Finite-dimensional output stabilization for a class of linear distributed parameter systems -- a small-gain approach

Abstract

A small-gain approach is proposed to analyze closed-loop stability of linear diffusion-reaction systems under finite-dimensional observer-based state feedback control. For this, the decomposition of the infinite-dimensional system into a finite-dimensional slow subsystem used for design and an infinite-dimensional residual fast subsystem is considered. The effect of observer spillover in terms of a particular (dynamic) interconnection of the subsystems is thoroughly analyzed for in-domain and boundary control as well as sensing. This leads to the application of a small-gain theorem for interconnected systems based on input-to-output stability and unbounded observability properties. Moreover, an approach is presented for the computation of the required dimension of the slow subsystem used for controller design. Simulation scenarios for both scalar and coupled linear diffusion-reaction systems are used to underline the theoretical assessment and to give insight into the resulting properties of the interconnected systems.