Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
11032459 | Digital Signal Processing | 2018 | 9 Pages |
Abstract
In this paper, one robust identification method is proposed for the discrete-time linear systems with unknown time-varying disturbance. The disturbance is considered as a time-varying parameter for tracking estimation. A robust recursive least squares method is proposed using a forgetting factor. Moreover a new forgetting scheme to update the covariance matrix is developed to improve the stable convergence property of the time-invariant model parameters and the tracking performance of time-varying disturbance. The convergence performance of parameter estimation is analyzed with a proof. Two examples with different types of time-varying disturbance are shown to illustrate the effectiveness and advantage of the proposed method.
Related Topics
Physical Sciences and Engineering
Computer Science
Signal Processing
Authors
Tiecheng Pu, Jing Bai,