A mean-based adaptive fuzzy control scheme with state estimation performance is proposed for a class of uncertain nonlinear systems in the presence of only output measurement. In the control scheme, a mean-based fuzzy identifier without prior knowledge of membership functions is merged into direct adaptive controller with a linear state estimator. The structure of the mean-based fuzzy identifier is nonlinear in the adjusted parameters in order to diminish the unfavorable influence of initially designing membership functions on control performance. For the nonlinear structure, a mean method is used to derive adaptive laws. Compared with conventional methods, the advantage of the mean method is that the computation burden can be effectively alleviated because finding the derivative of fuzzy systems is not required. In addition, for the linear state estimator, the state estimation performance with beforehand given attenuation parameter is established by the design of a compensative controller. Finally, two examples are provided to demonstrate the applicability of the proposed scheme.
ASJC Scopus subject areas
- Artificial Intelligence