Title :
A Fast Parameter Tracking RLS Algorithm with High Noise Immunity
Author :
Jiang, J. ; Cook, R.
Author_Institution :
Department of Electrical Engineering, University of Western Ontario, London, Ontario, N6A 5B9, CANADA
Abstract :
A Recursive Least Squares (RLS) based fast parameter tracking algorithm with high noise immunity is proposed. The fast parameter tracking capability of the algorithm is achieved by perturbing the covariance matrix update equation whenever the signal model parameters change. Since the perturbing term depends on the auto- and cross-correlations of the signal and algorithm outputs, the proposed algorithm is very robust with respect to noise. The efficiency of the algorithm has been verified by Monte Carlo simulations.
Keywords :
Coaxial components; Covariance matrix; Monte Carlo methods; Noise level; Noise reduction; Recursive estimation; Resonance light scattering; Tellurium; Variable speed drives; White noise;
Conference_Titel :
American Control Conference, 1993
Conference_Location :
San Francisco, CA, USA
Print_ISBN :
0-7803-0860-3