High Gain Embedding Observer Design: Combining Differential Geometry and Algebra with Machine Learning

Research output: Contribution to book/Conference proceedings/Anthology/ReportConference contributionContributedpeer-review

Abstract

High gain observers are often used for the real-time estimation of the state of nonlinear systems. Several design methods are based on normal forms, which are based on differential geometric considerations. The embedding into a higher dimensional state could be advantageous regarding existence conditions and convergence. However, computation and implementation of such embedding observers is usually significantly more challenging. In this paper, we circumvent some of these problems by employing machine learning. The required functions for the implementation of the observer are approximated by neural networks.

Details

Original languageEnglish
Title of host publication2023 27th International Conference on System Theory, Control and Computing (ICSTCC)
PublisherIEEE
Pages62-69
Number of pages8
ISBN (electronic)9798350337983
ISBN (print)979-8-3503-3799-0
Publication statusPublished - 13 Oct 2023
Peer-reviewedYes

Conference

Title2023 27th International Conference on System Theory, Control and Computing
Abbreviated titleICSTCC 2023
Conference number27
Duration11 - 13 October 2023
Website
Degree of recognitionInternational event
LocationIbis Timisoara City Center Hotel
CityTimisoara
CountryRomania

External IDs

Scopus 85179509515
ORCID /0000-0002-3347-0864/work/156338278

Keywords

Keywords

  • Design methodology, Machine learning, Neural networks, Noise measurement, Observers, Real-time systems, Uncertain systems