Prediction and comparative analysis of emissions from gas turbines using random search optimization and different machine learning-based algorithms

• Autorzy: Aslan Emrah

Identyfikatory

DOI

10.24425/bpasts.2024.151956

• Języki publikacji: EN

Abstrakty

EN

Gas turbines are widely used for power generation globally, and their greenhouse gas emissions have increasingly drawn public attention. Compliance with environmental regulations necessitates sophisticated emission measurement techniques and tools. Traditional sensors used for monitoring emission gases can provide inaccurate data due to malfunction or miscalibration. Accurate estimation of gas turbine emissions, such as particulate matter, carbon monoxide, and nitrogen oxides, is crucial for assessing the environmental impact of industrial activities and power generation. This study used five different machine learning models to predict emissions from gas turbines, including AdaBoost, XGBoost, k-nearest neighbour, and linear and random forest models. Random search optimization was used to set the regression parameters. The findings indicate that the AdaBoost regressor model provides superior prediction accuracy for emissions compared to other models, with an accuracy of 99.97% and a mean squared error of 2.17 on training data. This research offers a practical modelling approach for forecasting gas turbine emissions, contributing to the reduction of air pollution in industrial applications.

Słowa kluczowe

EN

emission; gas turbines; efficiency; machine learning; random search optimization

PL

emisja; turbiny gazowe; sprawność; uczenie maszynowe; optymalizacja wyszukiwania losowego

• Wydawca: Polska Akademia Nauk, Wydział IV Nauk Technicznych
• Czasopismo: Bulletin of the Polish Academy of Sciences. Technical Sciences
• Rocznik: 2024
• Tom: Vol. 72, nr 6
• Strony: art. no. e151956
• Opis fizyczny: Bibliogr. 22 poz., rys., tab., wykr.

