System Identification by the ORSE technique with a Finite Number of Data Samples

This paper discusses application of Observability Range Space Extraction identification technique when only a finite number of data samples are available for identification. This is a suboptimal technique which directly identifies a state space model from time domain data. Due to its high accuracy in system eigenvalue estimation and numerical stability in multiple input, multiple output, and high dimensional system identification, this technique is successfully applied in model identification for active structure control problems. The MIT Middeck Active Control Experiment is used as an application example in this paper. This is an active structure control experiment to be conducted is space shuttle middeck.