Virtual adaptive meter of deleterious substances in combustion chamber of a gas turbine engine based on the RBF-network

DOI: 10.34759/trd-2021-117-14

Аuthors

Nikulin V. S.^*, Khizhnyakov Y. N., Yuzhakov A. A.

Perm National Research Polytechnic University, PNRPU, 29, Komsomolsky Prospekt, Perm, 614990, Russia

*e-mail: kalif23@yandex.ru

Abstract

The soft computing technology toolkit is based on fuzzy systems, probabilistic models, neural networks, genetic algorithms, etc., which have their own advantages and disadvantages. This toolkit application was considered for an aircraft gas turbine engine (GTE) operating under conditions of uncertainties such as regulating hardware elements aging, variable ambient environment parameters, and variable fuel parameters.

Combustion chamber, ensuring the process of the air-fuel mixture (AFM) burning, is one of the basic parts of the gas turbine engine. Today’s progress in aircraft building development imposes requirements to the aircraft and engine soft-hardware facilities integration simplicity, as well as reduction of deleterious substances exhaust to the environment.

The purpose of the presented study consists in the following:

– developing method and algorithm for the adaptive virtual measurer of the deleterious substances exhaust by the GTE combusting chamber based on the RBF-network;

– adaptive control of air consumption into the combustion chamber;

– adaptive control of the gases temperature behind the combustion chamber employing fuel consumption regulation by the homogeneous collector.

The following research techniques were used in this work:

– grapho-analytical method for the RBF-network architecture building as an alternative to the Kohonen algorithm;

– an algorithm for oxidizer feeding control with the RBF-network;

– creating an algorithm for the current total value of deleterious substances correction at the specified value exceedance;

– creating an algorithm for the fuel consumption control in the homogeneous collector while temperature control behind the GTE combustion chamber by the adaptive fuzzy regulator

Based on the total computing of the deleterious substances, the following conclusion can be made on the exhausts requirements, which is 18 kg, as well as improvement of control system of the remote guiding device (RGD), and combustion products temperature behind the GTE combustion chamber.

The results of the research confirmed the decline of the combustion process uncertainty impact, and exhausts reduction in the airfield vicinity.

Keywords:

gas turbine engine, combustion chamber, meter of deleterious substances, Gaussian function, RBF-network, adaptive fuzzy controller

References

1. Metechko L.B., Tikhonov A.I., Sorokin A.E., Novikov S.V. Trudy MAI, 2016, no. 85. URL: http://trudymai.ru/eng/published.php?ID=67495

2. Gurevich O.S. Upravlenie aviatsionnymi gazoturbinnymi dvigatelyami (Aircraft Gas Turbine Engine Control), Moscow, Izd-vo MAI, 2001, 100 p.

3. Inozemtsev A.A., Nikhamkin A.A., Sandratskii V.L. Osnovy konstruirovaniya aviatsionnykh dvigatelei i energeticheskikh ustanovok (Fundamentals of Aircraft Engines and Power Plants Design), Moscow, Mashinostroenie, 2008, vol. 2, 368 p.

4. Isaev A.I. Skorobogatov S.V. // Trudy MAI, 2018, no. 98. URL: http://trudymai.ru/eng/published.php?ID=87340

5. Andrievskaya N.V., Andrievskii O.A., Legotkina T.S., Khizhnyakov Yu.N., Storozhev A.A., Nikulin V.S., Yuzhakov A.A., Kuznetsov M.D. Mekhatronika. Avtomatizatsiya, Upravlenie, 2020, vol. 21, no. 6, pp. 348 - 355. DOI: 10.17587/mau.21.348-355

6. Dmitriev V.G., Munin A.G. Aerokosmicheskii kur'er, 2003, no. 2, pp. 15 - 17.

7. Cherepanov F.M., Yasnitskii L.N. Vestnik Permskogo universiteta. Seriya: Matematika. Mekhanika. Informatika, 2008, no. 4, pp. 151 - 155.

8. Yasnitskii L.N. Neirokomp'yutery: razrabotka, primenenie, 2015, no. 5, pp. 48 – 56.

9. Kallan R. Osnovnye kontseptsii neironnykh setei (Basic Concepts of Neural Networks), Moscow, Vil'yams, 2001, 288 p.

10. Devyatkov V.V. Sistemy iskusstvennogo intellekta (Artificial Intelligence Systems), Moscow, Mashinostroenie, 1991, 320 p.

11. Gostev V.I. Proektirovanie nechetkikh regulyatorov dlya sistem avtomaticheskogo upravleniya (Fuzzy Controllers Design for Automatic Control Systems), Saint Petersburg, BKhV-Peterburg, 2011, 416 p.

12. Osovskii S. Neironnye seti dlya obrabotki informatsii (Neural Networks for Information Processing), Moscow, Finansy i statistika, 2004, 344 p.

13. Khizhnyakov Yu.N. Nechetkoe, neironnoe i gibridnoe upravlenie (Fuzzy, Neural and Hybrid Control), Perm', Izd-vo Permskogo natsional'nogo issledovatel'skogo politekhnicheskogo universiteta, 2013, 303 p.

14. Baklanov A.V., Makarova G.F., Vasil'ev A.A., Nuzhdin A.A. Trudy MAI, 2018, no. 103. URL: http://trudymai.ru/eng/published.php?ID=100700

15. Pegat A. Nechetkoe modelirovanie i upravlenie (Fuzzy Modeling and Control), Moscow, BINOM. Laboratoriya znanii, 2007, 798 p.

16. Mosolov S.V., Sidlerov D.A., Ponomarev A.A. Trudy MAI, 2012, no. 59. URL: http://trudymai.ru/eng/published.php?ID=34989

17. Leonenkov A.V. Nechetkoe modelirovanie v srede MATLAB i FuzzyTech (Fuzzy Modeling in MATLAB and FuzzyTech), Saint Petersburg, BKhV-Peterburg, 2005, 736 p.

18. Yarushkina N.G. Osnovy teorii nechetkikh i gibridnykh system (Fundamentals of the Fuzzy and Hybrid Systems Theory), Moscow, Finansy i statistika, 2004, 320 p.

19. Mamdani E.H. Application of Fuzzy Algorithms for the Control of a Simple Dynamic Plant, Proceedings of the IEEE, 1974, pp. 121 - 159. DOI:10.1049/PIEE.1974.0328

20. Nikulin V.S., Storozhev S.A., Abdulin D.M., Khizhnyakov Yu.N. Trudy MAI, 2020, no. 116. URL: http://trudymai.ru/eng/published.php?ID=121086. DOI: 10.34759/trd-2021-116-1119

Download