A novel temperature prediction method without using energy equation based on physics-informed neural network (PINN): a case study on plate-circular/square pin-fin heat sinks

DOI10.1016/J.ENGANABOUND.2022.09.032OpenAlexW4303646514MaRDI QIDQ6138011

Mostafa Safdari Shadloo, Preecha Kaseethong, Somchai Wongwises, Kitti Nilpueng, Mehrdad Mesgarpour

Publication date: 16 January 2024

Published in: Engineering Analysis with Boundary Elements (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.enganabound.2022.09.032

Mathematics Subject Classification ID

Fluid mechanics (76-XX) Classical thermodynamics, heat transfer (80-XX)

Cites Work

• NSFnets (Navier-Stokes flow nets): physics-informed neural networks for the incompressible Navier-Stokes equations
• Deep-learning accelerated calculation of real-fluid properties in numerical simulation of complex flowfields
• Eliminating redundancy and irrelevance using a new MLP-based feature selection method
• A Modified BFGS Algorithm for Unconstrained Optimization
• Turbulence statistics in fully developed channel flow at low Reynolds number
• Understanding and Mitigating Gradient Flow Pathologies in Physics-Informed Neural Networks

This page was built for publication: A novel temperature prediction method without using energy equation based on physics-informed neural network (PINN): a case study on plate-circular/square pin-fin heat sinks