Factor analysis and machine learning for predicting endpoint carbon content in converter steelmaking

Abstract

The endpoint carbon content in the converter is critical for the quality of steel products, and accurately predicting this parameter is an effective way to reduce alloy consumption and improve smelting efficiency. However, most scholars currently focus on modifying methods to enhance model accuracy, while overlooking the extent to which input parameters influence accuracy. To address this issue, in this study, a prediction model for the endpoint carbon content in the converter was developed using factor analysis (FA) and support vector machine (SVM) optimized by improved particle swarm optimization (IPSO). Analysis of the factors influencing the endpoint carbon content during the converter smelting process led to the identification of 21 input parameters. Subsequently, FA was used to reduce the dimensionality of the data and applied to the prediction model. The results demonstrate that the performance of the FA–IPSO–SVM model surpasses several existing methods, such as twin support vector regression and support vector machine. The model achieves hit rates of 89.59%, 96.21%, and 98.74% within error ranges of ±0.01%, ±0.015%, and ±0.02%, respectively. Finally, based on the prediction results obtained by sequentially removing input parameters, the parameters were classified into high influence (5%–7%), medium influence (2%–5%), and low influence (0–2%) categories according to their varying degrees of impact on prediction accuracy. This classification provides a reference for selecting input parameters in future prediction models for endpoint carbon content.

Keywords

converter / endpoint carbon content / parameter classification / factor analysis / improved particle swarm optimization / support vector machine

References

[1] Y.J. Xia, H.B. Wang, and A.J. Xu, dmPINNs: An integrated data-driven and mechanism-based method for endpoint carbon prediction in BOF, Metals, 14(2024), No. 8, art. No. 926.

[2] Gu MQ, Xu AJ, Yuan F, He XM, Cui ZF. An improved CBR model using time-series data for predicting the end-point of a converter. ISIJ Int., 2021, 61(10): 2564.

[3] Madhavan N, Brooks GA, Rhamdhani MA, Rout BK, Overbosch A. General heat balance for oxygen steelmaking. J. Iron Steel Res. Int., 2021, 28(5): 538.

[4] Liu X, Bao YP, Hua CJ, Chu JH, Gu C, Wang M. Denaturation behavior of inclusions in industrial pure iron by calcium treatment. J. Iron Steel Res. Int., 2023, 30(2): 249

[5] 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.

[6] Zhang HY, Zhou QL, Yuan ZX, Liu ZM. RBF neural network base on affinity propagation clustering and its application in BOF steelmaking. J. Iron. Steel. Res., 2014, 26(1): 22

[7] Liu X, Bao YP, Zhao LH, Gu C. Establishment and application of steel composition prediction model based on t-distributed stochastic neighbor embedding (t-SNE) dimensionality reduction algorithm. J. Sustain. Metall., 2024, 10(2): 509.

[8] Li CR, Zhao HW, Yin Q. Prediction model of end-point carbon content for BOF based on LM BP neural network. Adv. Mater. Res., 2011, 189–193: 4446.

[9] Z. Liu, S.S. Cheng, and P.B. Liu, Prediction model of BOF endpoint temperature and carbon content based on PCA-GA-BP neural network, Metall. Res. Technol., 119(2022), No. 6, art. No. 605.

[10] D.Z. Wang, F. Gao, L.D. Xing, J.H. Chu, and Y.P. Bao, Continuous prediction model of carbon content in 120 t converter blowing process, Metals, 12(2022), No. 1, art. No. 151.

[11] Zhang CC, Dong WL, Ji CX, Li HB, Chen B, Zhao CL. Endpoint prediction of duplex process converter based on machine learning algorithm. Steelmaking, 2023, 39(4): 28

[12] Wang M, Li SL, Gao C, Fan Y. End-point prediction TSVR model accuracy of 80 t BOF steelmaking. Iron Steel, 2020, 55(7): 53

[13] Wang M, Gao C, Ai XG, Zhai BP, Li SL. Whale optimization end-point control model for 260 tons BOF steelmaking. ISIJ Int., 2022, 62(8): 1684.

