Advertisement

Pattern Recognition for Blast Furnace Temperature Classification

  • Henrik Saxén
  • Leif Lassus
Part of the Studies in Fuzziness and Soft Computing book series (STUDFUZZ, volume 71)

Abstract

The blast furnace (Fig. 1) is the main process in the world used in producing iron for primary steel production (Biswas 1981; Omori 1987). The furnace is a large refractory-lined counter-current heat exchanger and chemical reactor, where enriched and agglomerated ores, sinter or pellets, are reduced and smelted by hot gases formed by combustion of coke and hydrocarbons. Because of the extreme conditions in the furnace it is very difficult and costly to directly measure internal variables of the process. The internal state must, therefore, be estimated from information at the furnace boundaries, such as measurements of the top gas and hot metal quantities, temperature and chemical composition, blast parameters and wall temperatures.

Keywords

Blast Furnace Wall Temperature Cohesive Zone Blast Furnace Operation Winning Node 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Biswas, A. (1981): Principles of blast furnace ironmaking, Cootha Publishing House, Brisbane, Australia.Google Scholar
  2. Hirata, T., Yamamura, K., Morimoto, S.,Takada, H. (1990): Blast furnace operation system using neural networks and knowledge-base. In: Sixth international iron and steel congress. ISIJ, Nagoya, Japan, pp. 23–27Google Scholar
  3. Karjalahti, T. (1999): Rautaruukki Oy, personal communicationGoogle Scholar
  4. Kohonen, T. (1989): Self-organization and associative memory, 3rd edition. Springer-Verlag, Berlin Heidelberg New YorkCrossRefGoogle Scholar
  5. Lassus, L., Saxén, H. (1998): Tool for classification of blast furnace wall temperature. In: Heidelpriem, H. (ed.): IFAC Symposium Automation in Mining, Mineral and Metal Processing, Cologne, Germany. Pergamon Press, Oxford, pp. 277–281Google Scholar
  6. Matsuda, K., Nagai, N., Konishi, M., Kadoguchi, K., Yabata, T. (1989): Forecasting system for decreasing heat levels in blast furnace. Kobelco Technology Review, 5, 1–4.Google Scholar
  7. Matsuda, K., Nakayama, M., Otsuka Y., Konishi, M. (1994): In: Application of AI technology for blast furnace. First International Congress of Science and Technology of Iron-making. ISIJ, Sendai, Japan, pp. 302–307Google Scholar
  8. Nikus, M., Saxén, H. (1996): On-line model of gas distribution in the blast furnace. Steel Research 67, 121–126Google Scholar
  9. Omori, M. (Ed.) (1987): Blast furnace phenomena and modelling, Elsevier, LondonGoogle Scholar
  10. Otsuka, Y., Matsuda, K., Hanaoka, K. (1992): Application of neural network systems to pattern recognition of blast furnace operation data. Kobleco Technology Review, No. 15, 12–16Google Scholar
  11. Saxén, H. (1996): Interpretation of probe temperatures in the blast furnace using polynomial approximations. Steel Research, 67, 73–78Google Scholar
  12. Saxén, H., Lassus, L. (1999): Operation diagrams based on blast furnace wall temperatures. 58th Ironmaking Conference, ISS, Chicago, IL, pp. 75–79Google Scholar
  13. Saxén, H., Lassus, L., Seppänen, M., Karjalahti, T. (2000): Pattern recognition and classification of blast furnace wall temperatures. Ironmaking and Steelmaking, 27, 207–211CrossRefGoogle Scholar
  14. Zuo, G., Ma, J., Björkman, B. (1998): Some applications of neural networks for prediction of blast furnace irregularities. Steel Research, 69, 41–48Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2001

Authors and Affiliations

  • Henrik Saxén
    • 1
  • Leif Lassus
    • 2
  1. 1.Åbo Akademi UniversityBiskopsgatan 8Finland
  2. 2.Oy L M Ericsson AbJorvasFinland

Personalised recommendations