A machine learning framework for damage mechanism identification from acoustic emissions in unidirectional SiC/SiC composites

Abstract In this work, we demonstrate that damage mechanism identification from acoustic emission (AE) signals generated in minicomposites with elastically similar constituents is possible. AE waveforms were generated by SiC/SiC ceramic matrix minicomposites (CMCs) loaded under uniaxial tension and...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	C. Muir, B. Swaminathan, K. Fields, A. S. Almansour, K. Sevener, C. Smith, M. Presby, J. D. Kiser, T. M. Pollock, S. Daly
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Materials of engineering and construction. Mechanics of materials TA401-492 Computer software QA76.75-76.765
Acceso en línea:	https://doaj.org/article/a32a34e63afa41ae95684f6380fb93fe
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:a32a34e63afa41ae95684f6380fb93fe
record_format	dspace
spelling	oai:doaj.org-article:a32a34e63afa41ae95684f6380fb93fe2021-12-02T15:16:05ZA machine learning framework for damage mechanism identification from acoustic emissions in unidirectional SiC/SiC composites10.1038/s41524-021-00620-72057-3960https://doaj.org/article/a32a34e63afa41ae95684f6380fb93fe2021-09-01T00:00:00Zhttps://doi.org/10.1038/s41524-021-00620-7https://doaj.org/toc/2057-3960Abstract In this work, we demonstrate that damage mechanism identification from acoustic emission (AE) signals generated in minicomposites with elastically similar constituents is possible. AE waveforms were generated by SiC/SiC ceramic matrix minicomposites (CMCs) loaded under uniaxial tension and recorded by four sensors (two models with each model placed at two ends). Signals were encoded with a modified partial power scheme and subsequently partitioned through spectral clustering. Matrix cracking and fiber failure were identified based on the frequency information contained in the AE event they produced, despite the similar constituent elastic properties of the matrix and fiber. Importantly, the resultant identification of AE events closely followed CMC damage chronology, wherein early matrix cracking is later followed by fiber breaks, even though the approach is fully domain-knowledge agnostic. Additionally, the partitions were highly precise across both the model and location of the sensors, and the partitioning was repeatable. The presented approach is promising for CMCs and other composite systems with elastically similar constituents.C. MuirB. SwaminathanK. FieldsA. S. AlmansourK. SevenerC. SmithM. PresbyJ. D. KiserT. M. PollockS. DalyNature PortfolioarticleMaterials of engineering and construction. Mechanics of materialsTA401-492Computer softwareQA76.75-76.765ENnpj Computational Materials, Vol 7, Iss 1, Pp 1-10 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Materials of engineering and construction. Mechanics of materials TA401-492 Computer software QA76.75-76.765
spellingShingle	Materials of engineering and construction. Mechanics of materials TA401-492 Computer software QA76.75-76.765 C. Muir B. Swaminathan K. Fields A. S. Almansour K. Sevener C. Smith M. Presby J. D. Kiser T. M. Pollock S. Daly A machine learning framework for damage mechanism identification from acoustic emissions in unidirectional SiC/SiC composites
description	Abstract In this work, we demonstrate that damage mechanism identification from acoustic emission (AE) signals generated in minicomposites with elastically similar constituents is possible. AE waveforms were generated by SiC/SiC ceramic matrix minicomposites (CMCs) loaded under uniaxial tension and recorded by four sensors (two models with each model placed at two ends). Signals were encoded with a modified partial power scheme and subsequently partitioned through spectral clustering. Matrix cracking and fiber failure were identified based on the frequency information contained in the AE event they produced, despite the similar constituent elastic properties of the matrix and fiber. Importantly, the resultant identification of AE events closely followed CMC damage chronology, wherein early matrix cracking is later followed by fiber breaks, even though the approach is fully domain-knowledge agnostic. Additionally, the partitions were highly precise across both the model and location of the sensors, and the partitioning was repeatable. The presented approach is promising for CMCs and other composite systems with elastically similar constituents.
