Abstract
Dephosphorization is essential content in the steelmaking process, and the process after the converter has no dephosphorization function. Therefore, phosphorus must be removed to the required level in the converter process. In order to better control the end-point phosphorus content of basic oxygen furnace (BOF), a prediction model of end-point phosphorus content for BOF based on monotone-constrained backpropagation (BP) neural network was established. Through the theoretical analysis of the dephosphorization process, ten factors that affect the end-point phosphorus content were determined as the input variables of the model. The correlations between influencing factors and end-point phosphorus content were determined as the constraint condition of the model. 200 sets of data were used to verify the accuracy of the model, and the hit ratios in the range of ± 0.005% and ± 0.003% are 94% and 74%, respectively. The fit coefficient of determination of the predicted value and the actual value is 0.8456, and the root-mean-square error is 0.0030; the predictive accuracy is better than that of ordinary BP neural network, and this model has good interpretability. It can provide useful reference for real production and also provide a new approach for metallurgical predictive modeling.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.References
H. Kagechika, ISIJ Int. 46 (2006) 939–958.
S. Basu, A.K. Lahiri, S. Seetharaman, J. Halder, ISIJ Int. 47 (2007) 766–768.
S. Basu, Samnath, Studies on dephosphorisation during steelmaking, Royal Institute of Technology, Stockholm, Sweden, 2007.
K. Liu, L. Liu, P. He, Iron and Steel 43 (2008) No. 7, 32–36.
Z. Wang, F.M. Xie, B. Wang, Q. Liu, X.C. Lu, L.N. Hu, F. Cai, Steel Res. Int. 85 (2014) 599–606.
C.R. Li, H.W. Zhao, X. Xie, Q. Yin, Iron and Steel 46 (2011) No. 4, 23–25.
T.H. Zhu, C.S. Feng, F. He, Steelmaking 28 (2012) No. 2, 10–13.
T.B. Winkler, J. Chipman, Trans. AIME 167 (1946) 111–133.
Y. Qu, Principles of steelmaking, 3rd ed., Metallurgical Industry Press, Beijing, China, 1987.
R. Hüsken, R. Fechner, J. Cappel, Iron Steel Technol. 8 (2011) 46–58.
X.G. Huang, Principles of iron and steel metallurgy, 2rd ed., Metallurgical Industry Press, Beijing, China, 2002.
G.W. Healy, J. Iron Steel Inst. 208 (1970) 664–668.
H. Suito, R. Inoue, M. Takada, Tetsu-to-Hagané 67 (1981) 2645–2654.
P.J. Werbos, The roots of backpropagation: from ordered derivatives to neural networks and political forecasting, John Wiley & Sons, Hoboken, USA, 1994.
M. Tanaka, Pattern Recogn. Lett. 135 (2020) 354–359.
M.T. Hagan, M.B. Menhaj, IEEE Trans. Neural Networks 5 (1994) 989–993.
H.B. Demuth, M.H. Beale, O. De Jess, M.T. Hagan, Neural network design, Mechanical Industry Press, Beijing, China, 2014.
W.H. Joerding, J.L. Meador, Neural Networks 4 (1991) 847–856.
H. Kurt, S. Maxwell, W. Halbert, Neural Networks 2 (1989) 359–366.
A.G. Hou, X.F. Jiang, Baosteel Technology 26 (2008) No. 2, 1–10.
J.G. Zhi, W. Wu, Q. Gao, T. Xu, H.M. Luo, X.F. Zhang, Iron and Steel 55 (2020) No. 7, 72–77.
W. Wu, Q.X. Yang, Q. Gao, J.Q. Zeng, J. Mater. Res. Technol. 9 (2020) 2754–2761.
H. Jalkanen, L. Holappa, in: VII International Conference on Molten Slags Fluxes and Salts, South African Institute of Mining and Metallurgy, Marshalltown, USA, 2004, pp. 71–76.
E.T. Turkdogan, ISIJ Int. 40 (2000) 827–832.
Y.J. Xia, J. Li, D.D. Fan, G.D. Hou, ISIJ Int. 59 (2019) 1519–1526.
Y. Ogasawara, Y. Miki, Y. Uchida, N. Kikuchi, ISIJ Int. 53 (2013) 1786–1793.
Acknowledgements
This work was financially supported by the National Natural Science Foundation of China (No. 51974023) and Key R&D Program Projects in Jiangxi Province (20171ACE50020).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Zhou, Kx., Lin, Wh., Sun, Jk. et al. Prediction model of end-point phosphorus content for BOF based on monotone-constrained BP neural network. J. Iron Steel Res. Int. 29, 751–760 (2022). https://doi.org/10.1007/s42243-021-00655-6
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s42243-021-00655-6