Advertisement

Prediction of the hot metal silicon content in blast furnace based on extreme learning machine

  • Haigang Zhang
  • Sen ZhangEmail author
  • Yixin Yin
  • Xianzhong Chen
Original Article

Abstract

Silicon content in hot metal is an important indicator for the thermal condition inside the blast furnace in the iron-making process. The operators often refer the silicon content and its change trend for the guidance of next production. In this paper, we establish the neural network model for the prediction of silicon content in hot metal based on extreme learning machine (ELM) algorithm. Considering the imbalanced operating data, weighted ELM (W-ELM) algorithm is employed to make prediction for the change trend of silicon content. The outliers hidden in the real production data often tend to undermine the accuracy of prediction model. First, an outlier detection method based on W-ELM model is proposed from a statistical view. Then we modified the ordinary ELM and W-ELM algorithms in order to reduce the interference of outliers, and proposed two enhanced ELM frameworks respectively for regression and classification applications. In the simulation part, the real operating data is employed to verify the better performance of the proposed algorithm.

Keywords

Extreme learning machine Blast furnace Silicon content Outlier detection 

Notes

Acknowledgements

This work has been supported by the National Natural Science Foundation of China (NSFC Grant No. 61333002, No. 61673056 and No. 61671054).

References

  1. 1.
    Gao CH, Ge QH and Jian L (2014) Rule extraction from fuzzy-based blast furnace SVM multiclassifier for decision-making. IEEE Trans Fuzzy Syst 22:586–596CrossRefGoogle Scholar
  2. 2.
    Chen XZ, Wei JD, Xu D (2012) 3-dimension imaging system of burden surface with 6-radars array in a blast furnace. ISIJ Int 52:2048–2054CrossRefGoogle Scholar
  3. 3.
    Bhattacharaya T (2005) Prediction of silicon content in blast furnace hot metal using partial least squares (PLS). ISIJ Int 45:1943–1945CrossRefGoogle Scholar
  4. 4.
    Jiao KX, Zhang JL, Liu ZJ, Liu F, Liang LS (2016) Formation mechanism of the graphite-rich protective layer in blast furnace hearths. Int J Miner Metall Mater 23:16–24CrossRefGoogle Scholar
  5. 5.
    SAXéN H, Pettersson F (2007) Nonlinear prediction of the hot metal silicon content in the blast furnace. ISIJ Int 47:1732–1737CrossRefGoogle Scholar
  6. 6.
    Jian L, Gao CH (2013) Binary coding SVMs for the multiclass problem of blast furnace system. IEEE Trans Ind Electron 60:3846–3856CrossRefGoogle Scholar
  7. 7.
    Nick RS, Tillander A, Jonsson TL (2013) Mathematical model of solid flow behavior in a real dimension blast furnace. ISIJ Int 53:979–987CrossRefGoogle Scholar
  8. 8.
    stermark R, Saxén H (1996) VARMAX-modelling of blast furnace process variables. Eur J Oper Res 90: 85–101CrossRefzbMATHGoogle Scholar
  9. 9.
    Cao JW, Zhang K, Luo M, Yin C, Lai X (2016) Extreme learning machine and adaptive sparse representation for image classification. Neural Netw 81:91–102CrossRefGoogle Scholar
  10. 10.
    Zeng JS, Gao CH (2009) Improvement of identification of blast furnace ironmaking process by outlier detection and missing value imputation. J Proc Control 19:1519–1528CrossRefGoogle Scholar
  11. 11.
    Luo SH, Liu XG, Zeng JS (2007), Identification of multi-fractal characteristics of silicon content in blast furnace hot metal. ISIJ Int 47:1102–1107CrossRefGoogle Scholar
  12. 12.
    Waller M, Saxén H (2000) On the development of predictive models with applications to a metallurgical process. Ind Eng Chem Res 39:982–988CrossRefGoogle Scholar
  13. 13.
    Jian L, Gao CH, Xia ZQ(2011) A sliding-window smooth support vector regression model for nonlinear blast furnace system. Steel Res Int 82:169–179CrossRefGoogle Scholar
  14. 14.
