Abstract:

Radial Gaussian function networks based on fuzzy systems is applied to the state estimation of nonlinear time varying systems. A hierarchically structural self organizing learning method is given, and a state estimation method is proposed. The structure and characteristics of the observer are discussed. The results of estimation show that the proposed nonlinear state observer can observe real systems state satisfactorily.

Key words: sta te estimation, fuzzy neur al networ ks, Gaussian function, nonlinear syst em-time dependence