Chaotic System Identification Based on a Fuzzy Wiener Model with Particle Swarm Optimization
LI Yong1, TANG Ying-Gan2
1Key Laboratory of Network Control and Intelligent Instrument (Ministry of Education), Chongqing University of Posts and Telecommunications, Chongqing 400065 2Institute of Electrical Engineering, Yanshan University, Qinhuangdao 066004
Chaotic System Identification Based on a Fuzzy Wiener Model with Particle Swarm Optimization
LI Yong1, TANG Ying-Gan2
1Key Laboratory of Network Control and Intelligent Instrument (Ministry of Education), Chongqing University of Posts and Telecommunications, Chongqing 400065 2Institute of Electrical Engineering, Yanshan University, Qinhuangdao 066004
A fuzzy Wiener model is proposed to identify chaotic systems. The proposed fuzzy Wiener model consists of two parts, one is a linear dynamic subsystem and the other is a static nonlinear part, which is represented by the Takagi-Sugeno fuzzy model. Identification of chaotic systems is converted to find optimal parameters of the fuzzy Wiener model by minimizing the state error between the original chaotic system and the fuzzy Wiener model. Particle swarm optimization algorithm, a global optimizer, is used to search the optimal parameter of the fuzzy Wiener model. The proposed method can identify the parameters of the linear part and nonlinear part simultaneously. Numerical simulations for Henón and Lozi chaotic system identification show the effectiveness of the proposed method.
A fuzzy Wiener model is proposed to identify chaotic systems. The proposed fuzzy Wiener model consists of two parts, one is a linear dynamic subsystem and the other is a static nonlinear part, which is represented by the Takagi-Sugeno fuzzy model. Identification of chaotic systems is converted to find optimal parameters of the fuzzy Wiener model by minimizing the state error between the original chaotic system and the fuzzy Wiener model. Particle swarm optimization algorithm, a global optimizer, is used to search the optimal parameter of the fuzzy Wiener model. The proposed method can identify the parameters of the linear part and nonlinear part simultaneously. Numerical simulations for Henón and Lozi chaotic system identification show the effectiveness of the proposed method.
LI Yong;TANG Ying-Gan. Chaotic System Identification Based on a Fuzzy Wiener Model with Particle Swarm Optimization[J]. 中国物理快报, 2010, 27(9): 90503-090503.
LI Yong, TANG Ying-Gan. Chaotic System Identification Based on a Fuzzy Wiener Model with Particle Swarm Optimization. Chin. Phys. Lett., 2010, 27(9): 90503-090503.
[1] Chen G and Dong X 1998 From Chaos to Order (Singapore: World Scientific) [2] Lin S L and Tung P C 2009 Chaos Solitons Fractals 42 3234 [3] Barrett M D 1996 Phyica D 91 340 [4] Gao J H and Zheng Z G 2007 Chin. Phys. Lett. 24 359 [5] Sun F Y 2006 Chin. Phys. Lett. 23 32 [6] Yau H T and Shieh C S 2008 Nonlinear Analysis: Real World Applications 9 1800 [7] Guan X P, Peng H P, Li L X and Wang Y Q 2001 Acta. Phys. Sin. 50 26 (in Chinese) [8] Parlitz U 1996 Phys. Rev. Lett. 76 1232 [9] Tang Y G and Guan X P 2009 Chaos Solitons Fractals 40 1391 [10] Chen G R, Chen Y and Ogmen H 1997 IEEE Control Systems Mag. 17 29 [11] Ming X, Chen G R and Tian Y T 2001 Mathematical and Computer Modeling 33 483 [12] Yeh J P 2007 Chaos Solitons Fractals 32 1178 [13] Takagi T and Sugeno M 1985 IEEE Trans. Systems, Man and Cybernetics 15 116 [14] Kennedy J, Eberhart R C and Shi Y 2001 Swarm Intelligence (San Francisco, CA: Morgan Kaufman) [15] Rosenstein M T T, Collins J J and Luca C J D 1993 Physica D 65 117
2010, Vol. 27 
