Abstract | ||
---|---|---|
Using vector orthogonal polynomials as basis func- tions for the representation of the rational form of a linear time invariant system, in frequency domain identification problems, it is shown that the notorious numerical ill conditioning of these maximum likelihood problems can be overcome completely. For the identification of high order (100/100) systems operating over a wide frequency band, or even in the situation of over- or undermodelling, condition numbers less than 10 are reported for real measurements. |
Year | DOI | Venue |
---|---|---|
2005 | 10.1109/TAC.2005.858651 | IEEE Trans. Automat. Contr. |
Keywords | Field | DocType |
Robustness,Transfer functions,Frequency domain analysis,Polynomials,Frequency measurement,Frequency estimation,Equations,Vectors,Maximum likelihood estimation,Frequency response | Frequency domain,Mathematical optimization,Orthogonal functions,Linear system,Linear form,Orthogonal polynomials,Frequency band,Basis function,System identification,Mathematics | Journal |
Volume | Issue | ISSN |
50 | 11 | 0018-9286 |
Citations | PageRank | References |
5 | 0.57 | 7 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
A. Bultheel | 1 | 117 | 17.02 |
M. Van Barel | 2 | 47 | 6.56 |
Yves Rolain | 3 | 209 | 37.68 |
Rik Pintelon | 4 | 1011 | 163.45 |