Structural identification and software package for linear multivariable systems

✍ Scribed by Katsuhisa Furuta; Shoshiro Hatakeyama; Hidetaka Kominami

• Publisher: Elsevier Science
• Year: 1981
• Tongue: English
• Weight: 622 KB
• Volume: 17
• Category: Article
• ISSN: 0005-1098
• DOI: 10.1016/0005-1098(81)90023-6

✦ Synopsis

This paper is concerned with the structural Guidorzi (1975) identified the observability indices by identification of linear multivariable systems and an computing a certain criterion function for all possible interactive identification package. The structural identification combinations of observability indices. In these structural is done by taking the time-invariant subsystem from the identification methods based on realization, there is a realizations of the input-output relations identified using data problem of how to determine the order of the minimally of disjoint time intervals, and the statistical hypothesis test is realized system based on the computed results. There emplo/ced to determine the order, where the input-output frequently happens to be a difficulty in determining the order relation is identified based on the generalized least squares from the numerical values. method using the possibly larger model for the plant. The This paper proposes to identify a linear time-invariant identification package is for the identification of the input-multivariable system in the following way output relation of a linear multivariable system, for the (1) The records of input-output data are divided into structural identification based on the realization and for data several disjoint time intervals, and for each section of the data management~ record, an input-output relation is identified.

(2) The several input--output relations identified for different time intervals are realized and the common timeinvariant part in these relations is taken as the representation