• To understand the basic system identification process, which involves a combination of model selection, data analysis, and noise assumptions.

• To acquire a knowledge of several system identification techniques, and to understand when each method is applicable.

• To understand the effect of the model, noise, and system identification on the estimated model, that is, to understand the effects of the assumptions used to obtain a model estimate.

• Typical model structures used in system identification: state-space, polynomial matrix, impulse response, and frequency domain models.

• Model properties: controllability, observability, reachability, and linearity.

• Requirements for the identifiability of a model, specifically, persistency.

• Regression and least-squares analysis for linear-in-the-parameters models.

• Consistency of estimated models and other useful statistical properties.

• Parameter estimation methods such as instrumental variable methods.

i.d.R. Bearbeitung von Übungsaufgaben und Fachgespräch oder mündliche Prüfung

• C. T. Chen, “Linear System Theory and Design”, 3rd ed. New York: Oxford University Press, 1999.

• M. Verhaegen and V. Verdult, “Filtering and System Identification: A Least Squares Approach”, 1st ed. New York: Cambridge University Press, 2007.

• L. Ljung, “System Identification: Theory for the User”, 3rd ed. Upper Saddle River, NJ: Prentice-Hall, 1999.

• R. Pintelon and J. Schoukens, “System Identification: A Frequency Domain Approach”, 1st ed. New York: Wiley-IEEE Press, 2001.