×

zbMATH — the first resource for mathematics

The Frisch scheme in dynamic system identification. (English) Zbl 0714.93058
Summary: The use of the Frish scheme in the identification of linear dynamic systems is investigated in order to describe the whole family of models that can explain given input-output noisy sequences. Unlike the algebraic case, it is shown that, in general, only a single model is compatible with the data. These results are first proposed for single-input single- output systems and then generalized to the multivariable case.

MSC:
93E12 Identification in stochastic control theory
93B30 System identification
93C55 Discrete-time control/observation systems
62M10 Time series, auto-correlation, regression, etc. in statistics (GARCH)
PDF BibTeX XML Cite
Full Text: DOI
References:
[1] Beghelli, S.; Guidorzi, R.P., Transformation between input-output multistructural models: properties and applications, Int. J. control, 37, 6, 1385-1400, (1983) · Zbl 0541.93009
[2] De Moor, B.; Vandewalle, J., A geometric approach to the maximal corank problem in the analysis of linear relations, (), 1900-1995
[3] De Moor, B.; Vandewalle, J., The uniqueness versus the non-uniqueness principle in the identification of linear relations from noisy data, (), 1663-1665
[4] Guidorzi, R.P., Invariants and canonical forms for systems structural and parametric identification, Automatica, 17, 117-133, (1981) · Zbl 0451.93027
[5] Guidorzi, R.P.; Beghelli, S., Input-output multistructural models in multivariable systems identification, (), 461-465 · Zbl 0541.93009
[6] Kalman, R.E., Identification from real data, (), 161-196
[7] Kalman, R.E., System identification from noisy data, (), 135-164
[8] Kalman, R.E., Identification of noisy systems, () · Zbl 0608.93068
[9] Satake, I., ()
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.