Optimization of fuzzy PID controllers using Q-learning algorithm

• Autorzy: Boubertakh H. , Labiod S. , Tadjine M. , Glorennec P.-Y.
• Języki publikacji: EN

Abstrakty

EN

In this article, we first chose the design settings of the fuzzy PID controllers (FPIDC) so that the FPIDCs mimic the classical PID controllers. The advantage of these controllers is the combination of the simplicity of the classical PID controllers and the interpretability of fuzzy controllers which makes the task of parameters tuning easier. Secondly, we present a method for optimizing the closed-loop system consisting of a FPIDC and an unknown plant using the Q-learning algorithm (QLA). Specifically, QLA minimizes a cost function which quantifies the performance of FPIDC. Without loss of generality the square error sum cost function is used. The QLA, which is a nonmodel-based method, iteratively search of the best parameters so that the output of the cost function is less then satisfaction threshold. Finally, a simulation example is used to prove the effectiveness of the proposed method.

Słowa kluczowe

EN

fuzzy PID controllers; classical PID controllers; akagi-Sugeno fuzzy systems; Q-learning

• Wydawca: Polish Academy of Sciences, Committee of Automatic Control and Robotics
• Czasopismo: Archives of Control Sciences
• Rocznik: 2008
• Tom: Vol. 18, no. 4
• Strony: 415--435
• Opis fizyczny: Bibliogr. 21 poz.

Twórcy

autor

Boubertakh H.

autor

Labiod S.

autor

Tadjine M.

autor

Glorennec P.-Y.

• LAMEL, Faculte des Sciences de l'Ingnieur, University of Jijel, Jijel, Algeria,

Bibliografia

• [1] J. M. ADAMS and K. S. RATTAN: A genetic multi-stage fuzzy PID controller with a fuzzy switch. Proc. IEEE Mt. Conf. on Systems, Man, and Cybernetics, Tucson, AZ, USA, 4 (2001), 2239-2244,
• [2] K. J. ASTROM and T. HAGGLUND: PID controllers, theory, design and tuning. Instrument Society of America, Research Triangle Park, North Carolina, 1995.
• [3] H. BOUBERTAKH and P. Y. GLORENNEC: Optimization of a fuzzy PI controller using reinforcement learning. Proc. IEEE Int. Conf on Information and Communication Technologies: From Theory to Applications, Damascus, (2006), 1657- 1662.
• [4] H.-Y. CHUNG, B.-C. CHEN and J.-J. LIN: A PI-type fuzzy controller with selftuning scaling factors. Fuzzy Sets and Systems, 93 (1998), 23-28.
• [5] Y. DING, H. YING and S. SHAO: Typical Takagi-Sugeno PI and PD fuzzy controllers: analytical structures and stability analysis. Fuzzy Sets and Systems, 151 (2003), 245-262.
• [6] H.-B. DUAN, D.-B WANG and X.-F. Yu: Novel approach to nonlinear PID parameter optimization using Ant Colony optimization algorithm. J. of Bionic Engineering, 3 (2006), 73-78.
• [7] J. JANTZEN: Foundations of fuzzy control. West Sussex (England), John Wiley &Sons Ltd, 2007.
• [8] C.-N. Ko, T.-L. LEE, H.-T. FAN and C.-J. Wu: Genetic auto-tuning and rule reduction of fuzzy PID controllers. Proc. IEEE Mt. Conf on Systems. Man, and Cybernetics, Taipei, Taiwan, (2006), 1096-1101.
• [9] B. M. MOHAN and AMBALAL V. PATEL: Analytical structures and analysis of the simplest fuzzy PD controllers. IEEE Trans. Systems, Man, and Cybernetics, Part B: Cybernetics, 32 (2002), 239-248.
• [10] B. M. MOHAN and A. SINHA: Analytical structure and stability analysis of a fuzzy PID controller. Applied Soft Computing, 8 (2008), 749-758.
• [11] B. S. MOON: Equivalence between fuzzy logic controllers and PI controllers for single input systems. Fuzzy Sets and Systems, 69 (1995), 105-113.
• [12] M. MUZIMUTO: Realization of PID controls by fuzzy control methods. Fuzzy Sets and Systems, 105 (1995), 171-182.
• [13] R. S. SUTTON and A. G. BARTO: Reinforcement learning: An introduction. Bradford Books. MIT Press, Cambridge, Mass., 1998.
• [14] K. S. TANG, K. M. MAN and G. CHEN: A G-A optimized fuzzy PD+I controller for nonlinear systems. Proc. Int. Conf on Industrial Electronics, Control, and Instrumentation, Denver, USA, (2001), 718-723.
• [15] K. S. TANG, K. M. MAN and G. CHEN: An optimal fuzzy PID controller. IEEE Trans. Industrial electronics, 48 (2001), 757-765.
• [16] H. A. VAROL and Z. BINGUL: A new PID tuning technique using Ant algorithm. Proc. American Control Conf, Boston, Massachusetts, USA, (2004), 2154-2159.
• [17] C. J. C. H. WATKINS: Learning from delayed rewards. PhD Thesis, University of Cambridge, England, 1989.
• [18] C. J. C. H. WATKINS and P. DAYAN: Technical note, Q-learning. Machine Learning, 8 (1992), 279-292.
• [19] C.-J. Wu, T.-L. LEE, Y.-Y. Fu and L.-C. LAI: Auto-tuning fuzzy PID control of a pendubot system. Proc. 4th IEEE Int. Conf. on Mechatronics, Kumamoto, Japan, (2007), 1-6.
• [20] R. R. YAGER and D. P. FILEV: Essential of fuzzy modeling and control. John Wiley & Sons Inc., 1994.
• [21] L. ZHENG and CO. YAMATAKE-HONEYWELL: A practical guide to tune of proportional and integral (PI) like fuzzy controllers. Proc. IEEE Mt. Conf. on Fuzzy Systems, San Diego, CA, USA, (1992), 633-640