Design of acoustic absorbing metasurfaces using a data-driven approach

<div><p>The design of acoustic metasurfaces with desirable properties is challenging due to their artificial nature and the large space of physical and geometrical parameters. Until recently, design strategies were primarily based on numerical simulations based on finite-element or finit...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Hamza Baali (14603380) (author)
مؤلفون آخرون: Mahmoud Addouche (4422286) (author), Abdesselam Bouzerdoum (17900021) (author), Abdelkrim Khelif (4422280) (author)
منشور في: 2023
الموضوعات:
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1864513528331763712
author Hamza Baali (14603380)
author2 Mahmoud Addouche (4422286)
Abdesselam Bouzerdoum (17900021)
Abdelkrim Khelif (4422280)
author2_role author
author
author
author_facet Hamza Baali (14603380)
Mahmoud Addouche (4422286)
Abdesselam Bouzerdoum (17900021)
Abdelkrim Khelif (4422280)
author_role author
dc.creator.none.fl_str_mv Hamza Baali (14603380)
Mahmoud Addouche (4422286)
Abdesselam Bouzerdoum (17900021)
Abdelkrim Khelif (4422280)
dc.date.none.fl_str_mv 2023-05-29T03:00:00Z
dc.identifier.none.fl_str_mv 10.1038/s43246-023-00369-0
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/Design_of_acoustic_absorbing_metasurfaces_using_a_data-driven_approach/25139693
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Engineering
Materials engineering
Mechanical engineering
Information and computing sciences
Data management and data science
Machine learning
Metamaterials
Electromagnetic wave propagation
Acoustic wave propagation
Locally resonant structures (LRS)
Metasurfaces
Sound absorption
Acoustic cloaking
Complete sound reflection
Complete sound transmission
Wavefront tailoring
Finite Element methods (FEM)
Finite-difference time-domain (FDTD) methods
Genetic algorithms
Neural network architectures
Gradient-based optimization
Backpropagation algorithm
Mean squared error (MSE) loss
Levenberg-Marquardt algorithm
Two-Microphone transfer function method
Reflection factor
Dynamic signal acquisition module
dc.title.none.fl_str_mv Design of acoustic absorbing metasurfaces using a data-driven approach
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <div><p>The design of acoustic metasurfaces with desirable properties is challenging due to their artificial nature and the large space of physical and geometrical parameters. Until recently, design strategies were primarily based on numerical simulations based on finite-element or finite-difference time-domain methods, which are limited in terms of computational speed or complexity. Here, we present an efficient two-stage data-driven approach for analyzing and designing membrane-type metasurface absorbers with desirable characteristics. In the first stage, a forward model consisting of a neural network is trained to map an input, comprising the membrane parameters, to the observed sound absorption spectrum. In the second stage, the learned forward model is inverted to infer the input parameters that produce the desired absorption response. The metasurface membrane parameters, which serve as input to the neural network, are estimated by minimizing a loss function between the desired absorption profile and the output of the learned forward model. Two devices are then fabricated using the estimated membrane parameters. The measured acoustic absorption responses of the fabricated devices show a very close agreement with the desired responses.</p><p> </p></div><h2>Other Information</h2> <p> Published in: Communications Materials<br> License: <a href="https://creativecommons.org/licenses/by/4.0" target="_blank">https://creativecommons.org/licenses/by/4.0</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1038/s43246-023-00369-0" target="_blank">https://dx.doi.org/10.1038/s43246-023-00369-0</a></p>
eu_rights_str_mv openAccess
id Manara2_da4b0a89ae28d9b545ba0075656c083c
identifier_str_mv 10.1038/s43246-023-00369-0
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/25139693
publishDate 2023
