Identification of a Class of Multi-signal Based Neuro-fuzzy Wiener Systems

A novel multi-signal based identification approach is presented for the neuro-fuzzy Wiener model with process noise. A combined multi-signal composed of two random signals of different amplitude is adopted to solve the identification problem of the nonlinear block separated from the linear part. Then the least square method is employed to identify the nonlinearity of the Wiener model. Next, the linear parameters of the Wiener model are obtained by using the recursive least square method based on auxiliary model. Finally, an example is used to verify the effectiveness of the proposed method.