DESIGN AND APPROXIMATION CAPABILITIES ANALYSIS OF TIME-VARIANT FUZZY SYSTEMS

In this paper, the design and analysis for a class of time-variant fuzzy systems are investigated. Firstly, a novel modeling method for time-variant fuzzy system, called variable weighted interpolating modeling (VWIM)method is proposed. It is pointed out that the time-variant fuzzy systems constructed by VWIM method can be represented by some interpolation functions. Then, VWIM method is applied to the nonlinear dynamic systems modeling. It is proved that time-variant fuzzy systems based on VWIM method are universal approximators to a class of nonlinear systems. And, the approximation error bounds for various classes of time-variant fuzzy systems are established. Finally, a simulation example is provided to demonstrate how to utilize a time-variant fuzzy system to approximate a given nonlinear system with arbitrary precision.