Input Design for Identification in Connected Systems
Input design is of essential importance in system identification to provide sufficient probing capabilities to guarantee the convergence of parameter estimators to their true values; namely, the estimators are consistent. Input conditions for consistent estimation depend on sensor characteristics, system configurations, noise locations and distributions, and identification algorithms. The previous chapters consider only the basic formulation in which the input u k can be directly designed. This chapter covers input design in more general system configurations.
KeywordsMeasurement Noise Discrete Fourier Transform Full Rank Input Noise Toeplitz Matrice
Unable to display preview. Download preview PDF.