A high-dimensional and high-precision onboard modeling method for adaptive variable cycle engine
-
Qiangang Zheng
Abstract
Adaptive variable cycle engines, capable of switching seamlessly between subsonic and supersonic modes, have become a central focus in propulsion research. Accurate and real-time onboard models are crucial for predicting performance in flight and supporting advanced functions such as control optimization, health monitoring, and fault-tolerant control. Yet, reconciling accuracy with computational efficiency remains challenging due to the engines’ inherent high dimensionality and strong nonlinearity. Here we present an NN-ΔNN-based modeling framework, where a neural network captures nonlinear dynamics, a ΔNN component represents high-dimensional features, and a Kalman filter enhances adaptability. Simulations show that this approach improves accuracy of key parameters by 0.17–1.6 times compared with NN-PSM across a wide flight envelope. It also achieves rapid thrust-tracking under single- and multi-component degradation within seconds, with low steady-state error, demonstrating strong adaptability and real-time capability.
Funding source: General Project of the National Natural Science Foundation of China
Award Identifier / Grant number: 52372389
Funding source: the National Science and Technology Major Project
Award Identifier / Grant number: J2022-I-0003-0003
Funding source: Aero Engine Corporation of China Industry-University Research Cooperation Project
Award Identifier / Grant number: HFZL2023CXY013
Funding source: Nanjing University of Aeronautics and Astronautics Forward Layout Research Special Key Cultivation Project
Award Identifier / Grant number: ILB240101A24
Acknowledgments
The authors would like to thank the institutions and project teams involved for their support during the development of this study, as well as the reviewers for their insightful comments that helped improve the manuscript.
-
Research ethics: Not applicable.
-
Informed consent: Not applicable.
-
Author contributions: All authors have accepted responsibility for the entire content of this manuscript and approved its submission.
-
Use of Large Language Models, AI and Machine Learning Tools: None declared.
-
Conflict of interest: The authors state no conflict of interest.
-
Research funding: This work was supported in part by the General Project of the National Natural Science Foundation of China (No. 52372389), in part by the National Science and Technology Major Project (J2022-I-0003-0003), in part by the Aero Engine Corporation of China industry-university research cooperation project (No. HFZL2023CXY013), and in part by the Nanjing University of Aeronautics and Astronautics Forward Layout Research Special Key Cultivation Project (ILB240101A24).
-
Data availability: Not applicable.
References
1. Adibhatla, S, Brown, H, Gastineau, Z. Intelligent engine control (IEC). In: AIAA 1st intelligent system technical conference. AIAA; 1992.10.2514/6.1992-3484Search in Google Scholar
2. M Baptista, A Kumar, B Brunell, Model-Based life extending control for aircraft engines, AIAA-2004-6465.10.2514/6.2004-6465Search in Google Scholar
3. Curlett, BP, Felder, JL. Object-orienged approach gas turbine engine simulation. NASA-TM-106907.Search in Google Scholar
4. Csank, JT, Chin, JC, May, RD, Litt, JS, Guo, TH. Implementation of enhanced propulsion control modes for emergency flight operation. NASA-TM-2011-217028.10.2514/6.2011-1590Search in Google Scholar
5. Volponi, A, Simon, DL. Enhanced selftuning on-board real-time model (eSTIRM) for aircraft engine performance health tracking. NASA/CR-2008-215272.Search in Google Scholar
6. Luppold, R, Roman, J, Keer, L. Estimating in-flight engine performance variation using Kalman filter concepts. AIAA-1989-2584.10.2514/6.1989-2584Search in Google Scholar
7. Chen, Q, Shi, H, Sheng, H, Liu, Y, Li, J, Zhang, J, et al.. Novel dual-twin model-based nonlinear onboard adaptive modeling method for aircraft engine with fuel measurement uncertainty awareness. Energy 2025:331:136924.10.1016/j.energy.2025.136924Search in Google Scholar
8. Li, H, Guo, Y, Ren, X. New method for improving tracking accuracy of aero-engine on-board model based on separability index and reverse searching. Aerospace 2025;12:175. https://doi.org/10.3390/aerospace12030175.Search in Google Scholar
9. Marinai, L, Gatto, EL, Pachidis, V, Philidis, P. Multiple-point adaptive performance simulation tuned to aeroengine test-bed data. J Propul Power 2009;25:635–41.10.2514/1.38823Search in Google Scholar
10. Wei, Z, Zhang, S. Auto-updating model-based control for thrust variation mitigation and acceleration performance enhancement of gas turbine aero-engines. Propul Power Res 2024;13:394–415 https://doi.org/10.1016/j.jppr.2023.02.008.Search in Google Scholar
11. Xue, W, Guo, Y. Aircraft engine sensor fault diagnostics based on estimation of engine’s health degradation. Chin J Aeronaut 2009;22:18–21.10.1016/S1000-9361(08)60064-3Search in Google Scholar
