Prediction of Bath Temperature Using Neural Networks
Commenced in January 2007
Frequency: Monthly
Edition: International
Paper Count: 32769
Prediction of Bath Temperature Using Neural Networks

Authors: H. Meradi, S. Bouhouche, M. Lahreche

Abstract:

In this work, we consider an application of neural networks in LD converter. Application of this approach assumes a reliable prediction of steel temperature and reduces a reblow ratio in steel work. It has been applied a conventional model to charge calculation, the obtained results by this technique are not always good, this is due to the process complexity. Difficulties are mainly generated by the noisy measurement and the process non linearities. Artificial Neural Networks (ANNs) have become a powerful tool for these complex applications. It is used a backpropagation algorithm to learn the neural nets. (ANNs) is used to predict the steel bath temperature in oxygen converter process for the end condition. This model has 11 inputs process variables and one output. The model was tested in steel work, the obtained results by neural approach are better than the conventional model.

Keywords: LD converter, bath temperature, neural networks.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1061398

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1776

References:


[1] G. Poferl et al., Dynamisation of the LD process (first results), second EOSC 1997.
[2] H J Whittaker et al., The use of neural networks in BOS process modelling, ECSC workshop Brussels, 22 and 23 January 1998, pp. 135- 44.
[3] Xianwen Gao et al., Intelligent compound control of direct current electric arc furnace, IFAC 1997, pp. 135-40.
[4] Shujiang Li et al., Neural network techniques and its application in ladle furnace burden, IFAC, korea, 1997, pp. 165-68.
[5] J. Poferl, Dynamic refining LD converter, ISIJ, Vol 28, 1988, pp. 59-67.
[6] M. V. Spangler, (1994). Uses of Process Insights at a Refractory Gold Plant, Pavilion Users Conference, October 17, 1994, pp. 1-7.
[7] G. Dreyfus, les réseaux de neurones, Mécanique Industrielle et Matériaux, n┬░51 (septembre 1998).
[8] S. J. Qin and al.: Advances in instrumentation and control; Proc. Conf, Austin, TX, USA, October 1993, ISA, vol. 48, N┬░3, pp. 1711-1720.
[9] J. Tenner and al.: Intelligent processing and manufacturing of materials; Proc. Conf. IPMM -99; Honolulu, july 1999.
[10] J. Tenner; Prediction of mechanical properties in steel heat treatment process using neural networks; Ironmaking and steelmaking, 2001, Vol. 25, pp. 15-22.
[11] H. Gutte; the mathematical simulation of the LD process; technical report, TU-BAF, Germany, January 2000.
[12] J.-P. Corriou; Les réseaux de neurones pour la modélisation et la conduite des procédés, Lavoisier, 1997.
[13] K. Andersen et al; IEEE Trans. Ind. Appl., 26 (1990) n┬░5, pp. 824-30.
[14] Bhatt et al ; IEEE Contr. Syst. Mag., 10 (1990), pp. 24-29.
[15] P. Bhagat; Chem. Eng. Progr., 86 (1990), pp. 55-60.
[16] W. E. Staib et al; Iron steel Eng., 69 (1992), pp. 29-32.
[17] M. A. Reuter et al; Metall. Trans., 23 B (1992), pp. 643-650.
[18] A. Datta and al.; Adaptive neural net models for desulphurization of hot metal and steel; Steel research , 65 n┬░11, (1994), pp. 466-471.
[19] Data Engine; Overview and User Manuel; MIT, 2nd Edition, May 1999.