As core thermal energy equipment in steel, power, and petrochemical industries, industrial heating furnaces' combustion control directly impacts energy efficiency, costs, and pollutant emissions-critical for industrial decarbonization. However, combustion processes' high nonlinearity, time-variability, multi-disturbance, and multi-objective constraints make traditional manual/single strategies ineffective for complex fluctuations and optimization, failing high-efficiency, low-carbon demands. Recent intelligent control technologies, integrating data-driven and mechanism-based models, have advanced temperature field modeling, parameter prediction, multi-objective optimization, and advanced control, boosting accuracy, stability, and emission reduction. This paper reviews intelligent combustion control model progress, compares model applicability, addresses key limitations (e.g., poor generalization, weak real-time integration), and proposes future directions (cross-model integration, data-scarce modeling, online optimization), providing theoretical and technical references for heating furnaces' energy-efficient, lowcarbon, and intelligent upgrading.
WangGJiaoLJWangHM, et al.Development status of intelligent manufacturing technology in iron and steel industry. Environ Eng2020; 38: 173–176.
2.
ZhaoJLingMZhaoEM, et al.Industrial reheating furnaces: a review of energy efficiency assessments, waste heat recovery potentials, heating process characteristics and perspectives for steel industry. Process Saf Environ Prot2021; 147: 1209–1228.
3.
DuDMCaoDHHeQ. Discussion on low-carbon transformation of power industry in China under the goal of ‘dual carbon’. Thermal Power Generation2022; 51: 1–9.
4.
DuSHuangZJinL, et al.Recent progress in data-driven intelligent modeling and optimization algorithms for industrial processes. Algorithms2024; 17: 69.
5.
YaoSCLiLQLuZM, et al.Status and prospect of boiler combustion optimization technology driven by machine learning. Clean Coal Technology2024; 30: 228–243.
6.
BlackburnLDTuttleJFAnderssonK, et al.Dynamic machine learning-based optimization algorithm to improve boiler efficiency. J Process Control2022; 120: 129–149.
7.
ChengYHuangYPangB, et al.Thermalnet: a deep reinforcement learning-based combustion optimization system for coal-fired boiler. Eng Appl Artif Intell2018; 74: 303–311.
8.
HuXZouQZouH. Design and application of fractional order predictive functional control for industrial heating furnace. IEEE Access2018; 6: 66565–66575.
9.
YangTGuoHLiangH, et al.Intelligent combustion control of the hot blast stove: a reinforcement learning approach. Processes2023; 11: 3191.
10.
ZetterholmJJiXSundelinB, et al.Dynamic modelling for the hot blast stove. Appl Energy2017; 185: 2142–2150.
11.
ZetterholmJJiXSundelinB, et al.Model development of a blast furnace stove. Energy Procedia2015; 75: 1758–1765.
12.
CenYAnJ. Intelligent control strategy based on PSO-Elman prediction model for ignition temperature in sintering process. In: 2019 Chinese control conference (CCC). Piscataway, NJ, USA: IEEE, 2019, pp.1264–1269.
13.
YanFZhangXYangC, et al.Data-driven modelling methods in sintering process: current research status and perspectives. Can J Chem Eng2023; 101: 4506–4522.
14.
DingCYChangRDGuoSL, et al.Research status of intelligent control of sintering process and prediction of metallurgical properties of sinter. Iron and Steel2024; 59: 42–56.
15.
HuZFangJZhengR, et al.Efficient model predictive control of boiler coal combustion based on NARX neutral network. J Process Control2024; 134: 103158.
16.
HeDFZhangYDLiLM, et al.Lexicographic economic model predictive control without terminal constraints for circulating fluidized bed combustion systems. J Chem Ind Eng2020; 71: 1210–1216.
17.
AdamczykWPWęcelGKlajnyM, et al.Modeling of particle transport and combustion phenomena in a large-scale circulating fluidized bed boiler using a hybrid Euler–Lagrange approach. Particuology2014; 16: 29–40.
18.
ZhangRXueAGaoF. Temperature control of industrial coke furnace using novel state space model predictive control. IEEE Trans Ind Inf2014; 10: 2084–2092.
