Abstract
Gas stirring is commonly used in pyrometallurgical vessels to enhance mass and heat transfer and to promote impurity removal. In the case of secondary steelmaking, the spout eye area is caused by the escape of the gas from the top of the smelt where the liquid steel is directly exposed to the air, and oxygen can be picked up through the spout eye area that can reduce the quality of steel. Thus, controlling the size of the spout eye area is very important to improving the quality of the steel and to keeping the consistency of the product. The set of prevailing models to predict spout eye size are based on specific practically difficult variables, e.g., height of slag in hot upper layer of vessels and gas flow rate at nozzle exit. Recently, the cold model results showed that the stirring process can be conveniently monitored by the signals such as (1) the image signal from the top of the vessel, (2) the sound of the stirring process, and (3) the vibration on the wall of the vessel. This article outlines the key details of a novel research investigation using neural-network–based predictive modeling such as general regression neural networks (GRNN) with genetic adaptive calibrations. Predictive capacities and generalization potentials of five model constructs (i.e., with different sets of input parameters) were explored, and the neural net modeling yielded encouraging outcomes, e.g., (1) excellent goodness-of-fit generalization measures including high values of correlation and R 2 validation parameters (e.g., r = 0.921 and R 2 = 0.845 in a model validation), and (2) low values of root mean square of errors (e.g., 3.034). Overall, the research outlined in this article demonstrates that the spout eye size can be effectively predicted by predictive neural net modeling with convenient and practically measurable variables such as sound and vibration observations on the steelmaking vessels. These results have only been demonstrated for a cold model of the process, and further work is required to show that this approach can be extended to industrial operations.
Similar content being viewed by others
Abbreviations
- A*:
-
nondimensional spout eye area
- a :
-
average relative spout eye area within 4.0 seconds
- v :
-
average vibration magnitude (m/s2)
- \( \dot{v}_{i} \) :
-
acceleration collected on the wall of the vessel at a sampling rate of 250 Hz, m/s2
- vf :
-
summation of vibration amplitudes corresponding to the frequency (1–120 Hz)
- l i :
-
amplitude of the spectrum
- s :
-
average of sound intensity (W/m2)
- sf :
-
summation of sound amplitudes corresponding to the frequency (500–4500 Hz)
- h :
-
height of upper layer slag/oil (m)
- Q :
-
stirring gas flow rate (m3/s)
- R 2 :
-
coefficient of multiple determination, known as the Nash-Sutcliffe efficiency coefficient
- r :
-
correlation between the actual and predicted values
- RMSE:
-
root mean square of errors
References
E. Turkdogan and R.J. Fruehan: Fundamentals of Iron and Steelmaking, 11th ed., R.J. Fruehan, ed., The AISE Steel Foundation, Warrendale, PA, 1998.
G.A. Brooks and Subgayo: ISSTech 2003 Conference Proceedings, Iron & Steel Society, Warrendale, PA, 2003.
G.A. Brooks and Subgayo: Ironmaker Steelmaker, 2003, vol. 30 (10), pp. 17–21.
K.J. Graham, K. Krishnapisharody, G.A. Irons, and J.F. MacGregor: Can. Metall. Q., 2007, vol. 46 (4), pp. 397–406.
Subagyo and G.A. Brooks: ISIJ Int., 2003, vol. 43 (8), pp. 1286–89.
M. Iguchi, K.-I. Miyamoto, S. Yamashita, D. Iguchi, and M. Zeze: ISIJ Int., 2004, vol. 44, no. 3, pp. 636–38.
K. Krishnapisharody and G.A. Irons: Metall. Mater. Trans. B, 2006, vol. 37B, pp. 763–72.
K. Krishnapisharody and G.A. Irons: Metall. Mater. Trans. B, 2007, vol. 38B, pp. 501–02.
K. Krishnapisharody and G.A. Irons: Metall. Mater. Trans. B, 2007, vol. 38B, pp. 367–75.
K. Krishnapisharody and G.A. Irons: Metall. Mater. Trans. B, 2007, vol. 38B, pp. 377–88.
D. Mazumdar and J.W. Evans: Metall. Mater. Trans. B, 2004, vol. 35B, pp. 400–04.
D. Mazumdar and J.W. Evans: Metall. Mater. Trans. B, 2007, vol. 38B, pp. 497–99.
Subagyo, G.A. Brooks, and G.A. Irons: ISIJ Int., 2003, vol. 43 (2), pp. 262–63.
K. Yonezawa and K. Schwerdtfeger: Metall. Mater. Trans. B, 1999, vol. 30B, pp. 411–18.
K. Yonezawa and K. Schwerdtfeger: Metall. Mater. Trans. B, 2000, vol. 31B, pp. 461–68.
K. Yonezawa and K. Schwerdtfeger: ISIJ Int., 2004, vol. 44(1), pp. 217–19.
K.J. Graham, K. Krishnapisharody, G.A. Irons, and J.F. MacGregor: AISTech - Iron and Steel Technology Conference Proceedings, 2007.
X. Xu, G.A. Brooks, and W. Yang: Chemeca 2008, Newcastle, Australia. 2008.
X. Xu, G. Brooks, and W. Yang: Metall. Mater. Trans. B, 2010, vol. 41B, pp. 1025–32.
X. Xu, G.A. Brooks, and W. Yang: 2010 TMS Conference (Jim Evans Symposium), Seattle, WA, 2010.
S. Haykin: Neural Networks: A Comprehensive Foundation, 2nd ed., Prentice Hall, Upper Saddle River, NJ, 1999.
X. Liu and D.T. Pham: Neural Networks for Identification, Prediction, and Control, Springer-Verlag, London, U.K., 1995.
P. Peretto: An Introduction to Modeling of Neural Networks, Cambridge University Press, Cambridge, U.K., 1992.
V.N. Vapnik: The Nature of Statistical Learning Theory, 2nd ed., Springer-Verlag, New York, NY, 2000.
M.A. Reuter, T.J. Van Der Walt, and J.S.J. Van Deventer: Metall. Trans. B, 1992, vol. 23B, pp. 643–50.
A. Meghlaoui, R.T. Bui, J. Thibault, L. Tikasz, and R. Santerre: Metall. Mater. Trans. B, 1998, vol. 29B, pp. 1007–19.
W. Chang and S. Na: Metall. Mater. Trans. B, 2001, vol. 32B, pp. 723–31.
E. Palaneeswaran, P.E.D. Love, M. Kumaraswamy, and S.T. Ng: Build. Res. Inform., 2008, vol. 36, no. 5, pp. 450–65.
Z. Zivkovic, I. Mihajlovic, I. Djuric, and N. Strbac: Metall. Mater. Trans. B, 2010, vol. 41B, pp. 1116–22.
L. Rutkowski:. IEEE Trans. Neural Networks, 2004, vol. 15, no. 3, pp. 576–96.
D.F. Specht: IEEE Trans. Neural Networks, 1991, vol. 2, no. 6, pp. 568–76.
X.D. Xu, G.A. Brooks, and W. Yang: Ironmaking Steelmaking, 2010, vol. 37, no. 8, pp. 620–23.
Author information
Authors and Affiliations
Corresponding author
Additional information
Manuscript submitted June 13, 2011.
Rights and permissions
About this article
Cite this article
Palaneeswaran, E., Brooks, G. & Xu, X.B. Neural-Net–Based Predictive Modeling of Spout Eye Size in Steelmaking. Metall Mater Trans B 43, 571–577 (2012). https://doi.org/10.1007/s11663-012-9636-4
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11663-012-9636-4