Prediction of silicon content in the hot metal using Bayesian networks and probabilistic reasoning

(1) * Wandercleiton Cardoso Mail (University of Genoa, Liguria, Italy)
(2) Renzo di Felice Mail (University of Genoa, Liguria, Italy)
*corresponding author


The blast furnace is the principal method of producing cast iron. In the production of cast iron, the control of silicon is vital because this impurity is harmful to almost all steels. Artificial neural networks with Bayesian regularization are more robust than traditional back-propagation networks and can reduce or eliminate the need for tedious cross-validation. Bayesian regularization is a mathematical process that converts a nonlinear regression into a "well-posed" statistical problem in the manner of ridge regression. The main objective of this work was to develop an artificial neural network to predict silicon content in hot metal by varying the number of neurons in the hidden layer by 10, 20, 25, 30, 40, 50, 75, and 100 neurons. The results show that all neural networks converged and presented reliable results, neural networks with 20, 25, and 30 neurons showed the best overall results. However, In short, Bayesian neural networks can be used in practice because the actual values correlate excellently with the values calculated by the neural network.



Article metrics

Abstract views : 659 | PDF views : 153




Full Text



[1] A. F. Ibragimov, I. I. Iskhakov, G. B. Skopov and A. N. Kirichenko, "Using Oxygen-Enriched Blast During the Operation of Shaft Furnaces of the Mednogorsk Copper–Sulfur Combine LLC," Metallurgist, vol. 63, n. 1-2, 2019. doi: 10.1007/s11015-019-00794-y.

[2] A. Ge, A neural network approach to the modeling of blast furnace, vol. 1, Massachusetts, 1999, p. 71. Available at: Google Scholar.

[3] A. Kandiri, E. M. Golafshani and A. Behnood, "Estimation of the compressive strength of concretes containing ground granulated blast furnace slag using hybridized multi-objective ANN and salp swarm algorithm," Construction and Building Materials, vol. 248, p. 118676, 2020. doi: 10.1016/j.conbuildmat.2020.118676.

[4] A. M. Mhaya, G. F. Huseien, I. Faridmehr, A. R. Z. Abidin, R. Alyousef and M. Ismail, "Evaluating mechanical properties and impact resistance of modified concrete containing ground Blast Furnace slag and discarded rubber tire crumbs," Construction and Building Materials, vol. 295, p. 123603, 2021. doi: 10.1016/j.conbuildmat.2021.123603.

[5] A. V. Pavlov, A. A. Polinov, N. A. Spirin, O. P. Onorin, V. V. Lavrov and I. A. Gurin, "Decision-Making Support in Blast-Furnace Operation," Steel in Translation, vol. 49, n. 3, 2019. doi: 10.3103/S0967091219030082.

[6] D. A. Muchnik, A. I. Trikilo, V. P. Lyalyuk and D. A. Kassim, "Coke Quality and Blast-Furnace Performance," Coke and Chemistry, vol. 61, n. 1, 2018. doi: 10.3103/S1068364X18010040.

[7] D. O. L. Fontes, L. G. S. Vasconcelos and R. P. Brito, "Blast furnace hot metal temperature and silicon content prediction using soft sensor based on fuzzy C-means and exogenous nonlinear autoregressive models," Computers & Chemical Engineering, vol. 141, p. 107028, 2020. doi: 10.1016/j.compchemeng.2020.107028.

[8] F. Pettersson, N. Chakraborti and H. Saxén, "A genetic algorithms based multi-objective neural net applied to noisy blast furnace data," Applied Soft Computing, vol. 7, n. 1, pp. 387-397, 2007. doi: 10.1016/j.asoc.2005.09.001.

[9] A. Itman, R. Vilarim, W. Cardoso and L. C. Casteletti, "Effect of niobium in the phase transformation and corrosion resistance of one austenitic-ferritic stainless," Materials Research, vol. 17, n. 4, pp. 801-806, 2014. doi: 10.1590/1516-1439.190113.

[10] A. Itman, W. Cardoso, R. Vilarim, L. C. Gontijo and L. C. Casteletti, "Austenitic-ferritic stainless steel containing niobium," REM - International Engineering Journal, vol. 66, n. 4, pp. 467-471, 2013. doi: 10.1590/S0370-44672013000400010.

