ISSN 2466-4677; e-ISSN 2466-4847
Journal Menu
Archive
Last Edition
Journal Menu
Archive
Comparative analysis of machine learning methods for solving the problem of predicting failures in gas turbine engines
Authors:
Maria Lapina1
, Mikhail Kondrashov2
, Mikhail Babenko1
, Feroz Shaik3
,
B. Deepanraj3
1North-Caucasus Federal University, 355017, Stavropol, Russia
2MIREA – Russian Technological University, Russian Federation, 119454, Moscow, Russia
3Prince Mohammad Bin Fahd University, Al-Khobar, 31952, Saudi Arabia
Received: 5 June 2025
Revised: 30 August 2025
Accepted: 13 September 2025
Published: 30 September 2025
Abstract:
Gas turbine energy technologies are one of the most important components of the modern and advanced energy industry. An important task is to ensure the uninterrupted operation of the equipment in a given period; therefore, monitoring and diagnostics of the technical condition of the equipment continue to play an important role in ensuring the quality of the gas turbine engine. The article examines the work on equipment diagnostics using machine learning. It discusses various solutions for combining machine- learning methods and dealing with unbalanced data to solve the problem of predicting the failure of gas turbine equipment on a dataset that has the above disadvantages. There is a review of the solutions and methods under consideration to deal with the problems of the dataset. At the end, the authors provide a comparative table of the results of the application of the considered solutions based on the quality metrics of the Recall, Precision, F1-score classification, and PR-AUC and ROC-AUC curves.
Keywords:
Machine learning, equipment failure prediction, gas turbine engine, gas turbine power plant, data imbalance, fuzzy logic, SMOTE, Tomek Links
References:
[1] Y.K. Petrenya, Development of Gas Turbine Energy Technologies in Russia. Herald of the Russian Academy of Sciences, 89(2), 2019: 101-104. https://doi.org/10.1134/S1019331619020163
[2] A.A. Kudinov, Thermal power plants. Schematics and Equipment: Training Manual. INFRA-M, Moscow, 2015.
[3] V.G. Zlobin, A.A. Verholancev, Gas turbine installations. Part 1. Thermal schemes. Thermodynamic cycles. Training Manual. St. Petersburg State University of Industrial Technologies and Design, Saint Petersburg, 2020. (In Russian)
[4] W.C. Saj, M.V. Shcherbakov, A classification approach based on a combination of deep neural networks for predicting failures of complex multi-object systems. Modeling, Optimization and Information Technology, 8(2), 2020: 1-11. (In Russian) https://doi.org/10.26102/2310-6018/2020.29.2.037
[5] S. Dedyukhin, K.D. Andreev, Malfunction diagnostics of gas turbine units using vibrodiagnostics. International Journal of Humanities and Natural Sciences, 5(1), 2021: 16-25. (In Russian)
https://doi.org/10.24412/2500-1000-2021-5-1-16-25
[6] A.D. Fentaye, A.T. Baheta, S.I. Gilani, K.G. Kyprianidis, A Review on Gas Turbine Gas-Path Diagnostics: State-of-the-Art Methods, Challenges and Opportunities. Aerospace, 6(7), 2019: 83.
https://doi.org/10.3390/aerospace6070083
[7] R. Kurz, K. Brun, C. Meher-Homji, Gas Turbine Degradation. 43rd Turbomachinery & 30th Pump Users Symposia (Pump & Turbo 2014), 23-25 September 2014, Houston, USA, pp.1-36.
https://doi.org/10.21423/R15W5P
[8] V.V. Sakhin, The design and operation of power plants. Book 2. Gas turbines. Heat exchangers: a textbook. Ministry of Education and Science of the Russian Federation, Baltic State Technical University, St. Petersburg, 2015.
