Identification method for nonlinear dynamic system using Wiener neural network
非线性动态系统的Wiener神经网络辨识法

A novelWiener neural network structure is presented and applied to nonlinear dynamic system identification. Firstly, the nonlinear dynamic system is described by a Wiener model which consists of a linear dynamic part in cascade with a nonlinear static gain. Secondly, a novel neural network structure is designed, the weights in which are corresponding with the parameters of the Wiener model. Thirdly, backward-propagation methods for the adjustment of weights in the network are discussed. Finally, parameters of the linear dynamic part and the nonlinear static gain in the Wiener model are determined simultaneously by iterative training. A numerical simulation of Wiener model is provided to validate the effectiveness. Simulation results show that the suggested identification schemes are practically feasible.