Efficient reliability analysis considering uncertainty in random field parameters: Trained neural networks as surrogate models

He, X; Wang, F; Li, W; Sheng, D

Efficient reliability analysis considering uncertainty in random field parameters: Trained neural networks as surrogate models

He, X

Wang, F Li, W

Sheng, D

Permalink

Publisher:: ELSEVIER SCI LTD
Publication Type:: Journal Article
Citation:: Computers and Geotechnics, 2021, 136
Issue Date:: 2021-08-01

Closed Access

	Filename	Description	Size
	1-s2.0-S0266352X2100210X-main.pdf	Published version	6.2 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	He, X https://orcid.org/0000-0001-5336-3663
dc.contributor.author	Wang, F
dc.contributor.author	Li, W https://orcid.org/0000-0002-4651-1215
dc.contributor.author	Sheng, D https://orcid.org/0000-0002-1665-6931
dc.date.accessioned	2022-04-20T23:11:05Z
dc.date.available	2022-04-20T23:11:05Z
dc.date.issued	2021-08-01
dc.identifier.citation	Computers and Geotechnics, 2021, 136
dc.identifier.issn	0266-352X
dc.identifier.issn	1873-7633
dc.identifier.uri	http://hdl.handle.net/10453/156526
dc.description.abstract	This paper presents an efficient reliability analysis framework, by using trained artificial neural networks (ANNs) as surrogate models, for geotechnical problems where the random field parameters like the mean and standard deviation are themselves uncertain. Random field theory has been extensively used to model soil uncertainty and spatial variability. However, due to limited availability of data, random field parameters can rarely be estimated accurately, often estimated in confidence intervals (uncertain parameters). Monte Carlo based reliability analysis is computationally extremely demanding because the function to map outcomes of random fields to structural response can only be calculated via numerical simulations. The authors have used trained ANNs as surrogate models in reliability analysis. However, these ANNs are specific for random fields with deterministic parameters. This paper presents a new framework in which trained ANN models are for random fields with variable parameters. A key component is the design of experiments – generating representative outcomes. In the prediction of the bearing capacity for strip footings, the efficiency and accuracy of this framework are successfully demonstrated. This framework is also efficient in reliability sensitivity studies. One main finding is that ignoring random field parameter uncertainty could lead to underestimated failure probability and hence unsafe design.
dc.language	English
dc.publisher	ELSEVIER SCI LTD
dc.relation.ispartof	Computers and Geotechnics
dc.relation.isbasedon	10.1016/j.compgeo.2021.104212
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject	0905 Civil Engineering, 0914 Resources Engineering and Extractive Metallurgy, 0915 Interdisciplinary Engineering
dc.subject.classification	Geological & Geomatics Engineering
dc.title	Efficient reliability analysis considering uncertainty in random field parameters: Trained neural networks as surrogate models
dc.type	Journal Article
utslib.citation.volume	136
utslib.for	0905 Civil Engineering
utslib.for	0914 Resources Engineering and Extractive Metallurgy
utslib.for	0915 Interdisciplinary 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 Civil and Environmental Engineering
pubs.organisational-group	/University of Technology Sydney/Strength - CBI - Centre for Built Infrastructure
utslib.copyright.status	closed_access	*
dc.date.updated	2022-04-20T23:11:03Z
pubs.publication-status	Published
pubs.volume	136

Abstract:

This paper presents an efficient reliability analysis framework, by using trained artificial neural networks (ANNs) as surrogate models, for geotechnical problems where the random field parameters like the mean and standard deviation are themselves uncertain. Random field theory has been extensively used to model soil uncertainty and spatial variability. However, due to limited availability of data, random field parameters can rarely be estimated accurately, often estimated in confidence intervals (uncertain parameters). Monte Carlo based reliability analysis is computationally extremely demanding because the function to map outcomes of random fields to structural response can only be calculated via numerical simulations. The authors have used trained ANNs as surrogate models in reliability analysis. However, these ANNs are specific for random fields with deterministic parameters. This paper presents a new framework in which trained ANN models are for random fields with variable parameters. A key component is the design of experiments – generating representative outcomes. In the prediction of the bearing capacity for strip footings, the efficiency and accuracy of this framework are successfully demonstrated. This framework is also efficient in reliability sensitivity studies. One main finding is that ignoring random field parameter uncertainty could lead to underestimated failure probability and hence unsafe design.

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

http://hdl.handle.net/10453/156526