Research on real-time improvement method of on-board physical mechanism model of turboshaft engine based on neural network
-
Yuan Liu
Abstract
On-board model is the basis of aero-engine advanced control algorithm. Physical mechanism model has high modeling accuracy, but its poor real-time performance limits its on-board application. Iterative solving algorithm is an important factor leading to the poor real-time performance of the physical mechanism model. Therefore, this paper proposes an improved real-time performance method of the on-board physical mechanism model of turboshaft engine based on neural network. This method establishes a solver model of engine flow balance and pressure balance equations based on neural network. It does not need to repeatedly calculate the inlet, compressor and other component models when solving the balance equation, thus improving the real-time performance of the model. Meanwhile, the powerful nonlinear fitting ability of neural network ensures the modeling accuracy. The simulation results show that compared with the conventional physical mechanism model, the calculation time of the proposed method is reduced by 70.8 %. The maximum modeling error of the key performance parameters at the steady-state condition is no more than 0.6 %, the relative error of the key parameters at the ground point is no more than 0.3 % under the large step of fuel and the variable flight altitude, and the relative error of the key parameters at the variable flight speed is no more than 0.2 %. The effectiveness of the proposed method is verified. The maximum modeling error is less than 0.5 %, which verifies the effectiveness of the proposed method.
-
Research ethics: Not applicable.
-
Informed consent: Not applicable.
-
Author contributions: All authors have accepted responsibility for the entire content of this submitted manuscript and approved its submission.
-
Use of Large Language Models, AI and Machine Learning Tools: None declared.
-
Conflict of interest: The authors declare no conflicts of interest regarding this article.
-
Research funding: None declared.
-
Data availability: Not applicable.
References
1. Lv, C, Chang, J, Bao, W, Yu, D. Recent research progress on airbreathing aero-engine control algorithm. Propul Power Res 2022;11:1–57. https://doi.org/10.1016/j.jppr.2022.02.003.Suche in Google Scholar
2. Lu, F, Huang, J, Ji, C, Zhang, D, Jiao, H. Gas path on-line fault diagnostics using a nonlinear integrated model for gas turbine engines. Int J Turbo Jet Engines 2014;31:261–75. https://doi.org/10.1515/tjj-2014-0001.Suche in Google Scholar
3. Gou, L, Shen, Y, Zheng, H, Zeng, A. Multi-fault diagnosis of an aero-engine control system using joint sliding mode observers. IEEE Access 2020;8:10186–97. https://doi.org/10.1109/access.2020.2964572.Suche in Google Scholar
4. Zheng, Q, Pang, S, Zhang, H, Hu, Z. A study on aero-engine direct thrust control with nonlinear model predictive control based on deep neural network. Int J Aeronaut Space Sci 2019;20:933–9. https://doi.org/10.1007/s42405-019-00191-4.Suche in Google Scholar
5. Sun, T, Sun, XM, Sun, A. Optimal output tracking of aircraft engine systems: a data-driven adaptive performance seeking control. IEEE Trans Circuits Syst II: Express Briefs 2021;69:1467–71. https://doi.org/10.1109/tcsii.2021.3115777.Suche in Google Scholar
6. Chen, J, Hu, Z, Wang, J. Aero‐engine real‐time models and their applications. Math Probl Eng 2021:9917523.10.1155/2021/9917523Suche in Google Scholar
7. Lin, YH, Zhang, HB. Establishment of state variable model of aeroengine with improved least square fitting. Appl Mech Mater 2011; 40:27–33.10.4028/www.scientific.net/AMM.40-41.27Suche in Google Scholar
8. Castiglione, T, Perrone, D, Strafella, L, Ficarella, A, Bova, S. Linear model of a turboshaft aero-engine including components degradation for control-oriented applications. Energies 2023;16:2634. https://doi.org/10.3390/en16062634.Suche in Google Scholar
