Gas turbine engine dynamic model based on variable-memory LSTM architecture


The buildup of thermodynamic cycle parameters is the main way to increase gas turbine engine efficiency. However, the growth of engine pressure and temperature ratio leads to the increase in the turbine heat load, which reduces the engine lifetime dramatically. In terms of gas turbine engines, to avoid the engine life loss is a crucial problem especially for small engines, because the limited size of a small gas turbine engine does not allow implementing various measures for nozzle vane cooling. In light of this, the contribution of the turbine heat control is essentially increasing. It places great demands on the accuracy of control over the main engine variables (such as the rotor speed and turbine outlet temperature). The state-of-the-industry gas turbine engines use an on-board engine mathematical model to improve the quality of the control. These models deal with engine processes of short duration and considerable overshooting. For that reason, the model accuracy is the main aspect in the control process. However, the issues of accurate and at the same time resource-saving calculation of rapidly varying processes of changing the rotor speed and the turbine gas temperature remain under-investigated. In the work, neural network methods were used to model the unsteady modes of a small gas turbine engine. Using the data obtained as a result of firing tests of the JetCat P-60 engine, the engine regression neural network model was created. The main issue that arose during the creation of the model was to describe the dynamics of rapidly varying processes with pronounced overshoot. For this purpose, modification of the architecture of the classical LSTM network was carried out, the essence of which was to add a functional dependence of the exit node on the memory tensor. This allowed us to make the memory size independent of the number of model outputs, thereby increasing the modeling accuracy. The developed architecture was proposed a new name - VMLSTM network. As a result of comparison with the traditional Elman network and the classic LSTM network, the developed VMLSTM network showed the least value of the average error with a comparable number of modifiable model parameters. In addition, unlike the existing neural networks, the developed network demonstrated the ability to simulate turbine outlet gas over-temperature at the moments when the engine operating mode changes. The developed neural network architecture increases the reliability of modeling the dynamics of a small gas turbine engine as an object of control, which in the conditions of economical use of computing resources opens up possibilities of its application in on-board microcomputers.

About the authors

A. V. Kuznetsov

Samara National Research University

Author for correspondence.

Postgraduate Student, Department of Power Plant Automatic Systems

Russian Federation

G. M. Makaryants

Samara National Research University


Doctor of Science (Engineering), Assistant Professor,
Professor of the Department of Power Plant Automatic Systems

