On Weighting in State-Space Subspace System Identification
1995 (English)In: Proc. European Control Conference, ECC95, 1995, 435-440 p.Conference paper (Refereed)
The aim of this contribution is to analyze a class of state-space subspace system identification (4SID) methods. In particular, the effect of different weighting matrices is studied. By a linear regression formulation, different cost-functions, which are rather implicit in the ordinary framework of 4SID, are compared. Expressions for asymptotic variances of pole estimation error are analyzed and from these expressions, some difficulties in choosing user specified parameters are pointed out. Another interesting result obtained is that a row weighting in the subspace estimation step does not affect the pole estimation error, asymptotically. This result holds for two different pole estimation methods, namely the shift invariance method and an optimally weighted least-squares method. In a numerical example, relative efficiency of the optimally weighted pole estimation method is indicated.
Place, publisher, year, edition, pages
1995. 435-440 p.
system identification, Parameter estimation, subspace methods, performance analysis
IdentifiersURN: urn:nbn:se:kth:diva-86534OAI: oai:DiVA.org:kth-86534DiVA: diva2:500807
Proc. European Control Conference, Roma, Italy, Sep. 1995
NR 201408052012-02-132012-02-132013-09-05Bibliographically approved