Hierarchical Maximum Likelihood Stochastic Gradient Identification Algorithm for Feedback Nonlinear Systems Using the Data Filtering Technique

This paper considers the parameter identification of feedback nonlinear systems with colored noise. The difficulty of the identification is that it need to estimate the parameters of the forward path subsystem and the feedback subsystem. According to the data filtering technique and the hierarchical identification principle, a hierarchical maximum likelihood forgetting factor stochastic gradient identification algorithm based on the filtered model is presented for the discussed feedback nonlinear systems. The simulation results show the effective of the proposed algorithm.