Grey-box modelling of a friction-affected dynamical system
Grey-box modelling of a friction-affected dynamical system
In this paper a grey-box model of a nonlinear dynamical system is constructed. This involves using a Gaussian process to emulate model error - the error that arises as a result of flaws in one’s physical-law based model of the system. The work shows how such an approach can be extended towards dynamical systems. Specifically, it is applied to experimental data, obtained from a dynamical system whose response is known to be strongly influenced by friction effects.
Green, Peter
fa393509-774c-4b94-8554-0cd2ab3bd82a
Hendijanizadeh, Mehdi
9631d6d8-f4fb-4088-8d66-950699eba189
Elliott, Stephen
721dc55c-8c3e-4895-b9c4-82f62abd3567
4 November 2015
Green, Peter
fa393509-774c-4b94-8554-0cd2ab3bd82a
Hendijanizadeh, Mehdi
9631d6d8-f4fb-4088-8d66-950699eba189
Elliott, Stephen
721dc55c-8c3e-4895-b9c4-82f62abd3567
Green, Peter, Hendijanizadeh, Mehdi and Elliott, Stephen
(2015)
Grey-box modelling of a friction-affected dynamical system.
IPW2015: 13th International Probabilistic Workshop, Liverpool, United Kingdom.
04 - 06 Nov 2015.
Record type:
Conference or Workshop Item
(Paper)
Abstract
In this paper a grey-box model of a nonlinear dynamical system is constructed. This involves using a Gaussian process to emulate model error - the error that arises as a result of flaws in one’s physical-law based model of the system. The work shows how such an approach can be extended towards dynamical systems. Specifically, it is applied to experimental data, obtained from a dynamical system whose response is known to be strongly influenced by friction effects.
Text
IPW_2015.pdf
- Accepted Manuscript
More information
Published date: 4 November 2015
Venue - Dates:
IPW2015: 13th International Probabilistic Workshop, Liverpool, United Kingdom, 2015-11-04 - 2015-11-06
Organisations:
Engineering Science Unit
Identifiers
Local EPrints ID: 384549
URI: http://eprints.soton.ac.uk/id/eprint/384549
PURE UUID: 72e06052-bf49-45c7-b731-7faf552da848
Catalogue record
Date deposited: 05 Jan 2016 12:42
Last modified: 14 Mar 2024 22:00
Export record
Contributors
Author:
Peter Green
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics