Identification of a class of nonlinear systems by a continuous-time recurrent neurofuzzy network

In this paper we present a new continuous-time recurrent neurofuzzy network structure for modeling and identification of a class of nonlinear systems, using a training algorithm motivated from previous works in adaptive observers. Using only output measurements and the knowledge of an excitation input signal, the proposed network is trained by generating estimates of an ideal network and jointly identifying its parameters. The objective is to make the network to dynamically behave as the plant. The stability of the network and the convergence of the training algorithm are established based on the Lyapunov stability theory. Two numerical examples and an experimental result are included to demonstrate the effectiveness of the proposed method.