Tuning of extended state observer with neural network-based control performance assessment

Kicki, P; Łakomy, K; Lee, KMB

Tuning of extended state observer with neural network-based control performance assessment

Kicki, P Łakomy, K Lee, KMB

Permalink

Publisher:: ELSEVIER
Publication Type:: Journal Article
Citation:: European Journal of Control, 2022, 64
Issue Date:: 2022-03-01

Closed Access

	Filename	Description	Size
	1-s2.0-S0947358021001412-main.pdf	Published version	4.73 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Kicki, P
dc.contributor.author	Łakomy, K
dc.contributor.author	Lee, KMB
dc.date.accessioned	2022-12-07T21:32:10Z
dc.date.available	2022-12-07T21:32:10Z
dc.date.issued	2022-03-01
dc.identifier.citation	European Journal of Control, 2022, 64
dc.identifier.issn	0947-3580
dc.identifier.issn	1435-5671
dc.identifier.uri	http://hdl.handle.net/10453/164233
dc.description.abstract	The extended state observer (ESO) is an inherent element of robust observer-based control systems that allows one to estimate the impact of disturbance on system dynamics. Proper tuning of ESO parameters is necessary to ensure a good quality of estimated quantities and impacts the overall performance of the robust control structure. In this paper, we propose a neural network (NN) based tuning procedure that allows the prioritization between selected quality criteria such as the control and observation errors and the specified features of the control signal. The designed NN provides an accurate assessment of the control system performance and returns a set of ESO parameters that delivers a near-optimal solution in terms of the user-defined cost function. The proposed tuning procedure, using an estimated state from the single closed-loop experiment, produces near-optimal ESO gains within seconds.
dc.language	English
dc.publisher	ELSEVIER
dc.relation.ispartof	European Journal of Control
dc.relation.isbasedon	10.1016/j.ejcon.2021.12.004
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject	0102 Applied Mathematics, 0906 Electrical and Electronic Engineering, 0913 Mechanical Engineering
dc.subject.classification	Industrial Engineering & Automation
dc.title	Tuning of extended state observer with neural network-based control performance assessment
dc.type	Journal Article
utslib.citation.volume	64
utslib.for	0102 Applied Mathematics
utslib.for	0906 Electrical and Electronic Engineering
utslib.for	0913 Mechanical Engineering
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Mechanical and Mechatronic Engineering
utslib.copyright.status	closed_access	*
dc.date.updated	2022-12-07T21:31:29Z
pubs.publication-status	Published
pubs.volume	64

Abstract:

The extended state observer (ESO) is an inherent element of robust observer-based control systems that allows one to estimate the impact of disturbance on system dynamics. Proper tuning of ESO parameters is necessary to ensure a good quality of estimated quantities and impacts the overall performance of the robust control structure. In this paper, we propose a neural network (NN) based tuning procedure that allows the prioritization between selected quality criteria such as the control and observation errors and the specified features of the control signal. The designed NN provides an accurate assessment of the control system performance and returns a set of ESO parameters that delivers a near-optimal solution in terms of the user-defined cost function. The proposed tuning procedure, using an estimated state from the single closed-loop experiment, produces near-optimal ESO gains within seconds.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/164233