Machine Learning-Based Modeling of Boiler Efficiency: Impact Analysis of Operational Variables Using Random Forest, XGBoost, and ANN
DOI:
https://doi.org/10.21070/r.e.m.v11i1.1833Keywords:
boiler efficiency, machine learning, XGBoost, operational optimizationAbstract
Enhancing Circulating Fluidized Bed (CFB) boiler efficiency is a critical objective in industrial energy management, often hampered by the intricate, non-linear dynamics of operational parameters. This study evaluates and benchmarks three machine learning architectures—Random Forest (RF), XGBoost, and Artificial Neural Network (ANN) to develop a robust predictive model for boiler thermal efficiency using historical industrial telemetry. The analysis utilizes six key operational variables, including Air-Fuel Ratio (AFR) and Bed Temperature, for model training and cross-validation. Empirical results demonstrate that XGBoost serves as the most effective predictive framework, achieving a Coefficient of Determination ( ) of 0.495 and a Root Mean Square Error (RMSE) of 0.040, thereby outperforming RF and ANN in capturing industrial data noise through its sequential optimization and regularization mechanisms. A primary finding identifies AFR as the most influential factor, exhibiting a strong positive correlation (0.84) and consistent top-tier feature importance rankings across all paradigms. This research provides a validated data-driven methodology for real-time boiler optimization, emphasizing stoichiometric synchronization as the paramount strategy for improving thermal performance and minimizing fuel-related operational expenditures.
References
[1] E. Gultom, Nasruddin, D. A. Fakhri Muzhoffar, and Sholahudin, “Performance analysis and multi-objective optimization of biomass co-firing power plants using multi-objective genetic algorithm,” Therm. Sci. Eng. Prog., vol. 63, p. 103716, Jul. 2025, doi: 10.1016/j.tsep.2025.103716.
[2] H. Zhu, J. Shen, K. Y. Lee, and L. Sun, “Multi-model based predictive sliding mode control for bed temperature regulation in circulating fluidized bed boiler,” Control Eng. Pract., vol. 101, p. 104484, Aug. 2020, doi: 10.1016/j.conengprac.2020.104484.
[3] F. Hong, D. Long, J. Chen, and M. Gao, “Modeling for the bed temperature 2D-interval prediction of CFB boilers based on long-short term memory network,” Energy, vol. 194, p. 116733, Mar. 2020, doi: 10.1016/j.energy.2019.116733.
[4] A. Milićević, S. Belošević, I. Tomanović, N. Crnomarković, L. Deng, and D. Che, “Numerical simulation-driven machine learning and particle swarm optimization of burner fuel distribution for cleaner combustion in a thermal power plant,” Eng. Appl. Artif. Intell., vol. 172, p. 114359, May 2026, doi: 10.1016/j.engappai.2026.114359.
[5] Y. Lv, F. Hong, T. Yang, F. Fang, and J. Liu, “A dynamic model for the bed temperature prediction of circulating fluidized bed boilers based on least squares support vector machine with real operational data,” Energy, vol. 124, pp. 284–294, Apr. 2017, doi: 10.1016/j.energy.2017.02.031.
[6] X. Jin, L. Zhang, F. Li, W. Xie, D. Ma, and Y. Wu, “An explainable transfer learning approach to predict carbon emission intensity of coal-fired power plants with multi-source monitoring data,” Expert Syst. Appl., vol. 298, p. 129743, Mar. 2026, doi: 10.1016/j.eswa.2025.129743.
[7] G. Yan, J. Qiao, Y. Wu, L. Zheng, and X. Xue, “NOx concentration modeling in CFB coal-fired power plants based on feature engineering and deep random forest,” Process Saf. Environ. Prot., vol. 195, p. 106754, Mar. 2025, doi: 10.1016/j.psep.2025.01.008.
[8] M. Ajona, P. Vasanthi, and D. S. Vijayan, “Application of multiple linear and polynomial regression in the sustainable biodegradation process of crude oil,” Sustain. Energy Technol. Assess., vol. 54, p. 102797, Dec. 2022, doi: 10.1016/j.seta.2022.102797.
[9] M. V. J. J. Suresh, K. S. Reddy, and A. K. Kolar, “ANN-GA based optimization of a high ash coal-fired supercritical power plant,” Appl. Energy, vol. 88, no. 12, pp. 4867–4873, Dec. 2011, doi: 10.1016/j.apenergy.2011.06.029.
[10] X. Ji et al., “Data-driven intelligent modeling for superheater wall temperature prediction and operational optimization of 1000 MW deep peak shaving coal-fired power plants,” Fuel, vol. 421, p. 139054, Oct. 2026, doi: 10.1016/j.fuel.2026.139054.
[11] T. Wang et al., “Three multi-fidelity data hybrid-driven strategies for multi-objective combustion optimization in coal-fired boilers using POD and XGBoost,” Energy, vol. 336, p. 138442, Nov. 2025, doi: 10.1016/j.energy.2025.138442.
[12] F. Wang, S. Ma, H. Wang, Y. Li, Z. Qin, and J. Zhang, “A hybrid model integrating improved flower pollination algorithm-based feature selection and improved random forest for NO X emission estimation of coal-fired power plants,” Measurement, vol. 125, pp. 303–312, Sep. 2018, doi: 10.1016/j.measurement.2018.04.069.
[13] D. Bera, N. D. Chatterjee, and S. Bera, “Comparative performance of linear regression, polynomial regression and generalized additive model for canopy cover estimation in the dry deciduous forest of West Bengal,” Remote Sens. Appl. Soc. Environ., vol. 22, p. 100502, Apr. 2021, doi: 10.1016/j.rsase.2021.100502.
[14] S. H. Masteali, M. Bayat, P. Bettinger, and M. Ghorbanpour, “Uncertainty analysis of linear and non-linear regression models in the modeling of water quality in the Caspian Sea basin: Application of Monte-Carlo method,” Ecol. Indic., vol. 170, p. 112979, Jan. 2025, doi: 10.1016/j.ecolind.2024.112979.
[15] V. I. Kuprianov, “Applications of a cost-based method of excess air optimization for the improvement of thermal efficiency and environmental performance of steam boilers,” Renew. Sustain. Energy Rev., vol. 9, no. 5, pp. 474–498, Oct. 2005, doi: 10.1016/j.rser.2004.05.006.
[16] Y. Wang, X. Li, T. Mao, P. Hu, X. Li, and GuanWang, “Mechanism modeling of optimal excess air coefficient for operating in coal fired boiler,” Energy, vol. 261, p. 125128, Dec. 2022, doi: 10.1016/j.energy.2022.125128.
[17] X. Liu, M. Zhang, J. Lu, and H. Yang, “Effect of furnace pressure drop on heat transfer in a 135MW CFB boiler,” Powder Technol., vol. 284, pp. 19–24, Nov. 2015, doi: 10.1016/j.powtec.2015.06.019.
Published
License
Copyright (c) 2026 Muhamad Iqbal Syachjaya Syachjaya, Heri Sutanto , Marcelinus Christwardana , Subhan Hasisi, Napolin Niuhardson Siregar
This work is licensed under a Creative Commons Attribution 4.0 International License.
Copyright Notice
Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution 4.0 International License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
