Modeling Microstructural Evolution During Dynamic Recrystallization of Alloy D9 Using Artificial Neural Network

Abstract

An artificial neural network (ANN) model was developed to predict the microstructural evolution of a 15Cr-15Ni-2.2Mo-Ti modified austenitic stainless steel (Alloy D9) during dynamic recrystallization (DRX). The input parameters were strain, strain rate, and temperature whereas microstructural features namely, %DRX and average grain size were the output parameters. The ANN was trained with the database obtained from various industrial scale metal-forming operations like forge hammer, hydraulic press, and rolling carried out in the temperature range 1173-1473 K to various strain levels. The performance of the model was evaluated using a wide variety of statistical indices and the predictability of the model was found to be good. The combined influence of temperature and strain on microstructural features has been simulated employing the developed model. The results were found to be consistent with the relevant fundamental metallurgical phenomena.

This is a preview of subscription content, log in to check access.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9

Notes

  1. 1.

    There were two models, one for %DRX and another for average grain size. However, in the text sometimes the word “model” is used to refer to the two models collectively.

References

  1. 1.

    R.W. Cahn and P. Haasen, Physical Metallurgy, Vol. III, 4th ed., North Holland, 1996

  2. 2.

    T. Sakai, J.J. Jonas 1984 Dynamic Recrystallization: Mechanical and Microstructural Considerations. Acta Metal. 32(2):89–209

    Article  Google Scholar 

  3. 3.

    S. Mandal, P.V. Sivaprasad, R.K. Dube 2006 Kinetics, Mechanism and Modelling of Microstructural Evolution During Thermomechanical Processing of a 15Cr-15Ni-2.2Mo-Ti Modified Austenitic Stainless Steel. J. Mater. Sci. 42:2724–2734

    Article  Google Scholar 

  4. 4.

    C.M. Sellars 1990 Modeling Microstructural Development During Hot Rolling. Mater. Sci. Technol. 15:1072

    Article  Google Scholar 

  5. 5.

    M.F. Ashby 1992 Physical Modeling of Materials Problem. Mater. Sci. Technol. 8:102

    CAS  Article  Google Scholar 

  6. 6.

    T.W. Kim, F.P.E. Dunne 1999 Modeling Heterogeneous Microstructure in Superplasticity. Proc. R. Soc. Lond. A Math. Phys. Sci. 455:719

    Article  Google Scholar 

  7. 7.

    T. Sakai, M. Ohashi, K. Chiba, J.J. Jonas 1988 Recovery and Recrystallization of Polycrystalline Nickel After Hot Working. Acta Metal. 36(7):1781–1790

    CAS  Article  Google Scholar 

  8. 8.

    W.C. Liu, J.G. Morris 2005 Effect of Initial Texture on the Recrystallization Texture of Cold Rolled AA 5182 Aluminum Alloy. Mater. Sci. Eng. A 402(1–2):215–227

    Article  Google Scholar 

  9. 9.

    S. Haykin 1999 Neural Networks: A Comprehensive Foundation. Prentice Hall, Upper Saddle River, New Jersey

    Google Scholar 

  10. 10.

    S.C. Juang, Y.S. Tarang, H.R. Lii 1998 A Comparison Between the Back-Propagation and Counter-Propagation Networks in the Modeling of the TIG Welding Process. J. Mater. Process. Technol. 75(1–3):54–62

    Article  Google Scholar 

  11. 11.

    M.S. Chun, J. Biglou, J.G. Lenard, J.G. Kim 1999 Using Neural Networks to Predict Parameters in the Hot Working of Aluminum Alloys. J. Mater. Process. Technol. 86(1–3):245–251

    Article  Google Scholar 

  12. 12.

    M. Riedmiller and H. Braun, A Direct Adaptive Method for Faster Back Propagation Learning: The RPROP Algorithm. Proceedings of International Conference in Neural Networks, San Francisco, CA, 1993

  13. 13.

    M. Riedmiller, Advanced Supervised Learning in Multi-layer Perceptrons - From Backpropagation to Adaptive Learning Algorithms, Special Issue on Neural Networks, Int. J. of Comp. Stand. Inter., 1994, 16, p 265–278

  14. 14.

