Abstract
The high and fluctuation property of sulfur content in hot metal (HM) is a prominent problem in COREX process. The precise prediction of sulfur content in HM of COREX can provide a theoretical basis and technical reference for stabilizing and reducing the sulfur content in HM. In this work, a three-layer back propagation (BP) neural network was developed to predict the sulfur content in HM of COREX. The main affecting factors regarded as input parameters of the model are determined by the statistical analysis, and the hysteretic heats corresponding to each input parameters are analyzed by calculating the Deng’s correlation degree. The final structure of the BP neural network model is 20-37-1. The results show that when the error of BP neural network model for predicting sulfur content in HM of COREX is ±0.1%, the hit rate is 86.7%. In order to further improve the prediction accuracy of the model, the time series process method is adopted to update the training samples in real time and optimize the model. When the prediction error of the improved model is ±0.1%, the hit rate increases to 96.7%. The improved BP model can provide technical guidance for judging the change of sulfur content in HM and subsequent operations.
Funding source: National Natural Science Foundation of China
Award Identifier / Grant number: 5180402751904023
Funding source: Fundamental Research Funds for the Central Universities
Award Identifier / Grant number: FRF-TP-19-035A2
Funding source: State Key Laboratory of Advanced Metallurgy
Award Identifier / Grant number: KF20-07
Acknowledgments
The authors would like to thank the National Natural Science Foundation of China (Grant Number: 51904023, 51804027), The Fundamental Research Funds for the Central Universities (Grant Number: FRF-TP-19-035A2) and the project of State Key Laboratory of Advanced Metallurgy (KF20-07) for their financial supports.
Author contribution: All the authors have accepted responsibility for the entire content of this submitted manuscript and approved submission.
Research funding: None declared.
Conflict of interest statement: The authors declare no conflicts of interest regarding this article.
References
Cavalcanti, F. M., M. Schmal, R. Giudici, and R. M. Brito. 2019. “A Catalyst Selection Method for Hydrogen Production through Water-Gas Shift Reaction Using Artificial Neural Networks.” Journal of Environmental Management 237: 585–94. https://doi.org/10.1016/j.jenvman.2019.02.092.Search in Google Scholar
Chen, R. J., H. W. Ni, X. W. Li, W. Y. Zhu, J. C. Xiong, H. Y. He, and H. Zhang. 2012. “Predicting Viscosity of Blast Furnace Slag Based on BP Neural Network Model: an Experimental Study.” Journal of Wuhan University of Science and Technology 35: 411–14.Search in Google Scholar
Cui, G. M., C. L. Gao, J. Hou, Z. H. Chen, and X. Ma. 2015. “Optimization of Pulverized Coal Injection in Blast Furnace Based on BP Neural Network Optimized by Genetic Algorithm.” Computer Measurement Control 23: 1568–74.Search in Google Scholar
Cybenko, G. 1989. “Approximation by Superpositions of a Sigmoidal Function.” Mathematics of Control Signals and Systems: 303–14, https://doi.org/10.1007/bf02551274.Search in Google Scholar
Fan, Z. G., G. B. Qiu, J. Y. Jia, and C. G. Bai. 2002. “Method to Predict the Coke Ratio Based on BP Neural Network.” Journal of Chongqing University (Natural Science Edition) 25: 85–8.Search in Google Scholar
Guo, Y. L., W. R. Xu, J. M. Zhu, and J. Y. Zhang. 2013. “Influence of Operational Parameters on Hot Metal Temperature in Corex Process.” Ironmaking and Steelmaking 40: 545–50. https://doi.org/10.1179/1743281212y.0000000078.Search in Google Scholar
Hecht-Nielsen, R. 1990. Neurocomputing. Menlo Park, CA: Addison-Wesley.Search in Google Scholar
Hinnela, J., H. Saxen, and F. Pettersson. 2003. “Modeling of the Blast Furnace Burden Distribution by Evolving Neural Networks.” Industrial & Engineering Chemistry Research 42: 2314–23. https://doi.org/10.1021/ie0203779.Search in Google Scholar
Hornik, K., M. Stinchcombe, and H. White. 1989. “Multilayer Feed Forward Networks Are Universal Approximators.” Neural Networks 2: 359–66. https://doi.org/10.1016/0893-6080(89)90020-8.Search in Google Scholar
Jiang, L. H., A. G. Wang, N. Y. Tian, W. C. Zhang, and Q. L. Fan. 2011. “BP Neural Network of Continuous Casting Technological Parameters and Secondary Dendrite Arm Spacing of Spring Steel.” Journal of Iron and Steel Research International 18: 25–9. https://doi.org/10.1016/s1006-706x(11)60099-x.Search in Google Scholar
