Development of a procedure for the synthesis of a micro gas turbine engine neural controller with account for fuel consumption constraints


Cite item

Full Text

Abstract

Neural networks are often used to model dynamic processes in objects and to synthesize their control systems. However, their application in real systems is now rather limited due to insufficient research into the process of creating control systems. The issues of creating neural network control systems for gas turbine engines, taking into account both their nonlinear dynamics and the fuel consumption constraints depending on the engine operating mode, remain practically unexplored. To take into account the fuel consumption constraints, a method was developed for modifying the misalignment between the actual and target RPM values during the training of the neural controller. The resulting neural controller is characterized by implicit fuel consumption constraints and non-linear dynamics of the engine itself. The developed method for modifying the neural network training error allows one to synthesize a nonlinear control system, taking into account the requirements for limitations in the automatic mode.

About the authors

A. V. Kuznetsov

Samara National Research University

Author for correspondence.
Email: a.v.kuznetsov91@mail.ru

Postgraduate Student

Russian Federation

G. M. Makaryants

Samara National Research University

Email: georgy.makaryants@gmail.com

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

Russian Federation

References

  1. Link C.J., Jack D.M. Aircraft engine controls: design, system analysis, and health monitoring. Reston, Virginia: American Institute of Aeronautics and Astronautics, 2009. 397 p.
  2. Evsyukov V.N. Nelineynye sistemy avtomaticheskogo upravleniya: uchebnoe posobie dlya studentov vuzov [Nonlinear automatic control systems: manual for university students]. Orenburg: GOU OGU Publ., 2007. 172 p.
  3. Chernodub A.N., Dzyuba D.A. A review of methods of neuro management. Problems in Programming. 2011. No. 2. P. 79-94. (In Russ.)
  4. Isermann R. Perspectives of automatic control. Control Engineering Practice. 2011. V. 19, Iss. 12. P. 1399-1407. doi: 10.1016/j.conengprac.2011.08.004
  5. Tao G. Multivariable adaptive control: A survey. Automatica. 2014. V. 50, Iss.11. P. 2737-2764. doi: 10.1016/j.automatica.2014.10.015
  6. Wang X., Zhao J., Xi-M. S. Overshoot-free acceleration of aero-engines: An energy-based switching control method. Control Engineering Practice. 2016. V. 47. P. 28-36. doi: 10.1016/j.conengprac.2015.12.007
  7. Xiaofeng L., Jing S., Yiwen Q., Ye Y. Design for aircraft engine multi-objective controllers with switching characteristics. Chinese Journal of Aeronautics. 2014. V. 27, Iss. 5. P. 1097-1110. doi: 10.1016/j.cja.2014.08.002
  8. Agüero J.L., Beroqui M.C., Pasquo H.D. Gas turbine control. Modifications for: Availability and limitation of spinning reserve and limitation of non-desired unloading. 2002. 8 p.
  9. Phillips Ch.L., Harbor R.D. Feedback Control systems. New Jersey: Prentice Hall, 2000. 664 p.
  10. Nabney I.T., Cressy D.C. Neural network control of a gas turbine. Neural Computing and Applications. 1996. V. 4, Iss. 4. P. 198-208. doi: 10.1007/BF01413818
  11. Vasilyev V.I., Valeyev S.S., Shilonosov A.A. Design of neurocontroller for gas-turbine engine multi-mode control. Proceedings of the 8th International Conference on Neural Information Processing (ICONIP-2001) (Shanghai, Nov. 14-18, 2001). V. 2. P. 746-750.
  12. Mu J., Rees D. Approximate model predictive control for gas turbine engines. Proceedings of the 2004 American Control Conference. 2004. V. 6. P. 5704-5709. doi: 10.23919/acc.2004.1384765
  13. Vasilyev V.I., Idrisov I.I. Algorithms of design and analysis of intelligent gas-tubine engine (GTE) control system. Vestnik UGATU. 2008. V. 11, no. 1. P. 34-42. (In Russ.)
  14. Bazazzadeh M., Badihi H., Shahriari A. Gas turbine engine control design using fuzzy logic and neural networks. International Journal of Aerospace Engineering. 2011. V. 2011. doi: 10.1155/2011/156796
  15. Vasilyev V.I., Valeyev S.S. Design of intelligent control systems of gas-turbine engine on the basis of minimal complexity principle. Vestnik UGATU. 2007. V. 9, no. 2. P. 32-41. (In Russ.)
  16. Sartori M.A., Antsaklis P.J. Implementations of learning control systems using neural networks. IEEE Control Systems Magazine. 1992. V. 12, Iss. 2. P. 49-57. doi: 10.1109/37.126853
  17. Jokar A., Zomorodian R., Ghofrani M.G., Khodaparast P. Active control of surge in centrifugal compressors using a brain emotional learning-based intelligent controller. Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science. 2015. V. 230, Iss.16. P. 2828-2839. doi: 10.1177/0954406215602281
  18. Gao W., Selmic R.R. Neural network control of a class of nonlinear systems with actuator saturation. Proceedings of the 2004 American Control Conference. 2004. V. 3. P. 2569-2574. doi: 10.23919/acc.2004.1383852
  19. Kuznetsov A.V., Makaryants G.M. Micro gas turbine engine imitation model. Vestnik of Samara University. Aerospace and Mechanical Engineering. 2017. V. 16, no 2. P. 65-74. doi: 10.18287/2541-7533-2017-16-2-65-74. (In Russ.)
  20. Haykin S. Neural networks. New Jersey: Prentice Hall, 1999. 896 p.
  21. Osowski S. Sieci neuronowe do przetwarzania informacji. Warszawa: Oficyna Wydawnicza Politechniki Warszawskiej, 2000. 325 p.
  22. Cybenko G. Approximation by superpositions of a sigmoidal function. Mathematics of Control, Signals, and Systems. 1989. V. 2, Iss. 4. P. 303-314. DOI:0.1007/bf02551274

Supplementary files

Supplementary Files
Action
1. JATS XML

Copyright (c) 2018 VESTNIK of Samara University. Aerospace and Mechanical Engineering

This website uses cookies

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

About Cookies