Nonlinear Identification for Control by Using NARMAX Models

Dan Stefanoiu, Janetta Culita (), Andreea-Cristina Voinea and Vasilica Voinea
Additional contact information
Dan Stefanoiu: Faculty of Automatic Control and Computers, National University of Science and Technology “Politehnica” Bucharest, 313 Splaiul Independentei, 060042 Bucharest, Romania
Janetta Culita: Faculty of Automatic Control and Computers, National University of Science and Technology “Politehnica” Bucharest, 313 Splaiul Independentei, 060042 Bucharest, Romania
Andreea-Cristina Voinea: Faculty of Automatic Control and Computers, National University of Science and Technology “Politehnica” Bucharest, 313 Splaiul Independentei, 060042 Bucharest, Romania
Vasilica Voinea: Faculty of Automatic Control and Computers, National University of Science and Technology “Politehnica” Bucharest, 313 Splaiul Independentei, 060042 Bucharest, Romania

Mathematics, 2024, vol. 12, issue 14, 1-52

Abstract: The identification (and control) of nonlinear systems is one of the most important and actual research directions. Moreover, many systems are multivariable. Different from linear system identification (where only a few classes of models are available), in the case of nonlinear systems, the class set of models is quite diverse. One of the most appealing nonlinear models belongs to the nonlinear ARMAX (NARMAX) class. This article focusses on the identification of such a model, which can be compared with other models (such as nonlinear ARX (NARX) and linear ARMAX) in an application based on the didactical installation ASTANK2. The mathematical foundation of NARMAX models and their identification method are described at length within this article. One of the most interesting parts is concerned with the identification of optimal models not only in terms of numerical parameters but also as structure. A metaheuristic (namely, the Cuckoo Search Algorithm) is employed with the aim of finding the optimal structural indices based on a special cost function, referred to as fitness . In the end, the performances of all three models (NARMAX, NARX, and ARMAX) are compared after the identification of the ASTANK2 installation.

Keywords: linear/nonlinear system identification; multivariable systems; identification for control; simulation of identification models; nonconvex optimization using biology inspired metaheuristics (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/12/14/2252/pdf (application/pdf)
https://www.mdpi.com/2227-7390/12/14/2252/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:12:y:2024:i:14:p:2252-:d:1438792

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().