Prediction of Silicon Content in Blast Furnace Molten Iron Using Grey Correlation Analysis and Machine Learning
QIU Guoxing1, CAI Mingchong1, ZHANG Yi2, SU Bingrui1, YANG Yongkun1, LI Xiaoming1,*
1 School of Metallurgical Engineering, Xi’an University of Architecture and Technology, Xi’an 710055, China 2 Laiwu Branch Technology Center, Shandong Iron and Steel Co., Ltd., Jinan 271103, China
Abstract: The silicon content in molten iron is commonly used as an important indicator to characterize the ‘chemical heat’ and economic benefits of the blast furnace. Establishment a timely and accurate prediction model for the silicon content in molten iron is of great significance for stable production of the blast furnace. In this work, an innovative prediction model was established by considering the time delay and the grey relational analysis (GRA) combining principal component analysis (PCA) and long short-term memory network (LSTM). Firstly, from the perspective of the reduction-oxidation behavior of silicon, the operating parameters, state parameters and result parameters relevant to the silicon content of blast furnace iron in production were selected. Secondly, through GRA, the degree of correlation between each parameter and the silicon content in molten iron was determined, and the main factors affecting the silicon content in molten iron were screened out. On this basis, a total of 8 544 sets of production data for a 3 200 m3 blast furnace in China were dimensionally reduced in one year. A prediction model was established using the 13 principal components obtained as input variables and the silicon content in molten iron as output variables. The prediction model has reasonable generalization ability, robustness and accuracy. The analysis of prediction results shows that the determination coefficient (R2) of the model is 0.929 7, the mean square error (MSE) and mean absolute error (MAE) are 0.001 2 and 0.025 4 respectively, realizing accurate prediction of the silicon content of blast furnace molten iron.
邱国兴, 蔡明冲, 张毅, 苏炳瑞, 杨永坤, 李小明. 基于灰色关联分析和机器学习的高炉铁水硅含量预测[J]. 材料导报, 2024, 38(20): 23080170-6.
QIU Guoxing, CAI Mingchong, ZHANG Yi, SU Bingrui, YANG Yongkun, LI Xiaoming. Prediction of Silicon Content in Blast Furnace Molten Iron Using Grey Correlation Analysis and Machine Learning. Materials Reports, 2024, 38(20): 23080170-6.
1 Dai Y X, Li J, et al. Ironmaking & Steelmaking, 2021, 48(4), 47. 2 Chen W, Kong F, Wang B, et al. Ironmaking & Steelmaking, 2019, 46(10), 74. 3 Han Y, Li J, Yang X L, et al. Complexity, DOI: 10.1155/2018/8079697. 4 Li J P, Hua C C, Yang Y N, et al. IEEE Transactions on Industrial Electronics, 2018, 65(6), 4933. 5 Le C Y, Bengio Y, Hinton G. Nature, 2015, 521(7553), 436. 6 Bao X J, Weng S H, Chen G, et al. Iron & Steel, 2022, 57(9), 166 (in Chinese). 包向军, 翁思浩, 陈光, 等. 钢铁, 2022, 57(9), 166. 7 Wang J H, Huang D M, Gong J Q, et al. In: The 13th China Iron and Steel Annual Meeting of China Metal Society. Chongqing, 2022, pp.53 (in Chinese). 王剑虎, 黄冬明, 龚敬群, 等. 中国金属学会第十三届中国钢铁年会. 重庆, 2022, pp.53. 8 Meng L R, Li F M, Liu X J, et al. Metallurgical Industry Automation, 2023, 47(2), 27 (in Chinese). 孟令茹, 李福民, 刘小杰, 等. 冶金自动化, 2023, 47(2), 27. 9 Liu X J, Li X, Liu E H, et al. Multipurpose Utilization of Mineral Resources, 2021(4), 91 (in Chinese). 刘小杰, 李欣, 刘二浩, 等. 矿产综合利用, 2021(4), 91. 10 Zeng Y F, Li X W. Control & Measurement, 2006, 22(19), 291 (in Chinese). 曾燕飞, 李小伟. 控制与测量, 2006, 22(19), 291. 11 Jiang Z H, Dong M L, Gui W H, et al. Acta Automatica Sinica, 2016, 42(5), 715 (in Chinese). 蒋朝辉, 董梦林, 桂卫华, 等. 自动化学报, 2016, 42(5), 715. 12 Zuang T, Yang C J. Metallurgical Industry Automation, 2017, 41(4), 1 (in Chinese). 庄田, 杨春节. 冶金自动化, 2017, 41(4), 1. 13 Song J H, Yang C J, Zhou Z, et al. Journal of Chemical Industry and Engineering, 2016, 67(3), 729 (in Chinese). 宋菁华, 杨春节, 周哲, 等. 化工学报, 2016, 67(3), 729. 14 Jiang Z H, Xu C, Gui W H, et al. Acta Automatica Sinica, 2022, 48(1), 194 (in Chinese). 蒋朝辉, 许川, 桂卫华, 等. 自动化学报, 2022, 48(1), 194. 15 Zhao N, Wang Y Y. Metallurgical Analysis, 2020, 40(2), 1 (in Chinese). 赵宁, 王玉英. 冶金分析, 2020, 40(2), 1. 16 Li Z L, Yang C J. Journal of Chemical Industry and Engineering, 2018, 69(3), 992 (in Chinese). 李泽龙, 杨春节. 化工学报, 2018, 69(3), 992. 17 Fukagawa T. Kawasaki SteelGIHO, 1991, 23(3), 203. 18 Vescovi M R, Farquhar A. IEEE Expert, 1997, 12(3), 42. 19 Wu X F, Fei M R. Journal-Zhejiang University Engineering Science, 2007, 41(10), 1722. 20 Jin Z B. Mining & Metallurgy in Hainan, 1994(4), 28 (in Chinese). 金智彬. 海南矿冶, 1994(4), 28. 21 Liang L S. Baosteel Technology, 2000(6), 36 (in Chinese). 梁利生. 宝钢技术, 2000(6), 36. 22 Yue Y J, Dong A, Zhao H, et al. Computer Simulation, 2017, 34(2), 362(in Chinese). 岳有军, 董安, 赵辉, 等. 计算机仿真, 2017, 34(2), 362. 23 Lyu Q, Liu Y M, Zhang Z F, et al. Journal of Iron & Steel Research, 2018, 30(12), 957 (in Chinese). 吕庆, 刘月明, 张振峰, 等. 钢铁研究学报, 2018, 30(12), 957. 24 Liu X J, Deng Y, Li X, et al. China Metallurgy, 2021, 31(2), 10 (in Chinese). 刘小杰, 邓勇, 李欣, 等. 中国冶金, 2021, 31(2), 10. 25 Smith M. Ironmaking & Steelmaking, 2015, 42(10), 734. 26 Jin Y L, Xu N P. Iron & Steel, 2004(1), 17 (in Chinese). 金永龙, 徐南平. 钢铁, 2004(1), 17. 27 Gaura E I, Brusey J, Allen M, et al. IEEE Sensors Journal, 2013, 13(10), 3816. 28 Huang C L, Tang Y L, Zhang X F, et al. Computer Simulation, 2020, 37(2), 398 (in Chinese). 黄陈林, 汤亚玲, 张学锋, 等. 计算机仿真, 2020, 37(2), 398. 29 Lee S Y, Tama B A, Choi C, et al. IEEE Access, 2020, 8, 21953.
渝公网安备50019002502923号 版权所有：《材料导报》编辑部
2024, Vol. 38 
