DocumentCode :
1631058
Title :
Switching fuzzy model construction based on optimal dividing planes
Author :
Ohtake, Hiroshi ; Tanaka, Kazuo ; Wang, Hua O.
Author_Institution :
Dept. of Mech. Eng. & Intell. Syst., Univ. of Electro-Commun., Chofu, Japan
fYear :
2009
Firstpage :
808
Lastpage :
813
Abstract :
This paper presents switching fuzzy model construction based on optimal dividing planes. In our previous papers, we proposed the switching fuzzy model with arbitrary dividing planes. However, dividing planes have been selected by controller designers before constructing the switching fuzzy model. Unfortunately, it is difficult to find suitable dividing planes for complicated nonlinear systems. Moreover, the switching fuzzy models constructed from different dividing planes are different. Therefore, the model construction affects the stability analysis results. In this paper, we propose switching fuzzy model construction method using multi-dimensional sector nonlinearity concept based on optimal dividing planes. The linear consequent parts of the switching fuzzy model based on optimal dividing planes are constructed from sectors which have minimum distance between a nonlinear system and sectors, and have richer information of the nonlinear system than the consequent parts of the ordinary Takagi-Sugeno fuzzy model. Two examples are provided to illustrate the validity of this approach.
Keywords :
control nonlinearities; control system synthesis; fuzzy control; nonlinear control systems; optimal control; stability; time-varying systems; controller design; multidimensional sector nonlinearity; nonlinear systems; optimal dividing planes; stability analysis; switching fuzzy model; Control theory; Fires; Fuzzy control; Fuzzy systems; Linear systems; Nonlinear systems; Optimal control; Stability analysis; State-space methods; Takagi-Sugeno model;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Fuzzy Systems, 2009. FUZZ-IEEE 2009. IEEE International Conference on
Conference_Location :
Jeju Island
ISSN :
1098-7584
Print_ISBN :
978-1-4244-3596-8
Electronic_ISBN :
1098-7584
Type :
conf
DOI :
10.1109/FUZZY.2009.5277398
Filename :
5277398
Link To Document :
بازگشت