Interlocking mechanism design based on deep-learning methods

Biological structural systems such as plant seedcoats, beak of woodpeckers or ammonites shells are characterized by complex wavy and re-entrant interlocking features. This allows to mitigate large deformations and deflect or arrest cracks, providing remarkable mechanical performances, much higher th...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Marco Maurizi, Chao Gao, Filippo Berto
Formato:	article
Lenguaje:	EN
Publicado:	Elsevier 2021
Materias:	Interlocking Sutured lines Machine learning Mechanical properties Engineering (General). Civil engineering (General) TA1-2040
Acceso en línea:	https://doaj.org/article/ff2ece379b184e96adc74acbe7f62d3e
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:ff2ece379b184e96adc74acbe7f62d3e
record_format	dspace
spelling	oai:doaj.org-article:ff2ece379b184e96adc74acbe7f62d3e2021-12-01T05:06:15ZInterlocking mechanism design based on deep-learning methods2666-496810.1016/j.apples.2021.100056https://doaj.org/article/ff2ece379b184e96adc74acbe7f62d3e2021-09-01T00:00:00Zhttp://www.sciencedirect.com/science/article/pii/S2666496821000224https://doaj.org/toc/2666-4968Biological structural systems such as plant seedcoats, beak of woodpeckers or ammonites shells are characterized by complex wavy and re-entrant interlocking features. This allows to mitigate large deformations and deflect or arrest cracks, providing remarkable mechanical performances, much higher than those of the constituent materials. Nature-inspired engineering interlocking joints has been recently proved to be an effective and novel design strategy. However, currently the design space of interlocking interfaces relies on relatively simple geometries, often built as a composition of symmetric circular or elliptical sutured lines. In the present contribution it is shown that deep-learning (DL) methods can be leveraged to enlarge the design space. Accurate and fast assessments of stiffness, strength and toughness of interlocking interfaces, generated through a cellular automaton-like method, can be obtained using a convolutional neural network trained on a limited number of finite element results. A simple application of a DL model for the recognition of interlocking mechanisms in 2-D interfaces is introduced. It is also shown that DL models, pre-trained on small resolution geometries, can accurately predict structural properties on larger design spaces with relatively small amounts of new training data. This work is addressed to give new insights into the study and design of a new generation of advanced and novel interlocked structures through data-driven methods.Marco MauriziChao GaoFilippo BertoElsevierarticleInterlockingSutured linesMachine learningMechanical propertiesEngineering (General). Civil engineering (General)TA1-2040ENApplications in Engineering Science, Vol 7, Iss , Pp 100056- (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Interlocking Sutured lines Machine learning Mechanical properties Engineering (General). Civil engineering (General) TA1-2040
spellingShingle	Interlocking Sutured lines Machine learning Mechanical properties Engineering (General). Civil engineering (General) TA1-2040 Marco Maurizi Chao Gao Filippo Berto Interlocking mechanism design based on deep-learning methods
description	Biological structural systems such as plant seedcoats, beak of woodpeckers or ammonites shells are characterized by complex wavy and re-entrant interlocking features. This allows to mitigate large deformations and deflect or arrest cracks, providing remarkable mechanical performances, much higher than those of the constituent materials. Nature-inspired engineering interlocking joints has been recently proved to be an effective and novel design strategy. However, currently the design space of interlocking interfaces relies on relatively simple geometries, often built as a composition of symmetric circular or elliptical sutured lines. In the present contribution it is shown that deep-learning (DL) methods can be leveraged to enlarge the design space. Accurate and fast assessments of stiffness, strength and toughness of interlocking interfaces, generated through a cellular automaton-like method, can be obtained using a convolutional neural network trained on a limited number of finite element results. A simple application of a DL model for the recognition of interlocking mechanisms in 2-D interfaces is introduced. It is also shown that DL models, pre-trained on small resolution geometries, can accurately predict structural properties on larger design spaces with relatively small amounts of new training data. This work is addressed to give new insights into the study and design of a new generation of advanced and novel interlocked structures through data-driven methods.
format	article
author	Marco Maurizi Chao Gao Filippo Berto
author_facet	Marco Maurizi Chao Gao Filippo Berto
author_sort	Marco Maurizi
title	Interlocking mechanism design based on deep-learning methods
title_short	Interlocking mechanism design based on deep-learning methods
title_full	Interlocking mechanism design based on deep-learning methods
title_fullStr	Interlocking mechanism design based on deep-learning methods
title_full_unstemmed	Interlocking mechanism design based on deep-learning methods
title_sort	interlocking mechanism design based on deep-learning methods
publisher	Elsevier
publishDate	2021
url	https://doaj.org/article/ff2ece379b184e96adc74acbe7f62d3e
work_keys_str_mv	AT marcomaurizi interlockingmechanismdesignbasedondeeplearningmethods AT chaogao interlockingmechanismdesignbasedondeeplearningmethods AT filippoberto interlockingmechanismdesignbasedondeeplearningmethods
_version_	1718405580833423360

Interlocking mechanism design based on deep-learning methods

Ejemplares similares