    Tang X, Zhuang L, Jiang C (2009) Prediction of silicon content in hot metal using support vector regression based on chaos particle swarm optimization. Expert Syst Appl 36:11853–11857CrossRefGoogle Scholar
  15. 15.
    Zeng JS, Liu XG, Gao CH, Luo SH, Jian L (2008) Wiener model identification of blast furnace ironmaking process. ISIJ Int 48:1734–1738CrossRefGoogle Scholar
  16. 16.
    Zheng DL, Liang RX, Zhou Y, Wang Y (2003) A chaos genetic algorithm for optimizing an artificial neural network of predicting silicon content in hot metal, J Univ Sci Technol Beijing 10:68Google Scholar
  17. 17.
    Huang GB, Zhu QY, Siew CK (2006) Extreme learning machine: theory and applications. Neurocomputing 70:489–501CrossRefGoogle Scholar
  18. 18.
    Huang GB, Zhou HM, Ding XJ, Zhang R (2012) Extreme learning machine for regression and multiclass classification. IEEE Trans Syst Man Cybern Part B Cybern 2:513–529CrossRefGoogle Scholar
  19. 19.
    Mao W, Wang J, Xue Z (2016) An ELM-based model with sparse-weighting strategy for sequential data imbalance problem. Int J Mach Learn Cyber. doi: 10.1007/s13042-016-0509-z Google Scholar
  20. 20.
    Zong WW, Huang GB, Chen YQ (2012) Weighted extreme learning machine for imbalance learning. Neurocomputing 101:229–242CrossRefGoogle Scholar
  21. 21.
    Zhang HG, Yin YX, Zhang S (2016) An improved ELM algorithm for the measurement of hot metal temperature in blast furnace. Neurocomputing 174:232–237.CrossRefGoogle Scholar
  22. 22.
    Huang GB, Wang DH, Lan Y (2011) Extreme learning machines: a survey. Int J Mach Learn Cyber 2:107–122CrossRefGoogle Scholar
  23. 23.
    Zhou XR (2014) Online Regularized and Kernelized Extreme Learning Machines with Forgetting Mechanism, Mathematical Problems in Engineering, Article ID 938548.Google Scholar
  24. 24.
    Pearson RK (2002) Outliers in process modeling and identification. IEEE Trans Control Syst Technol 10:55–63CrossRefGoogle Scholar
  25. 25.
    Fletcher R (1981) Practical methods of optimization: vol. 2 constrained optimization. New YorkGoogle Scholar
  26. 26.
    Sohn BY, Kim GB (1997) Detection of outliers in weighted least squares regression. Korean J Comp Appl Math 4:441–452MathSciNetzbMATHGoogle Scholar
  27. 27.
    Sohn BY (1994), Weighted least squares regression diagnostics and its application to robust regression, Doctoral Thesis. Dept. of Statistics Korea University, SeoulGoogle Scholar
  28. 28.
    Limo K (1996) Robust error measure for supervised neural network learning with outliers. IEEE Trans Neural Netw 7:247–250Google Scholar
  29. 29.
    Jian L, Gao CH, Li L, Zend JS (2008), Application of least squares support vector machines to predict the silicon content in blast furnace hot metal. ISIJ Int 48:1659–1660CrossRefGoogle Scholar
  30. 30.
    Zhang K, Luo MX (2015) Outlier-robust extreme learning machine for regression problems. Neurocomputing 151:1519–1527CrossRefGoogle Scholar
  31. 31.
    Ankur M, Bikash CP (2016) Bad data detection in the context of leverage point attacks in modern power networks. IEEE Trans Smart Grid. doi: 10.1109/TSG.2016.2605923 Google Scholar
  32. 32.
    Cao J, Wang W, Wang J, Wang R (2016), Excavation equipment recognition based on novel acoustic statistical features. IEEE Trans Cybern. doi: 10.1109/TCYB.2016.2609999 Google Scholar
  33. 33.
    Bache K, Lichman M (2013) UCI Machine Learning Repository, (http://archive.ics.uci. edu/ml), School of Information and Computer Sciences, University of California, Irvine

Copyright information

© Springer-Verlag Berlin Heidelberg 2017

Authors and Affiliations

  • Haigang Zhang
    • 1
    • 2
  • Sen Zhang
    • 1
    • 2
    Email author
  • Yixin Yin
    • 1
    • 2
  • Xianzhong Chen
    • 1
    • 2
  1. 1.School of Automation and Electrical EngineeringUniversity of Science and Technology Beijing(USTB)BeijingChina
  2. 2.Key Laboratory of Advanced Control of Iron and Steel Process (Ministry of Education)University of Science and Technology BeijingBeijingChina

Personalised recommendations