Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
559318 | Digital Signal Processing | 2015 | 11 Pages |
Abstract
The identification of nonlinear systems is a hot topic in the identification fields. In this paper, a data filtering based multi-innovation stochastic gradient algorithm is derived for Hammerstein nonlinear controlled autoregressive moving average systems by adopting the key-term separation principle and the data filtering technique. The proposed algorithm provides a reference to improve the identification accuracy of the nonlinear systems with colored noise. The simulation results show that the new algorithm can more effectively estimate the parameters of the Hammerstein nonlinear systems than the multi-innovation stochastic gradient algorithm.
Related Topics
Physical Sciences and Engineering
Computer Science
Signal Processing
Authors
Yawen Mao, Feng Ding,