Русская версия English version

Improving the accuracy of identification and tuning of linear systems with state controllers using an artificial neural network

A.A. Anisimov, M.E. Sorokovnin, S.V. Tararykin

Vestnik IGEU, 2023 issue 6, pp. 57—68

Download PDF

Abstract in English: 

Background. High potential capabilities of control systems with state controllers can be realized only if automatic tuning tools are available. Since the tuning is carried out in real-time mode, which places increased demands on performance, it is proposed to use an artificial neural network to reduce its duration. However, under the conditions of noise in the measurement channels, the quality of identification of the parameters of the control object is significantly reduced. In this regard, the aim of the study is to find the optimal composition of measurement channels at the network input, which allows minimizing the influence of noise on the estimates of object parameters to improve the quality of tuning.

Materials and methods. During the study, state space methods are used to design a vector-matrix model of an object and synthesize a state controller. A radial artificial neural network is used to solve the problem of identifying the parameters of a vector-matrix model. The training of networks, the study of the effectiveness of their work, as well as the development of models is carried out using the tools of the MatLab software package.

Results. The authors have developed the method to select the optimal composition of measurement channels which gives the maximum signal-to-noise ratio and forming the corresponding structure of a radial artificial neural network to solve the problems of object parameters identification and control system tuning with state controller. It is proposed to use the sensitivity functions of the state coordinates of control object parameters variation to estimate power of information signals at the inputs of neural network.

Conclusions. The results of the conducted computational experiments have confirmed the effectiveness of the developed method, which makes it possible to increase the accuracy of identification and tuning of systems with state regulators under noise conditions. The obtained results can be used to ensure a given quality of control with parametric uncertainty of the object.

References in English: 

1. Anisimov, A.A., Tararykin, S.V. Strukturno-parametricheskiy sintez, optimizatsiya i nastroyka sistem upravleniya tekhnologicheskimi ob"ektami [Structural-parametric synthesis, optimization and tuning of control systems for technological objects]. Ivanovo, 2015. 296 p.

2. Anisimov, A.A., Tararykin, S.V. Avtomaticheskaya nastroyka polinomial'nykh regulyatorov elektromekhanicheskikh sistem s ispol'zovaniem iskusstvennoy neyronnoy seti [Automatic tuning of polynomial regulators of electromechanical systems using an artificial neural network]. Mekhatronika, avtomatizaciya, upravlenie, 2008, no. 8, pp. 13–18.

3. Tararykin, S.V. Strukturno-parametricheskiy sintez i tsifrovaya realizatsiya regulyatorov mekhatronnykh system [Structural-parametric synthesis and digital implementation of mechatronic system regulators]. Ivanovo, 2019. 216 p.

4. Eremenko, Yu.I., Poleshchenko, D.A., Glushchenko, A.I. Analiz metodov realizatsii skhemy neyrosetovogo upravleniya s samonastroykoy [Analysis of methods for implementing a neural network control scheme with self-tuning]. Pribory i sistemy. Upravlenie, kontrol', diagnostika, 2012, no. 6, pp. 50–55.

5. Shamigulov, P.V. Raschet parametrov nastroyki regulyatorov sistem avtomaticheskogo regulirovaniya [Calculation of tuning parameters of regulators of automatic control systems]. Pribory i sistemy. Upravlenie, kontrol', diagnostika, 2010, no. 3, pp. 22–25.

6. Osovskiy, S. Neyronnye seti dlya obrabotki informatsii [Neural networks for information processing]. Moscow: Finansy i statistika, 2002. 344 p.

7. Rutkovskaya, D., Pilin'skiy, M., Rutkovskiy, L. Neyronnye seti, geneticheskie algoritmy i nechetkie sistemy [Neural networks, genetic algorithms and fuzzy systems]. Moscow: Goryachaya liniya-Telekom, 2004. 452 p.

8. Yakh"yaeva, G.E. Nechetkie mnozhestva i neyronnye seti [Fuzzy sets and neural networks]. Moscow: BINOM. Laboratoriya znaniy, 2016. 316 p.

9. Kokotovich, P.V., Rutman, R.S. Chuvstvitel'nost' sistem avtomaticheskogo upravleniya [Sensitivity of automatic control systems]. Avtomatika i telemekhanika, 1965, no. 4, pp. 730–750.

10. Kokotovich, P.V. Metod tochek chuvstvitel'nosti v issledovanii i optimizatsii lineynykh sistem upravleniya [The method of sensitivity points in the research and optimization of linear control systems]. Avtomatika i telemekhanika, 1964, no. 1, pp. 1670–1676.

11. Rozenvasser, E.N., Yusupov, R.M. Chuvstvitel'nost' sistem avtomaticheskogo upravleniya [Sensitivity of automatic control systems]. Leningrad: Energiya, 1969. 208 p.

12. Basharin, A.V., Novikov, V.A., Sokolovskiy, G.G. Upravlenie elektroprivodami [Control of electric drives]. Leningrad: Energoizdat,1982. 392 p.

Key words in Russian: 
мехатронная система, регулятор состояния, идентификация параметров, настройка линейных систем, радиальная искусственная нейронная сеть, функции чувствительности системы
Key words in English: 
mechatronic system, state controller, parameter identification, linear system tuning, radial artificial neural network, system sensitivity functions
The DOI index: 
10.17588/2072-2672.2023.6.057-068
Downloads count: 
51