Data-driven recursive subspace identification based online modelling for prediction and control of molten iron quality in blast furnace ironmaking

Data-driven recursive subspace identification based online modelling for prediction and control of molten iron quality in blast furnace ironmaking

For access to this article, please select a purchase option:

Buy article PDF
(plus tax if applicable)
Buy Knowledge Pack
10 articles for $120.00
(plus taxes if applicable)

IET members benefit from discounts to all IET publications and free access to E&T Magazine. If you are an IET member, log in to your account and the discounts will automatically be applied.

Learn more about IET membership 

Recommend Title Publication to library

You must fill out fields marked with: *

Librarian details
Your details
Why are you recommending this title?
Select reason:
IET Control Theory & Applications — Recommend this title to your library

Thank you

Your recommendation has been sent to your librarian.

In blast furnace ironmaking operation, the molten iron temperature and the silicon content ([Si]) are two key molten iron quality (MIQ) indices. The measurement, modelling and control of these indices have always been of importance in metallurgic engineering and automation. In this study, data-driven methods for online prediction and control of multivariate MIQ indices are proposed by integrating hybrid modelling and control techniques together. First, a data-driven hybrid method that combines canonical correlation analysis and correlation analysis is proposed to identify the most influential controllable variables as the modelling inputs from multitudinous factors. Then a data-driven online model for prediction of MIQ is established by recursive subspace identification (R-SI) with forgetting factor. Unlike the conventional SI modelling, the proposed R-SI-based online modelling only identifies subspace matrices for a data-driven input–output model without explicitly estimating the system matrices, which can reduce the computation complexity. Finally, a predictive controller is designed to maintain the MIQ indices at an expected level by using the developed MIQ prediction model as an online predictor. Since the parameters of the predictor are updated adaptively by the latest process data, the predictive controller can produce more reliable and stable control performance. Experiments using industrial data have verified the superiority and practicability of the proposed methods.


