Title :
Analysis and application of minimum variance discrete linear system identification
Author :
Kotob, S. ; Kaufman, H.
Author_Institution :
Computer Sciences Corporation, Falls Church, VA, USA
fDate :
10/1/1977 12:00:00 AM
Abstract :
An on-line minimum variance (MV) parameter identifier is developed which embodies both accuracy and computational efficiency. The formulation results in a linear estimation problem with both additive and multiplicative noise (AMN). The resulting filter which utilizes both the covariance of the parameter vector itself and the covariance of the error in identification is proven to be mean-square convergent and mean-square consistent. The MV parameter identification scheme is then used to construct a stable state and parameter estimation algorithm.
Keywords :
Adaptive control; Linear systems, time-invariant discrete-time; Parameter identification; Adaptive control; Additive noise; Analysis of variance; Control systems; Covariance matrix; Linear systems; Noise measurement; Nonlinear filters; Parameter estimation; State estimation;
Journal_Title :
Automatic Control, IEEE Transactions on
DOI :
10.1109/TAC.1977.1101613