From Prediction to Operational Optimization: A Critical Review of Data-Driven Models and Digital Twins for Air-Cooled Steam Condensers

Anmar Yousif; Adil A. Al-Kumait

doi:10.71229/3vc4m911

Authors

Anmar Yousif Hasan Department of Mechanical Engineering, Tikrit University, Salah Al-Din, Iraq
Adil A. Al-Kumait Department of Mechanical Engineering, Tikrit University, Salah Al-Din, Iraq,

DOI:

https://doi.org/10.71229/3vc4m911

Keywords:

air-cooled steam condenser, back pressure prediction, fan control, operational optimization

Abstract

Accuracy of prediction of backpressure does not automatically mean efficient consumption of energy by air-cooled steam condensers. It is required to close this gap in situations where the performance of the equipment depends on the heat rejection according to weather conditions and electricity consumption by fans. The critical review analyzes 23 papers dealing with the data-driven prediction, hybrid digital twins, and control of air-cooled steam condensers. The comparison was made with respect to the following unified criteria: the source of the data, the objective of validation, the type of operating decision, the reference conditions, and the validation of the benefits. The findings of synthesis comprise the following three conclusions. First of all, accuracy and consistency of the predictions and agreement with the parent simulation reflect the performance of the method, but not its operational efficiency. Second, the implementation of digital twins into an industry is a breakthrough in research, although the estimates of the fuel savings can still be made by consumption models and not by independent measurements of savings. Finally, adaptive and spatially distributed control of fans resolves a number of operational problems, although the validation of such a control may be conditioned by particular weather and disturbance conditions and not guarantee the stability of operation in various seasonal or disturbance situations. This review develops the framework for distinguishing between the predictions, the improvements in control via simulation, industrial implementation, and operations to assess the progress in research and deployment.

Author Biography

Adil A. Al-Kumait, Department of Mechanical Engineering, Tikrit University, Salah Al-Din, Iraq,

References

[1] X. Li, N. Wang, L. Wang, Y. Yang, and F. Maréchal, "Identification of optimal operating strategy of direct air-cooling condenser for Rankine cycle based power plants," Applied Energy, vol. 209, pp. 153-166, 2018. https://doi.org/10.1016/j.apenergy.2017.10.081 DOI: https://doi.org/10.1016/j.apenergy.2017.10.081

[2] X. Du et al., "Back pressure prediction of the direct air cooled power generating unit using the artificial neural network model," Applied Thermal Engineering, vol. 31, no. 14-15, pp. 3009-3014, 2011. https://doi.org/10.1016/j.applthermaleng.2011.05.034 DOI: https://doi.org/10.1016/j.applthermaleng.2011.05.034

[3] X. Li et al., "A data-driven model for the air-cooling condenser of thermal power plants based on data reconciliation and support vector regression," Applied Thermal Engineering, vol. 129, pp. 1496-1507, 2018. https://doi.org/10.1016/j.applthermaleng.2017.10.103 DOI: https://doi.org/10.1016/j.applthermaleng.2017.10.103

[4] Y. Yang, X. Li, Z. Yang, Q. Wei, N. Wang, and L. Wang, "The application of cyber physical system for thermal power plants: Data-driven modeling," Energies, vol. 11, no. 4, p. 690, 2018. https://doi.org/10.3390/en11040690 DOI: https://doi.org/10.3390/en11040690

[5] M. Mohammadi and V. Esfahanian, "A comprehensive investigation to enhance predictive accuracy of data-driven models applied to air-cooled condensers: from domain expertise data preprocessing to hyperparameters optimization," Applied Thermal Engineering, vol. 267, p. 125792, 2025. https://doi.org/10.1016/j.applthermaleng.2025.125792 DOI: https://doi.org/10.1016/j.applthermaleng.2025.125792

[6] R. Raidoo and R. Laubscher, "Data-driven forecasting with model uncertainty of utility-scale air-cooled condenser performance using ensemble encoder-decoder mixture-density recurrent neural networks," Energy, vol. 238, p. 122030, 2022. https://doi.org/10.1016/j.energy.2021.122030 DOI: https://doi.org/10.1016/j.energy.2021.122030

[7] G. Zhao, Z. Cui, J. Xu, W. Liu, and S. Ma, "Hybrid modeling-based digital twin for performance optimization with flexible operation in the direct air-cooling power unit," Energy, vol. 254, p. 124492, 2022. https://doi.org/10.1016/j.energy.2022.124492 DOI: https://doi.org/10.1016/j.energy.2022.124492

[8] Z. Cui, H. Jing, D. Wang, B. Wang, and W. Chen, "Hybrid modeling-based digital twin of the direct air cooling system for operational performance optimization," Energy, vol. 320, p. 135419, 2025. https://doi.org/10.1016/j.energy.2025.135419 DOI: https://doi.org/10.1016/j.energy.2025.135419

[9] A. Xie, L. An, H. Chen, X. Xue, and G. Xu, "Performance optimization of the air-cooling system in a coal-fired power unit based on intelligent algorithms," Applied Thermal Engineering, vol. 230, p. 120791, 2023. https://doi.org/10.1016/j.applthermaleng.2023.120791 DOI: https://doi.org/10.1016/j.applthermaleng.2023.120791

