Journal of Materials Science

, Volume 43, Issue 16, pp 5508–5515 | Cite as

Prediction of metadynamic softening in a multi-pass hot deformed low alloy steel using artificial neural network

  • Y. C. Lin
  • Xiaoling Fang
  • Y. P. Wang


The metadynamic softening behaviors in 42CrMo steel were investigated by isothermal interrupted hot compression tests. Based on the experimental results, an efficient artificial neural network (ANN) model was developed to predict the flow stress and metadynamic softening fractions. The effects of deformation parameters on metadynamic softening behaviors in the hot deformed 42CrMo steel have been investigated by the experimental and predicted results from the developed ANN model. Results show that the effects of deformation parameters, such as strain rate and deformation temperature, on the softening fractions of metadynamic recrystallization are significant. However, the strain (beyond the peak strain) has little influence. A very good correlation between experimental and predicted results indicates that the excellent capability of the developed ANN model to predict the flow stress level and metadynamic softening, the metadynamic recrystallization behaviors were well evidenced.


Artificial Neural Network Flow Stress Root Mean Square Artificial Neural Network Model Dynamic Recrystallization 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.



This work was supported by 973 Program (grant no. 2006CB705401), China Postdoctoral Science Foundation (grant no. 20070410302), the Postdoctoral Science Foundation of Central South University.


  1. 1.
    Salehi AR, Serajzadeh S, Taheri AK (2006) J Mater Sci 41:1917. doi: 10.1007/s10853-006-4486-6 CrossRefGoogle Scholar
  2. 2.
    Roy RK, Kar S, Das K, Das S (2006) J Mater Sci 41:1039. doi: 10.1007/s10853-005-2226-y CrossRefGoogle Scholar
  3. 3.
    Elwazri AM, Essadiqi E, Yue S (2004) ISIJ Int 44:744. doi: 10.2355/isijinternational.44.744 CrossRefGoogle Scholar
  4. 4.
    Fernández AI, Uranga P, López B, Rodriguez-Ibabe JM (2000) ISIJ Int 40:893. doi: 10.2355/isijinternational.40.893 CrossRefGoogle Scholar
  5. 5.
    Di Schino A, Kenny JM, Abbruzzese G (2002) J Mater Sci 37:5291. doi: 10.1023/A:1021068806598 CrossRefGoogle Scholar
  6. 6.
    Morris DG, Gutierrez-Urrutia I, Muñoz-Morris MA (2007) J Mater Sci 42:1439. doi: 10.1007/s10853-006-0564-z CrossRefGoogle Scholar
  7. 7.
    Lin YC, Chen MS, Zhong J (2008) Mater Lett 62:2136. doi: 10.1016/j.matlet.2007.11.033 CrossRefGoogle Scholar
  8. 8.
    Lin YC, Chen MS, Zhong J (2008) Mech Res Commun 35:142. doi: 10.1016/j.mechrescom.2007.10.002 CrossRefGoogle Scholar
  9. 9.
    Lin YC, Chen MS, Zhong J (2008) Comput Mater Sci 42:470. doi: 10.1016/j.commatsci.2007.08.011 CrossRefGoogle Scholar
  10. 10.
    Rao KP, Prasad YKDV, Hawbolt EB (1998) J Mater Process Technol 77:166. doi: 10.1016/S0924-0136(97)00414-7 CrossRefGoogle Scholar
  11. 11.
    Poliak EI, Jonas JJ (2004) ISIJ Int 44:1874. doi: 10.2355/isijinternational.44.1874 CrossRefGoogle Scholar
  12. 12.
    Serajzadeh S (2008) Mater Sci Eng A 472:140. doi: 10.1016/j.msea.2007.03.037 CrossRefGoogle Scholar
  13. 13.
    Capdevila C, Garcia-Mateo C, Caballero FG, García de Andrés C (2006) Comput Mater Sci 38:192. doi: 10.1016/j.commatsci.2006.02.005 CrossRefGoogle Scholar
  14. 14.
    Perzyk M, Kochanski AW (2001) J Mater Process Technol 109:305. doi: 10.1016/S0924-0136(00)00822-0 CrossRefGoogle Scholar
  15. 15.
    Altinkok N, Koker R (2005) J Mater Sci 40:1767. doi: 10.1007/s10853-005-0689-5 CrossRefGoogle Scholar
  16. 16.
    Wang J, Van Der Wolk PJ, Van Der Zwaag S (2000) J Mater Sci 35:4393. doi: 10.1023/A:1004865209116 CrossRefGoogle Scholar
  17. 17.
    Mandal S, Sivaprasad PV, Dube RK (2007) J Mater Sci 42:2724. doi: 10.1007/s10853-006-1275-1 CrossRefGoogle Scholar
  18. 18.
    Kalaichelvi V, Sivakumar D, Karthikeyan R, Palanikumar K (2008) Mater Des. doi: 10.1016/j.matdes.2008.06.022.
  19. 19.
    Garcia-Mateo C, Capdevila C, Caballero FG, García de Andrés C (2007) J Mater Sci 42:5391. doi: 10.1007/s10853-006-0881-2 CrossRefGoogle Scholar
  20. 20.
    Lin YC, Zhang J, Zhong J (2008) Comput Mater Sci. doi: 10.1016/j.commatsci.2008.01.039
  21. 21.
    Sun YB, Indacochea JE (1988) J Mater Sci 23:2339. doi: 10.1007/BF01111885 CrossRefGoogle Scholar
  22. 22.
    Mittelstädt FG, Franco CV, Muzart J, de Souza AR, Cardoso LP (1996) J Mater Sci 31:431. doi: 10.1007/BF01139161 CrossRefGoogle Scholar
  23. 23.
    Choi IS, Nam SW, Rie KT (1985) J Mater Sci 20:2446. doi: 10.1007/BF00556073 CrossRefGoogle Scholar
  24. 24.
    Lee CK, Shih HC (2000) J Mater Sci 35:2361. doi: 10.1023/A:1004772203501 CrossRefGoogle Scholar
  25. 25.
    Lin YC, Zhang J, Zhong J (2008) Comput Mater Sci. doi: 10.1016/j.commatsci.2008.03.027
  26. 26.
    Lin YC, Zhang J, Zhong J (2008) Comput Mater Sci. doi: 10.1016/j.commatsci.2008.03.010
  27. 27.
    Bhadeshia HKDH (1999) ISIJ Int 39:966. doi: 10.2355/isijinternational.39.966 CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC 2008

Authors and Affiliations

  1. 1.Key Laboratory of Modern Complex Equipment Design and Extreme Manufacturing of the Ministry of Education, School of Mechanical and Electrical EngineeringCentral South UniversityChangshaChina
  2. 2.Department of Chemical and Petroleum EngineeringKaramay Vocational & Technical CollegeXinjiangChina
  3. 3.School of Chemical EngineeringInner Mongolia Polytechnic UniversityHuhhotChina

Personalised recommendations