Analysis and application of minimum variance discrete time system identificationAn on-line minimum variance 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. 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.
Document ID
19770045990
Acquisition Source
Legacy CDMS
Document Type
Conference Proceedings
Authors
Kotob, S. (Computer Sciences Corp. Falls Church, Va., United States)
Kaufman, H. (Rensselaer Polytechnic Institute, Troy, N.Y., United States)