Adaptive Observer for MIMO Linear Time Varying Systems
Résumé
The purpose of adaptive observer is to perform joint state-parameter estimatio- nof parameterized state space system. In this paper, we propose a new approach to adaptive observer design for multi-input-multi-output (MIMO) linear time varying (LTV) or state-affine systems. It is conceptually simple and computationally efficient. In the case of noise free system with constant unknown parameters, global exponential convergence for joint state-parameter estimation is established. In the presence of noises, it is proved that the estimation errors are bounded and converge in the mean to zero if the noises are bounded and have zero means. We also present a unified formulation for some known adaptive observers based on dynamic transformations. This general framework enhances the conceptual simplicity of the proposed approach. Potential applications of the adaptive observer are on-line continuous-time system identification, fault detection and isolation, and adaptive control. Two numerical examples are presented to illustrate the performance of the proposed adaptive observer.