Jing, G. L., W. T. Du, and Y. Y. Guo. 2012. “Studies on Prediction of Separation Percent in Electrodialysis Process via BP Neural Networks and Improved BP Algorithms.” Desalination 291: 78–93. https://doi.org/10.1016/j.desal.2012.02.002.Search in Google Scholar
Kumar, P. P., A. V. R. P. Dasu, M. Ranjan, and T. K. Naha. 2008. “Influence of Operational Parameters on Silicon in Hot Metal from Corex.” Ironmaking and Steelmaking 35: 108–14. https://doi.org/10.1179/030192307x239588.Search in Google Scholar
Li, W. G. 2008. Operation Status Quo and Technical Problems of COREX-3000. 11–8. Baosteel Technol.Search in Google Scholar
McCormick, K., J. Saleedo, J. Peck, and A. Wheeler. 2017. SPSS Statistics for Data Analysis and Visualization, Indianopolis, United States of America. John Wiley & Sons Inc.10.1002/9781119183426Search in Google Scholar
McCoy, J. T., and L. Auret. 2019. “Machine Learning Applications in Minerals Processing: A Review.” Minerals Engineering 132: 95–109. https://doi.org/10.1016/j.mineng.2018.12.004.Search in Google Scholar
Ren, Y. J., J. W. Wang, X. B. Zhang, and H. W. Zhao. 2012. “Prediction Model of Hot Metal Temperature for BF-BOF Interface Based on LM BP Neural Network.” Iron and Steel 47: 40–2.Search in Google Scholar
Tosun, N. 2006. “Determination of Optimum Parameters for Multi-Performance Characteristics in Drilling by Using Grey Relational Analysis.” The International Journal of Advanced Manufacturing Technology 28: 450–55. https://doi.org/10.1007/s00170-004-2386-y.Search in Google Scholar
Wang, S. M., and G. P. Xia. 2001. “Method of Flying Dynamic Real-Time Forecast Based on BP Neural Network.” JournaI of Beijing University of Aeronautics and Astronautics 27: 636–9.Search in Google Scholar
Wang, A. L., Z. S. Fu, and F. M. Liu. 2018. “Asphalt Foaming Quality Control Model Using Neural Network and Parameters Optimization.” International Journal of Pavement Research and Technology 11: 401–7. https://doi.org/10.1016/j.ijprt.2017.12.005.Search in Google Scholar
Wang, W. H. 2008. “Application of BP Network and Principal Component Analysis to Forecasting the Silicon Content in Blast Furnace Hot Metal.” In Second International Symposium on Intelligent Information Technology Application, 42–6. Shanghai: IEEE.10.1109/IITA.2008.515Search in Google Scholar
Wen, B., J. S. L. Wu, H. Zhou, and K. Gu. 2018. “A BP Network Based Mathematical Model for Predicting Si Content in Hot Metal from COREX Process.” Journal of Iron and Steel Research 30: 776–81.Search in Google Scholar
Wu, S. L., L. X. Wang, M. Y. Kou, B. B. Du, Y. N. Lu, and K. Gu. 2017. “Analysis of Operational Parameters Affecting the Sulfur Content in Hot Metal of the COREX Process.” Metallurgical and Materials Transactions B 48: 276–85. https://doi.org/10.1007/s11663-016-0810-y.Search in Google Scholar
You, Y., Y. Y. Li, Z. G. Luo, H. F. Li, Z. S. Zou, and R. Y. Yang. 2019. “Investigating the Effect of Particle Shape on the Charging Process in Melter Gasifiers in COREX.” Powder Technology 351: 305–13. https://doi.org/10.1016/j.powtec.2019.04.040.Search in Google Scholar
Yuan, J. Q., and B. Zhu. 2015. “Pressure Transfer Modeling for an Urban Water Supply System Based on Pearson Correlation Analysis.” Journal of Hydroinformatics 17: 90–8.10.2166/hydro.2014.037Search in Google Scholar
Zhang, J. H., G. A. Xie, and F. M. Shen. 2006. “Optimization and Analysis of Sulfur Content in Hot Metal Based on Neural Network.” Journal of Materials and Metallurgy 5: 86–9.Search in Google Scholar
Zhang, J. H., Y. L. Jin, F. M. Shen, and X. L. Su. 2007. “Prediction Model of Silicon Content in Hot Metal Using Optimized BP Network.” Journal of Iron and Steel Research 19: 60–3.Search in Google Scholar
Zhou, H., Q. F. Hou, M. Y. Kou, S. Yao, and S. L. Wu. 2019. “Discrete Element Method Study of Solid Descending and Residence Properties in COREX Shaft Furnace with Center Gas Supply Device.” Journal of Iron and Steel Research International 26: 669–78. https://doi.org/10.1007/s42243-019-00295-x.Search in Google Scholar
Zhou, H., S. Y. Wang, B. B. Du, M. Y. Kou, Z. Y. Tang, J. H. Yang, S. L. Wu, and D. Y. E. 2020. “Influence of Center Gas Supply Device on Gas–Solid Flow in COREX Shaft Furnace through DEM–CFD Model.” International Journal of Chemical Reactor Engineering 18. 20200012, https://doi.org/10.1515/ijcre-2020-0012.Search in Google Scholar
Zhu, M. Y. 2009. Modern Metallurgy. Beijing: Metallurgy Industry.Search in Google Scholar
© 2020 Walter de Gruyter GmbH, Berlin/Boston
