Prediction of lime utilization ratio of dephosphorization in BOF steelmaking based on online sequential extreme learning machine with forgetting mechanism

Abstract

The machine learning models of multiple linear regression (MLR), support vector regression (SVR), and extreme learning machine (ELM) and the proposed ELM models of online sequential ELM (OS-ELM) and OS-ELM with forgetting mechanism (FOS-ELM) are applied in the prediction of the lime utilization ratio of dephosphorization in the basic oxygen furnace steelmaking process. The ELM model exhibites the best performance compared with the models of MLR and SVR. OS-ELM and FOS-ELM are applied for sequential learning and model updating. The optimal number of samples in validity term of the FOS-ELM model is determined to be 1500, with the smallest population mean absolute relative error (MARE) value of 0.058226 for the population. The variable importance analysis reveals lime weight, initial P content, and hot metal weight as the most important variables for the lime utilization ratio. The lime utilization ratio increases with the decrease in lime weight and the increases in the initial P content and hot metal weight. A prediction system based on FOS-ELM is applied in actual industrial production for one month. The hit ratios of the predicted lime utilization ratio in the error ranges of ±1%, ±3%, and ±5% are 61.16%, 90.63%, and 94.11%, respectively. The coefficient of determination, MARE, and root mean square error are 0.8670, 0.06823, and 1.4265, respectively. The system exhibits desirable performance for applications in actual industrial production.

Keywords

basic oxygen furnace steelmaking / machine learning / lime utilization ratio / dephosphorization / online sequential extreme learning machine / forgetting mechanism

References

[[1]] Huang XH. . Principles of Iron and Steel Metallurgy, 2013 4 Beijing Publishing house of Metallurgical Industry

[[2]] Kitamura SY, Shibata H, Shimauchi KI, Saito SY. The importance of dicalcium-silicate on hot metal dephosphorization reaction. Rev. Met. Paris, 2008, 105(5): 263,

[[3]] W.K. Yang, J. Yang, Y.Q. Shi, et al., Effect of temperature on dephosphorization of hot metal in double-slag converter steelmaking process by high-temperature laboratorial experiments, Steel Res. Int., 92(2021), No. 3, art. No. 2000438.

[[4]] H. Sun, J. Yang, X.W. Lu, et al., Dephosphorization in double slag converter steelmaking process at different temperatures by industrial experiments, Metals, 11(2021), No. 7, art. No. 1030.

[[5]] Yang J, Kuwabara M, Asano T, Chuma A, Du J. Effect of lime particle size on melting behavior of lime-containing flux. ISIJ Int., 2007, 47(10): 1401,

[[6]] R.H. Zhang, J. Yang, S.W. Wu, H. Sun, and W.K. Yang, Comparison of the prediction of BOF end-point phosphorus content among machine learning models and metallurgical mechanism model, Steel Res. Int., 94(2023), No. 5, art. No. 2200682.

[[7]] Xin ZC, Zhang JS, Jin Y, Zheng J, Liu Q. Predicting the alloying element yield in a ladle furnace using principal component analysis and deep neural network. Int. J. Miner. Metall. Mater., 2023, 30(2): 335,

[[8]] Feng K, Xu AJ, He DF, Yang LZ. Case-based reasoning method based on mechanistic model correction for predicting endpoint sulphur content of molten iron in KR desulphurization. Ironmaking Steelmaking, 2020, 47: 799,

[[9]] L. Qi, H. Liu, Q. Xiong, and Z.X. Chen, Just-in-time-learning based prediction model of BOF endpoint carbon content and temperature via vMF mixture model and weighted extreme learning machine, Comput. Chem. Eng., 154(2021), art. No. 107488.

[[10]] Z.L. Wang, Y.P. Bao, and C. Gu, Convolutional neural network-based method for predicting oxygen content at the end point of converter, Steel Res. Int., 94(2023), No. 1, art. No. 2200342.

[[11]] S.L. Jiang, X.Y. Shen, and Z. Zheng, Gaussian process-based hybrid model for predicting oxygen consumption in the converter steelmaking process, Processes, 7(2019), No. 6, art. No. 352.

[[12]] L.S. Carlsson, P.B. Samuelsson, and P.G. Jönsson, Interpretable machine learning—Tools to interpret the predictions of a machine learning model predicting the electrical energy consumption of an electric arc furnace, Steel Res. Int., 91(2020), No. 11, art. No. 2000053.

[[13]] Wei GS, Zhu R, Yang LZ, Tang TP. Hybrid modeling for endpoint carbon content prediction in EAF steelmaking. Materials Processing Fundamentals 2018, 2018 Switzerland Springer International Publishing 211,

[[14]] L.Z. Yang, B. Li, Y.F. Guo, S. Wang, B.T. Xue, and S.Y. Hu, Influence factor analysis and prediction model of end-point carbon content based on artificial neural network in electric arc furnace steelmaking process, Coatings, 12(2022), No. 10, art. No. 1508.

[[15]] Q.D. Yang, J. Zhang, and Z. Yi, Predicting molten steel endpoint temperature using a feature-weighted model optimized by mutual learning cuckoo search, Appl. Soft Comput., 83(2019), art. No. 105675.

