Identyfikacja prostych modeli dynamiki poprzez iterowany algorytm genetycznymodelowanie

• Autorzy: Hoczek T.

Warianty tytułu

EN

Identification of simple dynamics models by iterated genetic algorithm

• Języki publikacji: PL

Abstrakty

PL

W niniejszym artykule zaproponowano metodę identyfikacji opartą na iterowanym algorytmie genetycznym dla systemów FOPDT (First Order Plus Dead Time) oraz SOPDT (Second Order Plus Dead Time), w których występują zakłócenia o znacznej amplitudzie. Zbadano również wpływ poziomu zakłóceń na dokładność identyfikacji systemu.

EN

An iterated genetic algorithm for identification of FOPDT (First Order Plus Dead Time) and SOPDT (Second Order Plus Dead Time) models is proposed in the paper. It is designed for high noise/signal ratio systems. The method proposed requires a little knowledge about the identified system, including determination of search space borders. It may be also used for approximation of higher order systems by FOPDT or SOPDT models. The identification results were compared with those obtained from other methods, such as the traditional "two point" method and modern MatlabŽ ident(.) tool. Additionally, the impact of interference/ noise level on the model identification accuracy was analyzed. The identified model can be used for tuning PID regulators or can be implemented in more advanced control schemas e.g. Smith predictor or MPC. System identification with use of a genetic algorithm offers numerous advantages and may be implemented as an efficient alternative to classical methods, especially when the interference level is high.

Słowa kluczowe

PL

FOPDT; SOPDT; algorytmy genetyczne; identyfikacja; modelowanie

EN

SOPDT; FOPDT; genetic algorithm; system identification

• Wydawca: Wydawnictwo PAK
• Czasopismo: Pomiary Automatyka Kontrola
• Rocznik: 2012
• Tom: R. 58, nr 10
• Strony: 850--853
• Opis fizyczny: bibliogr. 16 poz., rys., tab., wzory

Twórcy

autor

Hoczek T.

• Politechnika sląska, Wydział Automatyki Elektroniki i Informatyki, ul. Akademicka 16, 44-100 Gliwice,

Bibliografia

• [1] Ziegler J. G. and Nichols N. B.: Optimum settings for automatic controllers, Transactions of the ASME 64:759-768 (1942).
• [2] Astrom K. J. and Eykohoff P.: System Identyfication - A Survey. Automatica, 7:123-162 (1971).
• [3] Sundaresan K. R., Prasad C. C. and Krishnaswamy P .R.: Evaluating parameters from process transients, Industrial and Engineering Chemistry Process Design and Development, 17:237-241(1978).
• [4] Sundaresan K. R. and Krishnaswamy P. R.: Estimation of time delay, time constant parameters in time, frequency and Laplace domains, The Canadian Journal of Chemical Engineering, 56:257-262 (1978).
• [5] Huang C. T. and Clements W. C.: Parameter estimation for the second-order plus deadtime-model, Industrial Engineering Chemistry Process Design andDevelopment, 21:601-603 (1982).
• [6] Goldberg D. E.: Genetic Algorithms in Search, Optimization, and Machine Learning. Addison-Wesley (1989).
• [7] Vladu E.: Using Genetic Algorithms in System Identification. Electrical Engineering 496:85-89 (1991).
• [8] Astrom K. J. and Hagglund T.: PID Controllers: Theory, Design and Tuning (Second Edition, Instrument Society of America) (1995).
• [9] Bi Q., Cai W. J., Lee E. L., Wang Q. G., Hang C. C. And Zhang Y.: Robust identification of first-order plus dead-time model from step response, Control Engineering Practice, 7,1:71-77(1999).
• [10] Wierzchon S. T.: Sztuczne systemy immunologiczne. Teoria i zastosowania (2001).
• [11] Kealy Tony and O'dwyer Aidan : Comparison of open and closed loop process identification techniques in the time domain. Proceedings of the 3nd Wismarer Automatisierungssymposium, 1.3-4 (2001).
• [12] Ueda T., Ono I., Okamoto M.: Development of System Identication Technique Based on Real-Coded Genetic Algorithm. Genome Informatics 13: 387 (2002).
• [13] Vu Duong and Stubberud A.: System Identification by Genetic Algorithm. Aerospace Conference Proceedings 5:5-14 (2002).
• [14] Ljung L.: Identification for Control: Simple Process Models. LiTH-ISY-R-2465, (2003).
• [15] Sekaj I.: Genetic Algorithms for Control System Design Applications. Journal of Cybernetics and Informatics, 1:31-37 (2003).
• [16] Rao G. P. and Unbehauen H.: Identification of continuous-time systems. Electrical Engineering, 153:185-220 (2006).Shin G.W.: Genetic Algorithm for Identification of Time Delay Systems from Step Responses, International Journal of Control, Automation and Systems, 5:79-85, (2007).