Modeling of the Thermal State Change of Blast Furnace Hearth With Support Vector Machines

2012 ◽  
Vol 59 (2) ◽  
pp. 1134-1145 ◽  
Author(s):  
Chuanhou Gao ◽  
Ling Jian ◽  
Shihua Luo
Keyword(s):  
Blast Furnace ◽  
Support Vector Machines ◽  
Thermal State ◽  
Support Vector ◽  
State Change ◽  
Furnace Hearth ◽  
Blast Furnace Hearth ◽  
Vector Machines

scholarly journals Monitoring Liquid Level of Blast Furnace Hearth and Torpedo Ladle by Electromotive Force Signal

Metals ◽  
2018 ◽  
Vol 8 (9) ◽  
pp. 665 ◽  
Author(s):  
Ying Li ◽  
Lei Zan ◽  
Yao Ge ◽  
Han Wei ◽  
Zhenghao Zhang ◽  
...  
Keyword(s):  
Blast Furnace ◽  
Electromotive Force ◽  
Thermal State ◽  
Single Layer ◽  
Graphite Crucible ◽  
The State ◽  
Liquid Level ◽  
Double Layers ◽  
Furnace Hearth ◽  
Blast Furnace Hearth

The state of a blast furnace hearth, especially the liquid level of hot metal and slag during the tapping process, is of crucial importance with respect to a long campaign blast furnace. In practice, the state of the hearth is evaluated mainly by the experience of operators. In this paper, the electromotive force (EMF) is used to monitor the liquid level of a laboratory scale of blast furnace hearth and the effect of liquid level, EMF sensors position and the thickness of refractory on EMF signals are tested using a single layer of water and double layers of water and oil. After laboratory experiments, the electromotive force (EMF) is used to monitor the liquid level of torpedo ladle successfully. Laboratory experimental results show that the change in liquid level can be characterized by EMF signal. The state of liquid surface and local thermal state cause the EMF signal to vary in the circumferential direction of the vessel. Furthermore, the EMF signal magnitude decreases with the decrease of the thickness of the graphite crucible. Finally, the main conclusions of the laboratory experiment are supported by the torpedo ladle experiment.

Predicting the thermal state of the blast-furnace hearth

2009 ◽  
Vol 39 (5) ◽  
pp. 402-405 ◽  
Author(s):  
V. I. Bol’shakov ◽  
I. G. Murav’eva ◽  
Yu. S. Semenov ◽  
S. T. Shuliko ◽  
E. I. Shumel’chik
Keyword(s):  
Blast Furnace ◽  
Thermal State ◽  
Furnace Hearth ◽  
Blast Furnace Hearth

scholarly journals Improving the Solution of Least Squares Support Vector Machines with Application to a Blast Furnace System

2012 ◽  
Vol 2012 ◽  
pp. 1-12 ◽  
Author(s):  
Ling Jian ◽  
Shuqian Shen ◽  
Yunquan Song
Keyword(s):  
Blast Furnace ◽  
Support Vector Machines ◽  
Saddle Point ◽  
Least Squares ◽  
Null Space ◽  
Support Vector ◽  
Point System ◽  
Trend Prediction ◽  
Vector Machines ◽  
Saddle Point System

The solution of least squares support vector machines (LS-SVMs) is characterized by a specific linear system, that is, a saddle point system. Approaches for its numerical solutions such as conjugate methods Sykens and Vandewalle (1999) and null space methods Chu et al. (2005) have been proposed. To speed up the solution of LS-SVM, this paper employs the minimal residual (MINRES) method to solve the above saddle point system directly. Theoretical analysis indicates that the MINRES method is more efficient than the conjugate gradient method and the null space method for solving the saddle point system. Experiments on benchmark data sets show that compared with mainstream algorithms for LS-SVM, the proposed approach significantly reduces the training time and keeps comparable accuracy. To heel, the LS-SVM based on MINRES method is used to track a practical problem originated from blast furnace iron-making process: changing trend prediction of silicon content in hot metal. The MINRES method-based LS-SVM can effectively perform feature reduction and model selection simultaneously, so it is a practical tool for the silicon trend prediction task.

Sign in / Sign up

Export Citation Format

Share Document