AI-enhanced multiscale finite element methods for forward and inverse uncertainty quantification problems in structural mechanics

Πυριαλάκος, Στέφανος Χρήστος; Pyrialakos, Stefanos Christos

dc.contributor.author	Πυριαλάκος, Στέφανος Χρήστος
dc.contributor.author	Pyrialakos, Stefanos Christos
dc.date.accessioned	2025-01-17T07:41:52Z
dc.date.available	2025-01-17T07:41:52Z
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/60803
dc.identifier.uri	http://dx.doi.org/10.26240/heal.ntua.28499
dc.rights	Default License
dc.subject	Computational Homogenization	en
dc.subject	Neural Networks	en
dc.subject	Bayesian Inference	en
dc.subject	Stochastic Optimization	en
dc.subject	CNT-reinforced Composites	en
dc.subject	Υπολογιστική Ομογενοποίηση	el
dc.subject	Νευρωνικά Δίκτυα	el
dc.subject	Μπεϋζιανή Επικαιροποίηση	el
dc.subject	Στοχαστική Βελτιστοποίηση	el
dc.subject	Σύνθετα ενισχυμένα με CNT	el
dc.title	AI-enhanced multiscale finite element methods for forward and inverse uncertainty quantification problems in structural mechanics	en
heal.type	doctoralThesis
heal.secondaryTitle	Μέθοδοι πεπερασμένων στοιχείων σε πολλαπλές κλίμακες ενισχυμένες με ΑΙ για ευθέα και αντίστροφα προβλήματα ποσοτικοποίησης αβεβαιότητας στη δομική μηχανική	el
heal.classification	Multiscale Material Modeling	en
heal.classification	Uncertainty Quantification	en
heal.classification	Machine Learning	en
heal.classification	Μοντελοποίηση Πολλαπλών Κλιμάκων	el
heal.classification	Ποσοτικοποίηση Αβεβαιότητας	el
heal.classification	Μηχανική Μάθηση	el
heal.language	en
heal.access	free
heal.recordProvider	ntua	el
heal.publicationDate	2024-06-01
heal.abstract	Over recent decades, there has been growing interest in high-performance materials tailored for complex engineering applications. By modifying material structures at fine scales, exceptional properties such as enhanced mechanical strength, improved thermal conductivity, and novel optical features can be achieved. To address the time-consuming and costly experimentation on these materials, several computational techniques have been developed. Among them, the multiscale computational homogenization method via the well-established FE^2 algorithm has gained significant attention. Despite its computational intensity, this algorithm is favored for its ability to reliably predict the complex macroscopic behavior of multiscale material systems due to non-linear phenomena at finer scales. However, identifying the parameters that characterize material behavior at fine scales still remains a nontrivial undertaking. This thesis presents a cost-efficient framework using machine learning strategies for implementing the computational homogenization modeling approach on multi-query analyses investigating fine-scale parameters. Novel computational methodologies are proposed for accurate and efficient forward and inverse uncertainty quantification analyses on multiscale material systems and are validated through real-world case studies. First, this thesis presents a strategy for performing Bayesian inference on microscale material properties using experimental observations from the visible structure. To tackle the computational load of repeated FE^2 analyses, a feed-forward neural network (FFNN) is used to emulate material behavior affected by microstructural parameters. This is achieved by training the FFNN on a dataset from offline representative volume element (RVE) solutions. Next, the thesis generalizes the FE^2 algorithm by employing a sequence of FFNNs to represent different scales in the multiscale system, with each FFNN learning the constitutive law of its corresponding length scale. This results in a FFNN that emulates macroscopic behavior by incorporating mechanisms from each finer scale. Based on this scheme, the thesis, subsequently, proposes a methodology to identify optimal typologies of nanocomposite materials for desirable structural responses under uncertain conditions. Finally, a hierarchical Bayesian framework is introduced to utilize disjoint experimental measurements in multiscale material systems for joint parameter inference. This framework integrates experimental data from different scales and material compositions to yield informed parameters for future model predictions.	en
heal.sponsor	European Regional Development Fund and Greek national Funds under grant MATERIALIZE - an integrated cloud platform for the simulation and standardization of high performance materials and products	en
heal.sponsor	European High Performance Computing Joint Undertaking under grant DCoMEX - Data driven computational mechanics at exascale	en
heal.advisorName	Παπαδόπουλος, Βησσαρίων
heal.committeeMemberName	Παπαδόπουλος, Βησσαρίων
heal.committeeMemberName	Σπηλιόπουλος, Κωνσταντίνος
heal.committeeMemberName	Λαγαρός, Νικόλαος
heal.committeeMemberName	Ζέρης, Χρήστος
heal.committeeMemberName	Χαριτίδης, Κωνσταντίνος
heal.committeeMemberName	Φραγκιαδάκης, Μιχαήλ
heal.committeeMemberName	Τριανταφύλλου, Σάββας
heal.academicPublisher	Σχολή Πολιτικών Μηχανικών	el
heal.academicPublisherID	ntua
heal.fullTextAvailability	false