Predictive Model for BOF Steelmaking Using RBF Neural Network

Abstract:

Effective control of the endpoint steel temperature and contents of carbon, sulphur, etc. is one of the main tasks of BOF steelmaking process. This paper established a multivariable predictive model for BOF steelmaking using RBF neural network. The input data is pretreated and standardized. Receding horizon control method is used to increase the accuracy of the model. Simulation and experiment comparisons show that the model is validated and has high hit rate.

• Periodical: Applied Mechanics and Materials (Volumes 58-60)
• Pages: 1214-1218
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.58-60.1214
• Online since: June 2011
• Authors: Ya Ping Zhu, Xiao Dong Zhao, Sheng Lin Xu
• Keywords: Component Concentration, Endpoint Temperature, Hit Rate, Neural Network (NN)

References

[1] L. H. Yang, L. Liu and P. He: Control of Carbon content and temperature at end point for converter process based on 2-output neural network. Iorn and Steel, Vol. 37-11(2002)，pp.13-15.

[2] H. S. Lu and J. Z. Cao: Scheduling of BOF producing Molton steel for CSP and PM. International Conference on Computational Intelligence and Software Engineering, (2009), pp.1-3.

DOI: 10.1109/cise.2009.5364345

[3] P. Dario and P. Macro: Production scheduling in steelmaking-continuous plant. Computers and Chemical Engineering, Vol. 28-12(2004), pp.2823-2835.

DOI: 10.1016/j.compchemeng.2004.08.031

[4] C. Unal, T. Murat and D. Feridun: A thermodynamic analysis of a steel production step carried out in the ladle furnace. Applied Thermal Engineering, Vol. 21-8(2001), pp.643-655.

DOI: 10.1016/s1359-4311(00)00076-4

[5] S. M. Xie, K. sun and C. Chen: BOF endpoint prediction based on RBF neural network. Journal of Shengyang University of Technology, Vol. 28-4(2006), pp.405-408.

[6] M. Han, L. W. Jiang and Y. Zhao: endpoint prediction model of basic oxygen furnace steelmaking based on PSO-ICA and RBF neural network. Information and control, Vol. 39-1(2010), pp.82-87.

DOI: 10.1109/icicip.2010.5565236

[7] L. Z. Chang and Z. B. Li: study on BP neural net based converter static control model. Steelmaking, Vol. 22-6(2006), pp.41-44.

[8] S. M. Xie, X. W. Gao and T. Y. Chai: BOF endpoint prediction based on gray model. Journal of Iron and Steel Research, Vol. 11-4(1999), pp.46-51.

[9] D. F. Wang and H. W. Hong: Study on application of artificial neural network in end-point prediction of BOF steelmaking. Research on Iron and Steel, Vol. 143-2(2005), pp.27-31.

[10] L. P. Qu, Y. Y. Qu ,J. Bai and H. W. Zhang: Study on intelligent control strategy of BOF. Metallurgical Industry Automation, Vol. 43-3(2007), pp.24-27.

[11] S. M. Xie, J. Tao and T. Y. Chai: Intelligent method for BOF endpoint phosphorus estimation. Control Theory & Applications, Vol. 20-4(2003), pp.55-59.

[12] H. Tu, X. Hong, S. B. Shao and G. C. Jiang: Development of the dynamic Mn & P end-point control technology for BOF steelmaking. Shanghai Metals, Vol. 24-2(2002), pp.27-30.

[13] Y. L. Yang, Z. Xu and W. H. Wang: applicaiton of Matlab based RBF neural network. Mentallurgical Collections, Vol. 184-6(2009), pp.39-44.

[14] X.Y. Ding, J. Wang and S.P. Yang: Predictive model of BOF based on LM-BP neural network combining with learning rate. Second International Symposium on Knowledge Acuiqision and Modeling(2009), pp.155-157.

DOI: 10.1109/kam.2009.192

[15] J. Tao , S. S. Ouyang and X. Wang: Intelligent method for BOF endpoint [P] & [Mn] estimation. Proccedings of the 6th World Congress on Intelligent Control and Automation(2006), pp.7802-7806.

DOI: 10.1109/wcica.2006.1713488