Alloy additives prediction system for steelmaking process

Tadeusz Wieczorek, Paweł Świtała

Abstract


For adjustments of steel composition alloy additions are added to the ladle furnace for obtaining the grade of steel being manufactured. The prediction of steel composition is a crucial factor of secondary metallurgy. Calculations usually are made basing on the equilibrate chemical processes in molten steel. In the paper the problem of prediction of alloy additions has been solved using Artificial Neural Nets and the SVM algorithm. Review of applications of computational intelligence in secondary steelmaking has been made. The prediction system used by authors has been introduced. Details of the neural network prediction and other approaches to the prediction problem, i.e. Support Vector Regression Module and Multivariate Linear Regression have been introduced. Experimental results and the final conclusions and recommendations have been presented.

Keywords


secondary steelmaking; neural networks; computational intelligence; SVM

Full Text:

PDF (Polski)

References


Cortes C, Vapnik V.: Support-Vector Networks. Machine Learning, 20, 1995.

Engh T.A.: Principles of metal refining. Oxford Univ. Press, Oxford 1992.

Ghosh A.: Secondary steelmaking. CRC Press Boca Raton, New York 2001.

Drucker H., Burges C.J.C., Kaufman L., Smola A., Vapnik V.: Support Vector Regression Machines. Advances in Neural Information Processing Systems 9, NIPS 1996, MIT Press 1997, s. 155-161.

Karbowniczek M.: Elektrometalurgia stali. AGH, Kraków 1993.

Larose D.: Metody i modele eksploracji danych. PWN, Warszawa 2008.

Meireles M., Almeida P., Simoes M.: A Comprehensive Review for Industrial Applicability of Artificial Neural Networks. IEEE Transactions on Industrial Electronics 2003, 3, s. 585-601.

Scholkopf B., Smola A.J.: Learning With kernels. MIT Press Cambridge MA 2002.

Siemens A.G.: SIMELT NEC - neural network based energy control efficiency. Industrial solution and services. Siemens Press, 2005, s. 1-8.

Wieczorek T.: Optymalizacja struktury sztucznych sieci neuronowych typu perceptron wielowarstwowy. W: Węgrzyn S., Znamierowski L., Czachórski T,, Kozielski S. (red.) Nowe technologie sieci komputerowych. WKŁ, Warszawa 2006, s. 153-164

Wieczorek T.: Neuronowe modelowanie procesów technologicznych. Politechnika Śląska, Gliwice 2008.

Wieczorek T., Mączka K., Świtała P.: Automatyczne tworzenie baz wiedzy z wykorzystaniem drzew decyzyjnych. Bazy danych - nowe technologie. Architektura, metody formalne i zaawansowana analiza danych. Kozielski S., Małysiak B., Kasprowski P., Mrozek D. (red). WKŁ, Warszawa 2007, s. 385-392.

Wieczorek T., Pilarczyk M.: Classification of steel scrap in the EAF process using image analysis methods. Archives of Metallurgy and Materials, 2008, Vol.53, No. 2, s. 613-618.

Wieczorek T., Świtała P.: Wykorzystanie algorytmu CART do automatycznego tworzenia bazy wiedzy systemu ekspertowego. Bazy danych - nowe technologie, WKŁ, Warszawa 2008.

Yanguang S., Daixian W., Yan T., Shi T., Fang Y., Wang S.: An Intelligent Ladle Furnace Control System, Proceedings of the 3th World Congress on Intelligent Control and Autmation, Hefei P.R. China, 1,2000, s. 330+334.




DOI: http://dx.doi.org/10.21936/si2010_v31.n2B.423