CONSTRAINED RECURSIVE PARAMETER ESTIMATION FOR ADAPTIVE CONTROL

In adaptive control of systems with poles close to the unit circle, application of recursive estimation techniques can lead to excursions of poles outside the unit circle even when the process has no unstable poles. In this work, we propose a novel constrained formulation for recursive estimation of parameters using pseudo linear regression approach. The Jury's stability criterion is used to impose constraints in the parameter space. The proposed strategy has considerable computational advantage when compared to moving window constrained estimation . We demonstrate the efficacy of the proposed method using experimental data collected from a laboratory heater-mixer setup.