Understanding the training of PINNs for unsteady flow past a plunging foil through the lens of input subdomain level loss function gradients - Archive ouverte HAL Access content directly
Conference Papers Year : 2023

Understanding the training of PINNs for unsteady flow past a plunging foil through the lens of input subdomain level loss function gradients

Abstract

Recently immersed boundary method inspired physics-informed neural networks (PINNs) including the moving boundary-enabled PINNs (MB-PINNs) have shown the ability to accurately reconstruct velocity and recover pressure as a hidden variable for unsteady flow past moving bodies. Considering flow past a plunging foil, MB-PINNs were trained with global physics loss relaxation and also in conjunction with a physics-based undersampling method, obtaining good accuracy. The purpose of this study was to investigate which input spatial subdomain contributes to the training under the effect of physics loss relaxation and physics-based undersampling. In the context of MB-PINNs training, three spatial zones: the moving body, wake, and outer zones were defined. To quantify which spatial zone drives the training, two novel metrics are computed from the zonal loss component gradient statistics and the proportion of sample points in each zone. Results confirm that the learning indeed depends on the combined effect of the zonal loss component gradients and the proportion of points in each zone. Moreover, the dominant input zones are also the ones that have the strongest solution gradients in some sense.
Fichier principal
Vignette du fichier
FMFP_2023_ZonalAnalysis_LossContributions_RahulSundar_etal_Final.pdf (1.9 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-04463178 , version 1 (07-03-2024)

Identifiers

  • HAL Id : hal-04463178 , version 1

Cite

Rahul Sundar, Didier Lucor, Sunetra Sarkar. Understanding the training of PINNs for unsteady flow past a plunging foil through the lens of input subdomain level loss function gradients. 10th International and 50th National Conference on Fluid Mechanics and Fluid Power (FMFP), Dec 2023, Jodhpur, France. ⟨hal-04463178⟩
103 View
11 Download

Share

Gmail Mastodon Facebook X LinkedIn More