Applying Data Mining Techniques to Assess Steel Plant Operation Conditions

  • Khan Muhammad Badruddin
  • Isao Yagi
  • Takao Terano
Chapter
Part of the Intelligent Systems Reference Library book series (ISRL, volume 25)

Abstract

The improvement in the operation of melting the scrap metal in electric arc furnace, to make various types of steel products, requires complex expertise. This work discusses data mining approach to this problem. We flattened the time series data of the whole operation into the form which is suitable for conventional data mining methods. This paper describes the methodology for transformation of the time series data and discusses the possible applicability of different classification methods in this domain.

Keywords

Data Mining Time Series Data Molten Steel Data Mining Technique Objective Variable 
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. 1.
    Toulouevski, Y.N., Zinurov, I.Y.: Preheating of Scrap by Burner and Off-Gases. In: Innovation in Electric Arc Furnaces, Scientific Basis for Selection, pp. 110–111. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  2. 2.
    Bell, S., et al.: Final Report on Energy Efficiency and Energy Savings in Recycling, p. 8 (2006); 2005-43(CF), 8Google Scholar
  3. 3.
    Ao, H., et al.: ‘ECOARC’ Technology. In: 58th Electric Arc Furnace Conference, Iron and Steel Society, Warrendale, Pa, USA, pp. 325–336 (2000)Google Scholar
  4. 4.
    Peaslee, K.D., et al.: Final Technical Report:Development of a Process to Continuously Melt, Refine, and Cast High Quality Steel, DE-FC36-03ID14279, p. 12 (2006)Google Scholar
  5. 5.
    Sandberg, E.: Section 2.2: Variable availability.Thesis: Energy and Scrap Optimisation of Electric Arc Furnaces by Statistical Analysis of Process Data (2005)Google Scholar
  6. 6.
    Toulouevski, Y.N., Zinurov, I.Y.: Principles of Automation of Heat Control. In: Innovations in Electric Arc Furnaces; Scientific Basis for Selection, pp. 227–228. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  7. 7.
    Parker, S.: Measuring up: Size is No Obstacle to Benchmarking for Competitive. Rochester Business Journal 8 (1996)Google Scholar
  8. 8.
    SGL Group; The Carbon Company, http://www.sglgroup.com/cms/international/home/index.html?__locale=en (Cited: June 15, 2011)
  9. 9.
    Schult, H.: Benchmark Analysis - A Tool To Define The Next Development Steps? SEAISI, Singapore (2011)Google Scholar
  10. 10.
    Lüngen, B., Harste, K.: Quo Vadis Stahlindustrie. Stahl und Eisen (January 2011)Google Scholar
  11. 11.
    Dorndorf, M., et al.: Simetal Eaf Quantum – The Future Approach For Efficient Scrap Melting. SEAISI, Singapore (2011)Google Scholar
  12. 12.
    Mizukami, H., et al.: Off-gas Treatment Technology of ECOARC. NKK Tehnical Report, No.176, 2002(3), pp. 1–5 (2002) (in Japanese)Google Scholar
  13. 13.
    Toulouevski, Y.N., Zinurov, I.Y.: Modern Steelmaking in Electric Arc Furnaces: History and Prospects for Development. In: Innovation in Electric Arc Furnaces, Scientific Basis for Selection, p. 2. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  14. 14.
    Toulouevski, Y.N., Zinurov, I.Y.: Furnace Operation with Hot Heel. In: Innovation in Electric Arc Furnaces, Scientific Basis for Selection, pp. 16–17. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  15. 15.
    Jiawei, H., Micheline, K.: Data Mining Concepts and Techniques, p. 7. Morgan Kaufmann, San FranciscoGoogle Scholar
  16. 16.
    Hall, M., et al.: The WEKA Data Mining Software: An Update. SIGKDD Explorations 11(1) (2009)Google Scholar
  17. 17.
    Jiawei, H., Micheline, K.: Classification by Decision Tree Induction. Data Mining Concepts and Techniques, 6.3Google Scholar
  18. 18.
    Cohen, W.W.: In Fast effective rule induction. In: Prieditis, A., Russell, S.J. (eds.) Proceedings of the Twelfth International Conference on Machine Learning In Fast effective rule induction, Tahoe City, California, July 9-12, pp. 115–123. Morgan Kaufmann, San Francisco (1995)Google Scholar
  19. 19.
    Gaines, B.R., Compton, P.: Induction of ripple-down rules applied. J. Intell. Inf. Syst. 5, 211–228 (1995)CrossRefGoogle Scholar
  20. 20.
    Martin, B.: Thesis: Instance based Learning; Nearest Neighbour with Generalization (1995)Google Scholar
  21. 21.
    Bishop, C.M.: Model Selection. Pattern Recognition and Machine Learning, 1.3Google Scholar
  22. 22.
    Jiawei, H., Micheline, K.: Data Mining Concepts and Techniques, vol. 2, pp. 334–335. Morgan Kaufmann, San FranciscoGoogle Scholar
  23. 23.
    Quinlan, R.: C4.5: Programs for Machine Learning. Morgan Kaufmann, San Mateo (1993)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Khan Muhammad Badruddin
    • 1
  • Isao Yagi
    • 1
  • Takao Terano
    • 1
  1. 1.Tokyo Institute of TechnologyMeguro-kuJapan

Personalised recommendations