Prediction of End-point Phosphorus Content of Molten Steel in BOF with Machine Learning Models
Abstract
The main task of basic oxygen furnace (BOF) steelmaking is dephosphorization, thus the prediction and control of End-point phosphorus content of molten steel is of great significance. Four machine learning regression models (Lasso, Random Forest, Xgboost, and Neural Network) were established to predict end-point phosphorus content of molten steel in BOF according to raw and auxiliary material data, process parameters, and data of production quality. The prediction effect of four models were further compared, and their prediction results were interpreted via model’s interpretability and Permutation Importance Method. Results showed that compared with linear regression and Neural Network regression model, two kinds of ensemble tree model had higher prediction accuracy, better stability in small data sets, and lower requirements on data pre-processing. The influencing factors of end-point phosphorus (P) content in BOF were ranked by importance as: Tapping temperature > Turning down times > Steel scrap amount > Operation habits of different work groups > Blowing oxygen amount > Sulfur and Phosphorus content of molten iron > Addition amount of lime, limestone, and light-burned dolomite in slagging agents > Slag-splashing amount.
References
[1] K. He, L. Wang, A review of energy use and energy-efficient technologies for the iron and steel industry, Renewable and Sustainable Energy Reviews, 70 (2017) 1022-1039. https://doi.org/10.1016/j.rser.2016.12.007
[2] G. W. Healy, New look at phosphorus distribution, J Iron Steel Inst, 208(7) (1970) 664-668.
[3] H. Suito, R. Inoue, and M. Takada, Phosphorus distribution between liquid iron and MgO saturated slags of the system CaO-MgO-FeOx-SiO2, Tetsu-to-Hagane, 67(16) (1981) 2645-2654. https://doi.org/10.2355/tetsutohagane1955.67.16_2645
[4] A. Sobandi, H. G. Katayama, T. Momono, Activity of Phosphorus Oxide in CaO–MnO–SiO2–PO2. 5 (–MgO, FetO) Slags, ISIJ international, 38(8) (1998) 781-788. https://doi.org/10.2355/isijinternational.38.781
[5] W. Yang, J. Yang, Y. Shi, Z. Yang, F. Gao, R. Zhang, G. Ye, Effect of basicity on dephosphorization of hot metal with a low basicity slag at 1653 K, Ironmaking & Steelmaking, 48(1) (2021) 69-77. https://doi.org/10.1080/03019233.2020.1731256
[6] X. F. Jiang, X. Wang, Study on logistic information acquisition technology in steelmaking practice based on RFID, In 2008 7th World Congress on Intelligent Control and Automation, June, Chongqing, China, 2008, p. 7946-7950. IEEE. https://doi.org/10.1109/WCICA.2008.4594171
[7] C. R. Li, H. W. Zhao, X. Xie, Q. Yin, Prediction of end-point phosphorus content for BOF based on LM BP neural network, Iron and Steel/ Gangtie, 46(4) (2011) 23-25. http://www.chinamet.cn/Jweb_gt/EN/abstract/abstract145429.shtml
[8] H. B. Wang, A. J. Xu, L. X. Ai, N. Y. Tian, Prediction of endpoint phosphorus content of molten steel in BOF using weighted K-means and GMDH neural network, Journal of Iron and Steel Research International, 19(1) (2012) 11-16. https://doi.org/10.1016/S1006-706X(12)60040-5
[9] F. He, L. Zhang, Prediction model of end-point phosphorus content in BOF steelmaking process based on PCA and BP neural network, Journal of Process Control, 66 (2018) 51-58. https://doi.org/10.1016/j.jprocont.2018.03.005
[10] D. A. Sala, A. Jalalvand, A. Van Yperen-De Deyne, E. Mannens, Multivariate time series for data-driven endpoint prediction in the basic oxygen furnace, In 2018 17th IEEE international conference on machine learning and applications (ICMLA), December, Orlando, FL, USA, 2018, pp. 1419-1426. IEEE. https://doi.org/10.1109/ICMLA.2018.00231
[11] K. X. Zhou, W. H. Lin, J. K. Sun, J. S. Zhang, D. Z. Zhang, X. M. Feng, Q. Liu, Prediction model of end-point phosphorus content for BOF based on monotone-constrained BP neural network, Journal of Iron and Steel Research International, 29(5) (2022) 751-760. https://doi.org/10.1007/s42243-021-00655-6
[12] H. Li, S. Barui, S. Mukherjee, K. Chattopadhyay, Least Squares Twin Support Vector Machines to Classify End-Point Phosphorus Content in BOF Steelmaking, Metals, 12(2) (2022) 268. https://doi.org/10.3390/met12020268
[13] F. Li, J. Wu, F. Dong, J. Lin, G. Sun, H. Chen, J. Shen, Ensemble machine learning systems for the estimation of steel quality control, In 2018 IEEE International Conference on Big Data (Big Data), Seattle, WA, USA, 2018, pp. 2245-2252. https://doi.org/10.1109/BigData.2018.8622583