Russian Federation


  1. Gurevich O.S. Sistemy avtomaticheskogo upravleniya aviatsionnymi GTD: entsiklopedicheskiy spravochnik [Aviation gas turbine engine control systems: Encyclopedic reference book]. Moscow: Torus Press Publ., 2011. 208 p.
  2. Jaw L., Mattingly J. Aircraft engine controls. Reston, Va: American Institute of Aeronautics and Astronautics, Inc., 2009. 364 p.
  3. Gol'berg F.D., Batenin A.V. Matematicheskie modeli gazoturbinnykh dvigateley kak ob"ektov upravleniya [Mathematical models of gas turbine engines as objects of control]. Moscow: Moscow Aviation Institute Publ., 1999. 79 p.
  4. Integral'nye sistemy avtomaticheskogo upravleniya silovymi ustanovkami samoleta / pod red. A.A. Shevyakova [Integrated systems for automatic control of aircraft power plants / ed. by A.A. Shevyakov]. Moscow: Mashinostroenie Publ., 1983. 283 p.
  5. Shevyakov A.A. Sistemy avtomaticheskogo upravleniya aviatsionnymi vozdushno-reaktivnymi silovymi ustanovkami [Automatic control systems for aviation air-breathing propulsion systems]. Moscow: Mashinostroenie Publ., 1992. 424 p.
  6. Teoriya avtomaticheskogo upravleniya silovymi ustanovkami letatel'nykh apparatov / pod red. A.A. Shevyakova [Theory of automatic control of aircraft power plants / ed. by A.A. Shevyakov]. Moscow: Mashinostroenie Publ., 1976. 344 p.
  7. Badami M., Ferrero M.G., Portoraro A. Dynamic parsimonious model and experimental validation of a gas microturbine at part-load conditions. Applied Thermal Engineering. 2015. V. 75. P. 14-23. doi: 10.1016/j.applthermaleng.2014.10.047
  8. Arsalis A. Thermoeconomic modeling and parametric study of hybrid SOFC–gas turbine-steam turbine power plants ranging from 1.5 to 10MWe. Journal of Power Sources. 2008. V. 181, Iss. 2. P. 313-326. doi: 10.1016/j.jpowsour.2007.11.104
  9. Akhmedzyanov D.A. Non-stable regimes of aviation GTE. Vestnik UGATU. 2006. V. 7, no. 1 (14). P. 36-46. (In Russ.)
  10. Gras’ko T.V., Mayatskiy S.A. Numerical technique for projected gas turbine engine’s main chamber combustion analysis. Vestnik UGATU. 2014. V. 18, no. 3 (64). P. 23-29. (In Russ.)
  11. Maksimov A.V., Kiselev E.A., Kurgalin S.D., Zuev S.A. Mathematical model describing air flow dynamics in a turbine spirometer. Proceedings of the Institute for System Programming of the RAS. 2019. V. 31, no. 1. P. 105-114. (In Russ.). doi: 10.15514/ISPRAS-2019-31(1)-7
  12. Biryukov R.V., Kiselyov Yu.V. Empirical model of the thermal state of rotor bearings and oil system at gas turbine engines. Izvestiya Samarskogo Nauchnogo Tsentra RAN. 2016. V. 18, no. 2 (3). P. 848-852. (In Russ.)
  13. Asgari H., Chen X.Q., Morini M., Pinelli M., Sainudin R., Spina P.R., Venturini M. NARX models for simulation of the start-up operation of a singleshaft gas turbine. Applied Thermal Engineering. 2016. V. 93. P. 368-376. doi: 10.1016/j.applthermaleng.2015.09.074
  14. Nikpey H., Assadi M., Breuhaus P. Development of an optimized artificial neural network model for combined heat and power micro gas turbines. Applied Energy. 2013. V. 108. P. 137-148. doi: 10.1016/j.apenergy.2013.03.016
  15. Ali Lilo M., Latiff L.A., Abu A.B.H., Al Mashhadany Y.I., Ilijan A.K. Gas Turbine bearing and vibration classification of using multi-layer Neural Network. 2015 International Conference on Smart Sensors and Application (ICSSA) (May, 26-28, 2015, Kuala Lumpur, Malaysia). 2015. P. 20-23. doi: 10.1109/ICSSA.2015.7322503
  16. Elman J.L. Finding structure in time. Cognitive science. 1990. V. 14, Iss. 2. P. 179-211. doi: 10.1016/0364-0213(90)90002-E
  17. Jordan M.I. Serial order: A parallel distributed processing approach. Advances in Psychology. 1997. V. 121. P. 471-495. doi: 10.1016/s0166-4115(97)80111-2
  18. Siegelmann H.T., Horne B.G., Giles C.L. Computational capabilities of recurrent NARX neural networks. IEEE Transactions on Systems, Man and Cybernetics, Part B (Cybernetics). 1997. V. 27, Iss 2. P. 208-215. doi: 10.1109/3477.558801
  19. Hochreiter S., Schmidhuber J. Long short-term memory. Tech. Rep. no. FKI-207-95. Fakultat fur Informatik, Technische Universitat Munchen, 1995.
  20. Hochreiter S., Schmidhuber J. Long short-term memory. Neural Computation. 1997. V. 9, Iss. 8. P. 1735-1780. doi: 10.1162/neco.1997.9.8.1735
  21. Gers F.A., Schmidhuber J., Cummins F. Learning to forget: continual prediction with LSTM. Neural Computation. 2000. V. 12, Iss. 10. P. 2451-2471. doi: 10.1162/089976600300015015
  22. Gers F.A., Schmidhuber J. Recurrent nets that time and count. Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium (July, 25-27, 2000, Como, Italy). 2000. doi: 10.1109/ijcnn.2000.861302
  23. Greff K., Srivastava R.K., Koutnik J., Steunebrink B.R., Schmidhuber J. LSTM: A search space Odyssey. IEEE Transactions on Neural Networks and Learning Systems. 2017. V. 28, Iss. 10. P. 2222-2232. doi: 10.1109/tnnls.2016.2582924



Abstract: 428

PDF (Russian): 298




  • There are currently no refbacks.

Copyright (c) 2020 VESTNIK of Samara University. Aerospace and Mechanical Engineering

License URL:

This website uses cookies

You consent to our cookies if you continue to use our website.

About Cookies