Investigation on the Processing-Properties of Hot Deformed TA15 Titanium Alloy via Support Vector Regression


Article Preview

According to an experimental dataset on the tensile strength and elongation of TA15 titanium alloy under different hot deformation process parameters including temperature, strain, strain rate and cooling condition, support vector regression (SVR) combined with particle swarm optimization (PSO) for its parameter optimization, is proposed to establish a model for prediction of the tensile strength and elongation of hot deformed TA15 titanium alloy. For tensile strength, the mean absolute percentage error (MAPE) achieved by SVR is 0.65% and 0.68% for the training and test set, respectively. At the same time, the MAPE for elongation achieved by SVR is 1.51% and 3.36% for the training and test set, respectively. The MAPEs for both tensile strength and elongation achieved by SVR are much smaller than those of BPNN by using identical training and test samples. Accordingly, the established SVR model was adopted to illustrate the relationships among tensile strength, elongation, and the process parameters. From the 3D surface of tensile strength vs. temperature and strain rate, it is found that to reach a higher tensile strength, a strain rate lower than 0.01s-1 is required, and a lower strain will be helpful for achieving the maximum elongation. These suggest that SVR as a novel approach has a theoretical significance and potential practical value in fabrication of TA15 titanium alloy with desired properties.



Edited by:

Enhou Han, Guanghong Lu and Xiaolin Shu




J.F. Pei et al., "Investigation on the Processing-Properties of Hot Deformed TA15 Titanium Alloy via Support Vector Regression", Materials Science Forum, Vol. 689, pp. 134-143, 2011

Online since:

June 2011




[1] Q. Hong and Z.Q. Zhang: J. Aeronautical Mater. Vol. 21(2001), p.10.

[2] G.S. Wang: Rare Met. Mater. Vol. 19 (1995), p.353.

[3] W.C. Xu, D.B. Shan and C.F. Li: J. Aeronautical Mater. Vol. 8 (2005), p.10.

[4] Z.C. Sun, H. Yang and C.W. Shen: Forging & Stamping Technol. Vol. 2 (2008), p.110.

[5] C.W. Shen, H. Yang, Z.C. Sun and G.H. Cui: J. Plast. Eng. Vol. 14 (2007), p.101.

[6] W.C. Xu, D.B. Shan and Y. Lv: Ordnance Mater. Sci. Eng. Vol. 30 (2007), p.33.

[7] S. Malinov and W. Sha: Mater. Sci. Eng. Vol. 365 (2004), p.202.

[8] S. Malinov, W. Sha and J.J. McKeown: Comput. Mater. Sci. Vol. 21(2001), p.375.

[9] Y. Yue, J.C. Zhu, Y. Liu, Y. Wang and X.W. Yang: Rare Met. Mater. Eng. Vol. 38(2009), p.1811.

[10] V. Vapnik: The natural of statistical learning theory (Springer, New York 1995).

[11] C.Z. Cai, X.J. Zhu, Y.F. Wen, J.F. Pei and G.L. Wang: J. Supercond. Novel Magn. Vol. 23 (2010) p.737.

[12] D.O. Whiteson and N.A. Naumann: Neurocomputing Vol. 55 (2003) p.251.

[13] Z. Yuan and B.X. Huang: Proteins Vol. 57 (2004), p.558.

[14] C.Z. Cai, W.L. Wang, L.Z. Sun and Y.Z. Chen: Math. Biosci. Vol. 185(2003), p.111.

[15] C.Z. Cai, L.Y. Han, Z.L. Ji, X. Chen and Y.Z. Chen: Nucleic Acids Res. Vol. 31(2003), p.3692.

[16] C.Z. Cai, W.L. Wang and Y.Z. Chen: Int. J. Mod. Phys. C Vol. 14 (2003), p.575.

[17] J. Song and K. Burrage: BMC Bioinformatics Vol. 7 (2006), p.425.

[18] Y.F. Wen, C.Z. Cai, X.H. Liu, J.F. Pei, X.J. Zhu and T.T. Xiao: Corros. Sci. Vol. 51 (2009), p.349.

[19] J. Kennedy and R. Eberhart: Proc. IEEE Int. Conf. Neural Networks Vol. 4 (1995), p. (1941).

[20] G. Hu, J.W. Li, G. Fu, Z.Y. Wang: Aerospace Manuf. Technol. Vol. 4 (2005), p.1.