On the initialization of nonlinear LFR model identification with the best linear approximation

Research output: Contribution to journalConference articlepeer-review

9 Citations (Scopus)
89 Downloads (Pure)

Abstract

Balancing the model complexity and the representation capability towards the process to be captured remains one of the main challenges in nonlinear system identification. One possibility to reduce model complexity is to impose structure on the model representation. To this end, this work considers the linear fractional representation framework. In a linear fractional representation the linear dynamics and the system nonlinearities are modeled by two separate blocks that are interconnected with one another. This results in a structured, yet flexible model structure. Estimating such a model directly from input-output data is not a trivial task as the involved optimization is nonlinear in nature. This paper proposes an initialization scheme for the model parameters based on the best linear approximation of the system and shows that this approach results in high quality models on a set of benchmark data sets.

Original languageEnglish
Pages (from-to)310-315
Number of pages6
JournalIFAC-PapersOnLine
Volume53
Issue number2
DOIs
Publication statusPublished - 2020
Event21st World Congress of the International Federation of Aufomatic Control (IFAC 2020 World Congress) - Berlin, Germany
Duration: 12 Jul 202017 Jul 2020
Conference number: 21
https://www.ifac2020.org/

Bibliographical note

Publisher Copyright:
Copyright © 2020 The Authors. This is an open access article under the CC BY-NC-ND license

Copyright:
Copyright 2021 Elsevier B.V., All rights reserved.

Funding

FundersFunder number
European Union's Horizon 2020 - Research and Innovation Framework Programme714663, 798627

    Keywords

    • Best Linear Approximation
    • Linear Fractional Representation
    • Neural Network
    • Nonlinear Identification

    Fingerprint

    Dive into the research topics of 'On the initialization of nonlinear LFR model identification with the best linear approximation'. Together they form a unique fingerprint.

    Cite this