Application of Least Squares Support Vector Machines to Predict the Silicon Content in Blast Furnace Hot Metal

Silicon content in blast furnace hot metal, acting as an important indicator of the inner thermal state of the furnace, is needed to be controlled strictly within proper bounds to produce iron with high quality. For this purpose, extensive thermodynamic and kinetic research on silicon transfer inside the blast furnace has been carried out in the past decades. Based on these studies, a fundamental understanding about this phenomenon has been progressively established. However, up to now, a fully reliable mechanistic model for silicon prediction is not still to emerge because of the exceeding difficulty in quantifying ironmaking process chemistry. Thus, data-driven modeling is being investigated quite intensively recently in an attempt to solve this intractable problem. In the process of data-driven modeling, the frequently used tools include neural net, partial least squares, fuzzy mathematics, nonlinear time series analysis, chaos, etc. The main motivation is that, most of these tools have universal nonlinear approximation capabilities and can approach any function in any precision. As an alternative tool, Least Squares Support Vector Machines (LS-SVM) is applied in this paper to predict the silicon content in BF hot metal. The results indicate that the hit rate of silicon prediction is improved greatly when using the established predictive model and the prediction precision can reach 10 3 in the magnitude.

[1]  F. Obeso,et al.  Hot metal temperature prediction in blast furnace using advanced model based on fuzzy logic tools , 2007 .

[2]  Richard J. Fruehan,et al.  Kinetics of the reaction of SiO(g) with carbon saturated iron , 1985 .

[3]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[4]  T. Bhattacharya.  Prediction of Silicon Content in Blast Furnace Hot Metal Using Partial Least Squares (PLS) , 2005 .

[5]  Gene H. Golub,et al.  Generalized cross-validation as a method for choosing a good ridge parameter , 1979, Milestones in Matrix Computation.

[6]  Richard J. Fruehan,et al.  The reaction of SiO(g) with liquid slags , 1986 .

[7]  Abdul Rahman Mohamed,et al.  Neural networks for the identification and control of blast furnace hot metal quality , 2000 .

[8]  Jian Chen,et al.  A predictive system for blast furnaces by integrating a neural network with qualitative analysis , 2001 .

[9]  Frank Pettersson,et al.  Nonlinear Prediction of the Hot Metal Silicon Content in the Blast Furnace , 2007 .

[10]  N. K. Batra.  ADIABATIC FLAME TEMPERATURE AND SILICON TRANSFER IN A BLAST FURNACE , 1997 .

[11]  Frank Pettersson,et al.  A genetic algorithms based multi-objective neural net applied to noisy blast furnace data , 2007, Appl. Soft Comput..

[12]  Henrik Saxén,et al.  Application of nonlinear time series analysis to the prediction of silicon content of pig iron , 2002 .

[13]  Chuanhou Gao,et al.  Time-dependent Fractal Characteristics on Time Series of Silicon Content in Hot Metal of Blast Furnace , 2005 .

[14]  F. Pettersson,et al.  Evolving Nonlinear Time-Series Models of the Hot Metal Silicon Content in the Blast Furnace , 2007 .

[15]  K. Aihara,et al.  Time series analysis and prediction on complex dynamical behavior observed in a blast furnace , 2000 .

[16]  Zhi-Min Zhou.  Measurement of time-dependent fractal dimension for time series of silicon content in pig iron , 2007 .

[17]  Masanori Tokuda,et al.  Kinetics of Silicon Transfer from a Gas Phase to Molten Iron , 1972 .

[18]  Masanori Tokuda,et al.  The transfer of silicon from the gas phase to molten iron in the blast furnace , 1976 .

[19]  Gang Du,et al.  A Blast Furnace Prediction Model Combining Neural Network with Partial Least Square Regression , 2005 .

[20]  Faustino Obeso,et al.  Blast furnace hot metal temperature prediction through neural networks-based models , 2004 .

[21]  Jiusun Zeng,et al.  Identification of Multi-fractal Characteristics of Silicon Content in Blast Furnace Hot Metal , 2007 .