Parametric CARMA model identification based on WTLMS algorithm
Nannan Zhao, Xinyu Ouyang · 2009
The wavelet transform domain least mean square (WTLMS) is known to have, in general, a fast convergence rate than the LMS algorithm. However, the previous papers used to identify the parameters of the CMA model with the WTLMS algorithm. In this work, a method of parametric CARMA model identification based on WTLMS algorithm is proposed, and its convergence analyses is also given. The proposed method realizes the parametric identification of CARMA model and improves greatly the precision of identification. The simulation results show the effectiveness of the proposed method.