Research on Time-varying RBF NN and Its Application

Abstract

The problem of how to approximate unknown time-varying nonlinear functions is researched in this paper. Firstly, a new RBF NN with time-varying weight is proposed to approximate the unknown time-varying nonlinear function. Secondly, the approximate theorem of the proposed time-varying RBF NN is obtained. Accordingly, a conclusion can be drawn that a continuous time-varying nonlinear function defined on finite time interval [0, T] can be approximated by at least a piecewise continuous time-varying weight vector and a finite number of RBF neurons. Finally, simulation examples are given to validate the effectiveness of proposed time-varying RBF NN.