The present work presents a model based on fuzzy logic tools to predict and simulate the hot metal temperature in a blast furnace (BF). As input variables this model uses the control variables of a current BF such as moisture, pulverised coal injection, oxygen addition, mineral/coke ratio and blast volume, and it yields as a result of the hot metal temperature. The variables employed to develop the model have been obtained from data supplied by current sensors of a Spanish BF. In the model training stage the adaptive neurofuzzy inference system and the subtractive clustering algorithms have been used.
Get full access to this article
View all access options for this article.
References
1.
FalzettiM.MochónJ.KumarS.: Proc. Conf. on ‘Application of artificial neural networks systems in the steel industry’, Brussels, Belgium, September 1998, ECSC Workshop, European Commission, 337.
TerpakJ.DorcakL.KostialI.: Proc. ICCC 2000 Conf., Podbanske, Slovakia, May2000, CSSS, 38.
4.
FalzettiM.ChiarottiU.JiménezJ.MochónJ.: ‘Investigation of fuzzy logic and neural network based strategies for control optimisation of ironmaking process’, EUR19348, 92–828-9221-2, European Commission, 2000, 24.
5.
MorrisJ.MartinE. B.: Proc. Conf. on ‘Application of artificial neural networks systems in the steel industry’, Brussels, Belgium, September 1998, ECSC Workshop, European Commission, 337.
GulleyN.JangJ. R.: ‘Fuzzy logic toolbox user’s guide’, The Mathworks, Natick, MA, 1995–2005.
11.
JangJ. S. R.SunC. T.MizutaniE.: ’Neuro-fuzzy and soft computing: a computational approach to learning and machine intelligence’, 607–614; 1996, Upper Saddle River, NJ, Prentice-Hall.
12.
YagerR. R.FilevD. P.: J. Intell. Fuzzy Syst., 1994, 2, 209.
13.
HensonM. A.SeborgD. E.: ‘Nonlinear process control’, 432; 1997, Upper Saddle River, NJ, Prentice Hall.
14.
SiegelmannH. T.: ‘Computational capabilities of recurrent NARX neural networks’, Technical report UMIACS-TR-95–12and CS-TR-3408, University of Maryland, College Park, MD, USA, 1997.
