Predictive control of Si content in blast furnace smelting based on improved SA-BP




Blast furnace, time lag analysis, BP neural network, improved simulated annealing algorithm


Blast furnace smelting process is a highly complex nonlinear dynamic process, its purpose is to refining the quality of liquid iron. From the point of view of chemical reaction kinetics, the main chemical reactions in the blast furnace are as many as 108 kinds, and the high complexity is obvious. From the point of view of hydrodynamics, there are three-phase mixed compressible viscous fluids in the blast furnace smelting process. The hydrodynamic equation is nonlinear, high-dimensional and high-coupling. In addition, the blast furnace smelting process has the characteristics of time-varying, high-dimensional, distributed parameters and other characteristics of the complex conditions and the failure of the operation under the conditions of the test, making the blast furnace smelting process automation and furnace temperature precision control to become metallurgical workers face the problem. In this study, from the data point of view, to explore the furnace temperature can be characterized by [Si] content prediction. Based on the data of 1000 furnace blast furnace, an accurate and reasonable prediction model of Si content in blast furnace is established. First of all, through the calculation of correlation coefficients of various factors and the time trend diagram, the general lag time between each parameter and Si content in the process of blast furnace production is obtained. Through correlation and analysis of the correlation between lag time, before and after the two largest furnace, with improved simulated annealing algorithm to determine the optimal initial weights, the content of Si, the N furnace of S content, the quantity of coal and air PML FL as input, the contents of Si in n+1 furnace as output to establish dynamic prediction model of improved SA-BP neural network based. Finally, the data used to detect the model is brought into the model to be tested, the error is analyzed, and the error local map is used to express the error visually. The model is tested.


Yu Xiaofeng (2016): Machine learning theory in the railway freight forecasting application [D]. Beijing Jiaotong University.

Yu Zhiheng (2016): . Based on the intelligent theory of traffic flow portfolio forecasting model [D]. Northeast Normal University.

Zhao Zhe (2015): Blast furnace smelting process monitoring and trend forecast [D]. Inner Mongolia University of Science and Technology.

Zeng Yanfei, Li Hushan. (2007): Design and implementation of predictive control model for [Si] content of blast furnace molten iron [J]. Microcomputer Information, (10): 64-66. [2017-08-02].

Liu Juanli. (2017): Blast furnace heat balance analysis of ironsaving process energy-saving direction [J]. Science and Technology Communication, 6 (11): 66-67. [2017-08-02].

Zhang Guobo, Li Jian. (2017): Calculation and analysis of heat balance and thermal efficiency of hot blast stove in No.2 blast furnace of Jiuquan Iron and Steel [J]. Metallurgy, 2014, 36 (04): 22-25. [2017-08-02] DOI: 10.16042 / j.cnki.cn62- 1053 / tf.2014.04.025

Gao Pan. (2013): Mathematical physical simulation of oxygen blast furnace technology [D]. Northeastern University.

Liu Wenwen. (2015): Based on statistical process control of large blast furnace hot metal quality control [D]. Shanghai Jiaotong University.

Yang Kun. (2016): Neural network based on the blast furnace molten iron silicon content modelling [D]. Yanshan University.

Hu Dengfei. (2014): Optimization model of blast furnace coal injection based on neural network prediction model [D]. Inner Mongolia University of Science and Technology.

QI Peng.(2010): Study on Prediction of Silicon Content in Hot Metal of Blast Furnace Based on Partial Least Squares [D]. Inner Mongolia University of Science and Technology.

LI Bao Jian, CHENG Chun Tian. (2014): Monthly discharge forecasting using wavelet neural networks with extreme learning machine [J]. Science China (Science Sciences), (12): 2441-2452.

Peter Schmoele, Michael Peters, Hans Bodo Luengen, Zhu Tingting.(2013): Development and prospect of blast furnace ironmaking [J]. World Steel, (01): 35-41.

Guo Yanling, Hu Junge, Zhou Wentao, Zhao Xiaoyan, Wang Xu, Huang Mingming (2014): Effect of coke quality on blast furnace ironmaking [J]. Shanghai Metal, (03): 51-55.

Mu Dong, Wang Chao, Wang Shengchun, Zhou Shengchuan. (2015): Based on parallel simulated annealing algorithm to solve the time-dependent vehicle routing problem [J]. Computer Integrated Manufacturing System, (06): 1626-1636.

LU Yu-ting, LIN Yu-ya, PENG Qiao-zi, WANG Ying-zhe.I (2015): mproved overview and simulated probing of simulated annealing algorithm [J]. College Mathematics, (06): 96-103.

Yue Zhenfang, Gao Yuelin.(2016): Improved teaching and optimization algorithm for simulated simulated annealing [J]. Journal of Henan Normal University (Natural Science Edition), (01): 149-154.

Wang Jie, LI Hui-hui, Peng Jin-zhu. (2016): An Quasirandom Initial Simulated Annealing Particle Swarm Optimization Algorithm [J]. Journal of Zhengzhou University (Natural Science Edition).03): 75-81.

Yan Lei, Ma Jian, Dong Hui, Gao Meng. (2017): Application of genetic algorithm and simulated annealing algorithm in multi-DNA sequence alignment [J]. Journal of Hainan Institute of Tropical and Oceanic Sciences, (02): 64- 69.

Zhou Ping, Li Ruifeng, Guo Dongwei, Wang Hong, Chai Tianyou.(2016): Multi-output support vector regression modelling of multicomponent hot metal mass index in blast furnace iron making process [J]. Control Theory & Applications, (06): 727-734.

Cui Gui-mei, Cheng history.(2014): Measurement of blast furnace temperature prediction based on distributed neural network model [J]. Journal of Iron and Steel Research, 2014, (06): 27-30.

Cui Gui-mei, Gao Cui-ling, Hou Jia, Chen Zhi-hui, MA Xiang. (2015): A optimization of blast furnace coal injection based on genetic algorithm for BP neural network [J]. Computer Measurement and Control, (05): 1568-1570 + 1574.

Real estate appraisal system based on GIS and BP neural network [J]. Transactions of Nonferrous Metals Society of China 2011, (S3): 626-630.

Tang YuHua, Zhang BaiDa, Wu JunJie, Hu TianJiang, Zhou Jing, Liu Fu Dong. (2013): Parallel architecture and optimization for discrete-event simulation of spike neural networks [J]. Science China (Technological Sciences), (02): 509-517.

Huang Li. (2008): BP neural network algorithm improvement and application research [D]. Chongqing Normal University.




How to Cite

Liu, W., Wang, H., & Shi, L. (2021). Predictive control of Si content in blast furnace smelting based on improved SA-BP. Journal of Mines, Metals and Fuels, 69(5), 155–163.