INTEGRATED APPLICATION OF SYNERGETIC APPROACH AND NEURAL NETWORK STRUCTURES TO THE PROBLEM OF ELECTRIC DRIVE INTELLECTUAL CONTROL SYSTEM SYNTHESIS

D. Marshakov; Anatoliy Kolesnikov; Andrey Aydinyan

doi:doi:10.12737/7165

INTEGRATED APPLICATION OF SYNERGETIC APPROACH AND NEURAL NETWORK STRUCTURES TO THE PROBLEM OF ELECTRIC DRIVE INTELLECTUAL CONTROL SYSTEM SYNTHESIS

Published в Vestnik of Don State Technical University · Volume 14, Issue 4, 2014 · Pages 60–71 · Rubrics: Technical sciences

DOI 10.12737/7165

Received: 08.12.2014 Accepted: 13.02.2015 Published: 13.02.2015 Language of publication: RUS

Authors

D. Marshakov · Anatoliy Kolesnikov ² · Andrey Aydinyan

2 Southern Federal University (The Department of synergetics and control processes, Head of department)

ABSTRACT

The applicability of the artificial neural networks to the synthesis of the intellectual systems with the synergetic control law is considered. The key points of the synergetic approach to the system synthesis problem are stated. An example of the synergetic synthesis of the robot electrodrive control law under the conditions of its uncon-trolled parametric variation and external disturbances is considered. An algorithm for synthesis of the neural net-work controller based on a predetermined synergetic control law is presented. The algorithm is based on the syn-ergetic controller behavior simulated by an artificial neural network as a result of its training through harmonic signals of different frequencies. The key element of the proposed integrated approach to the synthesis of the intelligent control system is that it involves a combination of the self-organization unity principle and the training of the neural network at the preliminary stage. This ensures a subsequent stable system operation.

KEYWORDS

synergetics artificial neural networks intelligent control self-organization neurocontroller

Information Text References

Authors:

2. Southern Federal University (The Department of synergetics and control processes, Head of department)

Type:

Article

Pages:

from 60 to 71

Status:

Published

Language:

Russian

Keywords:

synergetics, artificial neural networks, intelligent control, self-organization, neurocontroller

Text

Введение. Отличительной особенностью современных искусственных систем управления является наличие соответствующей совокупности прямых и обратных связей. В последнее время все большую популярность получают интеллектуальные системы управления, основанные на пяти следующих принципах [1]:

1) наличие тесного информационного взаимодействия управляющих систем с реальным внешним миром и использование специально организованных информационных каналов связи;

2) принципиальная открытость систем для повышения интеллектуальности и совершенствования собственного поведения;

3) наличие механизмов прогноза изменения внешнего мира и собственного поведения системы в динамически меняющемся внешнем мире;

4) построение управляющей системы в виде многоуровневой иерархической структуры в соответствии с правилом: повышение интеллектуальности и снижение требований к точности по мере повышения ранга иерархии;

5) сохраняемость функционирования при разрыве связей или потере управляющих воздействий от высших уровней иерархии управляющей структуры.

References

1. Makarov, I. M., Lokhin, V. M., eds. Intellektual´nye sistemy avtomaticheskogo upravleniya. [Intelligent automatic control systems.] Moscow : Fizmatlit, 2001, 576 p. (in Russian).

2. Kolesnikov, А. А. Sinergeticheskie metody upravleniya slozhnymi sistemami: teoriya sistemnogo sin-teza. [Synergetic methods of complex system control: theory of system synthesis.] Moscow : Editorial URSS ; KomKniga, 2006, 240 p. (in Russian).

3. Zakovorotny, V. L., Flek, M. B., Pham Dinh Tung. Sinergeticheskaya kontseptsiya pri postroenii sis-tem upravleniya tochnost´yu izgotovleniya detaley slozhnoy geometricheskoy formy. [Synergetic concept in construction of accuracy control systems for manufacturing parts of complex geometric forms.] Vestnik of DSTU, 2011, vol. 11, no. 10 (61), pp. 1785-1797 (in Russian).

4. Atroshchenko, О. I. Sinergeticheskiy sintez upravleniy dlya nelineynogo ob´´ekta upravleni-ya. [Synergetic control synthesis for nonlinear control object.] Vestnik of DSTU, 2008, vol. 8, no. 3, pp. 245-251 (in Russian).

5. Kolesnikov, А. А., Topchiyev, B.V. Sinergeticheskiy podkhod k probleme formirovaniya iskusstven-noy samoorganizatsii upravlyaemykh sistem. Chast´ 1. [Synergetic approach to the problem of forming artificial self-organization of control systems. Part 1.] Mekhatronika, avtomatizatsiya, upravlenie, 2005, no. 1, pp. 2-6 (in Russian).

6. Omatu, S., Khalid, M., Yusof, R. Neuro-Control and its applications. London : Springer-Verlag, 1995, 255 p.

7. Terekhov, V. А., Yefimov, D. V., Tyukin, I. Y. Neyrosetevye sistemy upravleniya. [Neural network control systems.] Moscow : Vysshaya shkola, 2002, 183 p. (in Russian).

8. Haykin, S. Neural networks and learning machines. 3rd edition. New Jersey : Prentice Hall, 2009, 936 p.

9. Kolesnikov, А. А., Topchiyev, B. V. Sinergeticheskiy podkhod k probleme formirovaniya iskusstven-noy samoorganizatsii upravlyaemykh sistem. Chast´ 2. [Synergetic approach to the problem of forming artificial self-organization of control systems. Part 2.] Mekhatronika, avtomatizatsiya, upravlenie, 2005, no. 2, pp. 2-11 (in Russian).

10. Medvedev, V. S., Potemkin, V.G. Neyronnye seti. MATLAB 6. [Neural networks. MATLAB 6.] Mos-cow : Dialog-MIFI, 2002, 496 p. (in Russian).

Доступ и загрузка

🗂 JATS XML ❝ To cite 📎 Citations

—

Views

—

Downloads

Citations

Индексируется в

INTEGRATED APPLICATION OF SYNERGETIC APPROACH AND NEURAL NETWORK STRUCTURES TO THE PROBLEM OF ELECTRIC DRIVE INTELLECTUAL CONTROL SYSTEM SYNTHESIS

Confirmation

Регистрация