This paper investigates the accurate prediction of molten iron temperature in blast furnace smelting. A prediction model based on Kolmogorov–Arnold Network-Long Short-Term Memory-Attention(KAN-LSTM-Attention) is proposed, combined with fuzzy control to achieve closed-loop temperature regulation. The model integrates the nonlinear mapping capability of KAN, the temporal feature extraction capability of Long Short-Term Memory (LSTM), and the dynamic weighting capability of the Attention mechanism. Experimental results show that the model exhibits low prediction error and good fitting performance on both training and test sets, achieving an 84% qualification rate within the industrial tolerance of ±15 °C. Furthermore, by adopting a fuzzy control strategy—through steps including fuzzification, rule reasoning, inference decision-making, and defuzzification—stable control of the molten iron temperature is realized, maintaining it within the range of 1495 °C to 1505 °C.
ChenW. Intelligent manufacturing transformation practice in the steel industry: research on the application and optimization strategies in blast furnace smelting. Fujian Metall2025; 54: 57–61. (in Chinese)
2.
WangCJ.Research on computer control technology in blast furnace smelting process in iron and steel mills. Ind Heat2025; 54: 36–39. in Chinese.
3.
YangXLiuXF, et al.Study on computer optimization control system of blast furnace smelting process. Ind Heat2025; 54: 44–48. (in Chinese)
4.
WangHHouYHeY, et al.A physical-constrained decomposition method of infrared thermography: pseudo restored heat flux approach based on ensemble Bayesian variance tensor fraction. IEEE Trans Ind Inf2024; 20: 3413–3424.
5.
LuoYXDongYLYangFQ, et al.Ultraviolet single-camera stereo-digital image correlation for deformation measurement up to 2600°C. Exp Mech2024; 64: 1343–1355.
6.
HanMBWangHNZhengHW, et al.Big data-driven CNN-GRU-attention model for blast furnace hot metal temperature prediction. China Metall2025: 1–14. DOI: 10.13228/j.boyuan.issn1006-9356.20250328. (in Chinese)
7.
CuiGDZhuYLMaKH, et al.Research on the prediction model of hot metal temperature in vanadium-titanium magnetite blast furnaces based on deep learning. Iron Steel Vanadium Titanium2025: 1–17. https://link.cnki.net/urlid/51.1245.TF.20250526.1842.002. (in Chinese)
8.
XuWHeZHYangK, et al.Prediction of molten iron temperature based on ICEEMDAN-KPCA-RVM. Metall Ind Autom2024; 48: 18–25. (in Chinese)
9.
ShobanaRJaintBKumarR. Design of a novel robust recurrent neural network for the identification of complex nonlinear dynamical systems. Soft COmput2024; 28: 2737–2751.
10.
ShobanaRKumarRJaintB. A recurrent neural network-based identification of complex nonlinear dynamical systems: a novel structure, stability analysis and a comparative study. Soft COmput2024; 28: 3941–3971.
11.
ShobanaRKumarRJaintB. Nonlinear dynamical system approximation and adaptive control based on hybrid-feed-forward recurrent neural network: simulation and stability analysis. Expert Syst2024; 41(9). DOI: 10.1111/exsy.13619.
12.
MengKLiuXJYiFY, et al.GA-XG boost-based interpretable model for predicting molten iron yield of blast furnace. Metall Ind Autom2024; 48: 108–121. (in Chinese)
13.
ShenZHanWHuY, et al.An interpretable hybrid deep learning model for molten iron temperature prediction at the iron-steel interface based on Bi-LSTM and transformer. Mathematics2025; 13: 975–975.
14.
LiuXJZhangYJLiX, et al.Blast furnace temperature monitoring and early warning system based on big data. China Metallurgy2023; 33: 98–105+140. (in Chinese)
15.
LeeNShinMSagingalievaA, et al. Predictive control of blast furnace temperature in steelmaking with hybrid depth-infused quantum neural networks. arxiv preprint arxiv:2504.12389. 2025. DOI: 10.48550/arXiv.2504.12389.
16.
