Modelling and Identification of Relatively Slowly Varying Systems.
Abstract
This thesis is concerned with the modeling and identification of a large class of nonlinear, time-varying, causal, bounded memory systems. A generic model is developed for such time-varying systems, and this model is formulated in terms of a finite set of parameters which adequately describe the unknown system mapping. Two separate models are considered for the variation in the parameters representing the unknown system. In the first, the variation is assumed to be unknown but bounded between measurement times, and in the second, the variation between measurement times is taken to be random, with known mean and covariance. In each case, two methods of processing the observations are considered.
Document Details
- Document Type
- Technical Report
- Publication Date
- Apr 01, 1975
- Accession Number
- ADA014002
Entities
People
- Philip Howard Fiske
Organizations
- University of Michigan