19.
LiaoFLYanZRWangL, et al.Coupled heat transfer of combustion in tubular heating furnace and flow in furnace tube and optimization of thermal deviation. Acta Pet Sin (Pet Process Sect)2025; 10: 1–18.
20.
TerrySLuHFidanI, et al.The influence of smart manufacturing towards energy conservation: a review. Technologies2020; 8: 31.
21.
WangJXuCZhangJ, et al.Big data analytics for intelligent manufacturing systems: a review. J Manuf Syst2022; 62: 738–752.
22.
JiaRXiongQXuG, et al.A method for two-dimensional temperature field distribution reconstruction. Appl Therm Eng2017; 111: 961–967.
23.
ModlińskiNMadejskiPJandaT, et al.A validation of computational fluid dynamics temperature distribution prediction in a pulverized coal boiler with acoustic temperature measurement. Energy2015; 92: 77–86.
24.
PollhammerWSpijkerCSixJ, et al.Modeling of a walking beam furnace using CFD – methods. Energy Procedia2017; 120: 477–483.
25.
CasalMJPorteiroJMíguezLJ, et al.New methodology for CFD three-dimensional simulation of a walking beam type reheating furnace in steady state. Appl Therm Eng2015; 86: 69–80.
26.
JiaCKJianTHengX, et al.Modelling the furnace temperature field of a municipal solid waste incinerator using the numerical simulation and the deep forest regression algorithm. Fuel2023; 347: 128511.
27.
Zhai NJ and Zhau XF. Temperature prediction of heating furnace based on deep transfer learning. Sensors 2020; 20: 4676.
28.
YangBLiuLHuangH, et al.A real-time temperature field prediction method for steel rolling heating furnaces based on graph neural networks. Int J Heat Mass Transfer2024; 235: 126220.
29.
RenSAnYPuY, et al.Online prediction of combustion temperature field in a furnace from operating parameters and multi-point temperature data. Energy AI2025; 21: 100530.
30.
WenXYZhenHTShengCX, et al.A novel online method incorporating computational fluid dynamics simulations and neural networks for reconstructing temperature field distributions in coal-fired boilers. Energy2024; 286: 129568.
31.
XuLWeiPGaoZQ, et al.Temperature field inversion of heat-source systems via physics-informed neural networks. Eng Appl Artif Intell2022; 113: 104902.
32.
WangQWangX. Parameters optimization of the heating furnace control systems based on BP neural network improved by genetic algorithm. J Internet Things2020; 2: 75–80.
33.
DuanYChenGBaoX, et al.GA BP prediction model for energy consumption of steel rolling reheating furnace. Sci Rep2025; 15: 11115.
34.
WangFQLiXLYuXB. Optimization of denitration system for coal-fired units based on GA-BP predictive control. Control Eng China2021; 28: 1490–1495.
35.
HeFChaiXZhuZ. Prediction of oxygen-blowing volume in BOF steelmaking process based on BP neural network and incremental learning. High Temp Mater Processes2022; 41: 403–416.
36.
LiuHYaoH. End point prediction of basic oxygen furnace (BOF) steelmaking based on improved bat-neural network. Metalurgija2019; 58: 207–210.
37.
LiSXuFSongD, et al.BP Neural network combined with thermodynamic calculation determining boiler optimal operation parameter value. In: Proceedings of the 2011 international conference on informatics, cybernetics, and computer engineering (ICCE). Berlin, Germany: Springer, 2011, pp. 409–417.
38.
FangHQXueHFLiN, et al.Boiler combustion optimization based on Bayesian neural network genetic algorithm. J Syst Simul2015; 27: 1790–1795.
39.
XiongDLNingHYXieM, et al.A predictive model for sintering ignition temperature based on a CNN-LSTM neural network with an attention mechanism. Processes2024; 12: 2185.
40.
WuXZhangHChenH, et al.Combustion optimization study of pulverized coal boiler based on proximal policy optimization algorithm. Appl Therm Eng2024; 254: 123857.
41.
