Dynamic wavelet neural network for nonlinear dynamic system identification

A dynamic neural network with a hidden layer that consists of wavelets for nonlinear dynamic system identification is presented. In order to model the dynamics of nonlinear dynamic systems, the external auto-regressive connection is introduced into the wavelet based neural network. For fast training of the wavelet neural network, a PID backpropagation algorithm is proposed. The procedure of using a wavelet neural network for modeling is described in detail in the article. Finally, an example for identification of a continuous-stirred-tank-reactor is given