Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Supervisory observer for parameter and state estimation of nonlinear systems using the DIRECT algorithm

Chong, Michelle S. LU orcid ; Postoyan, Romain ; Khong, Sei Zhen LU and Nesic, Dragan (2018) 56th IEEE Annual Conference on Decision and Control, CDC 2017 2018-January. p.2089-2094
Abstract

A supervisory observer is a multiple-model architecture, which estimates the parameters and the states of nonlinear systems. It consists of a bank of state observers, where each observer is designed for some nominal parameter values sampled in a known parameter set. A selection criterion is used to select a single observer at each time instant, which provides its state estimate and parameter value. The sampling of the parameter set plays a crucial role in this approach. Existing works require a sufficiently large number of parameter samples, but no explicit lower bound on this number is provided. The aim of this work is to overcome this limitation by sampling the parameter set automatically using an iterative global optimisation method,... (More)

A supervisory observer is a multiple-model architecture, which estimates the parameters and the states of nonlinear systems. It consists of a bank of state observers, where each observer is designed for some nominal parameter values sampled in a known parameter set. A selection criterion is used to select a single observer at each time instant, which provides its state estimate and parameter value. The sampling of the parameter set plays a crucial role in this approach. Existing works require a sufficiently large number of parameter samples, but no explicit lower bound on this number is provided. The aim of this work is to overcome this limitation by sampling the parameter set automatically using an iterative global optimisation method, called DIviding RECTangles (DIRECT). Using this sampling policy, we start with 1 + 2np parameter samples where np is the dimension of the parameter set. Then, the algorithm iteratively adds samples to improve its estimation accuracy. Convergence guarantees are provided under the same assumptions as in previous works, which include a persistency of excitation condition. The efficacy of the supervisory observer with the DIRECT sampling policy is illustrated on a model of neural populations.

(Less)
Please use this url to cite or link to this publication:
author
; ; and
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
host publication
2017 IEEE 56th Annual Conference on Decision and Control, CDC 2017
volume
2018-January
pages
6 pages
publisher
IEEE - Institute of Electrical and Electronics Engineers Inc.
conference name
56th IEEE Annual Conference on Decision and Control, CDC 2017
conference location
Melbourne, Australia
conference dates
2017-12-12 - 2017-12-15
external identifiers
  • scopus:85046161782
ISBN
9781509028733
DOI
10.1109/CDC.2017.8263955
language
English
LU publication?
yes
id
cd2dedf0-b685-44b0-9ca2-381daa104df6
date added to LUP
2018-05-15 13:49:33
date last changed
2024-01-14 20:06:23
@inproceedings{cd2dedf0-b685-44b0-9ca2-381daa104df6,
  abstract     = {{<p>A supervisory observer is a multiple-model architecture, which estimates the parameters and the states of nonlinear systems. It consists of a bank of state observers, where each observer is designed for some nominal parameter values sampled in a known parameter set. A selection criterion is used to select a single observer at each time instant, which provides its state estimate and parameter value. The sampling of the parameter set plays a crucial role in this approach. Existing works require a sufficiently large number of parameter samples, but no explicit lower bound on this number is provided. The aim of this work is to overcome this limitation by sampling the parameter set automatically using an iterative global optimisation method, called DIviding RECTangles (DIRECT). Using this sampling policy, we start with 1 + 2n<sub>p</sub> parameter samples where n<sub>p</sub> is the dimension of the parameter set. Then, the algorithm iteratively adds samples to improve its estimation accuracy. Convergence guarantees are provided under the same assumptions as in previous works, which include a persistency of excitation condition. The efficacy of the supervisory observer with the DIRECT sampling policy is illustrated on a model of neural populations.</p>}},
  author       = {{Chong, Michelle S. and Postoyan, Romain and Khong, Sei Zhen and Nesic, Dragan}},
  booktitle    = {{2017 IEEE 56th Annual Conference on Decision and Control, CDC 2017}},
  isbn         = {{9781509028733}},
  language     = {{eng}},
  month        = {{01}},
  pages        = {{2089--2094}},
  publisher    = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}},
  title        = {{Supervisory observer for parameter and state estimation of nonlinear systems using the DIRECT algorithm}},
  url          = {{http://dx.doi.org/10.1109/CDC.2017.8263955}},
  doi          = {{10.1109/CDC.2017.8263955}},
  volume       = {{2018-January}},
  year         = {{2018}},
}