Variance and bias computation for enhanced system identificationA study is made of the use of a series of variance and bias confidence criteria recently developed for the eigensystem realization algorithm (ERA) identification technique. The criteria are shown to be very effective, not only for indicating the accuracy of the identification results (especially in terms of confidence intervals), but also for helping the ERA user to obtain better results. They help determine the best sample interval, the true system order, how much data to use and whether to introduce gaps in the data used, what dimension Hankel matrix to use, and how to limit the bias or correct for bias in the estimates.
Document ID
19900053727
Acquisition Source
Legacy CDMS
Document Type
Conference Paper
Authors
Bergmann, Martin (Columbia Univ. New York, NY, United States)
Longman, Richard W. (Columbia University New York, United States)
Juang, Jer-Nan (NASA Langley Research Center Hampton, VA, United States)