Accurate prediction of endpoint carbon content in converter steelmaking is a key technology for enhancing process control, reducing costs, improving efficiency, and advancing intelligent steelmaking. However, traditional prediction models often suffer from challenges such as difficulty in obtaining mechanism parameters and limited interpretability. To address these issues, this study proposes a hybrid model (HM) for predicting endpoint carbon content that integrates both mechanism-based modeling and data-driven methods. First, the parameters of the mechanism model (MM) are optimized using a genetic algorithm (GA) to improve its effective representation of the converter smelting process. Subsequently, a nonlinear coupling between the optimized MM and a random forest (RF) model is established to construct the hybrid mechanism–data fusion framework. Validation using actual production data from S Steel Plant demonstrates that the HM outperforms traditional mechanism-based and purely data-driven models. Within the error intervals of (−0.01%, 0.01%) and (−0.02%, 0.02%), the hit rates reached 84.4% and 98.8%, respectively. The mean absolute error (MAE) and root mean squared error (RMSE) were (5.70 × 10−3)wt% and (7.27× 10−3)wt%, respectively. The results indicate that the proposed HM achieves high prediction accuracy and robustness while maintaining strong mechanistic interpretability, offering a promising approach for endpoint control and intelligent optimization in converter steelmaking.
| [1] |
Zhu MM, Li CH, Zhang XW, Yang ZJ. A new method to predict endpoint phosphorus content during converter steelmaking process via industrial data and mechanism analysis. Metall. Mater. Trans. B, 2024, 5564660.
|
| [2] |
Wang Z, Liu Q, Liu HT, Wei SZ. A review of end-point carbon prediction for BOF steelmaking process. High Temp. Mater. Processes (London), 2020, 391653.
|
| [3] |
X.X. Xie, H.J. Wang, W.M. Li, D.P. Zhan, X.Y. Li, and X.M. Zang, Prediction model of endpoint temperature of converter steelmaking based on PCA-BP neural network, Trans. Indian Inst. Met., 78(2025), No. 4, art. No. 90.
|
| [4] |
Jiang XP, Wang HH, Kong YJ, et al. Real-time prediction of C and P contents in BOF steelmaking using machine learning without sample analysis delay. Metall. Mater. Trans. B, 2026, 57: 5313.
|
| [5] |
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.
|
| [6] |
Zhao LH, Yang S, Xu YZ, Wang ZL, Liu X, Bao YP. Factor analysis and machine learning for predicting endpoint carbon content in converter steelmaking. Int. J. Miner. Metall. Mater., 2025, 32102469.
|
| [7] |
Li P, Zhan DP, Wang B, Wang MX, Yang NH. Data-driven and mechanistic hybrid model for predicting oxygen consumption in BOF steelmaking. Metall. Mater. Trans. B, 2025, 5632558.
|
| [8] |
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.
|
| [9] |
Zhang Q, Yang Y, Dai YX, Lin L. BOF smelting model based on coupling reaction mechanism. Iron steel, 2024, 59840
|
| [10] |
W.H. Lin, J.K. Sun, K.X. Zhou, et al., A modified mathematical model for end-point carbon prediction of BOF based on off-gas analysis, IOP Conf. Ser.: Mater. Sci. Eng., 668(2019), No. 1, art. No. 012014.
|
| [11] |
Li N, Lin WH, Cao LL, Liu Q, Sun LF, Liao SS. Carbon prediction model for basic oxygen furnace off-gas analysis based on bath mixing degree. Chin. J. Eng., 2018, 40101244
|
| [12] |
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.
|
| [13] |
Dai YS, Yang LB, Zhao JX, Wang J, Wang CY. Development and prospect of prediction model technology of endpoint of converter. Ind. Heat., 2024, 5387
|
| [14] |
Hinton GE, Osindero S, Teh YW. A fast learning algorithm for deep belief nets. Neural Comput., 2006, 1871527.
|
| [15] |
Zhang RH, Yang J. State of the art in applications of machine learning in steelmaking process modeling. Int. J. Miner. Metall. Mater., 2023, 30112055.
|
| [16] |
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, 295751.
|
| [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, 5564271.
|
| [18] |
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, 551224
|
| [19] |
Xie TY, Zhang CD, Zhou QL, Tian ZQ, Liu S, Guo HJ. TSC prediction and dynamic control of BOF steelmaking with state-of-the-art machine learning and deep learning methods. J. Iron Steel Res. Int., 2024, 311174.
|
| [20] |
Shi CY, Guo SY, Wang BS, Ma ZC, Wu CL, Sun P. Prediction model of BOF end-point phosphorus content and sulfur content based on LWOA-TSVR. Ironmaking Steelmaking, 2023, 507857.
|
| [21] |
M. Wang, S.L. Li, C. Gao, X.G. Ai, and B.P. Zhai, End-point dynamic control model for 260 tons BOF steelmaking based on PWWTSVR and LWOA, Steel Res. Int., 94(2023), No. 7, art. No. 2200872.
|
| [22] |
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.
|
| [23] |
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, 61102564.
|
| [24] |
Guo YZ, He DF, Li XL, Feng K. End-point temperature prediction of converter steelmaking based on key feature amplification and grey wolf algorithm improved affinity propagation clustering. Metall. Mater. Trans. B, 2025, 5622047.
|
| [25] |
Zhang JB, Ghalati MK, Fu J, Yang XA, El-Fallah GMAM, Dong HB. Boosting algorithms for predicting endpoint temperature in BOF steelmaking using big industrial datasets. J. Iron Steel Res. Int., 2025, 3271856.
|
| [26] |
Shlezinger N, Eldar YC, Boyd SP. Model-based deep learning: On the intersection of deep learning and optimization. IEEE Access, 2022, 10: 115384.
|
| [27] |
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, 311106.
|
| [28] |
F. Gao, D.Z. Wang, Y.P. Bao, X. Liu, L.D. Xing, and L.H. Zhao, A mechanistic model based on statistics for the prediction of a converter’s end-point molten steel temperature, Processes, 11(2023), No. 8, art. No. 2233.
|
| [29] |
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.
|
| [30] |
Biau G, Scornet E. A random forest guided tour. TEST, 2016, 252197.
|
| [31] |
Zhang HZ, Zimmerman J, Nettleton D, Nordman DJ. Random forest prediction intervals. Am. Stat., 2020, 744392.
|
| [32] |
Wang JH, Fang Q, Zhu WJ, et al. Multimodel predictions on converter raw material addition under GRNN optimization: A comparative study. Metall. Mater. Trans. B, 2024, 5521146.
|
| [33] |
Wang XH. Ferrous Metallurgy, 2007, Beijing: Higher Education Press, 21
|
| [34] |
Kang F, Han SX, Salgado R, Li JJ. System probabilistic stability analysis of soil slopes using Gaussian process regression with Latin hypercube sampling. Comput. Geotech., 2015, 63: 13.
|
Rights & permissions
University of Science and Technology Beijing
PDF
