Neural network-based prediction of additives in the steel refinement process
Tadeusz Wieczorek1
, Mirosław Kordos2
1Department of Management and Computer Science, Faculty of Material Engineering and Metallurgy, The Silesian University of Technology, Krasinskiego 8, 40-019 Katowice, Poland.
2Department of Mathematics and Computer Science, University of Bielsko-Biala, Willowa 2, 43-309 Bielsko-Biala, Poland.
DOI:
https://doi.org/10.7494/cmms.2010.1.0272
Abstract:
The paper presents a methodology of improving the efficiency of the steelmaking process based on computational intelligence solutions. To make fine adjustments to the steel composition alloy additions are added to the crude steel to adjust composition for the grade of steel being manufactured. The prediction of metal bath composition is a crucial factor in the economy of ladle furnace operation. Usually it is made by calculations based on the equilibrium of chemical reactions in molten steel. The paper presents the problem solution based on the prediction system build upon the committee of Artificial Neural Networks, the Support Vector Regression and Multivariate Linear Regression Model. A brief state of the art review of the application of computational intelligence (CI) in secondary steelmaking has been made. The prediction system used by authors has been introduced. Problems with data preparation have been presented. Experimental results and the final conclusions and recommendations have been presented. The solutions was implemented in one of the steelworks, where it allowed to improve the economy of the secondary steelmaking process.
Cite as:
Wieczorek, T., & Kordos, M. (2010). Neural network-based prediction of additives in the steel refinement process. Computer Methods in Materials Science, 10(1), 16 – 24. https://doi.org/10.7494/cmms.2010.1.0272
Article (PDF):
Keywords:
Steel refining, Neural networks, Computational intelligence, SVM, Prediction
References:
Bhadeshia, H., 1999, Neural Networks in Materials Science,ISIJ Int., 10, 966-979.
Bishop, C, 1996, Neural Networks for Pattern Recognition, Oxford University Press, Oxford. Engh, T.A., 1992, Principles of metal refining, Oxford Univ. Press, Oxford.
Eskander G. S., 2008, Round Trip Time Prediction Using the Symbolic Function Network Approach, Available from: http://arxiv.org/ftp/arxiv/papers/0806/0806.3646.pdf (last accessed 1.12.2009).
Ghosh, A, 2001, Secondary steelmaking, CRC Press Boca Raton, New York.
Jams, S.-L., 2001, Current status and future trends in the automation of mineral and metal processing, Control Engineering Practice, 9, 1021-1035.
Kodos, M., Duch, W., 2008, Variable Step Search Algorithm for Feedforward Networks, Neurocomputing, 71, 13-15, 2470-2480.
Li, M., Zhou, Z., Shi, L., 2004, The Neural Network Decoupling Control Based on The Internal Model Control, Proceedings of the 5th World Congress on Intelligent Control and Automation, Hangzhou, P.R. China.
Li, S., Gao, X., Chai, Т., 1997, Fuzzy control and its application in Ar stirring system, Proc. of Td Asian Control Conf. Seul., 3,711-714.
Meireles, M., Almeida, P., Simoes, M., 2003, A Comprehensive Review for Industrial Applicability of Artificial Neural Networks, IEEE Transactions on Industrial Electronics, 50, 3, 585-601.
Peter, J., Peaslee, K., Robertson, D., Thomas, В., 2005, Experimental Study of Kinetic Processes during the Steel Treatment at Two LMF’s, Conference Proceedings of AISTech, 1 &2, 959-973.
Roy, R., Collantes, L., Berdou, J., Whittaker H., Madill, J., 1999, Fuzzy Process Modeling for Secondary Steelmaking, Proc. of 18,h International Conference of the North American Fuzzy Information Processing Society, New York, 1, 864-868.
Setiono, R.,Thong, J., 2004, An approach to generate rules from neural networks for regression problems, European Journal of Operational Research, 155, 1,239-250.
Siemens A.G.,2005, SIMELT NEC – neural network based energy control efficiency, Industrial solution and services, Siemens Press, 1-8.
Smoła A, J., Scholkopf В., 1998, A Tutorial on Support Vector Regression, Available from:
http://www.svms.org/regression/SmSc98.pdf (last accessed 1.12.2009).
Staib, W.E., 1993, The Intelligent Arc Furnace, Steel Technology Int., 2, 103-107.
Van Gorp, J.,1999, Steel Plant Modeling and Analysis Using a Neural Network, ANNIE, Intelligent Engineering Systems Through Artificial Neural Networks, 9, 739-744.
Wieczorek, Т.,Mączka, К., Świtała, P., 2007, Automatyczne tworzenie baz wiedzy z wykorzystaniem drzew decyzyjnych, Bazy danych – nowe technologie. Bezpieczeństwo wybrane technologie i zastosowania, eds, Kozielski S., Małysiak В., Kasprowski P., Mrozek D., WKiŁ Warszawa, 385-392.
Wieczorek, Т.,2006, Intelligent control of the electric-arc steelmaking process using artificial neural networks, Computer Methods in Material Science, 6, 1, 9-14.
Wieczorek,Т.,Blachnik, M., Mączka, К., 2008, Building a model for time reduction of steel scrap meltdown in the electric arc furnace (EAF). General strategy with a comparison of feature selection methods, Lecture Notes in Artificial Intelligence, 5097, 1149-1159.
Wieczorek, Т., Pilarczyk, M., 2008, Classification of steel scrap in the EAF process using image analysis methods, Archives of Metallurgy and Materials, 53, 2, 613-618.
Wieczorek, Т.,Świtała, P., 2008, Wykorzystanie algorytmu CART do automatycznego tworzenia bazy wiedzy systemu ekspertowego, Bazy danych, rozwój metod i technologii. Architektura, metody formalne i zaawansowana analiza danych, eds, Kozielski S., Małysiak В., Kasprowski P., Mrozek D., WKiŁ Warszawa, 439-450.
Wong, В. К.,Lai, V. S., Lam, J., 2000, A bibliography of neural network business applications research, Computers & Operations Research, 27, 1045-1076.
Yanguang S.,Daixian W., Yan Т., Shi Т., Fang Y., Wang S., 2000, An Intelligent Ladle Furnace Control System, Proceedings of the 3th World Congress on Intelligent Control and Automation, Hefei P.R. China, 1, 330-334.