[14] M.Q. Gu, A.J. Xu, H.B. Wang, and Z.T. Wang, Real-time dynamic carbon content prediction model for second blowing stage in BOF based on CBR and LSTM, Processes, 9(2021), No. 11, art. No. 1987.

[15] H.D. Wang, H. Liu, F.G. Chen, H. Li, and X.J. Xue, Endpoint carbon content and temperature prediction model in BOF steelmaking based on posterior probability and intra-cluster feature weight online dynamic feature selection, High Temp. Mater. Process., 44(2025), No. 1, art. No. 20240067.

[16] Dong QQ, Li M, Hu SJ, Yu Y, Gu MQ. A dynamic control model of basic oxygen furnace last blowing stage based on improved conditional generative adversarial network. Metall. Mater. Trans. B, 2025, 56(1): 638.

[17] Xie TY, Zhang F, Li YR, Zhang Q, Wang YW, Shang H. Self-attention-based convolutional parallel network: An efficient multi-input deep learning model for endpoint prediction of high-carbon BOF steelmaking. Metall. Mater. Trans. B, 2024, 55(6): 4271.

[18] Y.K. Su, H. Liu, F.G. Chen, J.X. Liu, H. Li, and X.J. Xue, BOF steelmaking endpoint carbon content and temperature soft sensor model based on supervised weighted local structure preserving projection, High Temp. Mater. Process., 43(2024), No. 1, art. No. 20240030.

[19] Ding SF, Hua XP, Yu JZ. An overview on nonparallel hyperplane support vector machine algorithms. Neural Comput. Appl., 2014, 25(5): 975.

[20] Li XL, Cao ZY, Xu YL. Characteristics and trends of coal mine safety development. Energy Sources Part A, 2025, 47(1): 2316.

[21] X.L. Li, S.J. Chen, S. Wang, M. Zhao, and H. Liu, Study on in situ stress distribution law of the deep mine: Taking Linyi mining area as an example, Adv. Mater. Sci. Eng., 2021(2021), No. 1, art. No. 5594181.

[22] Shen WL, Shi GC, Wang YG, Bai JB, Zhang RF, Wang XY. Tomography of the dynamic stress coefficient for stress wave prediction in sedimentary rock layer under the mining additional stress. Int. J. Min. Sci. Technol., 2021, 31(4): 653.

[23] X.G. Kong, D. He, X.F. Liu, et al., Strain characteristics and energy dissipation laws of gas-bearing coal during impact fracture process, Energy, 242(2022), art. No. 123028.

[24] Huang HJ, Wei XX, Zhou YQ. An overview on twin support vector regression. Neurocomputing, 2022, 490: 80.

[25] Y. Wang, E.X. Du, S.Q. Yang, and L. Yu, Prediction and analysis of slope stability based on IPSO-SVM machine learning model, Geofluids, 2022(2022), art. No. 8529026.

[26] Zhang H, Li YN. Research on identification model of element logging shale formation based on IPSO-SVM. Petroleum, 2022, 8(2): 185.

[27] Wang Q, Tian XM. Soft sensing based on EMD and improved PSO-SVM. Appl. Mech. Mater., 2013, 291–294: 2817.

[28] H. Mojahedi, A.B. Sangar, and M. Masdari, Towards tax evasion detection using improved particle swarm optimization algorithm, Math. Probl. Eng., 2022(2022), art. No. 1027518.

[29] Gao YB, Hua J, Chen GW, Cai LP, Jia N, Zhu LK. Bi-directional prediction of wood fiber production using the combination of improved particle swarm optimization and support vector machine. BioResources, 2019, 14(3): 7229.

[30] Y.F. Ji, S.M. Ma, W. Peng, and Z.H. Cai, Research on alloy composition-process-wear properties of medium manganese steel based on machine learning, Tribol. Int., 200(2024), art. No. 110164.

[31] Q.F. Zhang, S. Chen, and Z.P. Fan, Bearing fault diagnosis based on improved particle swarm optimized VMD and SVM models, Adv. Mech. Eng., 13(2021), No. 6, art. No. 16878140211028451.

