The comprehensive status of blast furnaces was one of the most important factors affecting their economy, quality, and longevity. The blast furnace comprehensive status had the nature of “black box,” and it was “unpredictable.” In this study, a blast furnace comprehensive status score and prediction method based on a cascade system and a combined model were proposed to address this issue. A dual cascade evaluation system was developed by integrating subjective and objective weighting methods. The analytic hierarchy process, coefficient of variation, entropy weight method, and impart combinatorial games were jointly employed to determine the optimal weight distribution across indicators. Categorized statuses (raw material, gas flow, furnace body, furnace cylinder, and iron–slag) were evaluated. Based on the five categories of the status data, the second cascade was applied to upgrade the quantitative evaluation of the comprehensive status. The weights of the different categories were 0.22, 0.15, 0.22, 0.21, and 0.20, respectively. According to the data analysis, the results of the comprehensive status score closely matched the on-site production logs. Based on the blast furnace smelting period, the maximal information coefficient method was applied to the 100 parameters that were most relevant to the comprehensive status. A combined prediction model for a comprehensive status score was designed using bidirectional long short-term memory (BiLSTM) and categorical boosting (CatBoost). The test results indicated that the combined model reduced the mean absolute error by an average of 0.275 and increased the hit rate by an average of 5.65 percentage points compared to BiLSTM or CatBoost alone. When the error range was ±2.5, the combined model predicted a hit rate of 91.66% for the next hour’s comprehensive status score, and its high accuracy was deemed satisfactory for the field. SHapley Additive exPlanations (SHAP) and regression fitting were applied to analyze the linear quantitative relationship between the key variables and the comprehensive status score. When the furnace bottom center temperature was increased by 10°C, the comprehensive status score increased by 0.44. This method contributes to a more precise management and control of the comprehensive status of the blast furnace on-site.
| [1] |
Shi Q, Tang J, Chu MS. Key issues and progress of industrial big data-based intelligent blast furnace ironmaking technology. Int. J. Miner. Metall. Mater.. 2023, 30(9): 1651
|
| [2] |
Z. Zhang, J. Tang, M.S. Chu, et al., The amount prediction and optimization of the returned ore generated from sintering process based on SHAP value and ensemble learning, Steel Res. Int., 94(2023), No. 9, art. No. 2300114.
|
| [3] |
L. Shen, Z.P. Chen, Z.H. Jiang, and W.H. Gui, Soft sensor modeling of blast furnace wall temperature based on temporal–spatial dimensional finite-element extrapolation, IEEE Trans. Instrum. Meas., 70(2020), art. No. 2500314.
|
| [4] |
Gomes FSV, Côco KF, Salles JLF. Multistep forecasting models of the liquid level in a blast furnace hearth. IEEE Trans. Autom. Sci. Eng.. 2017, 14(2): 1286
|
| [5] |
Meng LL, Liu JX, Liu R, et al. . Prediction of silicon content of hot metal in blast furnace based on Optuna-GBDT. ISIJ Int.. 2024, 64(8): 1240
|
| [6] |
Jiang DW, Wang ZY, Li KJ, Zhang JL, Zhang S. Machine learning models for predicting and controlling the pressure difference of blast furnace. JOM. 2023, 75(11): 4550
|
| [7] |
Z.Y. Li, H.Z. Wang, J.H. Qian, Y.H. Cui, and Y. Fang, Efficient prediction for blast furnace gas holder level using novel preprocessing techniques and weight correction strategy, Eng. Appl. Artif. Intell., 138(2024), Part A, art. No. 109223.
|
| [8] |
S.H. Liu and W.Q. Sun, Knowledge- and data-driven prediction of blast furnace gas generation and consumption in iron and steel sites, Appl. Energy, 390(2025), art. No. 125819.
|
| [9] |
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
|
| [10] |
Hu YF, Zhou H, Yao S, et al. . Comprehensive evaluation of the blast furnace status based on data mining and mechanism analysis. Int. J. Chem. React. Eng.. 2022, 20(2): 225
|
| [11] |
Deng Y, Lyu Q. Establishment of evaluation and prediction system of comprehensive state based on big data technology in a commercial blast furnace. ISIJ Int.. 2020, 60(5): 898
|
| [12] |
Y.X. Wen, M.F. Rahman, H.L. Xu, and T.L.B. Tseng, Recent advances and trends of predictive maintenance from data-driven machine prognostics perspective, Measurement, 187(2022), art. No. 110276.
|
| [13] |
Chen CL, Hsieh CT, Chao YC. Expert system for realtime control of an ironmaking reactor. Int. J. Syst. Sci.. 1992, 23(1): 17
|
| [14] |
Naito M, Takeda K, Matsui Y. Ironmaking technology for the last 100 years: Deployment to advanced technologies from introduction of technological know-how, and evolution to next-generation process. ISIJ Int.. 2015, 55(1): 7
|
| [15] |
Ueda S, Natsui S, Nogami H, Yagi JI, Ariyama T. Recent progress and future perspective on mathematical modeling of blast furnace. ISIJ Int.. 2010, 50(7): 914
|
| [16] |
Chen J. A predictive system for blast furnaces by integrating a neural network with qualitative analysis. Eng. Appl. Artif. Intell.. 2001, 14(1): 77
|
| [17] |
Lee K, Ki JH. Rise of latecomers and catch-up cycles in the world steel industry. Res. Policy. 2017, 46(2): 365
|
| [18] |
Z.H. Jiang, J.C. Huang, W.H. Gui, et al., A novel motion state recognition method for blast furnace burden surface in ironmaking process, IEEE Trans. Instrum. Meas., 72(2023), art. No. 5023914.
