Prediction of blast furnace gas generation based on data quality improvement strategy

被引:27
作者
Liu, Shu-han [1 ,2 ]
Sun, Wen-qiang [1 ,2 ]
Li, Wei-dong [3 ,4 ]
Jin, Bing-zhen [5 ]
机构
[1] Northeastern Univ, Sch Met, Dept Energy Engn, Shenyang 110819, Liaoning, Peoples R China
[2] Northeastern Univ, State Environm Protect Key Lab Ecoind, Minist Ecol & Environm, Shenyang 110819, Liaoning, Peoples R China
[3] State Key Lab Met Mat Marine Equipment & Applicat, Anshan 114009, Liaoning, Peoples R China
[4] Ansteel Grp Corp Ltd, Ansteel Iron & Steel Res Inst, Anshan 114009, Liaoning, Peoples R China
[5] Angang Steel Co Ltd, Gen Heavy Sect Mill, Anshan 114021, Liaoning, Peoples R China
基金
中国国家自然科学基金;
关键词
Blast furnace gas; Iron and steel industry; Data quality improvement; Artificial intelligence; Gas generation prediction; MULTIOBJECTIVE OPTIMIZATION; SCHEDULING OPTIMIZATION; IRON; ALGORITHM;
D O I
10.1007/s42243-023-00944-2
中图分类号
TF [冶金工业];
学科分类号
0806 ;
摘要
The real-time energy flow data obtained in industrial production processes are usually of low quality. It is difficult to accurately predict the short-term energy flow profile by using these field data, which diminishes the effect of industrial big data and artificial intelligence in industrial energy system. The real-time data of blast furnace gas (BFG) generation collected in iron and steel sites are also of low quality. In order to tackle this problem, a three-stage data quality improvement strategy was proposed to predict the BFG generation. In the first stage, correlation principle was used to test the sample set. In the second stage, the original sample set was rectified and updated. In the third stage, Kalman filter was employed to eliminate the noise of the updated sample set. The method was verified by autoregressive integrated moving average model, back propagation neural network model and long short-term memory model. The results show that the prediction model based on the proposed three-stage data quality improvement method performs well. Long short-term memory model has the best prediction performance, with a mean absolute error of 17.85 m(3)/min, a mean absolute percentage error of 0.21%, and an R squared of 95.17%.
引用
收藏
页码:864 / 874
页数:11
相关论文
共 50 条
  • [31] A Fuzzy Modeling Method Based on Dirichlet Process Mixture Model for Blast Furnace Gas System
    Huang, Yan
    Lv, Zheng
    Liu, Ying
    Wang, Wei
    IFAC PAPERSONLINE, 2018, 51 (21): : 301 - 306
  • [32] Assessment of methanol and electricity co-production plants based on coke oven gas and blast furnace gas utilization
    Xu, Yi-Peng
    Liu, Run-Hao
    Shen, Meng-Zhuo
    Lv, Zheng-Ang
    Chupradit, Supat
    Metwally, Ahmed Sayed M.
    Sillanpaa, Mika
    Qian, Qian
    SUSTAINABLE PRODUCTION AND CONSUMPTION, 2022, 32 : 318 - 329
  • [33] Analysis on the Oversize Blast Furnace Desulfurization and a Sulfide Capacity Prediction Model Based on Congregated Electron Phase
    Wang Zhenyang
    Zhang Jianliang
    An Gang
    Liu Zhengjian
    Cheng Zhengming
    Huang Junjie
    Zhang Jingwei
    METALLURGICAL AND MATERIALS TRANSACTIONS B-PROCESS METALLURGY AND MATERIALS PROCESSING SCIENCE, 2016, 47 (01): : 127 - 134
  • [34] Gas Permeability Improvement Mechanism at the Lower Part of Blast Furnace by Converter Slag Injection from Tuyere and Quantification of its Effect
    Kato, Tsugunori
    Kasai, Akito
    Tadai, Rikizo
    Nozawa, Kentaro
    TETSU TO HAGANE-JOURNAL OF THE IRON AND STEEL INSTITUTE OF JAPAN, 2019, 105 (12): : 1118 - 1125
  • [35] Exergy-based parallel between steam- and combined-cycle power plant configurations burning blast furnace gas
    de Campos, Gustavo Bonolo
    Bringhenti, Cleverson
    Tomita, Jesuino Takachi
    INTERNATIONAL JOURNAL OF EXERGY, 2019, 29 (01) : 89 - 108
  • [36] Supply and Demand Forecasting of Blast Furnace Gas Based on Artificial Neural Network in Iron and Steel Works
    Zhang Qi
    Gu Yan-liang
    Ti Wei
    Cai Jiu-ju
    MANUFACTURING SCIENCE AND MATERIALS ENGINEERING, PTS 1 AND 2, 2012, 443-444 : 183 - 188
  • [37] A Deep Learning-based approach for forecasting off-gas production and consumption in the blast furnace
    Dettori, Stefano
    Matino, Ismael
    Colla, Valentina
    Speets, Ramon
    NEURAL COMPUTING & APPLICATIONS, 2022, 34 (02) : 911 - 923
  • [38] A Novel MIMO T-S Fuzzy Modeling for Prediction of Blast Furnace Molten Iron Quality With Missing Outputs
    Li, Junpeng
    Hua, Changchun
    Yang, Yana
    Guan, Xinping
    IEEE TRANSACTIONS ON FUZZY SYSTEMS, 2021, 29 (06) : 1654 - 1666
  • [39] Data-Driven Bayesian-Based Takagi-Sugeno Fuzzy Modeling for Dynamic Prediction of Hot Metal Silicon Content in Blast Furnace
    Li, Junpeng
    Hua, Changchun
    Yang, Yana
    Guan, Xinping
    IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS, 2022, 52 (02): : 1087 - 1099
  • [40] Optimization of Sizing and Operation Strategy of Distributed Generation System Based on a Gas Turbine and Renewable Energy
    Kim, Hye-Rim
    Kim, Tong-Seop
    ENERGIES, 2021, 14 (24)