Twórcy

autor

Aslan Emrah

• Dicle University, Silvan Vocational School, Diyarbakır, Turkey

• https://orcid.org/0000-0002-0181-3658

Bibliografia

• [1] R.J. Allam et al., “High efficiency and low cost of electricity generation from fossil fuels while eliminating atmospheric emissions, including carbon dioxide,” Energy Procedia, vol. 37, pp. 1135–1149, 2013, doi: 10.1016/j.egypro.2013.05.211.
• [2] T. Sebbagh, “Modeling, analysis, and techno-economic assessment of a clean power conversion system with green hydrogen production,” Bull. Pol. Acad. Sci. Tech. Sci., vol. 72, no. 4, p. e150115, 2024, doi: 10.24425/bpasts.2024.150115.
• [3] M.C. Chiong et al., “Liquid biofuels production and emissions performance in gas turbines: A review,” Energy Conv. Manag., vol. 173, pp. 640–658, 2018, doi: 10.1016/j.enconman.2018.0.
• [4] N. Guellouh, Z. Szamosi, and Z. Siménfalvi, “Combustors with low emission levels for aero gas turbine engines,” Int. J. Eng. Manag. Sci., vol. 4, no. 1, pp. 503–514, 2019, doi: 10.21791/IJEMS.2019.1.62.
• [5] P. Steckowicz, P. Pyrzanowski, and E. Bulut, “Development and implementation of robotized wire arc repair of gas turbine diaphram,” Bull. Pol. Acad. Sci. Tech. Sci., vol. 72, no. 2, p. e147920, 2024, doi: 10.24425/bpasts.2023.147920.
• [6] D. Rochelle and H. Najafi, “A review of the effect of biodiesel on gas turbine emissions and performance,” Renew. Sust. Energ. Rev., vol. 105, pp. 129–137, 2019, doi: 10.1016/j.rser.2019.01.056.
• [7] H. Mohamed, H.B. Ticha, and S. Mohamed, “Simulation of pollutant emissions from a gas-turbine combustor,” Combust. Sci. Technol., vol. 176, no. 5–6, pp. 819–834, 2004, doi: 10.1080/00102200490428422.
• [8] D.A. Wood, “Long-term atmospheric pollutant emissions from a combined cycle gas turbine: Trend monitoring and prediction applying machine learning,” Fuel, vol. 343, p. 127722, 2023, doi: 10.1016/j.fuel.2023.127722.
• [9] Y. Liu, X. Sun, V. Sethi, D. Nalianda, Y. Li, and L. Wang, “Review of modern low emissions combustion technologies for aero gas turbine engines,” Prog. Aeosp. Sci., vol. 94, pp. 12–42, 2017, doi: 10.1016/j.paerosci.2017.08.001.
• [10] T.A. Kuznetsova and A.A. Naborshchikov, “Optimal automatic control of NOχ emissions from combustion chambers of gas turbine aeroengine based on the Bellman method,” AIP Conf. Proc., vol. 2700, no. 1, p. 040013, 2023, doi: 10.1063/5.0137228.
• [11] A.A. Beige and A. Mardani, “An investigation on flame structure and NOχ formation in a gas turbine model combustor using large eddy simulation,” Phys. Fluids, vol. 35, no. 7, p. 075133, 2023, doi: 10.1063/5.0155974.
• [12] A.M. Starik, A.M. Savel’ev, O.N. Favorskii, and N.S. Titova, “Analysis of emission characteristics of gas turbine engines with some alternative fuels,” Int. J. Green Energy, vol. 15, no. 3, pp. 161–168, 2018, doi: 10.1080/15435075.2017.1324790.
• [13] A.B. Lebedev, A.N. Secundov, A.M. Starik, N.S. Titova, and A.M. Schepin, “Modeling study of gas-turbine combustor emission,” Proc. Combust. Inst., vol. 32, no. 2, pp. 2941–2947, 2009, doi: 10.1016/j.proci.2008.05.015.
• [14] S. Taha, F. Ismail, and S. Thiruchelvam, “Gas turbine performance monitoring and operation challenges: A review,” Gazi U. J. Sci., vol. 36, no. 1, pp. 154–171, 2023, doi: 10.35378/gujs.948875.
• [15] H. Kaya, P. Tüfekci, and E. Uzun, “Predicting CO and NOχ emissions from gas turbines: Novel data and a benchmark PEMS,” Turk. J. Electr. Eng. Comput. Sci., vol. 27, no. 6, pp. 4783–4796, 2019, doi: 10.3906/elk-1807-87.
• [16] H. Egware and C. Kwasi-Effah, “A novel empirical model for predicting the carbon dioxide emission of a gas turbine power plant,” Heliyon, vol. 9, no. 3, p. e14645, 2023, doi: 10.1016/j.heliyon.2023.e14645.
• [17] A. Lazzaretto and A. Toffolo, “Prediction of performance and emissions of a two-shaft gas turbine from experimental data,” Appl. Therm. Eng., vol. 28, no. 17–18, pp. 2405–2415, 2008, doi: 10.1016/j.applthermaleng.2008.01.021.
• [18] L.S. Coelho, H.V. Ayala, and V.C. Mariani, “CO and NOχ emissions prediction in gas turbine using a novel modeling pipeline based on the combination of deep forest regressor and feature engineering,” Fuel, vol. 355, p. 129366, 2024, doi: 10.1016/j.fuel.2023.129366.
• [19] M. Faqih, M.B. Omar, and R. Ibrahim, “Prediction of dry-low emission gas turbine operating range from emission concentration using semi-supervised learning,” Sensors, vol. 23, no. 8, p. 3863, 2023, doi: 10.3390/s23083863.
• [20] Q. Zhao, F. Liu, A. Jiao, Q. Yang, H. Xu, and X. Liao, “Prediction model of NOχ emissions in the heavy-duty gas turbine combustor based on MILD combustion,” Energy, vol. 282, p. 128974, 2023, doi: 10.1016/j.energy.2023.128974.
• [21] M. Jadikar, “Gas-Turbine CO and NOx Emission Data,” Kaggle, 2021. [Online]. Available: https://www.kaggle.com/datasets/muniryadi/gasturbine-co-and-nox-emission-data (accessed: 14.03.2024).
• [22] Y. Özüpak, “Analysis and experimental verification of efficiency parameters affecting inductively coupled wireless power transfer systems,” Heliyon, vol. 10, no. 5, p. e27420, 2024, doi: 10.1016/j.heliyon.2024.e27420.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr POPUL/SP/0154/2024/02 w ramach programu "Społeczna odpowiedzialność nauki II" - moduł: Popularyzacja nauki (2025).