[11] G. Ferrara, M. Pepe, E. Martinelli and R. D. Toledo, "Predicting shrinkage of alkali-activated blast furnace-fly ash mortars using artificial neural network (ANN)," Cement and Concrete Composites, vol. 124, p. 104265, 2021. doi: 10.1016/j.cemconcomp.2021.104265.

[12] I. F. Kurunov, "Ways of Improving Blast Furnace Smelting Efficiency with Injection of Coal-Dust Fuel and Natural Gas," Metallurgist, vol. 61, n. 9-10, 2018. doi: 10.1007/s11015-018-0557-6.

[13] I. G. Muraveva, D. N. Togobitskaya, N. G. Ivancha, A. I. Bel'kova and A. S. Nesterov, "Concept Development of an Expert System for Selecting the Optimal Composition of a Multicomponent Blast-Furnace Charge and Functional and Algorithmic Structure," Steel in Translation, vol. 51, n. 1, 2021. doi: 10.3103/S0967091221010095.

[14] I. Matino, S. Dettori, V. Colla, V. Weber and S. Salame, "Two innovative modelling approaches in order to forecast consumption of blast furnace gas by hot blast stoves," Energy Procedia, vol. 158, pp. 4043-4048, 2019. doi: 10.1016/j.egypro.2019.01.834.

[15] J. Li, C. Hua, J. Qian and X. Guan, "Low-rank based Multi-Input Multi-Output Takagi-Sugeno fuzzy modeling for prediction of molten iron quality in blast furnace," Fuzzy Sets and Systems, vol. 421, pp. 178-192, 2021. doi: 10.1016/j.fss.2020.08.012.

[16] J. Xie and P. Zhou, "Robust stochastic configuration network multi-output modeling of molten iron quality in blast furnace ironmaking," Neurocomputing, vol. 387, pp. 139-149, 2020. doi: 10.1016/j.neucom.2020.01.030.

[17] J. Zhang, S. Li and Z. Li, "Investigation the synergistic effects in quaternary binder containing red mud, blast furnace slag, steel slag and flue gas desulfurization gypsum based on artificial neural networks," Journal of Cleaner Production, vol. 273, p. 122972, 2020. doi: 10.1016/j.jclepro.2020.122972.

[18] M. S. Arif and I. Ahmad, "Artificial Intelligence Based Prediction of Exergetic Efficiency of a Blast Furnace," Computer Aided Chemical Engineering, vol. 50, pp. 1047-1052, 2021. doi: 10.1016/B978-0-323-88506-5.50161-3.

[19] P. Assis, L. Carvalho and A. Irgaliyev, "Artificial Neural Network based in committee machine for predicting fuel rate and sulfur Contents of a coke blast furnace," International Journal of Science and Research, vol. 8, n. 12, pp. 1492-1495, 2019. doi: 10.21275/ART20203638.

[20] S. Blotevogel, "Glass structure of industrial ground granulated blast furnace slags (GGBS) investigated by time-resolved Raman and NMR spectroscopies," Journal of Materials Science, vol. 56, n. 31, November 2021. doi: 10.1007/s10853-021-06446-4.

[21] S. Stein, C. Leng, S. Thornton and R. Michel, "A guided analytics tool for feature selection in steel manufacturing with an application to blast furnace top gas efficiency," Computational Materials Science, vol. 186, p. 110053, 2021. doi: 10.1016/j.commatsci.2020.110053.

[22] L. A. Dobrzanski, J. Trzaska, M. Gawron and M. Berliński, "The use of artificial neural networks for the prediction of sulphur content in hot metal produced in blast furnace," Journal of Achievements in Materials and Manufacturing Engineering, vol. 70, n. 2, pp. 86-92, 2015. Available at: http://

[23] V. M. Chizhikova, "Best Available Techniques in the Blast-Furnace Production," Metallurgist, vol. 64, n. 1-2, 2020. doi: 10.1007/s11015-020-00962-5.

