Investigation of Physics-Informed Neural Networks to Reconstruct a Flow Field with High Resolution
Particle image velocimetry (PIV) is a widely used experimental technique in ocean engineering, for instance, to study the vortex fields near marine risers and the wake fields behind wind turbines or ship propellers. However, the flow fields measured using PIV in water tanks or wind tunnels always ha...
Main Authors: | , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-10-01
|
Series: | Journal of Marine Science and Engineering |
Subjects: | |
Online Access: | https://www.mdpi.com/2077-1312/11/11/2045 |
_version_ | 1797458796600098816 |
---|---|
author | Zhou Yang Yuwang Xu Jionglin Jing Xuepeng Fu Bofu Wang Haojie Ren Mengmeng Zhang Tongxiao Sun |
author_facet | Zhou Yang Yuwang Xu Jionglin Jing Xuepeng Fu Bofu Wang Haojie Ren Mengmeng Zhang Tongxiao Sun |
author_sort | Zhou Yang |
collection | DOAJ |
description | Particle image velocimetry (PIV) is a widely used experimental technique in ocean engineering, for instance, to study the vortex fields near marine risers and the wake fields behind wind turbines or ship propellers. However, the flow fields measured using PIV in water tanks or wind tunnels always have low resolution; hence, it is difficult to accurately reveal the mechanics behind the complex phenomena sometimes observed. In this paper, physics-informed neural networks (PINNs), which introduce the Navier–Stokes equations or the continuity equation into the loss function during training to reconstruct a flow field with high resolution, are investigated. The accuracy is compared with the cubic spline interpolation method and a classic neural network in a case study of reconstructing a two-dimensional flow field around a cylinder, which is obtained through direct numerical simulation. Finally, the validated PINN method is applied to reconstruct a flow field measured using PIV and shows good performance. |
first_indexed | 2024-03-09T16:42:21Z |
format | Article |
id | doaj.art-ac81a6d19aa64deb87a533be47d10c14 |
institution | Directory Open Access Journal |
issn | 2077-1312 |
language | English |
last_indexed | 2024-03-09T16:42:21Z |
publishDate | 2023-10-01 |
publisher | MDPI AG |
record_format | Article |
series | Journal of Marine Science and Engineering |
spelling | doaj.art-ac81a6d19aa64deb87a533be47d10c142023-11-24T14:50:13ZengMDPI AGJournal of Marine Science and Engineering2077-13122023-10-011111204510.3390/jmse11112045Investigation of Physics-Informed Neural Networks to Reconstruct a Flow Field with High ResolutionZhou Yang0Yuwang Xu1Jionglin Jing2Xuepeng Fu3Bofu Wang4Haojie Ren5Mengmeng Zhang6Tongxiao Sun7State Key Laboratory of Ocean Engineering, Shanghai Jiao Tong University, Shanghai 200240, ChinaState Key Laboratory of Ocean Engineering, Shanghai Jiao Tong University, Shanghai 200240, ChinaState Key Laboratory of Ocean Engineering, Shanghai Jiao Tong University, Shanghai 200240, ChinaState Key Laboratory of Ocean Engineering, Shanghai Jiao Tong University, Shanghai 200240, ChinaShanghai Key Laboratory of Mechanics in Energy Engineering, Shanghai Institute of Applied Mathematics and Mechanics, School of Mechanics and Engineering Science, Shanghai University, Shanghai 200240, ChinaState Key Laboratory of Ocean Engineering, Shanghai Jiao Tong University, Shanghai 200240, ChinaState Key Laboratory of Ocean Engineering, Shanghai Jiao Tong University, Shanghai 200240, ChinaState Key Laboratory of Ocean Engineering, Shanghai Jiao Tong University, Shanghai 200240, ChinaParticle image velocimetry (PIV) is a widely used experimental technique in ocean engineering, for instance, to study the vortex fields near marine risers and the wake fields behind wind turbines or ship propellers. However, the flow fields measured using PIV in water tanks or wind tunnels always have low resolution; hence, it is difficult to accurately reveal the mechanics behind the complex phenomena sometimes observed. In this paper, physics-informed neural networks (PINNs), which introduce the Navier–Stokes equations or the continuity equation into the loss function during training to reconstruct a flow field with high resolution, are investigated. The accuracy is compared with the cubic spline interpolation method and a classic neural network in a case study of reconstructing a two-dimensional flow field around a cylinder, which is obtained through direct numerical simulation. Finally, the validated PINN method is applied to reconstruct a flow field measured using PIV and shows good performance.https://www.mdpi.com/2077-1312/11/11/2045physics-informed neural networkflow field reconstructionNavier–Stokes equationscontinuity equation |
spellingShingle | Zhou Yang Yuwang Xu Jionglin Jing Xuepeng Fu Bofu Wang Haojie Ren Mengmeng Zhang Tongxiao Sun Investigation of Physics-Informed Neural Networks to Reconstruct a Flow Field with High Resolution Journal of Marine Science and Engineering physics-informed neural network flow field reconstruction Navier–Stokes equations continuity equation |
title | Investigation of Physics-Informed Neural Networks to Reconstruct a Flow Field with High Resolution |
title_full | Investigation of Physics-Informed Neural Networks to Reconstruct a Flow Field with High Resolution |
title_fullStr | Investigation of Physics-Informed Neural Networks to Reconstruct a Flow Field with High Resolution |
title_full_unstemmed | Investigation of Physics-Informed Neural Networks to Reconstruct a Flow Field with High Resolution |
title_short | Investigation of Physics-Informed Neural Networks to Reconstruct a Flow Field with High Resolution |
title_sort | investigation of physics informed neural networks to reconstruct a flow field with high resolution |
topic | physics-informed neural network flow field reconstruction Navier–Stokes equations continuity equation |
url | https://www.mdpi.com/2077-1312/11/11/2045 |
work_keys_str_mv | AT zhouyang investigationofphysicsinformedneuralnetworkstoreconstructaflowfieldwithhighresolution AT yuwangxu investigationofphysicsinformedneuralnetworkstoreconstructaflowfieldwithhighresolution AT jionglinjing investigationofphysicsinformedneuralnetworkstoreconstructaflowfieldwithhighresolution AT xuepengfu investigationofphysicsinformedneuralnetworkstoreconstructaflowfieldwithhighresolution AT bofuwang investigationofphysicsinformedneuralnetworkstoreconstructaflowfieldwithhighresolution AT haojieren investigationofphysicsinformedneuralnetworkstoreconstructaflowfieldwithhighresolution AT mengmengzhang investigationofphysicsinformedneuralnetworkstoreconstructaflowfieldwithhighresolution AT tongxiaosun investigationofphysicsinformedneuralnetworkstoreconstructaflowfieldwithhighresolution |