Investigating the Effects of Labeled Data on Parameterized Physics-Informed Neural Networks for Surrogate Modeling: Design Optimization for Drag Reduction over a Forward-Facing Step

Physics-informed neural networks (PINNs) are gaining traction as surrogate models for fluid dynamics problems, combining machine learning with physics-based constraints. This study investigates the impact of labeled data on the performance of parameterized physics-informed neural networks (PINNs) fo...

Full description

Saved in:
Bibliographic Details
Main Authors: Erik Gustafsson, Magnus Andersson
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Fluids
Subjects:
Online Access:https://www.mdpi.com/2311-5521/9/12/296
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850040383503859712
author Erik Gustafsson
Magnus Andersson
author_facet Erik Gustafsson
Magnus Andersson
author_sort Erik Gustafsson
collection DOAJ
description Physics-informed neural networks (PINNs) are gaining traction as surrogate models for fluid dynamics problems, combining machine learning with physics-based constraints. This study investigates the impact of labeled data on the performance of parameterized physics-informed neural networks (PINNs) for surrogate modeling and design optimization. Different training approaches, including physics-only, data-only, and several combinations of both, are evaluated using fully connected (FCNN) and Fourier neural network (FNN) architectures. The test case focuses on reducing drag over a forward-facing step through optimal placement and sizing of an upstream obstacle. Results demonstrate that the inclusion of labeled data significantly enhances the accuracy and convergence rates of FCNNs, particularly in predicting flow separation and recirculation regions, and improves the stability of design optimization outcomes. Conversely, FNNs exhibit inconsistent responses to parameter changes when trained with labeled data, suggesting limitations in their applicability for certain design optimization tasks. The findings reveal that FCNNs trained with a balanced integration of data and physics constraints outperform both data-only and physics-only models, highlighting the importance of optimizing the training approach based on the specific requirements of fluid mechanics applications.
format Article
id doaj-art-147fea4a08aa4a0a9b9fee05e75826e3
institution DOAJ
issn 2311-5521
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Fluids
spelling doaj-art-147fea4a08aa4a0a9b9fee05e75826e32025-08-20T02:56:06ZengMDPI AGFluids2311-55212024-12-0191229610.3390/fluids9120296Investigating the Effects of Labeled Data on Parameterized Physics-Informed Neural Networks for Surrogate Modeling: Design Optimization for Drag Reduction over a Forward-Facing StepErik Gustafsson0Magnus Andersson1Department of Management and Engineering, Linköping University, SE-581 83 Linköping, SwedenDepartment of Management and Engineering, Linköping University, SE-581 83 Linköping, SwedenPhysics-informed neural networks (PINNs) are gaining traction as surrogate models for fluid dynamics problems, combining machine learning with physics-based constraints. This study investigates the impact of labeled data on the performance of parameterized physics-informed neural networks (PINNs) for surrogate modeling and design optimization. Different training approaches, including physics-only, data-only, and several combinations of both, are evaluated using fully connected (FCNN) and Fourier neural network (FNN) architectures. The test case focuses on reducing drag over a forward-facing step through optimal placement and sizing of an upstream obstacle. Results demonstrate that the inclusion of labeled data significantly enhances the accuracy and convergence rates of FCNNs, particularly in predicting flow separation and recirculation regions, and improves the stability of design optimization outcomes. Conversely, FNNs exhibit inconsistent responses to parameter changes when trained with labeled data, suggesting limitations in their applicability for certain design optimization tasks. The findings reveal that FCNNs trained with a balanced integration of data and physics constraints outperform both data-only and physics-only models, highlighting the importance of optimizing the training approach based on the specific requirements of fluid mechanics applications.https://www.mdpi.com/2311-5521/9/12/296machine learningPINNcomputational fluid dynamicsNavier–Stokeslaminar flowdata-driven fluid mechanics
spellingShingle Erik Gustafsson
Magnus Andersson
Investigating the Effects of Labeled Data on Parameterized Physics-Informed Neural Networks for Surrogate Modeling: Design Optimization for Drag Reduction over a Forward-Facing Step
Fluids
machine learning
PINN
computational fluid dynamics
Navier–Stokes
laminar flow
data-driven fluid mechanics
title Investigating the Effects of Labeled Data on Parameterized Physics-Informed Neural Networks for Surrogate Modeling: Design Optimization for Drag Reduction over a Forward-Facing Step
title_full Investigating the Effects of Labeled Data on Parameterized Physics-Informed Neural Networks for Surrogate Modeling: Design Optimization for Drag Reduction over a Forward-Facing Step
title_fullStr Investigating the Effects of Labeled Data on Parameterized Physics-Informed Neural Networks for Surrogate Modeling: Design Optimization for Drag Reduction over a Forward-Facing Step
title_full_unstemmed Investigating the Effects of Labeled Data on Parameterized Physics-Informed Neural Networks for Surrogate Modeling: Design Optimization for Drag Reduction over a Forward-Facing Step
title_short Investigating the Effects of Labeled Data on Parameterized Physics-Informed Neural Networks for Surrogate Modeling: Design Optimization for Drag Reduction over a Forward-Facing Step
title_sort investigating the effects of labeled data on parameterized physics informed neural networks for surrogate modeling design optimization for drag reduction over a forward facing step
topic machine learning
PINN
computational fluid dynamics
Navier–Stokes
laminar flow
data-driven fluid mechanics
url https://www.mdpi.com/2311-5521/9/12/296
work_keys_str_mv AT erikgustafsson investigatingtheeffectsoflabeleddataonparameterizedphysicsinformedneuralnetworksforsurrogatemodelingdesignoptimizationfordragreductionoveraforwardfacingstep
AT magnusandersson investigatingtheeffectsoflabeleddataonparameterizedphysicsinformedneuralnetworksforsurrogatemodelingdesignoptimizationfordragreductionoveraforwardfacingstep