Interval Technique for Parameter Estimation under Model Uncertainty

Authors:	Polyak Boris, Institute for Control Science, Russian Federation Nazin Sergey, Institute for Control Science, Russian Federation
Topic:	2.1 Control Design
Session:	Control and Estimation Under Set-Membership Uncertainty - II
Keywords:	bounded noise, intervals, linear equations, parameter estimation, uncertain linear systems, uncertainty.

Abstract

This paper is devoted to the problem of estimation of parameters for linear multi-output models with uncertain regressors and additive noise. The uncertainty is assumed to be described by intervals. Outer-bounding interval approximations of the non-convex feasible parameter set for uncertain system are obtained. The proposed method is based on the calculation of the interval solution for an interval system of linear algebraic equations and provides the parameter estimators for models with large number of measurements.