Damage mechanism identification in composites via machine learning and acoustic emission
Abstract Damage mechanism identification has scientific and practical ramifications for the structural health monitoring, design, and application of composite systems. Recent advances in machine learning uncover pathways to identify the waveform-damage mechanism relationship in higher-dimensional sp...
Main Authors: | , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Publishing Group
2021-06-01
|
Series: | npj Computational Materials |
Online Access: | https://doi.org/10.1038/s41524-021-00565-x |
id |
doaj-5a391a082cb849568002aaccc64712ce |
---|---|
record_format |
Article |
spelling |
doaj-5a391a082cb849568002aaccc64712ce2021-06-27T11:19:30ZengNature Publishing Groupnpj Computational Materials2057-39602021-06-017111510.1038/s41524-021-00565-xDamage mechanism identification in composites via machine learning and acoustic emissionC. Muir0B. Swaminathan1A. S. Almansour2K. Sevener3C. Smith4M. Presby5J. D. Kiser6T. M. Pollock7S. Daly8Materials Department, University of California-Santa BarbaraMaterials Department, University of California-Santa BarbaraNASA Glenn Research CenterMaterials Science and Engineering Department, University of Michigan-Ann ArborNASA Glenn Research CenterNASA Glenn Research CenterNASA Glenn Research CenterMaterials Department, University of California-Santa BarbaraMechanical Engineering Department, University of California-Santa BarbaraAbstract Damage mechanism identification has scientific and practical ramifications for the structural health monitoring, design, and application of composite systems. Recent advances in machine learning uncover pathways to identify the waveform-damage mechanism relationship in higher-dimensional spaces for a comprehensive understanding of damage evolution. This review evaluates the state of the field, beginning with a physics-based understanding of acoustic emission waveform feature extraction, followed by a detailed overview of waveform clustering, labeling, and error analysis strategies. Fundamental requirements for damage mechanism identification in any machine learning framework, including those currently in use, under development, and yet to be explored, are discussed.https://doi.org/10.1038/s41524-021-00565-x |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
C. Muir B. Swaminathan A. S. Almansour K. Sevener C. Smith M. Presby J. D. Kiser T. M. Pollock S. Daly |
spellingShingle |
C. Muir B. Swaminathan A. S. Almansour K. Sevener C. Smith M. Presby J. D. Kiser T. M. Pollock S. Daly Damage mechanism identification in composites via machine learning and acoustic emission npj Computational Materials |
author_facet |
C. Muir B. Swaminathan A. S. Almansour K. Sevener C. Smith M. Presby J. D. Kiser T. M. Pollock S. Daly |
author_sort |
C. Muir |
title |
Damage mechanism identification in composites via machine learning and acoustic emission |
title_short |
Damage mechanism identification in composites via machine learning and acoustic emission |
title_full |
Damage mechanism identification in composites via machine learning and acoustic emission |
title_fullStr |
Damage mechanism identification in composites via machine learning and acoustic emission |
title_full_unstemmed |
Damage mechanism identification in composites via machine learning and acoustic emission |
title_sort |
damage mechanism identification in composites via machine learning and acoustic emission |
publisher |
Nature Publishing Group |
series |
npj Computational Materials |
issn |
2057-3960 |
publishDate |
2021-06-01 |
description |
Abstract Damage mechanism identification has scientific and practical ramifications for the structural health monitoring, design, and application of composite systems. Recent advances in machine learning uncover pathways to identify the waveform-damage mechanism relationship in higher-dimensional spaces for a comprehensive understanding of damage evolution. This review evaluates the state of the field, beginning with a physics-based understanding of acoustic emission waveform feature extraction, followed by a detailed overview of waveform clustering, labeling, and error analysis strategies. Fundamental requirements for damage mechanism identification in any machine learning framework, including those currently in use, under development, and yet to be explored, are discussed. |
url |
https://doi.org/10.1038/s41524-021-00565-x |
work_keys_str_mv |
AT cmuir damagemechanismidentificationincompositesviamachinelearningandacousticemission AT bswaminathan damagemechanismidentificationincompositesviamachinelearningandacousticemission AT asalmansour damagemechanismidentificationincompositesviamachinelearningandacousticemission AT ksevener damagemechanismidentificationincompositesviamachinelearningandacousticemission AT csmith damagemechanismidentificationincompositesviamachinelearningandacousticemission AT mpresby damagemechanismidentificationincompositesviamachinelearningandacousticemission AT jdkiser damagemechanismidentificationincompositesviamachinelearningandacousticemission AT tmpollock damagemechanismidentificationincompositesviamachinelearningandacousticemission AT sdaly damagemechanismidentificationincompositesviamachinelearningandacousticemission |
_version_ |
1721358000111747072 |