[9] A.O. Onokwai, U.B. Akuru, D.A. Desai, Mathematical Modelling and Optimisation of Operating Parameters for Enhanced Energy Generation in Gas Turbine Power Plant with Intercooler. Mathematics, 13(1), 2025: 174. https://doi.org/10.3390/math13010174
[10] B. Novaković, Lj. Radovanović, D. Vidaković, L. Đorđević, B. Radišić, Evaluating Wind Turbine Power Plant Reliability Through Fault Tree Analysis. Applied Engineering Letters, 8(4), 2023: 175-182.
https://doi.org/10.18485/aeletters.2023.8.4.5
[11] H. Ghasemian, Q. Zeeshan, Failure Mode and Effect Analysis (FMEA) of Aeronautical Gas Turbine using the Fuzzy Risk Priority Ranking (FRPR) Approach. International Journal of Soft Computing and Engineering (IJSCE), 7(1), 2017: 81-92.
[12] A. Mishra, Machine Learning Classification Models for Detection of the Fracture Location in Dissimilar Friction Stir Welded Joint. Applied Engineering Letters, 5(3), 2020: 87-93.
https://doi.org/10.18485/aeletters.2020.5.3.3
[13] A.-T.W.K. Fahmi, K. Reza Kashyzadeh, S. Ghorbani, Advancements in Gas Turbine Fault Detection: A Machine Learning Approach Based on the Temporal Convolutional Network–Autoencoder Model. Applied Sciences, 14(11), 2024: 4551. https://doi.org/10.3390/app14114551
[14] H. Hanachi, C. Mechefske, J. Liu, A. Banerjee, Y. Chen, Performance-Based Gas Turbine Health Monitoring, Diagnostics, and Prognostics: A Survey. IEEE Transactions on Reliability, 67(3), 2018: 1340-1363. http://doi.org/10.1109/TR.2018.2822702
[15] S. Amirkhani, A. Tootchi, A. Chaibakhsh, Fault detection and isolation of gas turbine using series-parallel NARX model. ISA Transactions, 120, 2022: 205-221. https://doi.org/10.1016/j.isatra.2021.03.019
[16] M.S. Nashed, J.R. Renno, M.S. Mohamed, R. Reuben, Gas turbine failure classification using acoustic emissions with wavelet analysis and deep learning. Expert Systems with Applications, 232, 2023: 120684. https://doi.org/10.1016/j.eswa.2023.120684
[17] Engine Fault Detection Data: Sensor data for engine condition classification and predictive maintenance. Kaggle, 2025. https://www.kaggle.com/datasets/ziya07/engine-fault-detection-data (Accessed: 15 April 2025)
[18] I. Tomek, An Experiment with the Edited Nearest-Neighbor Rule. IEEE Transactions on Systems, Man, and Cybernetics, 6(6), 1976: 448-452. https://doi.org/10.1109/TSMC.1976.4309523
[19] A.T. Elhassan, M. Aljourf, M. Shoukri, Classification of Imbalance Data using Tomek Link (T-Link) Combined with Random Under-sampling (RUS) as a Data Reduction Method. Global Journal of Technology and Optimization, S1, 2017: 111. https://doi.org/10.4172/2229-8711.S1111
[20] R.M. Pereira, Y.M.G. Costa, C.N. Silla Jr., MLTL: A multi-label approach for the Tomek Link under sampling algorithm. Neurocomputing, 383, 2020: 95-105. https://doi.org/10.1016/j.neucom.2019.11.076
[21] E.F. Swana, W. Doorsamy, P. Bokoro, Tomek Link and SMOTE Approaches for Machine Fault Classification with an Imbalanced Dataset. Sensors, 22(9), 2022: 3246. https://doi.org/10.3390/s22093246
[22] A. Fernández, S. García, J. Luengo, E. Bernadó-Mansilla, F. Herrera, Genetics-Based Machine Learning for Rule Induction: State of the Art, Taxonomy, and Comparative Study. IEEE Transactions on Evolutionary Computation, 14(6), 2010: 913–941. https://doi.org/10.1109/TEVC.2009.2039140
[23] Engine Fault Detection Prediction. Kaggle, 2025.
