SYNTHESIS OF CONTROL SYSTEMS WITH MULTILAYER NEURAL NETWORKS BASED ON VELOCITY GRADIENT METHODS

Authors

Oxunjon Boborayimov, Tashkent State Technical University, Tashkent, Uzbekistan, Address: University street 2, 100095 Tashkent city, Republic of Uzbekistan. E-mail: boborayimov1992@mail.ru;Follow
Okyay Kaynak, Turkish Academy of Sciences, Department of Electrical and Electronics Engineering, Bogazici University, Turkey. Email: okyay.kaynak@boun.edu.tr.Follow

Abstract

In this manuscripts, the synthesis of control systems with multilayer neural networks based on the speed gradient methods is given. For adjusting the weight coefficients of the base processor element, the gradient method of minimizing the learning criterion is used. A procedure for the synthesis of neural network control systems based on the velocity gradient methods has been developed. This guarantees the stabilization of the system under external limited disturbances that are inaccessible to direct measurement. Taking into account the state vector of the control object in the network learning function ensures the consistency of the processes of setting the network coefficients and managing the dynamic object.

First Page

34

Last Page

39

References

1. Aggarval, Ch. (2020). Neyronnie seti i glubokoe obuchenie [Neural networks and deep learning]. SPb.: OOO «Dialektika», 720 p. (in Russian).
2. Vasilev, V.I., Ilyasov, B.G. (2009). Intellektualnie sistemi upravleniya. Teoriya i praktika [Intelligent control systems. Theory and practice]. M.: Radiotexnika, 392 p. (in Russian).
3. Gafarov, F.M., Galimyanov, A.F. (2018). Iskusstvennie neyronnie seti i prilojeniya [Artificial neural networks and applications]. Kazan: Izd-vo Kazan un-ta, 121 p. (in Russian).
4. Makarov, I.M. i dr. (2006). Iskusstvenniy intellekt i intellektualnie sistemi upravleniya [Artificial intelligence and intelligent control systems]. M.: Nauka, 333 p. (in Russian).
5. Yefimov, D.V. (2006). Robastnoe i adaptivnoe upravlenie kolebatelnimi rejimami nelineynix sistem [Robust and adaptive control of oscillatory modes of nonlinear systems]. Dissertatsii na soiskanie uchenoy stepeni doktora texnicheskix nauk po spesialnosti. Sankt-Peterburg. 282 p. (in Russian).
6. Miroshnik, I.V., Nikiforov, V.O., Fradkov, A.L. (2000). Nelineynoe i adaptivnoe upravlenie slojnimi dinamicheskimi sistemami [Nonlinear and adaptive control of complex dynamic systems]. SPb.: Nauka. 549 p. (in Russian).
7. Yusupbekov, A.N., Sevinov, J.U., Mamirov, U.F., Botirov, T.V. (2021). Synthesis Algorithms for Neural Network Regulator of Dynamic System Control. 14 th International Conference on Theory and Application of Fuzzy Systems and Soft Computing – ICAFS-2020. ICAFS 2020. Advances in Intelligent Systems and Computing, 1306. Springer, Cham. https://doi.org/10.1007/978-3-030-64058-3_90.
8. Yefimov, D.V. (2001). Analiz ustoychivosti adaptivnix neyrosetevix sistema upravleniya na osnove metoda razdeleniya dvijeniy [Analysis of the stability of adaptive neural network control systems based on the motion separation method]. Priborostroenie, 1, 20-25.
9. Natanson, I.P. (1999). Teoriya funksiy veshestvennoy peremennoy [Theory of functions of a real variable]. SPb.: Aan, 560 p. (in Russian).
10. Nikolenko, S., Kadurin, A., Arxangelskaya, Ye. (2018). Glubokoe obuchenie [Deep Learning]. SPb.: Piter, 480 p. (in Russian).
11. Fomin, V.N., Fradkov, A.L., Yakubovich, V.A. (1981). Adaptivnoe upravlenie dinamicheskimi ob’ektami [Adaptive control of dynamic objects]. M.: Nauka, 448 p. (in Russian).
12. Mallayev, A., Sevinov, J., Xusanov, S., Boborayimov, O. (2022). Algorithms for the synthesis of gradient controllers in a nonlinear control system. AIP Conference Proceedingsthis link is disabled (CAMSTech-II), 2467, 030003. https://doi.org/10.1063/5.0093749.
13. Igoshin, V.I. (2008). Matematicheskaya logika i teoriya algoritmov [Mathematical logic and theory of algorithms]. M.: Akademiya, 448 p. (in Russian).
14. Tyukin, I.Yu. (2001). Algoritmicheskiy sintez neyrosetevix sistem upravleniya nelineynimi dinamicheskimi ob’ektami v usloviyax neopredelennosti [Algorithmic synthesis of neural network control systems for nonlinear dynamic objects under uncertainty]. Diss. na soiskanie uchen, stepeni k-ta texn. nauk. SPbGETU. SPb., 254 p. (in Russian).
15. Kanushkin, S.V. (2018). Sinergeticheskiy podxod v upravlenii gruppoy bespilotnix letatelnix apparatov intellektualnoy sistemi oxrannogo monitoringa [Synergetic approach to managing a group of unmanned aerial vehicles of an intelligent security monitoring system]. Pravovaya informatika. 3, 25-37. (in Russian).
16. Igamberdiyev, X.Z., Sevinov, J.U., Zaripov, O.O. (2014). Regulyarniye metodi i algoritmi sinteza adaptivnix system upravleniya s nastraivayemimi modelyami [Regular methods of adaptive control system synthesis algorithms with customizable models]. T.: TashGTU, 160 p. (in Russian).
17. Sevinov, J.U., Boborayimov, O.Kh. (2022). Synthesis of management systems for dynamic objects based on speed gradient algorithms. Chemical Technology, Control and Management. 3/2022, 61-65.

Recommended Citation

Boborayimov, Oxunjon and Kaynak, Okyay (2023) "SYNTHESIS OF CONTROL SYSTEMS WITH MULTILAYER NEURAL NETWORKS BASED ON VELOCITY GRADIENT METHODS," Chemical Technology, Control and Management: Vol. 2023: Iss. 3, Article 5.
DOI: https://doi.org/10.59048/2181-1105.1474