SunLXuMJiaY, et al.Optimization study of low-NOx combustion in boiler based on pulverized coal preheating solution. Case Stud Thermal Eng2025; 65: 105647.
42.
XuWPohKSongS, et al.Research on reducing pollutant, improving efficiency and enhancing running safety for 1000 MW coal-fired boiler based on data-driven evolutionary optimization and online retrieval method. Appl Energy2025; 377: 123958.
43.
WenTXYaJHSiHS. On-line combustion optimization framework for coal-fired boiler combining improved cultural algorithm, deep learning, multi-objective evolutionary algorithm with improved case-based reasoning technology. Fuel2024; 358: 130225.
44.
YanHChenYYangB, et al.A novel hybrid forecasting approach for NOx emission of coal-fired boiler combined with CEEMDAN and self-attention improved by LSTM. Asia–Pac J Chem Eng2024; 19: e3057.
45.
JiZTaoWRenJ. Boiler furnace temperature and oxygen content prediction based on hybrid CNN, biLSTM, and SE-Net models. Appl Intel2024; 54: 8241–8261.
46.
LiXNiuPLiuJ. Combustion optimization of a boiler based on the chaos and Lévy flight vortex search algorithm. Appl Math Model2018; 58: 3–18.
47.
ShiYZhongWChenX, et al.Combustion optimization of ultra supercritical boiler based on artificial intelligence. Energy2019; 170: 804–817.
48.
SongJRomeroECYaoZ, et al.Improved artificial bee colony-based optimization of boiler combustion considering NOx emissions, heat rate and fly ash recycling for on-line applications. Fuel2016; 172: 20–28.
49.
WangZXueWLiK, et al.Dynamic combustion optimization of a pulverized coal boiler considering the wall temperature constraints: a deep reinforcement learning-based framework. Appl Therm Eng2025; 259: 124923.
50.
ShengWAZhangLQHuangS, et al.Measurement method of high temperature gas CO2 concentration in biomass power plant based on RBF neural network. Acta Metrol Sin2021; 42: 111–116.
51.
RenSJZhuBYWengQH, et al.Prediction method of NOx emission concentration of coal-fired boiler based on physics-informed neural network. Proc CSEE2024; 44: 8157–8166.
52.
LiGNiuPLiuC, et al.Enhanced combination modeling method for combustion efficiency in coal-fired boilers. Appl Soft Comput J2012; 12: 3132–3140.
53.
ZhengWWangCYangY, et al.Multi-objective combustion optimization based on data-driven hybrid strategy. Energy2020; 191: 116478.
54.
RahatAAWangCEversonMR, et al.Data-driven multi-objective optimisation of coal-fired boiler combustion systems. Appl Energy2018; 229: 446–458.
55.
YanAHuK. Multi-target stochastic configuration network model based on collaborative optimization and its applications. IEEE Trans Autom Sci Eng2025; 22: 16741–16752.
56.
ShunYShengWLBoS, et al.Multi-objective optimization of cost saving and emission reduction in blast furnace ironmaking process. Metals (Basel)2018; 8: 79.
57.
GaoDLuoGWangY, et al.The multi-objective optimization of blast furnace oxygen enrichment rate based on optimal carbon ratio. Metals (Basel)2023; 13: 77.
58.
ShiQTangJChuM. Process metallurgy and genetic algorithm multi-objective optimization of blast furnace hearth working state. Steel Res Int2025; 96: 2300671.
59.
SánchezRDíazPAVillegasFJ, et al.Fired heaters optimization by estimating real-time combustion products using numerical methods. Energies2024; 17: 6190.
60.
ShenWTianZZhaoL, et al.Life cycle assessment and multiobjective optimization for steam cracking process in ethylene plant. ACS Omega2022; 7: 15507–15517.
61.
LiXYangYWangH, et al.Design and simulation of hot blast stove combustion system based on fuzzy PID algorithm. Ind Heat2022; 51: 38–40.
62.
PangXX. Temperature control analysis of blast furnace burner based on PSO optimized fuzzy PID algorithm. Shanxi Metall2023; 46: 111–113.
