Physics-Informed Neural Networks for Multiphysics Coupling: Application to Conjugate Heat Transfer

التفاصيل البيبلوغرافية
العنوان: Physics-Informed Neural Networks for Multiphysics Coupling: Application to Conjugate Heat Transfer
المؤلفون: Coulaud, Guillaume, Duvigneau, Régis
المساهمون: Analysis and Control of Unsteady Models for Engineering Sciences (ACUMES), Inria Sophia Antipolis - Méditerranée (CRISAM), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Université Côte d'Azur, Inria, CNRS, LJAD
المصدر: https://inria.hal.science/hal-04225990Test ; RR-9520, Université Côte d'Azur, Inria, CNRS, LJAD. 2023.
بيانات النشر: HAL CCSD
سنة النشر: 2023
المجموعة: HAL Université Côte d'Azur
مصطلحات موضوعية: Physics-Informed Neural Networks, Multiphysics Coupling, Conjugate Heat Transfer, Deep Learning, Partial differential equations, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], [MATH.MATH-AP]Mathematics [math]/Analysis of PDEs [math.AP], [MATH.MATH-OC]Mathematics [math]/Optimization and Control [math.OC]
الوصف: Physics-Informed Neural Networks (PINNs) have emerged as a promising paradigm for modeling complex physical phenomena, offering the potential to handle diverse scenarios to simulate coupled systems. This is a supervised or unsupervised deep learning approach that aims at learning physical laws described by partial differential equations. This report presents an exploration of PINNs through three distinct test cases: heat transfer, and conjugate heat transfer, with forced and natural convection. The investigations reveal PINNs' proficiency in accommodating parameterized resolution, addressing piece-wise constant conditions, and enabling multiphysics coupling. Despite their versatility, challenges emerged, including difficulties in achieving high accuracy, error propagation near singularities, and limitations in scenarios with high Rayleigh values.
نوع الوثيقة: report
اللغة: English
العلاقة: Report N°: RR-9520; hal-04225990; https://inria.hal.science/hal-04225990Test; https://inria.hal.science/hal-04225990/documentTest; https://inria.hal.science/hal-04225990/file/RR-9520.pdfTest
الإتاحة: https://inria.hal.science/hal-04225990Test
https://inria.hal.science/hal-04225990/documentTest
https://inria.hal.science/hal-04225990/file/RR-9520.pdfTest
حقوق: http://hal.archives-ouvertes.fr/licences/publicDomainTest/ ; info:eu-repo/semantics/OpenAccess
رقم الانضمام: edsbas.4AB115E0
قاعدة البيانات: BASE