12. Yedavalli, RK. Robust estimation and fault diagnostics for aircraft engines with uncertain model data. In: Proceedings of the American control conference. 2007.10.1109/ACC.2007.4283156Search in Google Scholar
13. Bouraou, NI, Protasov, AG, Sopilka, YV, Zazhitsky, OV. Decision making of aircraft engine blades condition based on bispectral analysis of the vibroacoustical signal. AIP Conf Proc. 2005;760: 760–66. https://doi.org/10.1063/1.1916751.Search in Google Scholar
14. Onder, U, Buczak Anna, L, Nwadiogbu, E. Neural-networks-based sensor validation and recovery methodology for advanced aircraft engines. Honeywell Inc.; 2001:4389 p.10.1117/12.434229Search in Google Scholar
15. Liu, X. An improved hybrid Kalman filter design for aircraft engine based on a velocity-based LPV framework. Int J Aeronaut Space Sci 2017;18:535–44. https://doi.org/10.5139/ijass.2017.18.3.535.Search in Google Scholar
16. Pang, S, Lu, H, Li, Q, Gu, Z. An improved onboard adaptive aero-engine model based on an enhanced neural network and linear parameter variance for parameter prediction. Energies 2024;17:2888. https://doi.org/10.3390/en17122888.Search in Google Scholar
17. Ren, LH, Feng, YZ, Ye, Z, Yan, XZ, Ping, ZY. Aero-engine on-board model based on big quick access recorder data. Proc Inst Mech Eng G J Aerosp Eng 2023;237:824–34. https://doi.org/10.1177/09544100221110290.Search in Google Scholar
18. Xiang, D, Zheng, Q, Zhang, H, Chen, C, Fang, J. Aero⁃engine on⁃board adaptive steady⁃state model base on NN⁃PSM. J Aero Power 2022;37:409–23.Search in Google Scholar
19. de, PI, Arthur, R, Mihaela, M. Alarm-based predictive maintenance scheduling for aircraft engines with imperfect remaining useful life prognostics. Reliab Eng Syst Saf 2022;221. https://dx.doi.org/10.1016/j.ress.2022.108341.10.1016/j.ress.2022.108341Search in Google Scholar
20. Baumann, M, Koch, C, Staudacher, S. Application of neural networks and transfer learning to turbomachinery heat transfer. Aerospace 2022;9:49. https://doi.org/10.3390/aerospace9020049.Search in Google Scholar
21. Amare Desalegn, F, Valentina, Z, Konstantinos, K. Aircraft engine performance monitoring and diagnostics based on deep convolutional neural networks. Machines 2021;9:337. https://doi.org/10.3390/machines9120337.Search in Google Scholar
22. Balakrishnan, N, Devasigamani Angello, I, Anupama, KR, Nitin, S. Aero-engine health monitoring with real flight data using whale optimization algorithm based artificial neural network technique. Opt Mem Neural Network 2021;30:80–96. https://doi.org/10.3103/s1060992x21010094.Search in Google Scholar
23. Zhiyuan, W, Jafari, S, Shuguang, Z, Theoklis, N. Hybrid Wiener model: an on-board approach using post-flight data for gas turbine aero-engines modelling. Appl Therm Eng 2021;184. https://dx.doi.org/10.1016/j.applthermaleng.2020.116350.10.1016/j.applthermaleng.2020.116350Search in Google Scholar
24. Pourbabaee, B, Meskin, N, Khorasani, K. Sensor fault detection, isolation, and identification using multiple-model-based hybrid Kalman filter for gas turbine engines. IEEE Trans Control Syst Technol 2016;24:1184–200. https://doi.org/10.1109/tcst.2015.2480003.Search in Google Scholar
25. Xiao, L, Xu, M, Chen, Y, Chen, Y. Hybrid gray wolf optimization nonlinear model predictive control for aircraft engines based on an elastic bp neural network. Appl Sci 2019;9:1254. https://doi.org/10.3390/app9061254.Search in Google Scholar
26. 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.Search in Google Scholar
27. De Giorgi, MG, Campilongo, S, Ficarella, A. A diagnostics tool for aero-engines health monitoring using machine learning technique. Energy Proc 2018;148:860–7. https://doi.org/10.1016/j.egypro.2018.08.109.Search in Google Scholar
28. Grigor’ev, VA, Kalabukhov, DS, Rad’ko, VM. Application of neural network approximation methods in the generalization and presentation of the aircraft gas turbine engine turbomachinery characteristics. Russ Aeronaut 2015;58:48–53. https://doi.org/10.3103/s1068799815010080.Search in Google Scholar
29. Yuan, Y, Zhang, T, Lin, Z, Zhiwen, Z, Zhang, X. Actuator fault tolerant control of variable cycle engine using sliding mode control scheme. Actuators 2021;10:24. https://doi.org/10.3390/act10020024.Search in Google Scholar
30. Wang, Y, Pan, M, Zhou, W, Huang, J. Direct thrust control for variable cycle engine based on fractional order PID-nonlinear model predictive control under off-nominal operation conditions. Aero Sci Technol 2023;143: 108726.10.1016/j.ast.2023.108726Search in Google Scholar
31. Qiu, X, Xiaodong, C, Chen, J, Fan, B. Research on the analytical redundancy method for the control system of variable cycle engine. Sustainability 2022;14:5905. https://doi.org/10.3390/su14105905.Search in Google Scholar
© 2025 Walter de Gruyter GmbH, Berlin/Boston
