Neural Network Simulator of Gas Turbine Engines for Prototyping and Debugging of Control Systems on Unsteady Modes

The principle of creation of neural network simulator of gas turbine engines in the form of recurrent neural networks and their application in the hardware-in-the-loop simulation for testing and debugging automatic control and condition-monitoring systems is considered. A comparison of NARX and GRU architectures of simulators is carried out. A technique for constructing a gas turbine neural network simulator (model) and its implementation on a hardware-in-the loop simulation testbed is described. Hardware-in-the loop simulation is used for prototyping, testing and certification of developed products (physical objects) with a complex of mathematical models, where real systems are associated with virtual models in which they are located. The results of hardware-in-the loop simulation of the parameters of a gas turbine engine with a real full authority digital engine control system for startup mode, ground mode and flight modes are presented. An analysis of the accuracy and adequacy of the considered models is carried out. The accuracy required to solve control problems and form requirements for electronic control systems units has been confirmed. The intelligent modeling approach can be used to create full-fledged (complete) digital twins, where a model of physical processes and object behavior based on recurrent neural networks can be connected to 3D solid-state modeling to solve problems of object analysis and synthesis, its optimization and reliability increase. The development of such technologies makes it possible to create intelligent models that can be used in digital twins of complex technical systems

1. Prokhorov A., Lysachev M., Borov kov A. Digital twin. Analysis, trends, world experience, Moscow, LLC "AlliancePrint", 2020. 401 p. (in Russian).

2. Fuller A., Fan Z., Day C., Barlow C. Digital twin: Enabling technologies, challenges and open research, IEEE Access, 2020, vol. 8, pp. 108 952—108 971, available: https://doi.org/10.1109/access.2020.2998358

3. Zaccaria V., Stenfelt M., Aslanidou I., Kyprianidis K. G. Fleet Monitoring and Diagnostics Based on Digital Twin of Aero-Engines, GT2018-76414, ASME Turbo Expo 2018, 2018, Oslo, Norway.

4. Panov V., Cruz-Manzo S. Gas turbine performance digital twin for real-time embedded systems, ASME Turbo Expo 2020: Turbomachinery Technical Conference and Exposition, 2020, paper No: GT2020-14664, V005T05A010, 8 p., available: https://doi.org/10.1115/GT2020-14664

5. Zhou L., Wang H., Xu S. Aero-engine gas path system health assessment based on depth digital twin, Engineering Failure Analysis, 2022, vol. 142.

6. Jingkai Zh., Zhitao W., Shuying L., Pengfei W. A Digital Twin Approach for Gas Turbine Performance Based on Deep Multi-Model Fusion, available at http://dx.doi.org/10.2139/ssrn.4654368.

7. Lazzaretto A., Toffolo A. Analytical and neural network models for gas turbine design and off-design simulation, International Journal of Applied Thermodynamics, 2001, vol. 4, no. 4, pp. 173—182.

8. Basso M., Giarré L., Groppi S., Zappa G. NARX mo dels of an industrial power plant gas turbine, IEEE Transactions on Control Systems Technology, 2005, vol. 13, no. 4, pp. 599—604.

9. Baklacioglu T., Turan O., Aydin H. Dynamic modeling of exergy efficiency of turboprop engine components using hybrid genetic algorithm-artificial neural networks, Energy, 2015, vol. 86, pp. 709—721.

10. Asgari H., Xiaoqi Chen, Morini M., Pinelli M., Sainudiin R., Spina P. R., Venturini M. NARX models for simulation of the start-up operation of a single-shaft gas turbine, Applied Thermal Engineering, 2016, vol. 93, pp. 368—376.

11. Pogorelov G. I., Kulikov G. G., Abdulnagimov A. I., Badamshin B. I. Application of Neural Network Technology and High-performance Computing for Identification and Real-time Hardware-in-the-loop Simulation of Gas Turbine Engines, Procedia Engineering, 2017, vol. 176, pp. 402—408.

12. Chung J., Gulcehre C., Cho K., Bengio Y. Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling, NIPS 2014 Workshop on Deep Learning, December 2014, 2014.

13. Cherkasov B. A. Automatics and control of jet engines. Textbook for high schools, Moscow, Mashinostrienie, 1988, 360 p. (in Russian).

14. Kulikov G., Thompson H. (Eds.). Dynamic modelling of gas turbines: identification, simulation, condition monitoring, and optimal control, London, New York, Springer, 2004, 309 p.

15. Moller M. F. A Scaled Conjugate Gradient Algorithm for Fast Supervised Learning, in Neural Networks, 1993, vol. 6, pp. 525—533.

16. Diederik K., Ba J. Adam: A method for stochastic optimization, 2014, arΧiv:1412.6980 [cs.LG].

17. Kulikov G. G., Arkov V. Yu., Fatikov V. S., Abdulnagimov A. I., Pogorelov G. I. Methodology of complex hardwarein- the-loop functional modelling of gas turbines and its systems, Vestnik of the Samara state aerospace university, 2009, no. 3-2 (19), pp. 392—400 (in Russian).

18. Beale M. H., Hagan M. T., Demuth H. B. Deep Learning Toolbox™ User’s Guide [Online], available at: https://www.mathworks.com/help/deeplearning/index.html (date of access: 01.07.2024).