Hybrid End-Point Static Control Model for 80 Tons BOF Steelmaking

被引:4
|
作者
Wang, Miao [1 ]
Gao, Chuang [2 ]
Ai, Xingang [1 ]
Zhai, Baopeng [3 ]
Li, Shengli [1 ]
机构
[1] Univ Sci & Technol Liaoning, Sch Met & Mat, Anshan 114051, Liaoning, Peoples R China
[2] Univ Sci & Technol Liaoning, Sch Elect & Informat Engn, Anshan 114051, Liaoning, Peoples R China
[3] Angang Grp Automat Co Ltd, Anshan 114000, Peoples R China
关键词
End-point control model; Twin support vector regression; Whale optimization algorithm; Basic oxygen furnace; PREDICTION MODEL;
D O I
10.1007/s12666-022-02603-8
中图分类号
TF [冶金工业];
学科分类号
0806 ;
摘要
Accurate control of the basic oxygen furnace (BOF) end-point can effectively improve the quality of steel. A hybrid end-point static control model is proposed to calculate the oxygen blowing volume and lime weight, and realizes the control of the end-point of BOF. Firstly, the prediction model is established based on twin support vector regression (TSVR). Secondly, the difference between the predicted value and actual value of the obtained model is used as the objective function, combined with the whale optimization algorithm (WOA) and incremental algorithm to optimize the objective function. Finally, the optimal value vector of oxygen blowing volume and lime weight is obtained. The simulation calculation is carried out by using the actual production sample of an 80 tons BOF. The results show that the proposed prediction model has high prediction accuracy, and the calculated oxygen blowing volume and lime weight can meet the actual field production.
引用
收藏
页码:2281 / 2288
页数:8
相关论文
共 50 条
  • [31] Steelmaking process: Neural models improve end-point predictions
    Cunha, AP
    Pacianotto, TA
    Frattini, F
    Cia, AM
    EUROPEAN SYMPOSIUM ON COMPUTER-AIDED PROCESS ENGINEERING - 14, 2004, 18 : 631 - 636
  • [32] End-point carbon content correction in converter steelmaking based on the Kalman filter and CBR model
    Kang, Yi
    Tan, Yong-guang
    Zhao, Jun-xue
    Yang, Kai
    Liu, Wen-wen
    Yue, Shen
    IRONMAKING & STEELMAKING, 2024,
  • [33] Improved prediction model for BOF end-point manganese content based on IPSO-RELM method
    Zhang Z.
    Cao L.-L.
    Lin W.-H.
    Sun J.-K.
    Feng X.-M.
    Liu Q.
    Gongcheng Kexue Xuebao/Chinese Journal of Engineering, 2019, 41 (08): : 1052 - 1060
  • [34] Prediction model of BOF end-point phosphorus content and sulfur content based on LWOA-TSVR
    Shi, Chunyang
    Guo, Shiyu
    Wang, Baoshuai
    Ma, Zhicai
    Wu, Chun lei
    Sun, Peng
    IRONMAKING & STEELMAKING, 2023, 50 (07) : 857 - 866
  • [35] End-Point Prediction of Converter Steelmaking Based on Main Process Data
    Kang, Yi
    Zhao, Jun-xue
    Li, Bin
    Ren, Meng-meng
    Cao, Geng
    Yue, Shen
    An, Bei-qi
    STEEL RESEARCH INTERNATIONAL, 2024, 95 (08)
  • [36] PRODUCTION EXPERIENCE WITH END-POINT CONTROL
    WERANI, J
    ACTA PHARMACEUTICA SUECICA, 1988, 25 (4-5): : 247 - 266
  • [37] Prediction model of end-point phosphorus content for BOF based on monotone-constrained BP neural network
    Zhou, Kai-xiao
    Lin, Wen-hui
    Sun, Jian-kun
    Zhang, Jiang-shan
    Zhang, De-zheng
    Feng, Xiao-ming
    Liu, Qing
    JOURNAL OF IRON AND STEEL RESEARCH INTERNATIONAL, 2022, 29 (05) : 751 - 760
  • [38] Comparison of the Prediction of BOF End-Point Phosphorus Content Among Machine Learning Models and Metallurgical Mechanism Model
    Zhang, Runhao
    Yang, Jian
    Wu, Siwei
    Sun, Han
    Yang, Wenkui
    STEEL RESEARCH INTERNATIONAL, 2023, 94 (05)
  • [39] Prediction model of end-point phosphorus content for BOF based on monotone-constrained BP neural network
    Kai-xiao Zhou
    Wen-hui Lin
    Jian-kun Sun
    Jiang-shan Zhang
    De-zheng Zhang
    Xiao-ming Feng
    Qing Liu
    Journal of Iron and Steel Research International, 2022, 29 : 751 - 760
  • [40] End-point parametrization and guaranteed stability for a model predictive control scheme
    Weiland, S
    Stoorvogel, AA
    Tiagounov, AA
    PROCEEDINGS OF THE 40TH IEEE CONFERENCE ON DECISION AND CONTROL, VOLS 1-5, 2001, : 4832 - 4837