Top > JACIII > Intelligent Prediction of the Hearth Lining Temperature in Bla ...

single-jc.php

JACIII Vol.30 No.4 pp. 1033-1043
(2026)
doi: 10.20965/jaciii.2026.p1033

Research Paper:

Views over last 60 days: 139

Intelligent Prediction of the Hearth Lining Temperature in Blast Furnaces Based on Spatiotemporal Feature Fusion

Qifu Chen*1,*2, Jiaxin Cheng*3,*4, Jianqi An*1,*3,*4,† ORCID Icon, and Jinhua She*5 ORCID Icon

*1School of Future Technology, China University of Geosciences
No.388 Lumo Road, Wuhan, Hubei 430074, China

*2Hunan Valin Lianyuan Iron and Steel Co., Ltd.
No.1005 Jinxing North Road, Louxing District, Loudi, Hunan 417009, China

*3School of Artificial Intelligence and Automation, China University of Geosciences
No.388 Lumo Road, Wuhan, Hubei 430074, China

*4Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems
No.388 Lumo Road, Wuhan, Hubei 430074, China

*5School of Engineering, Tokyo University of Technology
1404-1 Katakura machi, Hachioji, Tokyo 192-0982, Japan

†Corresponding author

Received:
December 3, 2025
Accepted:
January 27, 2026
Published:
July 20, 2026
Creative Commons License
Keywords:
blast furnace, hearth lining temperature, spatiotemporal feature fusion, dual-attention mechanism, temperature forecasting
Abstract

Accurate forecasting of the hearth lining temperature in blast furnaces is essential for operational safety and efficiency, however it remains challenging owing to the complex spatiotemporal coupling and time-lag effects among process variables. To address this issue, we present a new spatiotemporal feature modeling framework that integrates gated recurrent units (GRUs) with a dual-attention mechanism to capture multi-scale temporal dependencies and dynamically assess variable importance. A convolutional neural network module is incorporated to extract localized spatial features from the time-series data, thereby enhancing the representation of the underlying metallurgical mechanisms. The validation on real industrial data showed that the proposed model achieved a root mean square error of 0.0523 and a hit rate of 94.26%, outperforming conventional long short-term memory and GRU models. This approach offers a reliable solution for intelligent health monitoring and proactive maintenance in modern data-driven ironmaking operations under highly dynamic and uncertain conditions.