[[16]] Bao YP, Li X, Wang M. A novel method for endpoint temperature prediction in RH. Ironmaking Steelmaking, 2019, 46(4): 343,

[[17]] Wang XJ, You MS, Mao ZZ, Yuan P. Tree-structure ensemble general regression neural networks applied to predict the molten steel temperature in ladle furnace. Adv. Eng. Inform., 2016, 30(3): 368,

[[18]] Liu YH, Lu HB, Zhang HQ, Wu X, Zhong YB, Lei ZS. Quality prediction of continuous casting slabs based on weighted extreme learning machine. IEEE Access, 2022, 10: 78231,

[[19]] Cemernek D, Cemernek S, Gursch H, et al.. Machine learning in continuous casting of steel: A state-of-the-art survey. J. Intell. Manuf., 2022, 33(6): 1561,

[[20]] Z. Chen, J.G. Wang, G.Q. Zhao, Y. Yao, and C. Xu, Endpoint temperature prediction of molten steel in VD furnace based on AdaBoost.RT-ELM, [in] 2020 IEEE 9th Data Driven Control and Learning Systems Conference (DDCLS), Liuzhou, 2020, p. 789.

[[21]] K. Feng, A.J. Xu, D.F. He, and H.B. Wang, An improved CBR model based on mechanistic model similarity for predicting end phosphorus content in dephosphorization converter, Steel Res. Int., 89(2018), No. 6, art. No. 1800063.

[[22]] S. Pal and C. Halder, Optimization of phosphorous in steel produced by basic oxygen steel making process using multi-objective evolutionary and genetic algorithms, Steel Res. Int., 88(2017), No. 3, art. No. 1600193.

[[23]] He F, Zhang LY. Prediction model of end-point phosphorus content in BOF steelmaking process based on PCA and BP neural network. J. Process. Contr., 2018, 66: 51,

[[24]] Wang HB, Cai J, Feng K. Predicting the endpoint phosphorus content of molten steel in BOF by two-stage hybrid method. J. Iron Steel Res. Int., 2014, 21: 65,

[[25]] Liu Z, Cheng SS, Liu PB. Prediction model of BOF end-point P and O contents based on PCA–GA–BP neural network. High Temp. Mater. Process., 2022, 41(1): 505,

[[26]] Zhou KX, Lin WH, Sun JK, et al.. Prediction model of endpoint phosphorus content for BOF based on monotone-constrained BP neural network. J. Iron Steel Res. Int., 2022, 29(5): 751,

[[27]] Acosta SM, Amoroso AL, Sant’Anna MO, Junior OC. Predictive modeling in a steelmaking process using optimized relevance vector regression and support vector regression. Ann. Oper. Res., 2022, 316(2): 905,

[[28]] Zhang R, Yang J. State of the art in applications of machine learning in steelmaking process modeling. Int. J. Miner. Metall. Mater., 2023, 30(11): 2055,

[[29]] Wu SW, Yang J, Zhang RH, Ono H. Prediction of end-point sulfur content in KR desulfurization based on the hybrid algorithm combining artificial neural network with SAPSO. IEEE Access, 2020, 8: 33778,

[[30]] Huang GB, Zhu QY, Siew CK. Extreme learning machine: Theory and applications. Neurocomputing, 2006, 70(1–3): 489,

[[31]] G.B. Huang, Q.Y. Zhu, and C.K. Siew, Extreme learning machine: A new learning scheme of feedforward neural networks, [in] 2004 IEEE International Joint Conference on Neural Networks, Budapest, 2005, p. 985.

[[32]] Liang NY, Huang GB, Saratchandran P, Sundararajan N. A fast and accurate online sequential learning algorithm for feedforward networks. IEEE Trans. Neural Netw., 2006, 17(6): 1411,

[[33]] Zhao JW, Wang ZH, Park DS. Online sequential extreme learning machine with forgetting mechanism. Neurocomputing, 2012, 87: 79,

[[34]] Pedregosa F, Varoquaux G, Gramfort A, et al.. Scikit-learn: Machine learning in python. J. Mach. Learn. Res., 2011, 12: 2825

[[35]] L. Ferrado, Pyoselm. A Python implementation of Online Sequential Extreme Machine Learning (OS-ELM) for Online Machine Learning, 2021 [2023-03-02]. https://github.com/leferrad/pyoselm

[[36]] L.J. Feng, C.H. Zhao, Y.L. Li, M. Zhou, H.L. Qiao, and C. Fu, Multichannel diffusion graph convolutional network for the prediction of endpoint composition in the converter steelmaking process, IEEE Trans. Instrum. Meas., 70(2021), art. No. 3000413.

[[37]] Iwasaki M, Matsuo M. Change and development of steelmaking technology. Nippon Steel Tech. Rep., 2011, 391: 88

[[38]] Sun H, Yang J, Yang WK, Zhang RH. Comprehensive evaluation of phosphorus enrichment capacity for decarburization slag at different temperatures based on industrial experiments, mineral phase analysis and ion-molecule coexistence theory. Metall. Mater. Trans. B, 2023, 54(1): 115,