[24]W. G. Kong, J. H. Liu, Y.W . Yu, X. M. Hou and Z. J. He, "Effect of w(MgO)/w(Al2O3) ratio and basicity on microstructure and metallurgical properties of blast furnace slag," Journal of Iron and Steel Research International, vol. 28, n. 10, 2021. doi: 10.1007/s42243-021-00622-1.

[25] X. Zhai, M. Chen and W. Lu, "Fuel Ratio Optimization of Blast Furnace Based on Data Mining," ISIJ International, vol. 60, n. 11, 2020. doi: 10.2355/isijinternational.ISIJINT-2020-238.

[26] X. Zhang, M. Kano and S. Matsuzaki, "A comparative study of deep and shallow predictive techniques for hot metal temperature prediction in blast furnace ironmaking," Computers & Chemical Engineering, vol. 130, p. 106575, 2019. doi: 10.1016/j.compchemeng.2019.106575.

[27] Y. S. Semenov, V. V. Gorupakha, A. M. Kuznetsov, I. Y. Semion, E. I. Schumel'chik, S. V. Vashchenko and A. Y. Khudyakov, "Experience of Using Manganese-Containing Materials in Blast-Furnace Charge," Metallurgist, vol. 63, n. 9-10, 2020. doi: 10.1007/s11015-020-00920-1.

[28] A. G. Oliveira, L. B. Totola, K. V. Bicalho and W. H. Hisatugu, "Prediction of Compression Index of Soft Soils from theBrazilian Coast Using Artificial Neural Networks andEmpirical Correlations," Soils and Rocks, vol. 43, pp. 109-121, 2020. doi: 10.28927/SR.431109.

[29] C. Kina, K. Turk, E. Atalay, I. Donmez and H. Tanyildizi, "Comparison of extreme learning machine and deep learning model in the estimation of the fresh properties of hybrid fiber-reinforced SCC," Neural Computing and Applications, vol. 33, n. 18, 2021. doi: 10.1007/s00521-021-05836-8.

[30] C. Völker, R. Firdous, D. Stephan and S. Kruschwitz, "Sequential learning to accelerate discovery of alkali-activated binders," Journal of Materials Science, vol. 56, n. 28, 2021. doi: 10.1007/s10853-021-06324-z.

[31] F. He and L. Zhang, "Prediction model of end-point phosphorus content in BOF steelmaking process based on PCA and BP neural network," Journal of Process Control, vol. 66, pp. 51-58, 2018. doi: 10.1016/j.jprocont.2018.03.005.

[32] K. B. D. Carro, G. R. Leite, A. G. Oliveira, C. B. Santos, I. S. Pinto, B. Fux and A. Falqueto, "Assessing geographic and climatic variables to predict the potential distribution of the visceral leishmaniasis vector Lutzomyia longipalpis in the state of Espı́rito Santo, Brazil," PLOS ONE, vol. 15, p. e0238198, 2020. doi: 10.1371/journal.pone.0238198.

[33] K. T. Ates, C. Sahin, Y. Kuvvetli, B. A. Kuren and A. Uysal, "Sustainable production in cement via artificial intelligence based decision support system: Case study," Case Studies in Construction Materials, vol. 15, p. e00628, 2021. doi: 10.1016/j.cscm.2021.e00628.

[34] L. North, K. Blackmore, K. Nesbitt and M. R. Mahoney, "Methods of coke quality prediction: A review," Fuel, vol. 219, pp. 426-445, 2018. doi: 10.1016/j.fuel.2018.01.090.

[35] L. Zhang, Y. Xue, Q. Xie and Z. Ren, "Analysis and neural network prediction of combustion stability for industrial gases," Fuel, vol. 287, p. 119507, 2021. doi: 10.1016/j.fuel.2020.119507.

[36] M. A. Rhamdhani and Q. G. Reynolds, "Computational Modelling in Pyrometallurgy: Part II," JOM, vol. 73, n. 10, 2021. doi: 10.1007/s11837-021-04839-z.

[37] M. Chen, X. Wan, J. Shi, P. Taskinen and A. Jokilaakso, "Experimental Study on the Phase Relations of the SiO2-MgO-TiO2 System in Air at 1500°C," JOM, 2021. doi: 10.1007/s11837-021-04870-0.

