10.14489/td.2025.07.pp.041-054

2025, 07 July

DOI: 10.14489/td.2025.07.pp.041-054

Mashoshin O. F., Huseynov H.
DEVELOPMENT OF AN INTEGRATED ALGORITHM FOR PROCESSING AIRCRAFT GTE DIAGNOSTIC PARAMETERS USING MULTILAYER NEURAL NETWORKS
(pp. 41-54)

Abstract. This paper presents a methodology for diagnosing the technical condition of aircraft gas turbine engines (GTE) using multilayer neural networks. A comprehensive algorithm for processing diagnostic parameters has been developed, taking into account their mutual influence and temporal dynamics. A new approach is proposed for forming an integral assessment of the engine’s technical condition based on a complex indicator (t), which combines information about current parameter values, their rate of change, and cumulative effects. The mathematical model includes a modified loss function with a regularization term and a dynamic coefficient of mutual parameter influence ij(t). Experimental studies were conducted using operational data from PS-90A aircraft engines over a period of 1000 flight hours. The analysis included vibration parameters (VIBN1, VIBN2), gas temperatures (T4, T7), and rotor speeds (n1, n2). Significant improvement in diagnostic accuracy was achieved: reduction in Root Mean Square Error (RMSE) for vibration parameters was 43.5 ‒ 44.9 %, for temperature parameters ‒ 36.6 ‒ 36.7 %, and for rotor speeds ‒ 36.3 ‒ 39.2 %. Statistical reliability of the results was confirmed at a significance level of p < 0,05 with a determination coefficient R2 > 0,95. The research results have practical significance for improving aircraft engine maintenance efficiency and ensuring flight safety.

Keywords: aircraft engine diagnostics, gas turbine engine, multilayer neural networks, diagnostic parameter processing, GTE technical condition, vibration diagnostics, parametric diagnostics, machine learning, adaptive algorithms, complex indicator, flight safety.

+ - About the Authors Click to collapse

O. F. Mashoshin, H. Huseynov (Moscow State Technical University of Civil Aviation, Moscow, Russia) E-mail: Данный адрес e-mail защищен от спам-ботов, Вам необходимо включить Javascript для его просмотра. , Данный адрес e-mail защищен от спам-ботов, Вам необходимо включить Javascript для его просмотра.

+ - References Click to collapse

1. Mashoshin, O. F. (2005). Diagnostics of aircraft gas turbine engines using information potential of controlled parameters [Doctoral dissertation, Moscow State Technical University of Civil Aviation]. [in Russian language]
2. Zhernakov, S. V. (2006). Application of neural network technology for diagnosing the technical condition of aircraft engines. Intellektual'nye Sistemy v Proizvodstve, (2), 70–83. [in Russian language]
3. Fentaye, A. D., Zaccaria, V., & Kyprianidis, K. (2021). Aircraft engine performance monitoring and diagnostics based on deep convolutional neural networks. Machines, 9(12), Article 337.
4. Kobayashi, T., & Simon, D. L. (2005). Hybrid neural-network genetic-algorithm technique for aircraft engine performance diagnostics. Journal of Propulsion and Power, 21(4), 751–758.
5. Zhernakov, S. V., & Gilmanshin, A. T. (2014). Application of intelligent algorithms based on fuzzy logic and neural networks for solving problems of aviation GTE failure diagnostics. In Intelligent Technologies for Information Processing and Management (ITIPM'2014) (pp. 112–115).
6. Zhang, X., & Zhao, R. (2020). Fault diagnosis for gas turbine engine using LSTM networks. IEEE Transactions on Neural Networks and Learning Systems. https://doi.org/10.1103/PhysRevLett.59.2229
7. Vasil'ev, V. I., Zhernakov, S. V., & Muslukhov, I. I. (2009). Onboard algorithms for monitoring GTE parameters based on neural network technology. Vestnik Ufimskogo Gosudarstvennogo Aviatsionnogo Tekhnicheskogo Universiteta, 12(1), 61–74. [in Russian language]
8. Vasil'ev, V. I., & Zhernakov, S. V. (2006). Monitoring and diagnostics of the technical condition of aircraft engines based on intelligent data analysis. Vestnik Ufimskogo Gosudarstvennogo Aviatsionnogo Tekhnicheskogo Universiteta, 7(2), 71–81. [in Russian language]
9. Krivosheev, I. A., & Sukhanov, A. V. (2014). Development of a comprehensive automated system for GTE diagnostics based on SCADA technologies and simulation modeling. Vestnik Ufimskogo Gosudarstvennogo Aviatsionnogo Tekhnicheskogo Universiteta, 18(2(63)), 134–141. [in Russian language]
10. Abdurakipov, S. S., & Butakov, E. B. (2020). Comparative analysis of machine learning algorithms for determining pre-failure and emergency conditions of aircraft engines. Avtometriya, 56(6), 34–48. [in Russian language]
11. Software, scientific enterprise and IT developer of engineering and social solutions. (2024). PO, nauchnoe predpriiatie i IT razrabotchik inzhenernykh i sotsial'nykh reshenii [Electronic resource]. Retrieved November 15, 2024, from https://divibi.ru/analyzer.html#services
12. Joly, R. B., Singh, R., Probert, S. D., & Ogaji, S. (2004). Gasturbine diagnostics using artificial neural-networks for a high bypass ratio military turbofan engine. Applied Energy, 78(4), 397–418.
13. Tayarani-Bathaie, S. S., Vanini, Z. N. S., & Khorasani, K. (2014). Dynamic neural network-based fault diagnosis of gas turbine engines. Neurocomputing, 125, 153–165.
14. Li, B., Zhao, Y. P., & Chen, Y. B. (2021). Unilateral alignment transfer neural network for fault diagnosis of aircraft engine. Aerospace Science and Technology, 118, Article 107031.

+ - Purchase digital version of a single article Click to collapse

This article is available in electronic format (PDF).

The cost of a single article is 700 rubles. (including VAT 20%). After you place an order within a few days, you will receive following documents to your specified e-mail: account on payment and receipt to pay in the bank.

After depositing your payment on our bank account we send you file of the article by e-mail.

To order articles please copy the article doi:

10.14489/td.2025.07.pp.041-054

and fill out the form