Dissertation/ Thesis
Incorporation of physical laws into neural networks for solving elasticity problems
| العنوان: | Incorporation of physical laws into neural networks for solving elasticity problems |
|---|---|
| المؤلفون: | Kafkas, Petros, Καυκάς, Πέτρος |
| المساهمون: | Rekatsinas, Christoforos, Ρεκατσίνας, Χριστόφορος, Σχολή Τεχνολογιών Πληροφορικής και Επικοινωνιών. Τμήμα Ψηφιακών Συστημάτων, Τεχνητή Νοημοσύνη - Artificial Intelligence |
| بيانات النشر: | Πανεπιστήμιο Πειραιώς |
| سنة النشر: | 2024 |
| المجموعة: | University of Piraeus: Dione / Πανεπιστημίο Πειραιώς: Διώνη |
| مصطلحات موضوعية: | Physics informed machine learning, Physics informed neural networks, Elasto-static plate bending, Boundary conditions, Mindlin plate model, Kirchhoff plate model, Finite Element Analysis (FEA), Boundary condition enforcement, Fourier feature embeddings, Self-scalable hyperbolic tangent, Training stability, Partial Differential Equations (PDEs), Elasticity problems, Isotropic plates, Neural networks, Simulation of plate bending, Comparative analysis (PINNs vs. FEA) |
| الوصف: | 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). |
| نوع الوثيقة: | master thesis |
| وصف الملف: | application/pdf |
| اللغة: | English |
| Relation: | https://dione.lib.unipi.gr/xmlui/handle/unipi/16834; http://dx.doi.org/10.26267/unipi_dione/4256 |
| DOI: | 10.26267/unipi_dione/4256 |
| الاتاحة: | https://dione.lib.unipi.gr/xmlui/handle/unipi/16834 https://doi.org/10.26267/unipi_dione/4256 |
| Rights: | Αναφορά Δημιουργού-Μη Εμπορική Χρήση-Όχι Παράγωγα Έργα 3.0 Ελλάδα ; http://creativecommons.org/licenses/by-nc-nd/3.0/gr/ |
| رقم الانضمام: | edsbas.2798B8E6 |
| قاعدة البيانات: | BASE |
| DOI: | 10.26267/unipi_dione/4256 |
|---|