On real and observable rational realizations of input-output equations
Sebastian Falkensteiner, Dmitrii Pavlov, Rafael Sendra
TL;DR
The paper tackles the problem of reconstructing rational state-space realizations from a single IO-equation $F$ for single-output rational systems, with a focus on real coefficients and observability. It develops an algebraic-differential framework linking IO-equations to hypersurfaces $ abla(F)$ and leverages proper parametrizations to study observability, proving equivalence between realizability and observable realizability for first-order IO-equations. The authors provide algorithmic methods to compute observable and real realizations (ObservableRealization and RealRealization) and obtain partial results for higher-order IO-equations, illustrating the approach with examples. This work enables a systematic, algebraic route to derive real and observable rational dynamical systems from IO data, with implications for identifiability and observability in control theory.
Abstract
Given a single (differential-algebraic) input-output equation, we present a method for finding different representations of the associated system in the form of rational realizations; these are dynamical systems with rational right-hand sides. It has been shown that in the case where the input-output equation is of order one, rational realizations can be computed, if they exist. In this work, we focus first on the existence and actual computation of the so-called observable rational realizations, and secondly on rational realizations with real coefficients. The study of observable realizations allows to find every rational realization of a given first order input-output equation, and the necessary field extensions in this process. We show that for first order input-output equations the existence of a rational realization is equivalent to the existence of an observable rational realization. Moreover, we give a criterion to decide the existence of real rational realizations. The computation of observable and real realizations of first order input-output equations is fully algorithmic. We also present partial results for the case of higher order input-output equations.