Full text
Cite this article as:
Q. Chen, J. Cheng, J. An, and J. She, “Intelligent Prediction of the Hearth Lining Temperature in Blast Furnaces Based on Spatiotemporal Feature Fusion,” J. Adv. Comput. Intell. Intell. Inform., Vol.30 No.4, pp. 1033-1043, 2026.
Data files:
References
  1. [1] J. An, X. Shen, M. Wu, and J. She, “A multi-time-scale fusion prediction model for the gas utilization rate in a blast furnace,” Control Engineering Practice, Vol.92, Article No.104120, 2019. https://doi.org/10.1016/j.conengprac.2019.104120
  2. [2] C. Liu, J. Tan, J. Li, Y. Li, and H. Wang, “Temporal hypergraph attention network for silicon content prediction in blast furnace,” IEEE Trans. on Instrumentation and Measurement, Vol.71, Article No.2521413, 2022. https://doi.org/10.1109/TIM.2022.3219475
  3. [3] J. Chen, “A predictive system for blast furnaces by integrating a neural network with qualitative analysis,” Engineering Applications of Artificial Intelligence, Vol.14, No.1, pp. 77-85, 2001. https://doi.org/10.1016/S0952-1976(00)00062-2
  4. [4] J. Wei and X. Chen, “Blast furnace gas flow strength prediction using FMCW radar,” ISIJ Int., Vol.55, No.3, pp. 600-604, 2015. https://doi.org/10.2355/isijinternational.55.600
  5. [5] D. Xiao, J. An, Y. He, and M. Wu, “The chaotic characteristic of the carbon-monoxide utilization ratio in the blast furnace,” ISA Trans., Vol.68, pp. 109-115, 2017. https://doi.org/10.1016/j.isatra.2017.03.004
  6. [6] Y. Li, S. Zhang, Y. Yin, W. Xiao, and J. Zhang, “A novel online sequential extreme learning machine for gas utilization ratio prediction in blast furnaces,” Sensors, Vol.17, No.8, Article No.1847, 2017. https://doi.org/10.3390/s17081847
  7. [7] G. Zhao, J. An, Y. Guo, Y. He, and M. Wu, “A multi-time-scale multi-step prediction method for gas utilization rate in a BF based on just-in-time learning,” Control Engineering Practice, Vol.147, Article No.105940, 2024.
  8. [8] S. Lu, H. Yu, H. Dong, X. Wang, and Y. Sun, “Single-step prediction method of burning zone temperature based on real-time wavelet filtering and KELM,” Engineering Applications of Artificial Intelligence, Vol.70, pp. 142-148, 2018. https://doi.org/10.1016/j.engappai.2018.01.010
  9. [9] X. Su, S. Zhang, Y. Yin, and W. Xiao, “Prediction model of hot metal temperature for blast furnace based on improved multi-layer extreme learning machine,” Int. J. of Machine Learning and Cybernetics, Vol.10, No.10, pp. 2739-2752, 2019. https://doi.org/10.1007/s13042-018-0897-3
  10. [10] H. Jiao, Y. Zhang, C. Luo, and Z. Bi, “Collaborative multiple rank regression for temperature prediction of blast furnace,” IEEE Trans. on Instrumentation and Measurement, Vol.71, Article No.3515110, 2022. https://doi.org/10.1109/TIM.2022.3180408
  11. [11] Z. Chen, M. Lu, Y. Zhou, and C. Chen, “Information synergy entropy based multi-feature information fusion for the operating condition identification in aluminium electrolysis,” Information Sciences, Vol.548, pp. 275-294, 2021. https://doi.org/10.1016/j.ins.2020.07.031
  12. [12] C.-Y. Shi, P.-L. Tao, S.-D. Li, Y.-K. Wang, and L. Zhang, “Prediction model of blast furnace molten iron temperature and molten iron silicon content based on improved arithmetic optimization twin support vector machine for regression,” J. of Mining and Metallurgy, Section B: Metallurgy, Vol.60, No.3, pp. 407-419, 2024. https://doi.org/10.2298/JMMB240928033S
  13. [13] Y. Yue, A. Dong, H. Zhao, and H. Wang, “Study on prediction model of blast furnace hot metal temperature,” 2016 IEEE Int. Conf. on Mechatronics and Automation, pp. 1396-1400, 2016. https://doi.org/10.1109/ICMA.2016.7558767
  14. [14] L. Zhang et al., “Prediction of blast furnace fuel ratio based on back-propagation neural network and K-nearest neighbor algorithm,” Steel Research Int., Vol.93, No.10, Article No.2200215, 2022. https://doi.org/10.1002/srin.202200215
  15. [15] X. Liu et al., “Control of silicon content in blast furnace iron based on GRA–LSTM–BAS prediction methods,” Ironmaking & Steelmaking: Processes, Products and Applications, Vol.51, No.2, pp. 127-138, 2024. https://doi.org/10.1177/03019233231221676
  16. [16] R. Liu et al., “Intelligent prediction and real-time monitoring system for gas flow distribution at the top of blast furnace,” ISIJ Int., Vol.63, No.10, pp. 1714-1726, 2023. https://doi.org/10.2355/isijinternational.ISIJINT-2023-099
  17. [17] E. Bozkurt, İ. M. Orak, and Y. Tunçkaya, “Performance analysis of hot metal temperature prediction in a blast furnace and expert suggestion system proposal using neural, statistical and fuzzy models,” Metallurgical Research & Technology, Vol.118, No.3, Article No.321, 2021. https://doi.org/10.1051/metal/2021043
  18. [18] K. Guo, Y. Zhang, S. Zhang, and W. Xiao, “Multi-variable prediction of blast furnace status driven by data,” IEEE Trans. on Instrumentation and Measurement, Vol.74, Article No.2527715, 2025. https://doi.org/10.1109/TIM.2025.3566715
  19. [19] S. Zhang, H. Jiang, Y. Yin, W. Xiao, and B. Zhao, “The prediction of the gas utilization ratio based on TS fuzzy neural network and particle swarm optimization,” Sensors, Vol.18, No.2, Article No.625, 2018. https://doi.org/10.3390/s18020625
  20. [20] D. Jiang et al., “Predictive modeling of blast furnace gas utilization rate using different data pre-processing methods,” Metals, Vol.12, No.4, Article No.535, 2022. https://doi.org/10.3390/met12040535
  21. [21] Y. Li, C. Yang, and Y. Sun, “Dynamic time features expanding and extracting method for prediction model of sintering process quality index,” IEEE Trans. on Industrial Informatics, Vol.18, No.3, pp. 1737-1745, 2022. https://doi.org/10.1109/TII.2021.3086763
  22. [22] C. Ma, X. Huang, Y. Zhao, T. Wang, and B. Du, “GRU-LSTM model based on the SSA for short-term traffic flow prediction,” J. of Intelligent and Connected Vehicles, Vol.8, No.1, Article No.9210051, 2025. https://doi.org/10.26599/JICV.2024.9210051
  23. [23] T. Li, M. Hua, and X. Wu, “A hybrid CNN-LSTM model for forecasting particulate matter (PM2.5),” IEEE Access, Vol.8, pp. 26933-26940, 2020. https://doi.org/10.1109/ACCESS.2020.2971348
  24. [24] J. Li, C. Yang, Y. Li, and S. Xie, “A context-aware enhanced GRU network with feature-temporal attention for prediction of silicon content in hot metal,” IEEE Trans. on Industrial Informatics, Vol.18, No.10, pp. 6631-6641, 2022. https://doi.org/10.1109/TII.2021.3112487
  25. [25] H. Li et al., “Prediction of blast furnace parameters using feature engineering and Stacking algorithm,” Ironmaking & Steelmaking: Processes, Products and Applications, Vol.49, No.3, pp. 283-296, 2022. https://doi.org/10.1080/03019233.2021.1992816

Creative Commons License  This article is published under a Creative Commons Attribution-NoDerivatives 4.0 Internationa License.

*This site is desgined based on HTML5 and CSS3 for modern browsers, e.g. Chrome, Firefox, Safari, Edge, Opera.

Last updated on Jul. 19, 2026