9. Ibrahem, IMA, Akhrif, O, Moustapha, H, Staniszewski, M. An ensemble of recurrent neural networks for real time performance modeling of three-spool aero-derivative gas turbine engine. J Eng Gas Turbines Power 2021;143:101004. https://doi.org/10.1115/1.4051112.Suche in Google Scholar
10. Tejero, F, MacManus, D, Heidebrecht, A, Sheaf, C. Artificial neural network for preliminary design and optimisation of civil aero-engine nacelles. Aeronaut J 2024;128:2261–80. https://doi.org/10.1017/aer.2024.38.Suche in Google Scholar
11. Zheng, Q, Fang, J, Hu, Z, Zhang, H. Aero-engine on-board model based on batch normalize deep neural network. IEEE Access 2019;7:54855–62. https://doi.org/10.1109/access.2018.2885199.Suche in Google Scholar
12. Zhang, C, Wang, N. Aero-engine condition monitoring based on support vector machine. Phys Procedia 2012;24:1546–52. https://doi.org/10.1016/j.phpro.2012.02.228.Suche in Google Scholar
13. Qi-hua, XU, Jun, SHI. Fault diagnosis for aero-engine applying a new multi-class support vector algorithm. Chin J Aeronaut 2006;19:175–82.10.1016/S1000-9361(11)60342-7Suche in Google Scholar
14. Nieto, PJG, Garcia-Gonzalo, E, Sanchez Lasheras, F, de Cos Juez, FJ. Hybrid PSO–SVM-based method for forecasting of the remaining useful life for aircraft engines and evaluation of its reliability. Reliab Eng Syst Saf 2015;138:219–31. https://doi.org/10.1016/j.ress.2015.02.001.Suche in Google Scholar
15. Kai, YIN, Wen-xiang, ZHOU, Kun, QIAO, Hong-jun, WANG, quan, HUANG. Research on methods of improving real-time performance for aero-engine component-level model. J Propuls Technol 2017;38:199.Suche in Google Scholar
16. Pang, S, Li, Q, Zhang, H. An exact derivative based aero-engine modeling method. IEEE Access 2018;6:34516–26. https://doi.org/10.1109/access.2018.2849752.Suche in Google Scholar
17. Gazzetta, H, Bringhenti, C, Barbosa, JR, Tomita, JT. Real-time gas turbine model for performance simulations. J Aero Technol Manag 2017;9:346–56. https://doi.org/10.5028/jatm.v9i3.693.Suche in Google Scholar
18. Liu, Y, Liu, W, Chen, F, Sun, B. Simplified real-time simulation model of two-axis turbojet engine performance. J Aeropower 1994;20-3+103-4.Suche in Google Scholar
19. Luo, X, Jia, GENG, Ming, L, Liu, B, Wang, L, Song, Z. Aircraft engine onboard model iterative calculation method research. J Syst Simul 2022:2649–58. https://doi.org/10.16182/j.issn1004731x.Joss.22-FZ0905.Suche in Google Scholar
20. Wang, Y, Qiuhong, L, Xianghua, H. Numerical calculation of aero engine model based on self-correcting broyden quasi-Newton method. J Aerod2016;31:249–56.Suche in Google Scholar
21. Yin, K, Zhou, W, Qiao, K, Wang, H, Jin, J. Research on improving real-time performance of aero engine component level model. Propuls Technol 2018;38:199–206.Suche in Google Scholar
22. Cai, C, Zheng, Q, Zhang, H. A new method to improve the real-time performance of aero-engine component level model. Int J Turbo Jet Engines 2020. https://doi.org/10.1515/tjj-2020-0033.Suche in Google Scholar
23. Chang-Kai, Y. Research on synthesis modeling and control technology of spin entry/exit process. Nanjing: Nanjing University of Aeronautics and Astronautics and London Astronautics; 2014.Suche in Google Scholar
24. Gurney, K. An introduction to neural networks. London: CRC Press; 2018.10.1201/9781315273570Suche in Google Scholar
25. Wu, Y, Feng, J. Development and application of artificial neural network. Wirel Pers Commun 2018;102:1645–56. https://doi.org/10.1007/s11277-017-5224-x.Suche in Google Scholar
26. Lu, X, Pan, H, Zhang, L, Ma, L, Wan, H. A dual path hybrid neural network framework for remaining useful life prediction of aero‐engine. Qual Reliab Eng Int 2024;40:1795–810. https://doi.org/10.1002/qre.3494.Suche in Google Scholar
27. Zheng, Q, Fang, J, Hu, Z, Zhang, H. Aero-engine on-board model based on batch normalize deep neural network. IEEE Access 2019;7:54855–62. https://doi.org/10.1109/access.2018.2885199.Suche in Google Scholar
© 2025 Walter de Gruyter GmbH, Berlin/Boston
