Wiener-Type Neural Network for Nonlinear System Identification

Jinzhu Peng and Rickey Dubay


Neural network, System identification, Wiener model, Nonlinear system


A Wiener-type neural network (WNN) is derived to formulate the well-known Wiener model, which has been popularly applied to identify the nonlinear systems. The WNN consists of a linear dynamic part in cascade with a nonlinear static gain. The Lipschitz criterion for order determination and back-propagation algorithm for updating the network weights are presented. Simulation results show that WNN identification approach has better performance than other similar neural networks.

Important Links:

Go Back