Power Generation Prediction of a Reheat-Regenerative Combined Cycle Steam Turbine Using an Artificial Neural Network
Keywords:
Artificial Neural Network, Electric Power Generation, Steam TurbineAbstract
Enhancing steam turbine efficiency in load management is challenging due to operational non-linearity and complexity. This study develops an Artificial Neural Network (ANN)-based prediction model for electric power generation in reheat-regenerative combined cycle steam turbines. Data preprocessing involved missing value removal and outlier detection using K-Means Clustering and the Grubbs Test, followed by Principal Component Analysis for dimensionality reduction. From 50 initial features, 13 key features were selected, explaining 95% of variance. The ANN model employed Bayesian Regularization, tangents sigmoid activation, and five hidden layers (22, 18, 14, 10, 6 nodes). Performance evaluation yielded an MSE of 0.00177, RMSE of 0.04203, and R² of 0.9985, demonstrating high accuracy. This study supports operational planning at the Banjarsari coal power plant, offering a neural network-based predictive approach to improve energy generation efficiency sustainably.References
A. Bahadori and H. B. Vuthaluru, “Estimation of Performance of Steam Turbines using a Simple Predictive Tool,” Appl Therm Eng, vol. 30, no. 13, pp. 1832–1838, Sep. 2010, doi: 10.1016/j.applthermaleng.2010.04.017.
D. M. R. F. Fernando, J. Waluyo, and N. Dewayanto, “Application of Newton-Raphson Method to Analyze Thermal Efficiency of Gas Turbine Before and After Engine Replacement,” ASEAN Journal of Systems Engineering, vol. 4, no. 1, pp. 8–12, 2020, doi: 10.22146/ajse.v4i1.60527.
F. S. Abdullah, A. N. Hamoodi, and R. A. Mohammed, “Performance Improvement in Steam Turbine in Thermal Power Plants Using Artificial Neural Network,” Journal Europeen des Systemes Automatises, vol. 54, no. 6, pp. 891–895, Dec. 2021, doi: 10.18280/jesa.540611.
Y. Lu et al., “Steam Turbine Power Prediction based on Encode-Decoder Framework Guided by The Condenser Vacuum Degree,” PLoS One, vol. 17, no. 10, Oct. 2022, doi: 10.1371/journal.pone.0275998.
K. Fakir, C. Ennawaoui, and M. El Mouden, “Deep Learning Algorithms to Predict Output Electrical Power of an Industrial Steam Turbine,” Applied System Innovation, vol. 5, no. 6, Dec. 2022, doi: 10.3390/asi5060123.
Y. Sun, Q. Zhou, L. Sun, L. Sun, J. Kang, and H. Li, “CNN–LSTM–AM: A Power Prediction Model for Offshore Wind Turbines,” Ocean Engineering, vol. 301, Jun. 2024, doi: 10.1016/j.oceaneng.2024.117598.
S. Li, D. Wunsch, and M. Giesselmann, “Comparative Analysis of Regression and Artificial Neural Network Models for Wind Turbine Power Curve Estimation,” J Sol Energy Eng, vol. 123, Aug. 2001, doi: 10.1115/1.1413216.
M. Pasandideh, M. Taylor, S. R. Tito, M. Atkins, and M. Apperley, “Predicting Steam Turbine Power Generation: A Comparison of Long Short-Term Memory and Willans Line Model,” Energies (Basel), vol. 17, no. 2, Jan. 2024, doi: 10.3390/en17020352.
G. James, D. Witten, T. Hastie, and R. Tibshirani, An Introduction to Statistical Learning, 2nd ed. New York: Springer, 2021. doi: doi.org/10.1007/978-1-0716-1418-1_1.
S. Dettori, V. Colla, G. Salerno, and A. Signorini, “A neural network-based approach for steam turbine monitoring,” in Smart Innovation, Systems and Technologies, vol. 69, Springer Science and Business Media Deutschland GmbH, 2017, pp. 203–211. doi: 10.1007/978-3-319-56904-8_20.
P. C. S. Reddy and A. Sureshbabu, “An adaptive model for forecasting seasonal rainfall using predictive analytics,” International Journal of Intelligent Engineering and Systems, vol. 12, no. 5, pp. 22–32, 2019, doi: 10.22266/ijies2019.1031.03.
A. Saenmuang and S. Sitjongsataporn, “Convergence and Stability Analysis of Spline Adaptive Filtering based on Adaptive Averaging Step-size Normalized Least Mean Square Algorithm,” International Journal of Intelligent Engineering and Systems, vol. 13, no. 2, pp. 267–277, Apr. 2020, doi: 10.22266/ijies2020.0430.26.
