A Method of Establishing Temperature Schedule during ASP Hot Strip Rolling

Abstract:

Based on the actual production data of ASP (Angang Strip Production) hot strip rolling line, mechanical properties of thin gauge X70 pipeline steel were simulated by BP neural network method. Recursive functions were used to verify the mechanical properties which calculated by BP neural network. Based on predicted mechanical properties with high precision, BP neural network and Genetic Algorithm (GA) were combined to establish the temperature schedule of X70 pipeline steel during ASP hot strip rolling. It is shown that there are four important temperatures during ASP hot strip rolling, such as rough rolling temperature, refine start rolling temperature, refine finish rolling temperature and coiling temperature. Temperature difference of adjacent stages and temperature of former stage is a linear function relationship. For a given mechanical properties, deviations between simulated temperature and actual temperature are within ±10°C. This method can be used to produce different strips with the same compositions but different strengths by regulating suitable temperature schedule, so it is effective to resolve conflicts during hot strip rolling.

• Periodical: Materials Science Forum (Volumes 704-705)
• Pages: 1298-1303
• DOI: https://doi.org/10.4028/www.scientific.net/MSF.704-705.1298
• Online since: December 2011
• Authors: Yan Feng Zhao, Dian Hua Zhang, Yun Bo Xu, Xiao Ying Hou, Guo Dong Wang
• Keywords: Angang Strip Production (ASP), BP Neural Network (BPNN), Simulate, Temperature Schedule, X70 Pipeline Steel

References

[1] J. Guan, H.J. Zhang, X.J. Ma and P. Wang: Angang Technology Vol. 1 (2010), pp.60-62.

[2] X.H. Liu, G.D. Wang, L.X. Du and Z.Y. Liu: Iron and steel Vol. 41, (2006), pp.32-26.

[3] R. Koker,N. Altinkok, A. Demir: Materials and Design Vol. 28 (2007) pp.616-627.

[4] P.D. Hodgson and R.K. Gibbs: ISIJ International Vol. 32 (1992) pp.1392-1338.

[5] S.M.K. Hosseini, A. Zarei-Hanzaki, M.J. Yazdan Panah and S. Yue: Materials Science and Engineering A Vol. 374 (2004), pp.122-128.

DOI: 10.1016/j.msea.2004.01.007

[6] C. Capdevila, C. Garcia-Mateo, F.G. Caballero and C. Garcia de Andres: Computational Materials Science Vol. 38 (2006), pp.192-201.

[7] A.J. Kulkarni, K. Krishnamurthy, S.P. Deshmukh, and R.S. Mishra: Materials Science and Engineering A Vol. 372 (2004), pp.213-220.

[8] N. Chakraborti, B.S. Kumar, V.S. Babu, S. Moitra and A. Mukhopadhyay: Computational Materials Science Vol. 37 (2006), pp.159-165.

[9] L.A. Dobrzanski, M. Kowalski, J. Madejski: Journal of Materials Processing Technology Vol. 164-165 (2005), pp.1500-1509.