English

Journal of Thermal Science

热科学学报

热科学学报 >

2025 , Vol. 34 >Issue 5: 1721 - 1735

DOI: https://doi.org/10.1007/s11630-025-2170-x

Effect of CO2 Gasification on Coal Burnout during Pressurized Oxy-Fuel Combustion by Experiment and Machine Learning Method

  • LEI Ming ,
  • YE Bin ,
  • TIAN Xi ,
  • HONG Dikun ,
  • ZHANG Qian ,
  • ZHANG Lei
展开
  • 1. Hebei Key Laboratory of Low Carbon and High Efficiency Power Generation Technology, North China Electric Power University, Baoding 071003, China
    2. School of Energy and Power Engineering, North China Electric Power University, Baoding 071003, China

网络出版日期: 2025-09-01

基金资助

This work is supported by National Key R&D Program of China (2024YFB4100081 and 2023YFB4104301). 

版权

Science Press, Institute of Engineering Thermophysics, CAS and Springer-Verlag GmbH Germany, part of Springer Nature 2025
收起

Effect of CO2 Gasification on Coal Burnout during Pressurized Oxy-Fuel Combustion by Experiment and Machine Learning Method

  • LEI Ming ,
  • YE Bin ,
  • TIAN Xi ,
  • HONG Dikun ,
  • ZHANG Qian ,
  • ZHANG Lei
Expand
  • 1. Hebei Key Laboratory of Low Carbon and High Efficiency Power Generation Technology, North China Electric Power University, Baoding 071003, China
    2. School of Energy and Power Engineering, North China Electric Power University, Baoding 071003, China

Online published: 2025-09-01

Supported by

This work is supported by National Key R&D Program of China (2024YFB4100081 and 2023YFB4104301). 

Copyright

Science Press, Institute of Engineering Thermophysics, CAS and Springer-Verlag GmbH Germany, part of Springer Nature 2025
Fold

摘要

本研究通过实验与机器学习相结合的方法，分析了加压富氧燃烧条件下煤的燃尽特性。实验结果表明，煤的转化率随氧气浓度，温度及压力的升高显著提升。在低氧浓度条件下，CO2气化反应加速煤的消耗，导致CO2/N2气氛中的煤燃尽度低于O2/CO2气氛，且在高温高压下差异更为显著；随着氧气浓度增加，CO2气化作用减弱，同时受CO2物理性质影响，O2/N2条件下的煤燃尽度反超O2/CO2条件。此外，高压环境下CO2气化对低反应活性煤种转化的促进作用更为明显。基于实验数据，研究采用四种独立机器学习算法及一种集成算法构建煤粉燃尽度预测模型：首先通过皮尔逊相关系数分析特征参数（氧气浓度，加热温度，燃烧长度及反应气氛）与输出变量（煤燃尽度）的关联性；随后将输入数据分别训练四种基础模型，将其预测结果作为元模型的输入特征；优选梯度提升回归（GBR）作为Stacking集成学习的元模型，构建高精度煤燃尽度预测模型。最后，引入SHAP分析评估实验样本中煤燃烧预测结果的可解释性，显著提升了模型预测结果的物理意义阐释能力。

关键词： pressurized oxy-fuel combustion; gasification; burnout; machine learning

本文引用格式

LEI Ming , YE Bin , TIAN Xi , HONG Dikun , ZHANG Qian , ZHANG Lei . Effect of CO2 Gasification on Coal Burnout during Pressurized Oxy-Fuel Combustion by Experiment and Machine Learning Method[J]. 热科学学报, 2025 , 34(5) : 1721 -1735 . DOI: 10.1007/s11630-025-2170-x