format	article
author	C. Muir B. Swaminathan K. Fields A. S. Almansour K. Sevener C. Smith M. Presby J. D. Kiser T. M. Pollock S. Daly
author_facet	C. Muir B. Swaminathan K. Fields A. S. Almansour K. Sevener C. Smith M. Presby J. D. Kiser T. M. Pollock S. Daly
author_sort	C. Muir
title	A machine learning framework for damage mechanism identification from acoustic emissions in unidirectional SiC/SiC composites
title_short	A machine learning framework for damage mechanism identification from acoustic emissions in unidirectional SiC/SiC composites
title_full	A machine learning framework for damage mechanism identification from acoustic emissions in unidirectional SiC/SiC composites
title_fullStr	A machine learning framework for damage mechanism identification from acoustic emissions in unidirectional SiC/SiC composites
title_full_unstemmed	A machine learning framework for damage mechanism identification from acoustic emissions in unidirectional SiC/SiC composites
title_sort	machine learning framework for damage mechanism identification from acoustic emissions in unidirectional sic/sic composites
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/a32a34e63afa41ae95684f6380fb93fe
work_keys_str_mv	AT cmuir amachinelearningframeworkfordamagemechanismidentificationfromacousticemissionsinunidirectionalsicsiccomposites AT bswaminathan amachinelearningframeworkfordamagemechanismidentificationfromacousticemissionsinunidirectionalsicsiccomposites AT kfields amachinelearningframeworkfordamagemechanismidentificationfromacousticemissionsinunidirectionalsicsiccomposites AT asalmansour amachinelearningframeworkfordamagemechanismidentificationfromacousticemissionsinunidirectionalsicsiccomposites AT ksevener amachinelearningframeworkfordamagemechanismidentificationfromacousticemissionsinunidirectionalsicsiccomposites AT csmith amachinelearningframeworkfordamagemechanismidentificationfromacousticemissionsinunidirectionalsicsiccomposites AT mpresby amachinelearningframeworkfordamagemechanismidentificationfromacousticemissionsinunidirectionalsicsiccomposites AT jdkiser amachinelearningframeworkfordamagemechanismidentificationfromacousticemissionsinunidirectionalsicsiccomposites AT tmpollock amachinelearningframeworkfordamagemechanismidentificationfromacousticemissionsinunidirectionalsicsiccomposites AT sdaly amachinelearningframeworkfordamagemechanismidentificationfromacousticemissionsinunidirectionalsicsiccomposites AT cmuir machinelearningframeworkfordamagemechanismidentificationfromacousticemissionsinunidirectionalsicsiccomposites AT bswaminathan machinelearningframeworkfordamagemechanismidentificationfromacousticemissionsinunidirectionalsicsiccomposites AT kfields machinelearningframeworkfordamagemechanismidentificationfromacousticemissionsinunidirectionalsicsiccomposites AT asalmansour machinelearningframeworkfordamagemechanismidentificationfromacousticemissionsinunidirectionalsicsiccomposites AT ksevener machinelearningframeworkfordamagemechanismidentificationfromacousticemissionsinunidirectionalsicsiccomposites AT csmith machinelearningframeworkfordamagemechanismidentificationfromacousticemissionsinunidirectionalsicsiccomposites AT mpresby machinelearningframeworkfordamagemechanismidentificationfromacousticemissionsinunidirectionalsicsiccomposites AT jdkiser machinelearningframeworkfordamagemechanismidentificationfromacousticemissionsinunidirectionalsicsiccomposites AT tmpollock machinelearningframeworkfordamagemechanismidentificationfromacousticemissionsinunidirectionalsicsiccomposites AT sdaly machinelearningframeworkfordamagemechanismidentificationfromacousticemissionsinunidirectionalsicsiccomposites
_version_	1718387526542032896

A machine learning framework for damage mechanism identification from acoustic emissions in unidirectional SiC/SiC composites

Ejemplares similares