Evaluation of the technical condition of a gas turbine plant using machine learning methods from artificial data assessing the technical condition of a gas turbine using machine learning methods with artificial data
Keywords:
gas turbine, technical condition, machine learning, random forest, forecasting, predictive maintenanceAbstract
Continuous monitoring of the technical condition of gas turbines, defect identification, failure prevention, and optimization of operation, maintenance, and repair processes are relevant tasks for the operators of this equipment. Various machine learning methods that are already being used in the field of gas turbines can help solve these tasks. The limiting factor in this regard is the lack of real operational data. This study examines the possibility of using synthetic data for training and testing machine learning models to determine the level of technical condition of a gas turbine installation. An open dataset created by other researchers using a mathematical model of a marine gas turbine engine was selected for analysis. The research presents the accuracy values obtained by different methods of evaluating machine learning models. The random forest model demonstrated the best results. It was found that when developing machine learning-based solutions for engineering tasks, additional methods for assessing the accuracy of predictions are required. The further development of this work is associated with the development of a proprietary mathematical model of a gas turbine installation capable of considering the influence of specific defects to create datasets for analysis and further research.
Metrics
References
ГОСТ
1. Roemer M. J., Kacprzynski G. J. Advanced diagnostics and prognostics for gas turbine engine risk assessment //2000 IEEE aerospace conference. proceedings. Т. 6. Big Sky: IEEE, 2000. С. 345-353. DOI: 10.1109/AERO.2000.877909.
2. Jordan M. I., Mitchell T. M. Machine learning: Trends, perspectives, and prospects //Science. – 2015. Т. 349. №. 6245. С. 255-260. DOI: 10.1126/science.aaa8415.
3. Sun L. et al. Real-time power prediction approach for turbine using deep learning techniques //Energy. 2021. Т. 233. С. 121130. DOI: 10.1016/j.energy.2021.121130.
4. Александров И. В., Дюк В. А., Фомин В. В. Использование методов машинного обучения для определения коэффициента расхода топлива газовой турбины фрегата //Морские интеллектуальные технологии. 2019. № 3-1. С. 156-160. EDN: LWWUPZ.
5. Coraddu A. et al. Machine learning approaches for improving condition-based maintenance of naval propulsion plants //Proceedings of the Institution of Mechanical Engineers, Part M: Journal of Engineering for the Maritime Environment. 2016. Т. 230, №. 1. С. 136-153. DOI: 10.1177/1475090214540874
6. Cisotto S., Herzallah R. Performance prediction using neural network and confidence intervals: A gas turbine application //2018 IEEE international conference on big data (Big data). IEEE, 2018. С. 2151-2159. DOI: 10.1109/BigData.2018.8621919
7. Кочуева О. Н. Разработка моделей прогнозирования выбросов оксидов углерода и азота газовых турбин на основе генетических алгоритмов //Деловой журнал Neftegaz.RU. 2022. № 5-6. С. 14-20. EDN: YMUQSO
8. Блинов В. Л., Дерябин Г. А. Определение эффективной мощности газотурбинного газоперекачивающего агрегата методами машинного обучения // Известия высших учебных заведений. Машиностроение. 2023. № 2(755). С. 63-72. EDN ZKYEBG. DOI: 10.18698/0536-1044-2023-2-63-72.