Abstract

In the present study, the coal burnout during pressurized oxy-fuel combustion is analyzed by combining experiment and machine learning. According to the experimental results, it is shown that the coal conversion increases significantly with the increase of oxygen concentration, temperature and pressure. At relatively low oxygen concentration, CO2 gasification expedites the coal consumption, so the coal burnout in O2/N2 environment is lower compared to that in O2/CO2 environment, especially at elevated temperature and pressure. As the oxygen concentration increases, the influence of CO2 gasification weakens and on account of the CO2 physical properties, the coal burnout in O2/N2 condition is higher than that in O2/CO2 condition. Furthermore, the impact of gasification on the conversion of coal with low reactivity is obvious at high pressure. On the basis of the experimental data, four independent machine learning algorithms and one integrated machine learning algorithm are employed to propose a prediction model of pulverized coal burnout. The Pearson correlation coefficient between the characteristic parameters (oxygen concentration, heating temperature, combustion length, and reaction atmosphere) and the output variable (coal burnout) is calculated. And then the input data are independently trained by combining four different base models to generate a prediction of the target variable (coal burnout) which is used as the input characteristics of the meta-model. Moreover, the Gradient Boosting Regression (GBR) model is selected as the meta-model of Stacking ensemble learning to construct the accurate prediction model of coal burnout. Finally, the application of SHAP analysis is employed to assess the interpretability of the forecasted outcomes for coal combustion in the experimental samples, thereby significantly enhancing the explanatory capacity of the predicted results.

Key words： pressurized oxy-fuel combustion; gasification; burnout; machine learning

参考文献

[1] Buhre B.J.P., Elliott L.K., Sheng C.D., et al., Oxy-fuel combustion technology for coal-fired power generation. Progress in Energy and Combustion Science, 2005, 31(4): 283–307. 
[2] Duan Y., Duan L., Anthony E.J., et al., Nitrogen and sulfur conversion during pressurized pyrolysis under CO2 atmosphere in fluidized bed. Fuel, 2017, 189: 98–106.
[3] Lei M., Zhang Y., Hong D., et al., Characterization of nitrogen and sulfur migration during pressurized coal pyrolysis and oxy-fuel combustion. Fuel, 2022, 317: 123484. 
[4] Wang X., Shan S., Wang Z., et al., Review on thermal-science fundamental research of pressurized oxy-fuel combustion technology. Frontiers in Energy, 2024, 18: 760–784. 
[5] Zhang J., Zheng Y., Wang X., et al., Nitrogen oxide reduction in pressurized oxy-coal combustion. Combustion and Flame, 2022, 246: 112418. 
[6] Yin C., Yan J., Oxy-fuel combustion of pulverized fuels: Combustion fundamentals and modeling. Applied Energy, 2016, 162: 742–762. 
[7] Hecht E.S., Shaddix C.R., Molina A., et al., Effect of CO2 gasification reaction on oxy-combustion of pulverized coal char. Proceedings of the Combustion Institute, 2011, 33: 1699–1706. 
[8] Bu C., Gómez-Barea A., Chen X., et al., Effect of CO2 on oxy-fuel combustion of coal-char particles in a fluidized bed: Modeling and comparison with the conventional mode of combustion. Applied Energy, 2016, 177: 247–259. 
[9] Shen Z., Zhang L., Liang Q., et al., In situ experimental and modeling study on coal char combustion for coarse particle with effect of gasification in air (O2/N2) and O2/CO2 atmospheres. Fuel, 2018, 233: 177–187. 
[10] Lei M., Zou C., Xu X., et al., Effect of CO2 and H2O on the combustion characteristics and ash formation of pulverized coal in oxy-fuel conditions. Applied Thermal Engineering, 2018, 133: 308–315. 
[11] Lei M., Sun C., Wang C., Effect of CO2 and H2O gasifications on the burning behavior and NO release process of pulverized coal at low oxygen concentrations during oxy-fuel combustion. Journal of Energy Engineering, 2019, 145: 04019003. 
[12] Hong D., Si T., Li X., et al., Reactive molecular dynamic simulations of the CO2 gasification effect on the oxy-fuel combustion of Zhundong coal char. Fuel Processing Technology, 2020, 199: 106305. 
[13] Yang Z., Khatri D., Verma P., et al., Experimental study and demonstration of pilot-scale, dry feed, oxy-coal combustion under pressure. Applied Energy, 2021, 285: 116367. 
[14] Li L., Duan L., Yang Z., et al., Pressurized oxy-fuel combustion of a char particle in the fluidized bed combustor. Proceedings of the Combustion Institute, 2021, 38: 5485–5492. 
[15] Liu Y., Zhang H., Shen Y., A data-driven approach for the quick prediction of in-furnace phenomena of pulverized coal combustion in an ironmaking blast furnace. Chemical Engineering Science, 2022, 260: 117945. 
[16] Bi H., Wang C., Lin Q., et al., Combustion behavior, kinetics, gas emission characteristics and artificial neural network modeling of coal gangue and biomass via TG-FTIR. Energy, 2020, 213: 118790. 
[17] Jin N., Guo L., Liu X., Machine learning-aided optimization of coal decoupling combustion for lowering NO and CO emissions simultaneously. Computers & Chemical Engineering, 2022, 162: 107822. 
[18] Adams D., Oh D.H., Kim D.W., et al., Prediction of SOx-NOx emission from a coal-fired CFB power plant with machine learning: Plant data learned by deep neural network and least square support vector machine. Journal of Cleaner Production, 2020, 270: 122310. 
[19] Lei M., Han H., Tian X., et al., Investigation of ash fusion characteristics on co-combustion of coal and biomass (straw, sludge, and herb residue) based on experimental and machine learning method. Environmental Science and Pollution Research, 2024, 31: 8467–8482. 
[20] Graeser P., Schiemann M., Emissivity of burning bituminous coal char particles-Burnout effects. Fuel, 2017, 196: 336–343. 
[21] Hong D., Wang Y., Zhai X., A ReaxFF study of the effect of pressure on the contribution of char-CO2 gasification to char conversion during pressurized oxy-fuel combustion. Fuel, 2022, 329: 125439. 
[22] Kim H., Choi J., Lim H., et al., Combustion characteristics of liquid carbon dioxide-dried coal at different pressures of CO2-O2 mixture. Energy, 2023, 266: 126431. 
[23] Niu Y., Liu S., Yan B., et al., Effects of CO2 gasification reaction on the combustion of pulverized coal char. Fuel, 2018, 233: 77–83. 
[24] Liu G.S., Niksa S., Coal conversion submodels for design applications at elevated pressures. Part II. Char gasification. Progress in Energy and Combustion Science, 2004, 30: 679–717. 
[25] Lin S.Y., Suzuki Y., Hatano H., et al., Pressure effect on char combustion in different rate-control zones: initial rate expression. Chemical Engineering Science, 2000, 55: 43–50. 
[26] Kim R.G., Hwang C.W., Jeon C.H., Kinetics of coal char gasification with CO2: Impact of internal/external diffusion at high temperature and elevated pressure. Applied Energy, 2014, 129: 299–307. 
[27] Anup K.S., Parthapratim G., Ranajit K.S., Characterization of porous structure of coal char from a single devolatilized coal particle: Coal combustion in a fluidized bed. Fuel Processing Technology, 2009, 90: 692–700. 
[28] Kelebopile L., Sun R., Wang H., et al., Pore development and combustion behavior of gasified semi-char in a drop tube furnace. Fuel Processing Technology, 2013, 111: 42–54. 
[29] Babiński P., Łabojko G., Kotyczka-Morańska M., et al., Kinetics of pressurized oxy-combustion of coal chars. Thermochimica Acta, 2019, 682: 178417.
[30] Xu N., Wang Z., Dai Y., et al., Prediction of higher heating value of coal based on gradient boosting regression tree model. International Journal of Coal Geology, 2023, 274: 104293. 
[31] Lei Q., Yu H., Lin Z., Understanding China’s CO2 emission drivers: Insights from random forest analysis and remote sensing data. Heliyon, 2024, 10: e29086.
[32] Tang W., Application of support vector machine system introducing multiple submodels in data mining. Systems and Soft Computing, 2024, 6: 200096. 
[33] Lin K.Y.C., Optimizing variable selection and neighbourhood size in the K-nearest neighbour algorithm. Computers & Industrial Engineering, 2024, 191: 110142. 
[34] Lazzarini R., Tianfield H., Charissis V., A stacking ensemble of deep learning models for IoT intrusion detection. Knowledge-Based Systems, 2023, 279: 110941.
[35] Katongtung T., Prasertpong P., Sukpancharoen S., et al., Predictive modeling for multifaceted hydrothermal carbonization of biomass. Journal of Environmental Chemical Engineering. 2024, 12: 114071.
Options
文章导航

/

〈 〉

微信公众号

主办单位：中国科学院工程热物理研究所　 出版单位：科学出版社

版权所有© 2023 热科学学报