alloys, American Society for Metals, Metals Park, OH 44073, (1984).Google Scholar
  2. [2]
    G. Terlinde, and G. Fischer, Beta titanium alloys, in Christoph Leyens and Manfred Peters (eds), Titanium and Titanium Alloys, WILEY VCH GmbH & Co. KGaA, (2003) 37–57.Google Scholar
  3. [3]
    R. A. Wood, Titanium Alloys Handbook, Metals and Ceramics Information Center, Battelle, (1972).Google Scholar
  4. [4]
    E. J. Dayhoff, Neural Network Architecture: An Introduction, VNR Press, New York, (1990).Google Scholar
  5. [5]
    J. M. Zurada, Introduction to Artificial Neural Systems, PWS Publishing Company, Boston, (1992).Google Scholar
  6. [6]
    R. Castro, L. Seraphin,Mem. Sci. Rev. Metall. 63 (1966) 1025–1058.Google Scholar
  7. [7]
    Y. T. Lee, G. Welsch, Young’s modulus and damping of Ti-6A1-4V alloy as a function of heat treatment and oxygen concentration,Mater. Sci. Eng. A. 128 (1990) 77–89.CrossRefGoogle Scholar
  8. [8]
    M. Jain, M.C. Chaturvedi, N.L. Richards, N.C. Goel, Microstructural characteristics in a phase during superplastic deformation of Ti-6A1-4V,Mater. Sci. Eng. A. 145 (1991) 205–214.CrossRefGoogle Scholar
  9. [9]
    S. Malinov, P. Markovsky, W. Sha, and Z. Guo, Resistivity study and computer modelling of the isothermal transformation kinetics of Ti-6A1-4V and Ti-6Al-2Sn-4Zr-2Mo-0.08Si alloys,Journal of Alloys and Compounds. 314 (2001) 181–192.CrossRefGoogle Scholar
  10. [10]
    N.S. Reddy, C.S. Lee, J.H. Kim, S.L. Semiatin, Determination of the beta-approach curve and beta-transus temperature for titanium alloys using sensitivity analysis of a trained neural network,Mater. Sci. Eng. A. 434 (2006) 218–226.CrossRefGoogle Scholar
  11. [11]
    M.L. Meier, D.R. Lesuer, A.K. Mukherjee, The effects of the α/β phase proportion on the superplasticity of Ti-6A1-4V and iron-modified Ti-6A1-4V,Mater. Sci. Eng. A. 154 (1992), 165–173.CrossRefGoogle Scholar
  12. [12]
    S.L. Semiatin, F. Montheillet, G. Shen, J.J. Jonas, Self-consistent modeling of the flow behavior of wrought alpha/beta titanium alloys under isothermal and nonisothermal hot-working conditions,Metall. Mater Trans. A. 33 (2002) 2719–2727.CrossRefGoogle Scholar
  13. [13]
    R. Boyer, G. Welsch, E.W. Collings, Material Properties Handbook: Titanium Alloys, ASM International, Materials Park, OH 44073, (1994).Google Scholar

Copyright information

© The Korean Society of Mechanical Engineers (KSME) 2007

Authors and Affiliations

  • J. H. Kim
    • 1
  • N. S. Reddy
    • 2
  • J. T. Yeom
    • 1
  • C. S. Lee
    • 2
  • N. K. Park
    • 1
  1. 1.Korea Institute of Machinery and MaterialsChangwon-CitySouth Korea
  2. 2.Department of Materials Science and EngineeringPohang University of Science and TechnologyPohangRepublic of Korea

Personalised recommendations