Prediction of Productivity and Energy Consumption in a Consteel Furnace Using Data-Science Models

  • Panagiotis SismanisEmail author
Conference paper
Part of the Lecture Notes in Business Information Processing book series (LNBIP, volume 353)


The potential to predict the productivity and the specific electric-energy furnace consumption is very important for the economic operation and performance of a Consteel electric-arc furnace. In this work, these two variables were predicted based on specific operating parameters with the use of machine learning. Actually, three different algorithms were tested for this study: the BRF method of support vector machine (SVM), the light gradient boosting method (lightGBM), and the Keras system with TensorFlow as backend. The results appear to be good enough for production scheduling, and are presented and discussed in this work.


Gradient boosting method Support vector machine Keras TensorFlow Productivity Energy Consteel 



The author is grateful to the top management for the continuous support on this type of studies.


  1. 1.
    Koehle, S.: Improvements in EAF operating practices over the last decade. In: Electric Furnace Conference Proceedings, Iron & Steel Society, Pittsburgh, PA, vol. 57, pp. 3–14 (1999)Google Scholar
  2. 2.
    Memoli, F., Guzzon, M., Giavani, C.: The evolution of preheating and the importance of hot heel in supersized Consteel® systems. In: AISTech 2011 Proceedings, Indianapolis, IN, vol. I, pp. 823–832 (2011)Google Scholar
  3. 3.
    Bouganosopoulos, B., Papantoniou, V., Sismanis, P.: Start-up experience and results of Consteel® at the SOVEL meltshop. Iron Steel Technol. (2), 38–46 (2009)Google Scholar
  4. 4.
    Pretorius, E.B., Carlisle, R.C.: Foamy slag fundamentals and their practical application to electric furnace steelmaking. In: Electric Furnace Conference Proceedings, Iron & Steel Society, New Orleans, LA, vol. 56, pp. 275–292 (1998)Google Scholar
  5. 5.
    Maes, R.: Celox® for on-line process control in modern steelmaking, (brochure), Heraeus Electro-Nite (2012)Google Scholar
  6. 6.
    Continuum/Anaconda Homepage. Accessed Sept 2017
  7. 7.
    McKinney, W.: pandas: a foundational Python library for data analysis and statistics. Accessed 20 Aug 2018
  8. 8.
    Pedregosa, F., et al.: Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825–2830 (2011)MathSciNetzbMATHGoogle Scholar
  9. 9.
    Ke, G., et al.: LightGBM: a highly efficient gradient boosting decision tree. In: 31st Conference on Neural Information Processing Systems (NIPS 2017), Advances in Neural Information Processing Systems 30, Microsoft Research (2017)Google Scholar
  10. 10.
    Chollet, F.: Deep Learning with Python. Manning Publications, Shelter Island (2018)Google Scholar
  11. 11.
    Brownlee, J.: Develop Deep Learning Models on Theano and TensorFlow Using Keras. Deep Learning with Python. Jason Brownlee, Melbourne (2018)Google Scholar
  12. 12.
    TensorFlow. Accessed Aug 2018
  13. 13.
    Sismanis, P.: Analysis of rolled-plates’ mechanical properties with a machine-learning software. In: AISTech 2018 Proceedings, Philadelphia, PA, AIST, pp. 2273–2286 (2018)Google Scholar
  14. 14.
    Zumel, N., Mount, J.: Practical Data Science with R. Manning Publications, Shelter Island (2014)Google Scholar
  15. 15.
    Avila, J., Hauck, T.: scikit-learn Cookbook, 2nd edn. Packt Publishing, Birmingham (2017)Google Scholar
  16. 16.
    Garreta, R., Moncecchi, G., Hauck, T., Hackeling, G.: scikit-learn: Machine Learning Simplified. Packt Publishing, Birmingham (2017)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Sidenor Steel Industry SAAthensGreece

Personalised recommendations