Acoustic field visualization and source localization via physics-informed learning of sparse data with adaptive sampling

Traditional methods for acoustic field visualization require considerable effort for capturing large amounts of acoustic data to achieve a high resolution field map, highly limiting their widespread use. In this study, we propose an approach for acoustic field visualization based on physics-informed...

Full description

Saved in:
Bibliographic Details
Main Authors: Jian Chen, Dan Xu, Weijian Fang, Shiwei Wu, Haiteng Wu
Format: Article
Language:English
Published: AIP Publishing LLC 2024-11-01
Series:AIP Advances
Online Access:http://dx.doi.org/10.1063/5.0227921
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850137712498049024
author Jian Chen
Dan Xu
Weijian Fang
Shiwei Wu
Haiteng Wu
author_facet Jian Chen
Dan Xu
Weijian Fang
Shiwei Wu
Haiteng Wu
author_sort Jian Chen
collection DOAJ
description Traditional methods for acoustic field visualization require considerable effort for capturing large amounts of acoustic data to achieve a high resolution field map, highly limiting their widespread use. In this study, we propose an approach for acoustic field visualization based on physics-informed neural networks (PINNs) by using a small amount of data, subsequently realizing accurate acoustic source localization. First, we present a PINN model integrated with an acoustic Helmholtz equation and adaptive sampling, the performance of which is testified via numerical simulations. The “no mesh” character of PINN enables achieving high resolution acoustic field visualization without requiring the capture of numerous data in advance. Furthermore, we experimentally validate the performance of the proposed method, which demonstrates that the acoustic sources can be precisely localized with sparse field data acquisition within a small area. This work would find potential applications in various acoustics, such as acoustic communication, biomedical imaging, and virtual reality.
format Article
id doaj-art-5e92f712ddef48568e4efb71b1ea4e84
institution OA Journals
issn 2158-3226
language English
publishDate 2024-11-01
publisher AIP Publishing LLC
record_format Article
series AIP Advances
spelling doaj-art-5e92f712ddef48568e4efb71b1ea4e842025-08-20T02:30:46ZengAIP Publishing LLCAIP Advances2158-32262024-11-011411115308115308-610.1063/5.0227921Acoustic field visualization and source localization via physics-informed learning of sparse data with adaptive samplingJian Chen0Dan Xu1Weijian Fang2Shiwei Wu3Haiteng Wu4State Key Laboratory of Fluid Power and Mechatronic Systems, School of Mechanical Engineering, Zhejiang University, Hangzhou 310027, ChinaState Key Laboratory of Fluid Power and Mechatronic Systems, School of Mechanical Engineering, Zhejiang University, Hangzhou 310027, ChinaState Key Laboratory of Fluid Power and Mechatronic Systems, School of Mechanical Engineering, Zhejiang University, Hangzhou 310027, ChinaState Key Laboratory of Fluid Power and Mechatronic Systems, School of Mechanical Engineering, Zhejiang University, Hangzhou 310027, ChinaKey Laboratory of Intelligent Robot for Operation and Maintenance of Zhejiang Province, Hangzhou Shenhao Technology, Hangzhou 311121, ChinaTraditional methods for acoustic field visualization require considerable effort for capturing large amounts of acoustic data to achieve a high resolution field map, highly limiting their widespread use. In this study, we propose an approach for acoustic field visualization based on physics-informed neural networks (PINNs) by using a small amount of data, subsequently realizing accurate acoustic source localization. First, we present a PINN model integrated with an acoustic Helmholtz equation and adaptive sampling, the performance of which is testified via numerical simulations. The “no mesh” character of PINN enables achieving high resolution acoustic field visualization without requiring the capture of numerous data in advance. Furthermore, we experimentally validate the performance of the proposed method, which demonstrates that the acoustic sources can be precisely localized with sparse field data acquisition within a small area. This work would find potential applications in various acoustics, such as acoustic communication, biomedical imaging, and virtual reality.http://dx.doi.org/10.1063/5.0227921
spellingShingle Jian Chen
Dan Xu
Weijian Fang
Shiwei Wu
Haiteng Wu
Acoustic field visualization and source localization via physics-informed learning of sparse data with adaptive sampling
AIP Advances
title Acoustic field visualization and source localization via physics-informed learning of sparse data with adaptive sampling
title_full Acoustic field visualization and source localization via physics-informed learning of sparse data with adaptive sampling
title_fullStr Acoustic field visualization and source localization via physics-informed learning of sparse data with adaptive sampling
title_full_unstemmed Acoustic field visualization and source localization via physics-informed learning of sparse data with adaptive sampling
title_short Acoustic field visualization and source localization via physics-informed learning of sparse data with adaptive sampling
title_sort acoustic field visualization and source localization via physics informed learning of sparse data with adaptive sampling
url http://dx.doi.org/10.1063/5.0227921
work_keys_str_mv AT jianchen acousticfieldvisualizationandsourcelocalizationviaphysicsinformedlearningofsparsedatawithadaptivesampling
AT danxu acousticfieldvisualizationandsourcelocalizationviaphysicsinformedlearningofsparsedatawithadaptivesampling
AT weijianfang acousticfieldvisualizationandsourcelocalizationviaphysicsinformedlearningofsparsedatawithadaptivesampling
AT shiweiwu acousticfieldvisualizationandsourcelocalizationviaphysicsinformedlearningofsparsedatawithadaptivesampling
AT haitengwu acousticfieldvisualizationandsourcelocalizationviaphysicsinformedlearningofsparsedatawithadaptivesampling