    T. Tollenaere 1990 SuperSAB: Fast Adaptive Back Propagation with Good Scaling Properties, Neural Network 3(5):561–573

    Article  Google Scholar 

  15. 15.

    Y.V.R.K. Prasad and N. Ravichandran (1991) Effect of Stacking Fault Energy on the Dynamic Recrystallization During Hot Working of FCC Metals: A Study Using Processing Maps, Bull. Mater. Sci. 14:1241–1248

    CAS  Article  Google Scholar 

  16. 16.

    S. Mandal, P.V. Sivaprasad, S. Venugopal, and K.P.N. Murthy, Constitutive Flow Behaviour of Austenitic Stainless Steels Under Hot Deformation: Artificial Neural Network Modeling to Understand, Evaluate and Predict. Model. Simul. Mater. Sci. Eng., 2006, 14, p 1053

    CAS  Article  Google Scholar 

  17. 17.

    S. Venugopal, P.V. Sivaprasad, and S. Venkadesan, Effect of Annealing Temperature on Engineering Properties of Alloy D9, Unpublished Work

  18. 18.

    D. Ponge, G. Gottstein 1998 Necklace Formation During Dynamic Recrystallization: Mechanisms and Impact on Flow Behavior. Acta Mater. 46(1):69–80

    CAS  Article  Google Scholar 

  19. 19.

    E. Brunger, X. Wang, G. Gottstein 1998 Nucleation Mechanisms of Dynamic Recrystallization in Austenitic Steel Alloy 800H. Scripta Mater. 38(12):1843–1849

    CAS  Article  Google Scholar 

  20. 20.

    K. Hornik, M. Stinchcombe, H. White 1989 Multilayer Feed Forward Networks are Universal Approximations. Neural Network 2(5):359–366

    Article  Google Scholar 

  21. 21.

    J.D. Olden, D.A. Jackson 2002 Illuminating the “Black Box”: A Randomization Approach for Understanding Variable Contributions in Artificial Neural Networks. Ecol. Model. 154(1–2):135–150

    Article  Google Scholar 

  22. 22.

    M. Gevrey, I. Dimopoulos, S. Lek 2003 Review and Comparison of Methods to Study the Contribution of Variables in Artificial Neural Network Models. Ecol. Model. 160 (3):249–264

    Article  Google Scholar 

  23. 23.

    J.D. Olden, M.K. Joy, R.G. Death 2004 An Accurate Comparison of Methods for Quantifying Variable Importance In Artificial Neural Networks Using Simulated Data. Ecol. Model. 178(3–4):389–397

    Article  Google Scholar 

  24. 24.

    G.D. Garson 1991 Interpreting Neural Network Connection Weights. Artif. Intell. Expert 6(7):47–51

    Google Scholar 

  25. 25.

    A.T.C. Goh 1995 Back-Propagation Neural Networks for Modelling Complex Systems. Artif. Intell. Eng. 9:143–151

    Article  Google Scholar 

Download references

Acknowledgments

The authors would like to express their sincere thanks to Dr. S. Venugopal, Head, Metal Forming & Tribology Section and Dr. S.K. Ray, Head, Materials Technology Division for useful discussions. The authors also gratefully acknowledge Dr. Baldev Raj, Director, Indira Gandhi Centre for Atomic Research (IGCAR) for his constant encouragement throughout the course of this work.

Author information

Affiliations

Authors

Corresponding author

Correspondence to P.V. Sivaprasad.

Rights and permissions

Reprints and Permissions

About this article

Cite this article

Mandal, S., Sivaprasad, P. & Dube, R. Modeling Microstructural Evolution During Dynamic Recrystallization of Alloy D9 Using Artificial Neural Network. J. of Materi Eng and Perform 16, 672–679 (2007). https://doi.org/10.1007/s11665-007-9098-z

Download citation

Keywords

  • artificial neural network
  • austenitic stainless steel
  • dynamic recrystallization
  • grain size
  • microstructural evolution