Please use this identifier to cite or link to this item: https://scholarbank.nus.edu.sg/handle/10635/233976
DC FieldValue
dc.titleMACHINE LEARNING FOR CONSTITUTIVE MODELLING
dc.contributor.authorDENG HAOXIANG
dc.date.accessioned2022-10-31T18:00:40Z
dc.date.available2022-10-31T18:00:40Z
dc.date.issued2022-07-12
dc.identifier.citationDENG HAOXIANG (2022-07-12). MACHINE LEARNING FOR CONSTITUTIVE MODELLING. ScholarBank@NUS Repository.
dc.identifier.urihttps://scholarbank.nus.edu.sg/handle/10635/233976
dc.description.abstractMachine learning (ML) techniques have been applied as surrogate models in the micro scale of multi-scale analysis to reduce the computational cost. These surrogate models provide the constitutive law of the micro scale simulations after a training process, called off-line learning. For history dependent materials, the recurrent neural network (RNN) is adopted for the training of path dependent mechanical responses, due to its advanced learning ability for history dependent behavior. However, the huge data generation time of RNN surrogate model limits the off-line learning efficiency. This thesis aims to address this limitation. Two sequential training strategies are considered. (i) An Error Correction (EC) strategy, where a reference surrogate model is first trained using limited data, and later refined using another trained model on the error correction. (ii) A Knowledge Transfer (KT) strategy, where a source surrogate model is first trained based on a simplified RVE, followed by a refinement of surrogate model based on target data generated with detailed RVEs. This thesis shows that the proposed two strategies, EC and KT, can improve the off-line learning efficiency.
dc.language.isoen
dc.subjectRecurrent neural network, error correction method, knowledge transfer, computational homogenization, multi-scale modelling, history-dependent behavior
dc.typeThesis
dc.contributor.departmentCIVIL & ENVIRONMENTAL ENGINEERING
dc.contributor.supervisorLeong Hien Poh
dc.description.degreeMaster's
dc.description.degreeconferredMASTER OF ENGINEERING (CDE)
dc.identifier.orcid0000-0003-0344-008X
Appears in Collections:Master's Theses (Restricted)

Show simple item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
DengHX.pdf7.17 MBAdobe PDF

RESTRICTED

NoneLog In

Page view(s)

33
checked on Mar 16, 2023

Download(s)

5
checked on Mar 16, 2023

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.