ZhangMH. A Big Data-based monitoring and early-warning system for blast furnace temperature. North China University of Science and Technology. 2024. DOI: 10.27108/d.cnki.ghelu.2024.001313. (in Chinese)
17.
PaixãoTMMucciacciaSSNavarroCL, et al.A machine learning approach for intra- and inter-cast hot metal temperature forecasting. Comput Chem Eng2025; 201: 109210.
18.
HeJLTangYChuMS, et al.Research on data management and mining of blast furnace ironmaking based on big data. J Iron Steel Res2024; 36: 844–854. (in Chinese)
19.
MumuniAMumuniF. Automated data processing and feature engineering for deep learning and big data applications: a survey. J Inf Intell2025; 3: 113–153.
20.
GongHLiYZhangJ, et al.A new filter feature selection algorithm for classification task by ensembling Pearson correlation coefficient and mutual information. Eng Appl Artif Intell2024; 131: 107865.
21.
MienyeIDJereN. A survey of decision trees: concepts, algorithms, and applications. IEEE Access2024; 12: 86716–86727.
22.
SomvanshiSJavedSAIslamMM, et al. A survey on Kolmogorov-Arnold network. ACM Comput Surv2025, 58(2): 1–35.
23.
JiTHouYZhangD. A comprehensive survey on Kolmogorov Arnold networks (KAN). arxiv preprint arxiv:2407.11075. 2024. doi:arXiv:2407.11075.
24.
KongYWangZNieY, et al.Unlocking the power of LSTM for long term time series forecasting. Proc AAAI Conf Artif Intell2025; 39: 11968–11976.
25.
AlizadeganHRashidi MalkiBRadmehrA, et al.Comparative study of long short-term memory (LSTM), bidirectional LSTM, and traditional machine learning approaches for energy consumption prediction. Energy Explor Exploit2025; 43: 281–301.
26.
DuanYLiuXLiX, et al.Dynamic prediction model of yield of molten iron based on multi-head attention mechanism. ISIJ Int2024; 64: 30–43.
27.
SahuSSimhaJB. Application of fuzzy logic control in iron box temperature regulation. J Res Appl Sci Eng Technol2023; 11: 1860–8163.
28.
BeheshtianSRoodbariSKGhorbaniH, et al. Advanced machine learning methods for accurate prediction of loss circulation in drilling well log. In: 2024 IEEE 11th international conference on computational cybernetics and cyber-medical systems (ICCC), 20 September 2025. DOI: 10.1109/ICCC62278.2024.10582962.
29.
BeheshtianSRoodbariSKGhorbaniH, et al. Comparative evaluation of machine learning and Bayesian deep learning methods for estimating ultimate recovery in shale well reservoirs. In: 2024 IEEE 11th international conference on computational cybernetics and cyber-medical systems (ICCC), 20 September 2025. DOI: 10.1109/ICCC62278.2024.10583113.
30.
DengCWangYMiW, et al.Deep learning-driven analysis of petrophysical dynamics in pay zone quality and reservoir characterization. Nat Resour Res2025; 34: 2047–2066.
31.
GhorbaniHAbadARB. Analysis of geomechanical processes of sand production for productive wells (study of Asmari reservoir in the Ahvaz oil field). Bull High Technol2022; 1: 10–18.
32.
BeheshtianSRoodbariSKGhorbaniH, et al.Machine learning prediction of gas hydrates phase equilibrium in porous medium. In: 2024 IEEE 18th International Symposium on Applied Computational Intelligence and Informatics (SACI), Timisoara, Romania, 2024, pp.000417–000424. DOI: 10.1109/SACI60582.2024.10619733.
33.
HuXXieJLiX, et al.Predicting hydrocarbon reservoir quality in deepwater sedimentary systems using sequential deep learning techniques. Geomech Geophys Geo-Energy Geo-Resour2025; 11: 96.
34.
LuXWangZZhaoM, et al.Data-driven insights into climate change effects on groundwater levels using machine learning. Water Resour Manage2025; 39: 3521–3536.
35.
