A novel recursive approach for online identification of continuous‐time switched nonlinear systems

This article focuses on the identification of switched nonlinear systems, which are characterized as a collection dynamical systems. Each subsystem is activated by discrete-valued variable (switching signal). Specifically, we consider continuous-time systems in state-space form our article. The amounts to simultaneous estimation switching signal and dynamic subsystems via all measured state-input vectors. However, problem challenging generally requires large computational complexity be solved. In this article, propose novel online approach address capable handle vectors sequence. particular, principle used for estimating developed based subspace method. Subsequently, integral concurrent learning identifier extended identify dynamics each recursively. effectiveness proposed demonstrated simulation results.