A SISO neuro-fuzzy wiener model identification by correlation analysis method

A novel identification algorithm is presented in this paper for neuro-fuzzy based single-input-single-output (SISO) Wiener model with colored noises. The independent identical distribution (iid) Gaussian random signals are adopted to identify the Wiener system, leading to the separation of linear part from nonlinear counterpart in the identification problem. Therefore, correlation analysis method can be used for the identification of the linear part. Moreover, least-squares-based parameter identification algorithm that can avoid the impact of colored noise is proposed to identify the static nonlinear part. Lastly, an example is used to verify the effectiveness of the proposed method.