ANN Modeling of a Steelmaking Process

  • Dipak Laha
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8298)


In a steelmaking shop, the output ‘yield’ is considered as an important performance measure while producing a specific amount of steel. It represents the operational efficiency of the steelmaking shop. It is the objective of management to maintain a high percentage of the yield. The present study was performed considering the open-hearth process of a steelmaking shop. The best subset regression analysis is applied to determine the most influencing variables influencing the output of the steelmaking process. Then, the multi-layer feed forward neural network with Levenberg-Marquardt (L-M) backpropagation algorithm is presented to predict the output yield of steel. In the present investigation, 0.0001 of MSE is set as a goal of the network training. The overtraining is given cognizance during the model building. The overall average of absolute percentage error (APE) of the model is found to be 0.5145% and the predicted yield based on the neural network is found to be in good agreement with the testing data set.


Yield of steel open-hearth process backpropagation neural networks best subset analysis Levenberg-Marquardt algorithm 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Bezerra, E.M., Ancelotti, A.C., Pardini, L.C., Rocco, J.A.F.F., Iha, K., Ribeiro, C.H.C.: Artificial neural networks applied to epoxy composites reinforced with carbon and E-glass fibers: Analysis of the shear mechanical properties. Materials Science and Engineering A 464, 177–185 (2007)CrossRefGoogle Scholar
  2. 2.
    Couderier, L., Hopkins, L., Wilkomirsky, I.: Fundamentals of metallurgical processes. Paragon Press (1978)Google Scholar
  3. 3.
    Falkus, J., Pietrzkiewicz, P., Pietrzyk, W., Kusiak, J.: Artificial neural network predictive system for oxygen steelmaking converter. In: Neural Networks and Soft Computing, pp. 825–830. Springer (2003)Google Scholar
  4. 4.
    Gresovnik, I., Kodelja, T., Vertnik, R., Sarler, B.: Application of artificial neural networks to improve steel production process. In: Proceedings of the IASTED International Conference on Artificial Intelligence and Soft Computing, pp. 249–255 (2012)Google Scholar
  5. 5.
    Hagan, M.T., Menhaj, M.B.: Training feedforward networks with the Marquardt algorithm. IEEE Transactions on Neural Networks 5, 989–993 (1994)CrossRefGoogle Scholar
  6. 6.
    Jalali-Heravi, M., Asadollahi-Baboli, M., Shahbazikhah, P.: QSAR study of heparanase inhibitors activity using artificial neural networks and Levenberg-Marquardt algorithm. European Journal of Medicinal Chemistry 43, 548–556 (2008)CrossRefGoogle Scholar
  7. 7.
    Karnik, S.R., Gaitonde, V.N., Campos Rubio, J., Esteves Correia, A., Abrão, A.M., Paulo Davim, J.: Delamination analysis in high speed drilling of carbon fiber reinforced plastics (CFRP) using artificial neural network model. Materials and Design 29, 1768–1776 (2008)CrossRefGoogle Scholar
  8. 8.
    Mazumdar, D., Evans, J.W.: Modeling of steelmaking processes. CRC Press (2009)Google Scholar
  9. 9.
    Monteiro, L.V., Sant’Anna, A.M.O.: Application of Neural network for modeling steelmaking process. Congrso Latino-lberoameroamericano de investigacion Oprative, 1618–1627 (2012)Google Scholar
  10. 10.
    Mukherjee, I., Routroy, S.: Comparing the performance of neural networks developed by using Levenberg-Marquardt and Quasi-Newton with the gradient descent algorithm for modelling a multiple response grinding process. Expert Systems with Applications 39, 2397–2407 (2012)CrossRefGoogle Scholar
  11. 11.
    Pal, M., Pal, S.K., Samantaray, A.K.: Artificial neural network modeling of weld joint strength prediction of a pulsed metal inert gas welding process using arc signals. Journal of Materials Processing Technology 202, 464–474 (2008)CrossRefGoogle Scholar
  12. 12.
    Rencher, A.C., Pun, F.C.: Inflation of R2 in best subset regression. Technimetrics 22, 49–53 (1980)CrossRefzbMATHGoogle Scholar
  13. 13.
    Shukla, A.K., Deo, B.: Mathematical modeling of phosphorus prediction in BOF steelmaking process: A fundamental approach to produce low phosphorus steels and ensure direct tap practices. In: International Conference on Metal and Alloys, METALL 2007 (2007)Google Scholar
  14. 14.
    Tsai, M.J., Li, C.H., Chen, C.C.: Optimal laser-cutting parameters for QFN packages by utilizing artificial neural networks and genetic algorithm. Journal of Materials Processing Technology 208, 270–283 (2008)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2013

Authors and Affiliations

  • Dipak Laha
    • 1
  1. 1.Department of Mechanical EngineeringJadavpur UniversityKolkataIndia

Personalised recommendations