Available on ORBi since
12 April 2022
Unpublished conference/Abstract (Scientific congresses and symposiums)
Recurrent Neural Networks (RNNs) with dimension reduction and break down in the context of high dimensional localization step in multi-scale analysis
Wu, Ling  ; Noels, Ludovic 
2022 • 18th European Mechanics of Materials Conference (EMMC18)
 

Files


Full Text
2022_EMMC18_RNNPCA.pdf
Author postprint (3.36 MB) Creative Commons License - Public Domain Dedication

All documents in ORBi are protected by a user license.

Send to



Details



Keywords :
Multiscale; Neural-Network; Elasto-plasticity; composites; Machine learning
Abstract :
[en] Artificial Neural Networks (NNWs) are appealing tools to serve as surrogate model of high dimensional and non-linear history-dependent problems in computational mechanics, in particular in multi-scale methods. Indeed, as shown in [1] once properly trained, they replace expensive micro-scale finite element resolutions allowing reducing the computational time by more than 4 orders of magnitude. Nevertheless, such a paradigm is essentially used as a mapping between the macro-stress and macro-strain tensors of the micro-scale boundary value response and the micro-structure information could not be recovered in a so-called localization step. In this talk, we present a Recurrent Neural Networks (RNNs)-based surrogate of the micro-scale boundary value problem, while being able to recover the evolution of the local micro-structure state variables for complex loading scenarios [2]. In order to address the curse of dimensionality arising because of the large amount of internal state variables in the micro-structure, we enrich the RNN with PCA dimension reduction and dimension break down, i.e. the use of several RNNs instead of a single one. Besides, the sequential training strategy is optimized in order to allow for GPU usage. [1] L. Wu, V.-D. Nguyen, N.G. Kilingar and L. Noels, Computer Methods in Applied Mechanics and Engineering, 360:113234, 2020. [2] L. Wu, L. Noels, Recurrent Neural Networks (RNNs) in computational mechanics for high dimensional problems: RNNs structure design through dimension reduction and break down; application to multi-scale localization step. Submitted.
Disciplines :
Mechanical engineering
Mechanical engineering
Aerospace & aeronautics 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 :
Recurrent Neural Networks (RNNs) with dimension reduction and break down in the context of high dimensional localization step in multi-scale analysis
Publication date :
04 April 2022
Event name :
18th European Mechanics of Materials Conference (EMMC18)
Event organizer :
EuroMech
Event place :
Oxford, United Kingdom
Event date :
4-6 April 2022
Audience :
International
European Projects :
H2020 - 862015 - MOAMMM - Multi-scale Optimisation for Additive Manufacturing of fatigue resistant shock-absorbing MetaMaterials
Name of the research project :
MOAMMM
Funders :
EC - European Commission
Funding number :
862015
Funding text :
This project has received funding from the European Union´s Horizon 2020 research and innovation programme under grant agreement No. 862015 for the project “Multiscale Optimisation for Additive Manufacturing of fatigue resistant shock-absorbing MetaMaterials (MOAMMM)” of the H2020-EU.1.2.1. - FET Open Programme.

Statistics


Number of views
26 (4 by ULiège)
Number of downloads
7 (0 by ULiège)

Bibliography


Similar publications



Contact ORBi