Unpublished conference/Abstract (Scientific congresses and symposiums)
Bayesian inference of multiscale model parameters with artificial neural networks as surrogate
Wu, Ling; Noels, Ludovic
2021EUROMECH Colloquium 618 Uncertainty Quantification in Computational Mechanics
 

Files


Full Text
abstract_template618_noels.pdf
Publisher postprint (555.94 kB)
Download

All documents in ORBi are protected by a user license.

Send to



Details



Keywords :
Multiscale; Composites; Bayesian inference; Neural Network; Non-linear
Abstract :
[en] In the context of multiscale models, it is not always possible to identify the constituents properties and inverse analysis is a way to identify them from experimental data conducted at the higher scale. For example, non-aligned Short Fibers Reinforced Polymer (SFRP) responses can be modelled by Mean-Field Homogenization (MFH) but some geometrical parameters, such as the effective aspect ratio, and some phase material parameters, such as the matrix model parameters, should be inferred from composite experimental responses in order to avoid extensive measurement campaigns at the micro-scale. In practice, because of the increase in the number of parameters in the non-linear models, this identification requires several loading conditions, and a unique set of parameters cannot reproduce all the experimental tests because, on the one hand, of the model limitations and, on the other hand, of the experimental errors [1]. Bayesian Inference (BI) allows circumventing these difficulties, but requires a large amount of the model evaluations during the sampling process. Although MFH is computationally efficient, when considering non-aligned inclusions, the evaluation cost of a non-linear response for a given set of model and material parameters remains too prohibitive. In this work, a Neural-Network (NNW) is first trained using the MFH model, and is then used as a surrogate model during the BI process which is conducted using experimental composite coupon tests as observation data [2].
Disciplines :
Materials science & engineering
Mechanical engineering
Author, co-author :
Wu, Ling ;  Université de Liège - ULiège > Département d'aérospatiale et mécanique > Computational & Multiscale Mechanics of Materials (CM3)
Noels, Ludovic  ;  Université de Liège - ULiège > Département d'aérospatiale et mécanique > Computational & Multiscale Mechanics of Materials (CM3)
Language :
English
Title :
Bayesian inference of multiscale model parameters with artificial neural networks as surrogate
Publication date :
13 December 2021
Event name :
EUROMECH Colloquium 618 Uncertainty Quantification in Computational Mechanics
Event organizer :
EUROMECH
Event place :
Esch-sur-Alzette, Luxembourg
Event date :
13-14 December 2021
By request :
Yes
Name of the research project :
The research has been funded by the Walloon Region under the agreement no 1410246-STOMMMAC (CT-INT 2013-03-28) in the context of M-ERA.NET Joint Call 2014.
Funders :
FWB - Fédération Wallonie-Bruxelles [BE]
Available on ORBi :
since 17 December 2021

Statistics


Number of views
120 (2 by ULiège)
Number of downloads
43 (1 by ULiège)

Bibliography


Similar publications



Contact ORBi