https://www.kaggle.com/code/rohitkumar211987/engine-fault-detection-prediction (Accessed: 15 April 2025)
[24] L. Prokhorenkova, G. Gusev, A. Vorobev, A.V. Dorogush, A. Gulin, CatBoost: unbiased boosting with categorical features. arXiv, 2019. https://doi.org/10.48550/arXiv.1706.09516
[25] M. Luo, Y. Wang, Y. Xie, L. Zhou, J. Qiao, S. Qiu, Y. Sun, Combination of Feature Selection and CatBoost for Prediction: The First Application to the Estimation of Aboveground Biomass. Forests, 12(2), 2021: 216. https://doi.org/10.3390/f12020216
[26] C. Seiffert, T.M. Khoshgoftaar, J. Van Hulse, A. Napolitano, RUSBoost: A Hybrid Approach to Alleviating Class Imbalance. IEEE Transactions on Systems, Man, and Cybernetics – Part A: Systems and Humans, 40(1), 2010: 185-197. https://doi.org/10.1109/TSMCA.2009.2029559
[27] C. Sun, M. Song, S. Hong, H. Li, A Review of Designs and Applications of Echo State Networks. arXiv, 2020. https://doi.org/10.48550/arXiv.2012.02974
[28] Y. Gorishniy, I. Rubachev, V. Khrulkov, A. Babenko, Revisiting Deep Learning Models for Tabular Data. Proceedings of the 35th International Conference on Neural Information Processing Systems, New York, USA, 2021: 1447.
[29] K. He, X. Zhang, S. Ren, J. Sun, Deep Residual Learning for Image Recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, Las Vegas, USA, pp.770-778.
https://doi.org/10.1109/CVPR.2016.90
[30] K. Bölat, T. Kumbasar, Interpreting Variational Autoencoders with Fuzzy Logic: A step towards interpretable deep learning based fuzzy classifiers. 2020 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE 2020), 19-24 July 2020, Glasgow, UK, pp.1-7. https://doi.org/10.1109/FUZZ48607.2020.9177631
[31] J. Demšar, Statistical Comparisons of Classifiers over Multiple Data Sets. Journal of Machine Learning Research, 7, 2006: 1-30.
© 2025 by the authors. This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License (CC BY-NC 4.0)
Volume 10
Number 4
December 2025
Last Edition
Volume 10
Number 4
December 2025
How to Cite
M. Lapina, M. Kondrashov, M. Babenko, F. Shaik, B. Deepanraj, Comparative Analysis of Machine Learning Methods for Solving the Problem of Predicting Failures in Gas Turbine Engines. Applied Engineering Letters, 10(3), 2025: 171-182.
https://doi.org/10.46793/aeletters.2025.10.3.5
More Citation Formats
Lapina, M., Kondrashov, M., Babenko, M., Shaik, F., & Deepanraj, B. (2025). Comparative Analysis of Machine Learning Methods for Solving the Problem of Predicting Failures in Gas Turbine Engines. Applied Engineering Letters, 10(3), 171-182.
https://doi.org/10.46793/aeletters.2025.10.3.5
Lapina, Maria, et al. “Comparative Analysis of Machine Learning Methods for Solving the Problem of Predicting Failures in Gas Turbine Engines.“ Applied Engineering Letters, vol. 10, no. 3, 2025, pp. 171-182.
https://doi.org/10.46793/aeletters.2025.10.3.5
Lapina, Maria, Mikhail Kondrashov, Mikhail Babenko, Feroz Shaik, and B. Deepanraj. 2025. “Comparative Analysis of Machine Learning Methods for Solving the Problem of Predicting Failures in Gas Turbine Engines.“ Applied Engineering Letters, 10 (3): 171-182.
https://doi.org/10.46793/aeletters.2025.10.3.5
Lapina, M., Kondrashov, M., Babenko, M., Shaik, F. and Deepanraj, B. (2025). Comparative Analysis of Machine Learning Methods for Solving the Problem of Predicting Failures in Gas Turbine Engines. Applied Engineering Letters, 10(3), pp. 171-182.
doi: 10.46793/aeletters.2025.10.3.5.