ANN Modeling of a Steelmaking Process
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.
KeywordsYield of steel open-hearth process backpropagation neural networks best subset analysis Levenberg-Marquardt algorithm
Unable to display preview. Download preview PDF.
- 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.Couderier, L., Hopkins, L., Wilkomirsky, I.: Fundamentals of metallurgical processes. Paragon Press (1978)Google Scholar
- 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.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
- 8.Mazumdar, D., Evans, J.W.: Modeling of steelmaking processes. CRC Press (2009)Google Scholar
- 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
- 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