[38] N. Dučić, A. Jovičić, S. Manasijević, R. Radiša, Ž. Ćojbašić and B. Savković, "Application of Machine Learning in the Control of Metal Melting Production Process," Applied Sciences, vol. 10, n. 17, 2020. doi: 10.3390/app10176048.

[39] Q. G. Reynolds and M. A. Rhamdhani, "Computational Modeling in Pyrometallurgy: Part I," JOM, vol. 73, n. 9, 2021. doi: 10.1007/s11837-021-04794-9.

[40] S. R. Jantre, S. Bhattacharya and T. Maiti, "Quantile Regression Neural Networks: A Bayesian Approach," Journal of Statistical Theory and Practice, vol. 15, n. 3, 2021. doi: 10.1007/s42519-021-00189-w.

[41] T. C. Alex, G. Mucsi, T. Venugopalan and S. Kumar, "BOF Steel Slag: Critical Assessment and Integrated Approach for Utilization," Journal of Sustainable Metallurgy, September 2021. doi: 10.1007/s40831-021-00435-2.

[42] T. N. Pandey, A. K. Jagadev, S. Dehuri and S. B. Cho, "A novel committee machine and reviews of neural network and statistical models for currency exchange rate prediction: An experimental analysis," Journal of King Saud University - Computer and Information Sciences, vol. 32, n. 9, pp. 987-999, 2020. doi: 10.1016/j.jksuci.2018.02.010.

[43] V. P. Lyalyuk, V. P. Sokolova, D. A. Kassim and I. A. Lyakhova, "Influence of the Stability of Coke Quality on Its Consumption in the Blast Furnace," Coke and Chemistry, vol. 61, n. 9, 2018. doi: 10.3103/S1068364X18090077.

[44] W. Liang, G. Wang, X. Ning, J. Zhang, Y. Li, C. Jiang and N. Zhang, "Application of BP neural network to the prediction of coal ash melting characteristic temperature," Fuel, vol. 260, p. 116324, 2020. doi: 10.1016/j.fuel.2019.116324.

[45] Y. B. Kang, "Progress of Thermodynamic Modeling for Sulfide Dissolution in Molten Oxide Slags: Sulfide Capacity and Phase Diagram," Metallurgical and Materials Transactions B, vol. 52, n. 5, 2021. doi: 10.1007/s11663-021-02224-4.

[46] Y. Hou, Y. Wu, Z. Liu, H. Han and P. Wang, "Dynamic multi-objective differential evolution algorithm based on the information of evolution progress," Science China Technological Sciences, vol. 64, n. 8, 2021. doi: 10.1007/s11431-020-1789-9.

[47] Y. Kellouche, B. Boukhatem, M. Ghrici, R. Rebouh and A. Zidol, "Neural network model for predicting the carbonation depth of slag concrete," Asian Journal of Civil Engineering, vol. 22, n. 7, 2021. doi: 10.1007/s42107-021-00390-z.

[48] Y. Liu, Y. Wang, L. Chen, J. Zhao, W. Wang and Q. Liu, "Incremental Bayesian broad learning system and its industrial application," Artificial Intelligence Review, vol. 54, n. 5, 2021. doi: 10.1007/s10462-020-09929-z.

[49] Z. H. Zhan, L. Shi, K. C. Tan and J. Zhang, "A survey on evolutionary computation for complex continuous optimization," Artificial Intelligence Review, 2021. doi: 10.1007/s10462-021-10042-y.

[50] Z. J. Xu, Z. Zheng and X. Q. Gao, "Operation optimization of the steel manufacturing process: A brief review," International Journal of Minerals, Metallurgy and Materials, vol. 28, n. 8, 2021. doi: 10.1007/s12613-021-2273-7.

[51] Z. Yi, Q. Liu and H. Shao, "Effect of MgO on Highly Basic Sinters with High Al2O3," Mining, Metallurgy & Exploration, vol. 38, n. 5, 2021. Doi: 10.1007/s42461-021-00445-4.

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

International Journal of Advances in Intelligent Informatics
ISSN 2442-6571  (print) | 2548-3161 (online)
Organized by UAD and ASCEE Computer Society
Published by Universitas Ahmad Dahlan
E: (paper handling issues) (publication issues)

View IJAIN Stats

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0