[14] H. Liu, B. Wang, X. Xiong, Basic oxygen furnace steelmaking end-point prediction based on computer vision and general regression neural network, Optik, 125(18) (2014) 5241-5248. https://doi.org/10.1016/j.ijleo.2014.05.004
[15] Z. Wang, J. Chang, Q. P. Ju, F. M. Xie, B. Wang, H. W. Li, B. Wang, X. C. Lu, G. Q. Fu, Q. Liu, Prediction model of end-point manganese content for BOF steelmaking process, ISIJ international, 52(9) (2012) 1585-1590. https://doi.org/10.2355/isijinternational.52.1585
[16] S. Chang, C. Zhao, Y. Li, M. Zhou, C. Fu, H. Qiao, Multi-channel graph convolutional network based end-point element composition prediction of converter steelmaking, IFAC-PapersOnLine, 54(3) (2021) 152-157. https://doi.org/10.1016/j.ifacol.2021.08.234
[17] M. Q. Gu, A. J. Xu, F. Yuan, X. M. He, Z. F. Cui, An improved CBR model using time-series data for predicting the end-point of a converter, ISIJ International, 61(10) (2021) 2564-2570. https://doi.org/10.2355/isijinternational.ISIJINT-2020-687
[18] S. Song, J. Li, W. Yan, Intelligent Case-based Hybrid Model for Process and Endpoint Prediction of Converter via Data Mining Technique, ISIJ International, 62(8) (2022) 1639-1648. https://doi.org/10.2355/isijinternational.ISIJINT-2021-598
[19] T. K. Ho, Random decision forests, In Proceedings of 3rd international conference on document analysis and recognition, Montreal, QC, Canada, 1995, pp. 278-282 vol.1. https://doi.org/10.1109/ICDAR.1995.598994
[20] T. Q. Chen, C. Guestrin, Xgboost: A scalable tree boosting system, In Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining, August, New York, NY, USA, 2016, pp. 785–794. https://doi.org/10.1145/2939672.2939785
[21] R. Hecht-Nielsen, III.3 - Theory of the Backpropagation Neural Network (E. Editor), Neural networks for perception(Academic Press), 1992, p. 65-93. https://doi.org/10.1016/B978-0-12-741252-8.50010-8
[22] J. Ranstam, J. A. Cook, LASSO regression, Journal of British Surgery, 105(10) (2018) 1348-1348. https://doi.org/10.1002/bjs.10895
[23] A. Altmann, L. Toloşi, O. Sander, T. Lengauer, Permutation importance: a corrected feature importance measure, Bioinformatics, 26(10) (2010) 1340-1347. https://doi.org/10.1093/bioinformatics/btq134
[24] W. Yang, J. Yang, Y. Shi, Z. Yang, F. Gao, R. Zhang, G. Ye, Effect of Temperature on Dephosphorization of Hot Metal in Double‐Slag Converter Steelmaking Process by High‐Temperature Laboratorial Experiments, Steel Research International, 92(3) (2021) 2000438. https://doi.org/10.1002/srin.202000438
[25] M. Wang, W. Yang, Dephosphorization in the early stage of converter steelmaking, Ironmaking & Steelmaking, 47(10) (2020) 1127-1134. https://doi.org/10.1080/03019233.2019.1673546
Authors retain copyright of the published papers and grant to the publisher the non-exclusive right to publish the article, to be cited as its original publisher in case of reuse, and to distribute it in all forms and media.
The Author(s) warrant that their manuscript is their original work that has not been published before; that it is not under consideration for publication elsewhere; and that its publication has been approved by all co-authors, if any, as well as tacitly or explicitly by the responsible authorities at the institution where the work was carried out. The Author(s) affirm that the article contains no unfounded or unlawful statements and does not violate the rights of others. The author(s) also affirm that they hold no conflict of interest that may affect the integrity of the Manuscript and the validity of the findings presented in it. The Corresponding author, as the signing author, warrants that he/she has full power to make this grant on behalf of the Author(s). Any software contained in the Supplemental Materials is free from viruses, contaminants or worms.The published articles will be distributed under the Creative Commons Attribution ShareAlike 4.0 International license (CC BY-SA).
Authors are permitted to deposit publisher's version (PDF) of their work in an institutional repository, subject-based repository, author's personal website (including social networking sites, such as ResearchGate, Academia.edu, etc.), and/or departmental website at any time after publication.
Upon receiving the proofs, the Author(s) agree to promptly check the proofs carefully, correct any typographical errors, and authorize the publication of the corrected proofs.
The Corresponding author agrees to inform his/her co-authors, of any of the above terms.