The identification of reduced-order models from high-dimensional data is achallenging task, and even more so if the identified system should not only besuitable for a certain data set, but generally approximate the input-outputbehavior of the data source. In this work, we consider the input-output dynamicmode decomposition method for system identification. We compare excitationapproaches for the data-driven identification process and describe anoptimization-based stabilization strategy for the identified systems.
展开▼