VoskanyanMGhorbaniHAzodiniaR. Utilizing citizen-driven scientific endeavors for freshwater pollution surveillance: a case report of Lake Sevan, Armenia. In: 2024 IEEE 22nd world symposium on applied machine intelligence and informatics (SAMI), Stará Lesná, Slovakia, 2024, pp.000505–000512. DOI: 10.1109/SAMI60510.2024.10432830.
36.
VoskanyanMGhorbaniHAzodiniaM. An investigation of the hydrochemical parameters for natural monuments. In: 2024 IEEE 11th international conference on computational cybernetics and cyber-medical systems (ICCC), Hanoi, Vietnam, 2024, pp.1–6. DOI: 10.1109/ICCC62278.2024.10582928.
37.
GhorbaniHAsadiSGhorbaniS, et al.Investigating the predictive contribution of attitude towards life and belief system on self-resilience and psychological toughness of cancer patients about the mediating role of emotion regulation. In: 2023 IEEE 21st world symposium on applied machine intelligence and informatics (SAMI), Herl'any, Slovakia, 2023, pp.000139–000146. DOI: 10.1109/SAMI58000.2023.10044491.
38.
HazbehOGhorbaniHMolaeiO, et al.Proposing a new model for estimation of oil rate passing through wellhead chokes in an Iranian heavy oil field. In: 2022 IEEE 22nd international symposium on computational intelligence and informatics and 8th IEEE international conference on recent achievements in mechatronics, automation, computer science and robotics (CINTI-MACRo), Budapest, Hungary, 2022, pp.000037–000044. DOI: 10.1109/CINTI-MACRo57952.2022.10029414.
39.
GhorbaniHMinasyanAAnsariD, et al.Anti-diabetic therapies on dental implant success in diabetes mellitus: a comprehensive review. Front Pharmacol2024; 15. DOI: 10.3389/fphar.2024.1506437.
40.
RezaeiJAzoujiRAzoujiM, et al.Application of the Analytical Hierarchy Process in the management of private ambulance care systems in three selected European countries: a strategic decision-making framework. Front Public Health2025; 13. DOI: 10.3389/fpubh.2025.1526586.
41.
GhorbaniHChalabyanAMinasyanA, et al.Application of analytical hierarchy process to the selection suitability of biological drug forms for psoriasis treatment. J Pharm Innov2025; 20: 94.
42.
DingHWangCGhorbaniH, et al.The impact of magnesium on shivering incidence in cardiac surgery patients: a systematic review. Heliyon2024; 10: e32127.
43.
ZhangGChenRGhorbaniH, et al.Artificial intelligence-enabled innovations in cochlear implant technology: advancing auditory prosthetics for hearing restoration. Bioeng Transl Med2025; 10. DOI: 10.1002/btm2.10752.
44.
TehraniPSGhorbaniHLajmorakS, et al.Laboratory study of polymer injection into heavy oil unconventional reservoirs to enhance oil recovery and determination of optimal injection concentration. AIMS Geosci2022; 8: 579–592.
45.
AghabalyanDGhorbaniHRiturajR. Relationship of medicine and philosophy: mathematical modeling of moral structures-etometry. In: 2023 IEEE 17th international symposium on applied computational intelligence and informatics (SACI), Timisoara, Romania, 2023, pp.000567–000574. DOI: 10.1109/SACI58269.2023.10158582.
46.
Erkınay ÖzdemirMBeşkardeşAHameşY. Intelligent sinter machine speed control system using optimized fuzzy logic controller: an experimental study in iron and steel plant. Arab J Sci Eng2024; 49: 16391–16406.
47.
GhiormezLPanoiuMPanoiuC. Fuzzy logic controller for power control of an electric arc furnace. Mathematics2024; 12: 3445.
48.
GuoJXuXYZhangJX, et al.Comparison of PlD control and fuzzy control based on MATLAB. Constr Mach Equip2025; 56: 67–72 + 10. (in Chinese)
49.
KrzywanskiJBorycaJUrbaniakD, et al.Fuzzy logic approach for modeling of heating and scale formation in industrial furnaces. Materials (Basel)2024; 17: 5355.