    1. 1)
      • 1. Zhou, B., Ye, H., Zhang, H.F., et al: ‘Process monitoring of iron- making process in a blast furnace with PCA-based methods’, Control Eng. Pract., 2016, 47, pp. 114.
    2. 2)
      • 2. Saxén, H., Gao, C.H., Gao, Z.: ‘Data-driven time discrete models for dynamic prediction of the hot metal silicon in the blast furnace – a review’, IEEE Trans. Ind. Inf., 2013, 9, (4), pp. 22132225.
    3. 3)
      • 3. Kuang, S.B., Li, Z.Y., Yan, D.L., et al: ‘Numerical study of hot charge operation in ironmaking blast furnace’, Miner. Eng., 2014, 63, (8), pp. 4556.
    4. 4)
      • 4. Östermark, R., Saxén, H.: ‘VARMAX-modeling of blast furnace process variables’, Eur. J. Oper. Res., 1996, 90, (1), pp. 85101.
    5. 5)
      • 5. Gao, C.H., Jian, L., Luo, S.H.: ‘Modeling of the thermal state change of blast furnace hearth with support vector machines’, IEEE Trans. Ind. Electron., 2011, 59, (2), pp. 11341145.
    6. 6)
      • 6. Jian, L., Gao, C.H., Xia, Z.H.: ‘Constructing multiple kernel learning framework for blast furnace automation’, IEEE Trans. Autom. Sci. Eng., 2012, 9, (4), pp. 763777.
    7. 7)
      • 7. Yuan, M., Zhou, P., Li, M.L., et al: ‘Intelligent multivariable modeling of blast furnace molten iron quality based on dynamic AGA-ANN and PCA’, J. Iron Steel Res. Int., 2015, 22, (6), pp. 487495.
    8. 8)
      • 8. Zhou, P., Yuan, M., Wang, H., et al: ‘Multivariable dynamic modeling for molten iron quality using online sequential random vector functional-link networks with self-feedback connections’, Inf. Sci., 2015, 325, pp. 237255.
    9. 9)
      • 9. Shi, L., Li, Z.L., Li, J.P.: ‘Model of hot metal silicon content in blast furnace based on principal component analysis application and partial least square’, J. Iron Steel Res., Int., 2011, 18, (10), pp. 1316.
    10. 10)
      • 10. Bhattacharaya, T.: ‘Prediction of silicon content in blast furnace hot metal using partial least squares (PLS)’, ISIJ Int., 2005, 12, (45), pp. 19431945.
    11. 11)
      • 11. Radhakrishnan, V.R., Mohamed, A.R.: ‘Neural networks for the identification and control of blast furnace hot metal quality’, J. Process Control, 2000, 10, (6), pp. 509524.
    12. 12)
      • 12. Jian, L., Gao, C.H.: ‘Binary coding SVMs for the multiclass problem of blast furnace system’, IEEE Trans. Ind. Electron., 2013, 60, (9), pp. 38463856.
    13. 13)
      • 13. Zhou, P., Li, R.F., Guo, D.W., et al: ‘GA-M-SVR dynamic modeling for multivariate molten iron quality indices in blast furnace ironmaking process’, J. Control Theory Appl., 2016, 33, pp. 19.
    14. 14)
      • 14. Zeng, J.S., Gao, C.H., Su, H.Y.: ‘Data-driven predictive control for blast furnace ironmaking process’, Comput. Chem. Eng., 2010, 34, (31), pp. 18541862.
    15. 15)
      • 15. Zeng, J.S., Gao, C.H.: ‘Improvement of identification of blast furnace ironmaking process by outlier detection and missing value imputation’, J. Process Control, 2009, 19, (9), pp. 15191528.
    16. 16)
      • 16. Marutiram, K., Radhikrishnan, V.R.: ‘Predictive control of blast furnaces’. Proc. of IEEE Region 10 Int. Conf. on EC3-Energy, Computer, Communication and Control Systems, 1991, vol. 3, pp. 488491.
    17. 17)
      • 17. Hardoon, D., Szedmak, S., Taylor, J.S.: ‘Canonical correlation analysis: an overview with application to learning methods’, Neural Comput., 2004, 16, (12), pp. 26392664.
    18. 18)
      • 18. Sargin, M.E., Yemez, Y., Erzin, E., et al: ‘Audiovisual synchronization and fusion using canonical correlation analysis’, IEEE Trans. Multimedia, 2007, 9, (7), pp. 13961403.
    19. 19)
      • 19. Mikheev, A.V., Kazakov, B.N.: ‘Correlation analysis of spectroscopic data’, J. Lumin., 2017, 184, pp. 117122.
    20. 20)
      • 20. Overschee P., Van, Moor B., De: ‘N4SID: Subspace algorithms for the identification of combined deterministic-stochastic systems’, Automatica, 1994, 30, (1), pp. 7593.
    21. 21)
      • 21. Verhaegen, M., Dewilde, P.: ‘Subspace model identification part 1. The output-error state-space model identification class of algorithms’, Int. J. Control, 1992, 56, (5), pp. 11871210.
    22. 22)
      • 22. Larimore, W.E.: ‘Canonical variate analysis in identification, filtering and adaptive control’. Proc. of the 29th CDC, Honolulu, HI, 1990, vol. 2, pp. 596601.
    23. 23)
      • 23. Zhou, P., Dai, W., Chai, T. Y.: ‘Multivariable disturbance observer based advanced feedback control design and its application to a grinding circuit’, IEEE Trans. Control Syst. Technol., 2014, 22, (22), pp. 14741485.
    24. 24)
      • 24. Liu, X.J, Kong, X.B., Lee, K.Y.: ‘Distributed model predictive control for load frequency control with dynamic fuzzy valve position modelling for hydro–thermal power system’, IET Control Theory Appl., 2016, 10, (14), pp. 16531664.
    25. 25)
      • 25. Zhou, P., Chai, T.Y., Zhao, J.H.: ‘DOB design for nonminimum-phase delay systems and its application in multivariable MPC control’, IEEE Trans. Circuits Syst. II, Exp. Briefs, 2012, 59, (8), pp. 525529.
    26. 26)
      • 26. Sun, J.Y., Keates, S.: ‘Canonical correlation analysis on data with censoring and error information’, IEEE Trans. Neural Netw. Learn. Syst., 2013, 24, (12), pp. 19091919.

Related content

This is a required field
Please enter a valid email address