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Design of acoustic absorbing metasurfaces using a data-driven approachHamza Baali (14603380)Mahmoud Addouche (4422286)Abdesselam Bouzerdoum (17900021)Abdelkrim Khelif (4422280)EngineeringMaterials engineeringMechanical engineeringInformation and computing sciencesData management and data scienceMachine learningMetamaterialsElectromagnetic wave propagationAcoustic wave propagationLocally resonant structures (LRS)MetasurfacesSound absorptionAcoustic cloakingComplete sound reflectionComplete sound transmissionWavefront tailoringFinite Element methods (FEM)Finite-difference time-domain (FDTD) methodsGenetic algorithmsNeural network architecturesGradient-based optimizationBackpropagation algorithmMean squared error (MSE) lossLevenberg-Marquardt algorithmTwo-Microphone transfer function methodReflection factorDynamic signal acquisition module<div><p>The design of acoustic metasurfaces with desirable properties is challenging due to their artificial nature and the large space of physical and geometrical parameters. Until recently, design strategies were primarily based on numerical simulations based on finite-element or finite-difference time-domain methods, which are limited in terms of computational speed or complexity. Here, we present an efficient two-stage data-driven approach for analyzing and designing membrane-type metasurface absorbers with desirable characteristics. In the first stage, a forward model consisting of a neural network is trained to map an input, comprising the membrane parameters, to the observed sound absorption spectrum. In the second stage, the learned forward model is inverted to infer the input parameters that produce the desired absorption response. The metasurface membrane parameters, which serve as input to the neural network, are estimated by minimizing a loss function between the desired absorption profile and the output of the learned forward model. Two devices are then fabricated using the estimated membrane parameters. The measured acoustic absorption responses of the fabricated devices show a very close agreement with the desired responses.</p><p> </p></div><h2>Other Information</h2> <p> Published in: Communications Materials<br> License: <a href="https://creativecommons.org/licenses/by/4.0" target="_blank">https://creativecommons.org/licenses/by/4.0</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1038/s43246-023-00369-0" target="_blank">https://dx.doi.org/10.1038/s43246-023-00369-0</a></p>2023-05-29T03:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1038/s43246-023-00369-0https://figshare.com/articles/journal_contribution/Design_of_acoustic_absorbing_metasurfaces_using_a_data-driven_approach/25139693CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/251396932023-05-29T03:00:00Z
spellingShingle Design of acoustic absorbing metasurfaces using a data-driven approach
Hamza Baali (14603380)
Engineering
Materials engineering
Mechanical engineering
Information and computing sciences
Data management and data science
Machine learning
Metamaterials
Electromagnetic wave propagation
Acoustic wave propagation
Locally resonant structures (LRS)
Metasurfaces
Sound absorption
Acoustic cloaking
Complete sound reflection
Complete sound transmission
Wavefront tailoring
Finite Element methods (FEM)
Finite-difference time-domain (FDTD) methods
Genetic algorithms
Neural network architectures
Gradient-based optimization
Backpropagation algorithm
Mean squared error (MSE) loss
Levenberg-Marquardt algorithm
Two-Microphone transfer function method
Reflection factor
Dynamic signal acquisition module
status_str publishedVersion
title Design of acoustic absorbing metasurfaces using a data-driven approach
title_full Design of acoustic absorbing metasurfaces using a data-driven approach
title_fullStr Design of acoustic absorbing metasurfaces using a data-driven approach
title_full_unstemmed Design of acoustic absorbing metasurfaces using a data-driven approach
title_short Design of acoustic absorbing metasurfaces using a data-driven approach
title_sort Design of acoustic absorbing metasurfaces using a data-driven approach
topic Engineering
Materials engineering
Mechanical engineering
Information and computing sciences
Data management and data science
Machine learning
Metamaterials
Electromagnetic wave propagation
Acoustic wave propagation
Locally resonant structures (LRS)
Metasurfaces
Sound absorption
Acoustic cloaking
Complete sound reflection
Complete sound transmission
Wavefront tailoring
Finite Element methods (FEM)
Finite-difference time-domain (FDTD) methods
Genetic algorithms
Neural network architectures
Gradient-based optimization
Backpropagation algorithm
Mean squared error (MSE) loss
Levenberg-Marquardt algorithm
Two-Microphone transfer function method
Reflection factor
Dynamic signal acquisition module