[10] R. A. Haffejee and R. Laubscher, "Application of machine learning to develop a real-time air-cooled condenser monitoring platform using thermofluid simulation data," Energy and AI, vol. 3, p. 100048, 2021. https://doi.org/10.1016/j.egyai.2021.100048 DOI: https://doi.org/10.1016/j.egyai.2021.100048

[11] H. Chen, W. Peng, C. Nie, G. Xu, and J. Lei, "Performance prediction and optimization of the air‐cooled condenser in a large‐scale power plant using machine learning," Energy Technology, vol. 9, no. 7, p. 2100045, 2021. https://doi.org/10.1002/ente.202100045 DOI: https://doi.org/10.1002/ente.202100045

[12] M. Zhu, X. Wu, J. Shen, and K. Lee, "Dynamic modeling, validation and analysis of direct air-cooling condenser with integration to the coal-fired power plant for flexible operation," Energy Conversion and Management, vol. 245, p. 114601, 2021. https://doi.org/10.1016/j.enconman.2021.114601 DOI: https://doi.org/10.1016/j.enconman.2021.114601

[13] T. Yang, W. Wang, D. Zeng, J. Liu, and C. Cui, "Closed-loop optimization control on fan speed of air-cooled steam condenser units for energy saving and rapid load regulation," Energy, vol. 135, pp. 394-404, 2017. https://doi.org/10.1016/j.energy.2017.06.142 DOI: https://doi.org/10.1016/j.energy.2017.06.142

[14] Y. Zhang, J. Liu, T. Yang, J. Liu, J. Shen, and F. Fang, "Dynamic modeling and control of direct air-cooling condenser pressure considering couplings with adjacent systems," Energy, vol. 236, p. 121487, 2021. https://doi.org/10.1016/j.energy.2021.121487 DOI: https://doi.org/10.1016/j.energy.2021.121487

[15] J. Li, Y. Bai, and B. Li, "Operation of air cooled condensers for optimised back pressure at ambient wind," Applied Thermal Engineering, vol. 128, pp. 1340-1350, 2018. https://doi.org/10.1016/j.applthermaleng.2017.09.122 DOI: https://doi.org/10.1016/j.applthermaleng.2017.09.122

[16] W. Huang, L. Chen, W. Wang, L. Yang, and X. Du, "Cooling performance optimization of direct dry cooling system based on partition adjustment of axial flow fans," Energies, vol. 13, no. 12, p. 3179, 2020. https://doi.org/10.3390/en13123179 DOI: https://doi.org/10.3390/en13123179

[17] W. Huang, L. Chen, L. Yang, and X. Du, "Energy-saving strategies of axial flow fans for direct dry cooling system," Energies, vol. 14, no. 11, p. 3176, 2021. https://doi.org/10.3390/en14113176 DOI: https://doi.org/10.3390/en14113176

[18] G. Zheng, W. Wen, H. Deng, and Y. Cai, "Cluster Partition Operation Study of Air-Cooled Fan Groups in a Natural Wind Disturbance," Energies, vol. 16, no. 9, p. 3717, 2023. https://doi.org/10.3390/en16093717 DOI: https://doi.org/10.3390/en16093717

[19] Z. Luo, J. Liu, and J. K. Huusom, "Energy-efficient operation of a direct air-cooled condenser based on divisional regulation," International Journal of Refrigeration, vol. 132, pp. 233-242, 2021. https://doi.org/10.1016/j.ijrefrig.2021.08.024 DOI: https://doi.org/10.1016/j.ijrefrig.2021.08.024

[20] Z. Luo and Q. Yao, "Multi-model-based predictive control for divisional regulation in the direct air-cooling condenser," Energies, vol. 15, no. 13, p. 4803, 2022. https://doi.org/10.3390/en15134803 DOI: https://doi.org/10.3390/en15134803

[21] Y. Sun, H. Deng, M. Du, and Y. Li, "Research on partition control of direct air‐cooling condenser based on multivariable Hammerstein CARMA model predictive control," IET Control Theory & Applications, vol. 18, no. 2, pp. 244-253, 2024. https://doi.org/10.1049/cth2.12571 DOI: https://doi.org/10.1049/cth2.12571

[22] H. Wang, L. Cao, G. Dang, Z. Zhu, S. Ma, and G. Yan, "Online parameter identification and backpressure optimization control of a direct air-cooled system based on dynoNet," Control Engineering Practice, vol. 172, p. 106912, 2026. https://doi.org/10.1016/j.conengprac.2026.106912 DOI: https://doi.org/10.1016/j.conengprac.2026.106912

[23] L. Ji, G. Yan, H. Liu, Z. Zhu, J. Xu, and S. Ma, "Real-time backpressure optimization for direct air-cooled units driven by digital twin technology and adversarial reinforcement learning," Energy, p. 140857, 2026. https://doi.org/10.1016/j.energy.2026.140857 DOI: https://doi.org/10.1016/j.energy.2026.140857