Incorporation of physical laws into neural networks for solving elasticity problems

Kafkas, Petros; Καυκάς, Πέτρος

dc.contributor.advisor	Rekatsinas, Christoforos
dc.contributor.advisor	Ρεκατσίνας, Χριστόφορος
dc.contributor.author	Kafkas, Petros
dc.contributor.author	Καυκάς, Πέτρος
dc.date.accessioned	2024-10-10T10:57:02Z
dc.date.available	2024-10-10T10:57:02Z
dc.date.issued	2024-07
dc.identifier.uri	https://dione.lib.unipi.gr/xmlui/handle/unipi/16834
dc.identifier.uri	http://dx.doi.org/10.26267/unipi_dione/4256
dc.format.extent	48	el
dc.language.iso	en	el
dc.publisher	Πανεπιστήμιο Πειραιώς	el
dc.rights	Αναφορά Δημιουργού-Μη Εμπορική Χρήση-Όχι Παράγωγα Έργα 3.0 Ελλάδα	*
dc.rights.uri	http://creativecommons.org/licenses/by-nc-nd/3.0/gr/	*
dc.title	Incorporation of physical laws into neural networks for solving elasticity problems	el
dc.type	Master Thesis	el
dc.contributor.department	Σχολή Τεχνολογιών Πληροφορικής και Επικοινωνιών. Τμήμα Ψηφιακών Συστημάτων	el
dc.description.abstractEN	This study investigates the performance of Physics-Informed-Neural-Networks (PINNs) in addressing elasto-static plate bending problems under various boundary conditions. To that effect, the bending of a square isotropic plate was simulated using the Mindlin and Kirchhoff models. The accuracy of the predictions is compared to the established method of Finite Element Analysis (FEA). For ensuring boundary condition compliance, a hard- enforced boundary method is adopted from the literature. Additionally, Fourier Feature Embeddings and Self-Scalable hyperbolic-tangent are employed for increased training stability. The findings confirm the results from previous studies regarding the ability of PINNs to successfully tackle electrostatic problems and confirm that PINNs show great promise as a novel method for solving Partial Differential Equations (PDEs).	el
dc.corporate.name	National Center of Scientific Research "Demokritos"	el
dc.contributor.master	Τεχνητή Νοημοσύνη - Artificial Intelligence	el
dc.subject.keyword	Physics informed machine learning	el
dc.subject.keyword	Physics informed neural networks	el
dc.subject.keyword	Elasto-static plate bending	el
dc.subject.keyword	Boundary conditions	el
dc.subject.keyword	Mindlin plate model	el
dc.subject.keyword	Kirchhoff plate model	el
dc.subject.keyword	Finite Element Analysis (FEA)	el
dc.subject.keyword	Boundary condition enforcement	el
dc.subject.keyword	Fourier feature embeddings	el
dc.subject.keyword	Self-scalable hyperbolic tangent	el
dc.subject.keyword	Training stability	el
dc.subject.keyword	Partial Differential Equations (PDEs)	el
dc.subject.keyword	Elasticity problems	el
dc.subject.keyword	Isotropic plates	el
dc.subject.keyword	Neural networks	el
dc.subject.keyword	Simulation of plate bending	el
dc.subject.keyword	Comparative analysis (PINNs vs. FEA)	el
dc.date.defense	2024-07-30

Αρχεία σε αυτό το τεκμήριο

Name:: kafkas_mtn2204.pdf
Μέγεθος:: 3.277Mb
Τύπος:: PDF
Description:: Master thesis

Προβολή/Άνοιγμα

Αυτό το τεκμήριο εμφανίζεται στις ακόλουθες συλλογές

Τμήμα Ψηφιακών Συστημάτων
Department of Digital Systems

Εμφάνιση απλής εγγραφής

Αναφορά Δημιουργού-Μη Εμπορική Χρήση-Όχι Παράγωγα Έργα 3.0 Ελλάδα

Εκτός από όπου διευκρινίζεται διαφορετικά, το τεκμήριο διανέμεται με την ακόλουθη άδεια:
Αναφορά Δημιουργού-Μη Εμπορική Χρήση-Όχι Παράγωγα Έργα 3.0 Ελλάδα