[32] D. Li and C. Chen, Research on exercise fatigue estimation method of Pilates rehabilitation based on ECG and sEMG feature fusion, BMC Med. Inform. Decis. Mak., 22(2022), No. 1, art. No. 67.

[33] Zhou JG, Guang FT, Tang RP. Scenario analysis of carbon emissions of China’s power industry based on the improved particle swarm optimization-support vector machine model. Pol. J. Environ. Stud., 2018, 27(1): 439.

[34] Wang Y, Yang SF, Li JS, Feng J, Wang F. Dephosph-orization by double-slag process in converter steelmaking. High Temp. Mater. Process., 2018, 37(7): 625.

[35] Zhang RH, Yang J, Sun H, Yang WK. Prediction of lime utilization ratio of dephosphorization in BOF steelmaking based on online sequential extreme learning machine with forgetting mechanism. Int. J. Miner. Metall. Mater., 2024, 31(3): 508.

[36] Zhang LQ, Min Y, Liu CJ, Huang J, Zheng CX, Ma W. Prediction of residual manganese content at the end point of converter smelting based on machine learning. Steelmaking, 2024, 40(5): 38

[37] Wang XZ, Han M, Wang J. Applying input variables selection technique on input weighted support vector machine modeling for BOF endpoint prediction. Eng. Appl. Artif. Intell., 2010, 23(6): 1012.

[38] Gao F, Bao YP, Wang M, Liu Y, Huang YS, Sun GT. Prediction model of end-point phosphorus content of converter based on FA-ELM. Iron Steel, 2020, 55(12): 24

[39] Shao X, Liu Q, Xin ZC, Zhang JS, Zhou T, Li SS. Hybrid model for BOF oxygen blowing time prediction based on oxygen balance mechanism and deep neural network. Int. J. Miner. Metall. Mater., 2024, 31(1): 106.

[40] Wang ZL, Bao YP. Development and prospects of molten steel deoxidation in steelmaking process. Int. J. Miner. Metall. Mater., 2024, 31(1): 18.

[41] Chen C, Wang N, Chen M. Prediction model of end-point phosphorus content in consteel electric furnace based on PCA-extra tree model. ISIJ Int., 2021, 61(6): 1908.

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

[43] C. Zhang, Z.H. Xu, Y.Y. Lao, and Y. Li, Dynamic process fault detection and diagnosis method based on factor analysis: Application on the three-tank system process, J. Chemom., 38(2024), No. 12, art. No. e3627.

[44] J.C. Li, N. Li, J.Z. Li, W. Wang, and H.L. Wang, Prediction of thermally modified wood color change after artificial weathering based on IPSO-SVM model, Forests, 14(2023), No. 5, art. No. 948.

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

[46] Liu YH, Yang B, Han XH. et al.. Predicting laser penetration welding states of high-speed railway Al butt-lap joint based on EEMD-SVM. J. Mater. Res. Technol., 2022, 21: 1316.

[47] D. Yang, Y. Peng, T. Zhou, T. Wang, and G. Lu, Percussion and PSO-SVM-based damage detection for refractory materials, Micromachines, 14(2023), No. 1, art. No. 135.

[48] X.Q. Ren, S.L. Liu, X.D. Yu, and X. Dong, A method for state-of-charge estimation of lithium-ion batteries based on PSO-LSTM, Energy, 234(2021), art. No. 121236.

[49] Cuong-Le T, Nghia-Nguyen T, Khatir S, Trong-Nguyen P, Mirjalili S, Nguyen KD. An efficient approach for damage identification based on improved machine learning using PSO-SVM. Eng. Comput., 2022, 38(4): 3069.

[50] Moayedi H, Raftari M, Sharifi A, Jusoh WAW, Rashid ASA. Optimization of ANFIS with GA and PSO estimating α ratio in driven piles. Eng. Comput., 2020, 36(1): 227.

[51] J. Zhu, J. Wu, Z. Chen, L. Cao, M. Yang, and W. Xu, Research on system of ultra-flat carrying robot based on improved PSO algorithm, Front. Neurorobot., 17(2023), art. No. 1294606.

RIGHTS & PERMISSIONS

University of Science and Technology Beijing