Identification of nonlinear nonautonomous state space systems from input-output measurements

Abstract

This paper presents a method to determine a nonlinear state-space model from a finite number of measurements of the inputs and outputs. The method is based on embedding theory for nonlinear systems, and can be viewed as an extension of the subspace identification method for linear systems. The paper describes the underlying theory and provides some guidelines for using the method in practice. To illustrate the use of the identification method, it was applied to a second-order nonlinear system.