Advances in Filtering Techniques for Stochastic Systems with Uncertain Parameters. Part I.
Abstract
Optimum estimation of the states of linear dynamic processes using noise corrupted measurements, commonly referred to as Kalman filtering, requires an exact knowledge of the equations which govern the complete stochastic system. In practical applications, however, these equations depend on parameters which can not be precisely defined. When the parameter uncertainties are sufficiently large, standard filtering techniques can produce inaccurate and inadequate estimates. In this dissertation, two alternative techniques of state estimation for systems with uncertain parameters are considered.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jan 01, 1978
- Accession Number
- ADA054396
Entities
People
- Calvin Chris Schneider Jr
Organizations
- University of California, Los Angeles