9. Campora U., Cravero C., Zaccone R. Marine gas turbine monitoring and diagnostics by simulation and pattern recognition //International journal of naval architecture and ocean engineering. 2018. – Т. 10. №. 5. С. 617-628. DOI: 10.1016/j.ijnaoe.2017.09.012
10. Zhong S., Fu S., Lin L. A novel gas turbine fault diagnosis method based on transfer learning with CNN //Measurement. 2019. Т. 137. С. 435-453. DOI: 10.1016/j.measurement.2019.01.022
11. Real-time simulation of a COGAG naval ship propulsion system / M. Altosole, G. Benvenuto, M. Figari, U. Campora // Proceedings of the institution of mechanical engineers, part M: Journal of engineering for the maritime environment. 2009. Т. 223, № 1. С. 47-62. DOI: 10.1243/14750902JEME121
APA
1. Roemer, M. J., & Kacprzynski, G. J. (2000, March). Advanced diagnostics and prognostics for gas tu bine engine risk assessment. IEEE aerospace conference. proceedings (Vol. 6, pp. 345-353). IEEE. http://dx.doi.org/10.1109/AERO.2000.877909
2. Jordan, M. I., & Mitchell, T. M. (2015). Machine learning: Trends, perspectives, and prospects. Science, 349(6245) , 255-260. https://doi.org/10.1126/science.aaa8415
3. Sun, L., Liu, T., Xie, Y., Zhang, D., & Xia, X. (2021). Real-time power prediction approach for turbine using deep learning techniques. Energy, 233, 121130. http://dx.doi.org/10.1016/j.energy.2021.121130
4. Alexandrov, I. V., Duke, V. A., & Fomin, V. V. (2019). Using machine learning methods to determine the fuel consumption coefficient of a frigate gas turbine [Ispol'zovanie metodov mashinnogo obucheniya dlya opredeleniya koefficienta raskhoda topliva gazovoj turbiny fregata]. Morskiye intellektual'nyye tekhnologii, (3-1), 156-160. https://www.elibrary.ru/lwwupz [In Russian]
5. Coraddu, A., Oneto, L., Ghio, A., Savio, S., Anguita, D., & Figari, M. (2016). Machine learning approaches for improving condition-based maintenance of naval propulsion plants. Proceedings of the Institution of Mechanical Engineers, Part M: Journal of Engineering for the Maritime Environment, 230(1), 136-153. https://doi.org/10.1177/1475090214540874
6. Cisotto, S., & Herzallah, R. (2018, December). Performance prediction using neural network and confidence intervals: A gas turbine application. IEEE international conference on big data (Big data) (pp. 2151-2159). IEEE. http://dx.doi.org/10.1109/BigData.2018.8621919
7. Kochueva, O. N. (2022). Development of models for forecasting emissions of carbon and nitrogen oxides from gas turbines based on genetic algorithms [Razrabotka modelej prognozirovaniya vybrosov oksidov ugleroda i azota gazovyh turbin na osnove geneticheskih algoritmov]. Delovoy zhurnal Neftegaz. RU, (5-6), 14-20. https://magazine.neftegaz.ru/articles/tsifrovizatsiya/ 740352-razrabotka-modeley-prognozirovaniya-vybrosov-oksidov-ugleroda-i-azota-gazovykh-turbin-na-osnove-gene/ [In Russian]
8. Blinov, V. L. & Deriabin G. A. (2023) Determination of the effective power of a gas turbine gas pumping unit using machine learning methods [Opredelenie effektivnoj moshchnosti gazoturbinnogo gazoperekachivayushchego agregata metodami mashinnogo obucheniya]. News of higher educational institutions. mechanical engineering 2 (755) . P. 63-72. https://doi.org/10.18698/0536-1044-2023-2-63-72. [In Russian]
9. Campora, U., Cravero, C., & Zaccone, R. (2018). Marine gas turbine monitoring and diagnostics by simulation and pattern recognition. International journal of naval architecture and ocean engineering, 10(5), 617-628. http://dx.doi.org/10.1016/j.ijnaoe.2017.09.012
10. Zhong, S. S., Fu, S., & Lin, L. (2019). A novel gas turbine fault diagnosis method based on transfer learning with CNN. Measurement, 137, 435-453. http://dx.doi.org/10.1016/j.measurement.2019.01.022
11. Altosole, M., Benvenuto, G., Figari, M., & Campora, U. (2009). Real-time simulation of a COGAG naval ship propulsion system. Proceedings of the institution of mechanical engineers, part M: Journal of engineering for the maritime environment, 223(1), 47-62. https://doi.org/10.1243/14750902JEME121
Downloads
Published
How to Cite
Issue
Section
Categories
URN
License
Copyright (c) 2023 G.A. Deryabin, S.M. Pankrashin, V.L. Blinov
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
