Intelligent recommendation model for reducing silicon deviation fluctuation of hot metal in BF and application
HAN Yang1, HU Zhi-bin2, YANG Ai-min2, LI Jie1, ZHANG Yu-zhu1
1. College of Metallurgy and Energy, North China University of Science and Technology, Tangshan 063210, Hebei, China; 2. College of Science, North China University of Science and Technology, Tangshan 063210, Hebei, China
Abstract:In order to ensure the smooth operation of the blast furnace, improve the quality of blast furnace thermal regulation, and deeply understand the dynamics of molten iron silicon content variation, the fluctuation mechanism of molten iron silicon content variation was studied with the No.3 blast furnace of an iron and steel complex in southern Hebei as the research object. Quantify the six decision spaces for decreasing the variation of silicon content in molten iron. Through the comparative analysis of single variable estimation method and complex correlation coefficient joint estimation method, the joint estimation method that can give consideration to the coupling and synergism between decision variables is selected to determine the response time of the variable momentum control decision variables of molten iron silicon content and eliminate the time lag between variables.Through the comparative analysis of Hopfield neural network, Boltzmann neural network and Elman neural network algorithm, the Elman neural network algorithm with memory function is selected, and the coupling nonlinear relationship between variables is determined by taking into account the time series characteristics of variables, so as to build an intelligent prediction model for the variation of molten iron silicon content in blast furnace. Based on the goal of minimizing the variation of silicon content in molten iron, an intelligent recommendation model for regulation and decision making is constructed; Through the comparative analysis of genetic algorithm (GA) and evolutionary strategy algorithm (ES), the ES algorithm with adaptive variation degree is selected, the recommendation model is solved intelligently, and the optimal control decision to maintain the minimum variation of molten iron silicon content is quickly obtained. The research results show that the response time estimation algorithm verifies that the sample set generated by joint estimation of response time of multiple decision variables takes into account the coupling and cooperation between decision variables; The comparison of prediction algorithms verifies the superiority of Elman neural network, and the hit rate of the prediction model constructed by the target algorithm is up to 94.10%; The comparison of intelligent optimization algorithm verifies that ES algorithm is significantly superior to the comparison algorithm in solving speed and results of recommended models, and the model maintains the excellent characteristics of offline testing in industrial application practice.
韩阳, 胡支滨, 杨爱民, 李杰, 张玉柱. 高炉铁水硅含量变动量调控决策的智能推荐模型及应用[J]. 钢铁, 2023, 58(4): 30-38.
HAN Yang, HU Zhi-bin, YANG Ai-min, LI Jie, ZHANG Yu-zhu. Intelligent recommendation model for reducing silicon deviation fluctuation of hot metal in BF and application[J]. Iron and Steel, 2023, 58(4): 30-38.
[1] 崔泽乾,韩阳,杨爱民,等.基于神经网络时间序列模型的高炉铁水硅含量量智能预报[J].冶金自动化,2021,45(3):51.(CUI Ze-qian, HAN Yang, YANG Ai-min, et al.Intelligent prediction of silicon content in hot metal of blast furnace based on neural network time series model[J]. Metallurgical Automation, 201,45(03):51.) [2] 邓勇,张建良,焦克新.温度和铁水成分对炭砖溶解行为的影响[J].钢铁,2018,53(5):25.(DENG Yong, ZHANG Jian-liang, JIAO Ke-xin. Effects of temperature and composition of molten iron on dissolution behavior of carbon brick[J]. Iron and Steel,2018,53(5):25.) [3] DAI Yu-xiang,LI Jing, SHI Cheng-bin,et al. Dephosphorization of high silicon hot metal based on double slag converter steelmaking technology[J]. Ironmaking and Steelmaking,2021,48(4):447. [4] HAN Yang, LI Jie, YANG Xiao-lei, et al. Dynamic prediction research of silicon content in hot metal driven by big data in blast furnace smelting process under hadoop cloud platform [J]. Complexity, 2018(1):1 [5] LI Jun-peng, HUA Chang-chun, YANG Ya-na, et al. Bayesian block structure sparse based T-S fuzzy modeling for dynamic prediction of hot metal silicon content in the blast furnace[J]. IEEE Transactions on Industrial Electronics, 2018,65(6):4933. [6] 高小强,王逸名,郑忠.高炉铁水硅含量预测评价与模型选择[J].钢铁研究学报,2007,19(5):5. (GAO Xiao-qiang, WANG Yi-ming,ZHENG Zhong. Evaluation and model selection of forecasting silicon content in hot metal of blast furnace[J]. Journal of Iron and Steel Research, 2007,19(5):5.) [7] CUI Ze-qian, HAN Yang, LU Chao-meng, et al. Prediction model of hot metal silicon content based on improved GA-BPNN[J]. Computational Intelligence and Neuroscience, 2021 (1):1. [8] ZHANG Xin-min, KANO Manabu, MATSUZAKI Shinroku. Ensemble pattern trees for predicting hot metal temperature in blastfurnace[J]. Computers and Chemical Engineering,2019, 121: 442. [9] 宋菁华,杨春节,周哲,等.改进型EMD-Elman神经网络在铁水硅含量预测中的应用[J].化工学报,2016,67(3):729.(SONG Jing-hua, YANG Chun-jie, ZHOU Zhe, et al. Application of improved EMD-Elman neural network in prediction of sic content in hot metal[J]. Chemical Engineering Journal,2016, 67(3): 729.) [10] HAN Yang, HAN Wei-gang, ZENG Kai. Improved multidomain convolutional neural network for intelligent tracking of marangoni effect process sequence images[J]. IEEE Transactions on Industrial Informatics,2022, 18(5): 3397. [11] HAN Yang, ZHANG Cai-jun, WANG Lu, et al. Industrial iot for intelligent steelmaking with converter mouth flame spectrum information processed by deep learning[J]. IEEE Transactions on Industrial Informatics,2020,16(4): 2640. [12] LI Jie, LIU Wen-qiang, HAN Yang, et al. Dynamic compensation model of bf slag homogenization thermal based on advanced deep learning algorithm[J]. IEEE Transactions on Industrial Informatics,2021,17(6): 4107. [13] 尹林子,李乐,蒋朝辉.基于粗糙集理论与神经网络的铁水硅含量预测[J].钢铁研究学报,2019,31(8):689.(YIN Lin-zi, LI Le, JIANG Chao-hui.Prediction of silicon content in hot metal using neural network and rough set theory[J]. Journal of Iron and Steel Research, 2019,31(8):689.) [14] 刘小杰,邓勇,李欣,等.基于大数据技术的高炉铁水硅含量预测[J].中国冶金,2021,31(2):10. (LIU Xiao-jie, DENG Yong, LI Xin, et al. Prediction of silicon content in hot molten of blast furnace based on big data technology[J]. China Metallurgy, 2021,31(2):10.)