|
| [19] |
Li HY, Bu XP, Liu XJ, et al. . Evaluation and prediction of blast furnace status based on big data platform of ironmaking and data mining. ISIJ Int.. 2021, 61(1): 108
|
| [20] |
Q. Shi, J. Tang, and M.S. Chu, Evaluation, prediction, and feedback of blast furnace hearth activity based on data-driven analysis and process metallurgy, Steel Res. Int., 95(2024), No. 2, art. No. 2300385.
|
| [21] |
H.W. Li, X. Li, X.J. Liu, X.P. Bu, S.J. Chen, and Q. Lyu, Evaluation and prediction models for blast furnace operating status based on big data mining, Metals, 13(2023), No. 7, art. No. 1250.
|
| [22] |
Li HY, Li X, Liu XJ, Bu XP, Li HW, Lyu Q. Prediction of blast furnace parameters using feature engineering and Stacking algorithm. Ironmaking Steelmaking. 2022, 49(3): 283
|
| [23] |
Liu DL, Tang J, Chu MS, Xue ZL, Shi Q, Feng JG. Hot metal temperature prediction technique based on feature fusion and GSO-DF. ISIJ Int.. 2024, 64(13): 1881
|
| [24] |
H.W. Li, X. Li, X.J. Liu, et al., Prediction of the vanadium content of molten iron in a blast furnace and the optimization of vanadium extraction, Separations, 10(2023), No. 10, art. No. 521.
|
| [25] |
Shi Q, Tang J, Chu MS. Process metallurgy and data-driven prediction and feedback of blast furnace heat indicators. Int. J. Miner. Metall. Mater.. 2024, 31(6): 1228
|
| [26] |
Y.X. Zhang, K. Guo, S. Zhang, Y.L. Yang, and W.D. Xiao, Spatio-temporal and multi-mode prediction for blast furnace gas flow, J. Franklin Inst., 361(2024), No. 18, art. No. 107330.
|
| [27] |
Liu SH, Sun WQ, Li WD, Jin BZ. Prediction of blast furnace gas generation based on data quality improvement strategy. J. Iron Steel Res. Int.. 2023, 30(5): 864
|
| [28] |
Liu QS, Wu JJ, Shao YC, Wang H, Zhu X, Liao Q. ANN-based model to predict the viscosity of molten blast furnace slag at high temperatures of >1600 K. J. Sustain. Metall.. 2023, 9(3): 1020
|
| [29] |
Li S, Chang JC, Chu MS, Li J, Yang AM. A blast furnace coke ratio prediction model based on fuzzy cluster and grid search optimized support vector regression. Appl. Intell.. 2022, 52(12): 13533
|
| [30] |
J.P. Li, C.C. Hua, and Y.N. Yang, Output space transfer-based MIMO RVFLNs modeling for estimation of blast furnace molten iron quality with missing indexes, IEEE Trans. Instrum. Meas., 70(2021), art. No. 2506610.
|
| [31] |
S.W. Lou, C.J. Yang, P. Wu, L.Y. Kong, and Y.H. Xu, Fault diagnosis of blast furnace iron-making process with a novel deep stationary kernel learning support vector machine approach, IEEE Trans. Instrum. Meas., 71(2022), art. No. 3521913.
|
| [32] |
Cheng EWL, Li H. Analytic hierarchy process. Measuring Bus. Excellence. 2001, 5(3): 30
|
| [33] |
Kesteven GL. The coefficient of variation. Nature. 1946, 158(4015): 520
|
| [34] |
Y.X. Zhu, D.Z. Tian, and F. Yan, Effectiveness of entropy weight method in decision-making, Math. Probl. Eng., 2020(2020), No. 1, art. No. 3564835.
|
| [35] |
B. Zhao, Y.B. Shao, C. Yang, and C. Zhao, The application of the game theory combination weighting-normal cloud model to the quality evaluation of surrounding rocks, Front. Earth Sci., 12(2024), art. No. 1346536.
|
| [36] |
Wang HS, Zhang YP, Liang J, Liu LL. DAFABiLSTM: Deep autoregression feature augmented bidirectional LSTM network for time series prediction. Neural Networks. 2023, 157: 240
|
| [37] |
J.T. Hancock and T.M. Khoshgoftaar, Catboost for big data: An interdisciplinary review, J. Big Data, 7(2020), No. 1, art. No. 94.
|
| [38] |
Wang MY, Tang J, Chu MS, Shi Q, Zhang Z. Prediction and optimization of flue pressure in sintering process based on SHAP. Int. J. Miner. Metall. Mater.. 2025, 32(2): 346
|
RIGHTS & PERMISSIONS
University of Science and Technology Beijing
PDF
