Funct. Mater. 2022; 29 (1): 154-163.

doi:https://doi.org/10.15407/fm29.01.154

Prediction of mechanical properties of hot rolled strips based on support vector quantile regression with adaptive QLASSO

Xiao-xia He1,2, Si-yu Huang1,2, Xin Zhang1,2, Wei-gang Li3

1College of Science, Wuhan University of Science and Technology, 430065 Wuhan, China
2Hubei Province Key Laboratory of Systems Science in Metallurgical Process, Wuhan University of Science and Technology, 430065 Wuhan, China
3Engineering Research Center of Metallurgical Automation and Measurement Technology of Ministry of Education, Wuhan University of Science and Technology, 40081 Wuhan, Hubei, China

Abstract: 

The prediction of mechanical properties of hot rolled strips can be used for online dynamic control of product properties and optimal design of new steel grade. This paper proposes a prediction model of support vector quantile regression (SVQR) which combines support vector regression (SVR) with quantile regression (QR), to solve the nonlinear problems and data heterogeneity problems in modeling. First, based on the measured data collected from a hot rolling production process, the Quantile-LASSO (QLASSO) method is introduced to identify the factors affecting the tensile strength. The experimental results show that FT (reheating temperature), FET (finishing entry temperature), CT (coiling temperature), RT (roughing exit temperature), FDH (finishing delivery thickness), Si, Mn, V, Ti, NbC (niobium carbide), NbN (niobium nitride) and Cs (residual carbon) have a great influence on the tensile strength. A predictive model is then created using these influencing factors as independent variables. Compared with other models, the model proposed in this paper has better prediction accuracy, and the prediction errors of its training set and testing set are 2.42 % and 2.55 % respectively.

Keywords: 
prediction of mechanical properties, support vector machine, quantile regression, hot rolled strips.

Full text in PDF

References: 
1. W.G.Li, W.Yang, Y.I.Zhao et al., Journal of Iron and Steel Research International, 26, 230 (2019).
https://doi.org/10.1007/s42243-018-0204-2
 
2. Wei-gang Li, Lu Xie, Yun-tao Zhao et al., Journal of Iron and Steel Research International, ???? (2020).
 
3. C.Z.Zhang, B.M.Gong, C.Y.Deng, D.P.Wang, Materials Science & Engineering A, 685, 310 (2017).
https://doi.org/10.1016/j.msea.2017.01.023
 
4. L.Wang, D.Tang, Y.Song, Iron and Steel, 11, 73 (2016).
 
5. S.Ding, G.Y.Tian, R.Sutthaweekul, NDT & E International, 107, 102 (2019).
https://doi.org/10.1016/j.ndteint.2019.102138
 
6. G.Khalaj, T.Azimzadegan, M.Khoeini, M.Etaat, Neural Computing and Applications, 23, 2301 (2013).
https://doi.org/10.1007/s00521-012-1182-0
 
7. X.Y.Sui, Z.M.Lv, The International Journal of Advanced Manufacturing Technology, 85, 1395 (2016).
https://doi.org/10.1007/s00170-015-8039-5
 
8. C.G.Shen, C.C.Wang, X.L.Wei et al., Acta Materialia, 179, 201 (2019).
https://doi.org/10.1016/j.actamat.2019.08.033
 
9. W.G.Li, W.Yang, Y.T.Zhao, H.F.Hu, Journal of Iron and Steel Research, 30, 302 (2018).
 
10. S.W.Wu, Z.Y.Liu, X.G.Zhou, N.A.Shi, Journal of Iron and Steel Research, 28, 1 (2016).
 
11. W.Yang, W.G.Li, Y.T.Zhao et al., Iron and Steel, 53, 44 (2018).
 
12. V.N.Vapnik, The Nature of Statistical Learning Theory, Springer, New York (1999).
 
13. G.Bassett, R.Koenker, Econometrica, 46, 33 (1978).
https://doi.org/10.2307/1913643
 
14. I.Takeuchi, Q.V.Le, T.D.Sears, A.J.Smola, J. Mach Learn Res, 7, 1231 (2006).
 
15. J.Shim, Y.Kim, J.Lee, C.Hwang, Comput. Stat., 27, 685 (2012).
https://doi.org/10.1007/s00180-011-0283-z
 
16. Y.Y.He, R.Liu, H.Y.Li et al., Applied Energy, 185, 254 (2017).
https://doi.org/10.1016/j.apenergy.2016.10.079
 
17. Shim Jooyong, Kim Yongtae, Lee Jangtaek, Hwang Changha, Comput. Stat., 27, 685 (2012).
https://doi.org/10.1007/s00180-011-0283-z
 
18. Zhao Weihua, Zhang Riquan, Lv Yazhao, Liu Jicai, Journal of the Korean Statistical Society, 42, 343 (2013).
https://doi.org/10.1016/j.jkss.2012.11.003
 
19. H.Zou, Journal of the American Statistical Association, 476, 1418 (2006).
https://doi.org/10.1198/016214506000000735
 
20. H.Wang, R.Li, C.Tsai, Biometrika, 3, 553 (2007).
https://doi.org/10.1093/biomet/asm053
 
21. H.C.Wang, Y.C.Xia, Journal of the American Statistical Association, 486, 747 (2009).
https://doi.org/10.1198/jasa.2009.0138
 
22. D.Nychka, G.Gray, P.Haaland et al., J. Am. Stat. Assoc., 90, 1171 (1995).
https://doi.org/10.1080/01621459.1995.10476623

Current number: