Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2026 Jan 4;26(1):330.
doi: 10.3390/s26010330.

Enhancing Efficiency in Coal-Fired Boilers Using a New Predictive Control Method for Key Parameters

Qinwu Li  1   2 , Libin Yu  1 , Tingyu Liu  2 , Lianming Li  3 , Yangshu Lin  1 , Tao Wang  2 , Chao Yang  1 , Lijie Wang  1 , Weiguo Weng  4 , Chenghang Zheng  1 , Xiang Gao  1
Affiliations

Enhancing Efficiency in Coal-Fired Boilers Using a New Predictive Control Method for Key Parameters

Qinwu Li et al. Sensors (Basel). .

Abstract

In the context of carbon neutrality, the large-scale integration of renewable energy sources has led to frequent load changes in coal-fired boilers. These fluctuations cause key operational parameters to deviate significantly from their design values, undermining combustion stability and reducing operational efficiency. To address this issue, we introduce a novel predictive control method to enhance the control precision of key parameters under complex variable-load conditions, which integrates a coupled predictive model and real-time optimization. The predictive model is based on a coupled Transformer-gated recurrent unit (GRU) architecture, which demonstrates strong adaptability to load fluctuations and achieves high prediction accuracy, with a mean absolute error of 0.095% and a coefficient of determination of 0.966 for oxygen content (OC); 0.0163 kPa and 0.987 for bed pressure (BP); and 0.300 °C and 0.927 for main steam temperature (MST). These results represent substantial improvements over lone implementations of GRU, LSTM, and Transformer models. Based on these multi-step predictions, a WOA-based real-time optimization strategy determines coordinated adjustments of secondary fan frequency, slag discharger frequency, and desuperheating water valves before deviations occur. Field validation on a 300 t/h boiler over a representative 24 h load cycle shows that the method reduces fluctuations in OC, BP, and MST by 62.07%, 50.95%, and 40.43%, respectively, relative to the original control method. By suppressing parameter variability and maintaining key parameters near operational targets, the method enhances boiler thermal efficiency and steam quality. Based on the performance gain measured during the typical operating day, the corresponding annual gain is estimated at ~1.77%, with an associated CO2 reduction exceeding 6846 t.

Keywords: GRU; Transformer; coal-fired boiler; operational parameter optimization; predictive control method.

PubMed Disclaimer

Conflict of interest statement

D.L., T.L. and T.W. are employed by the company Zhejiang HOPE Environmental Protection Engineering Co., Ltd. L.L. is employed by the company Zhejiang Materials Industry Group Corporation (ZJMI) Environmental Energy Co., Ltd. The remaining authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.

Figures

Figure 1
Figure 1
Schematic diagram of a boiler system.
Figure 2
Figure 2
Deployment architecture of the predictive control system for boiler operational parameters.
Figure 3
Figure 3
Structure diagram of the predictive model.
Figure 4
Figure 4
Schematic diagram of the real-time optimization control framework.
Figure 5
Figure 5
Comparison of the predicted and measured OC for different models.
Figure 6
Figure 6
Comparison of the predicted and measured BP for the different models.
Figure 7
Figure 7
Comparison of the predicted and measured MST for the different models.
Figure 8
Figure 8
Comparison of control performance for key parameters under steady-load conditions: (a) original control method; (b) proposed predictive control method.
Figure 9
Figure 9
Comparison of control performance for key parameters under rapid load conditions: (a) original control method; (b) proposed predictive control method.
Figure 10
Figure 10
Comparison of operating data on a typical day.
See this image and copyright information in PMC

References

    1. Wu X., Yang Y., Gong Y., Deng Z., Wang Y., Wu W., Zheng C., Zhang Y. Advances in air pollution control for key industries in China during the 13th five-year plan. J. Environ. Sci. 2023;123:446–459. doi: 10.1016/j.jes.2022.09.008. - DOI - PubMed
    1. Heptonstall P.J., Gross R.J.K. A systematic review of the costs and impacts of integrating variable renewables into power grids. Nat. Energy. 2021;6:72–83. doi: 10.1038/s41560-020-00695-4. - DOI
    1. Herc L., Pfeifer A., Duić N., Wang F. Economic viability of flexibility options for smart energy systems with high penetration of renewable energy. Energy. 2022;252:123739. doi: 10.1016/j.energy.2022.123739. - DOI
    1. Cerovac T., Ćosić B., Pukšec T., Duić N. Wind energy integration into future energy systems based on conventional plants—The case study of Croatia. Appl. Energy. 2014;135:643–655. doi: 10.1016/j.apenergy.2014.06.055. - DOI
    1. Shao C., Ding Y., Wang J., Song Y. Modeling and Integration of Flexible Demand in Heat and Electricity Integrated Energy System. IEEE Trans. Sustain. Energy. 2018;9:361–370. doi: 10.1109/TSTE.2017.2731786. - DOI

LinkOut - more resources