Deep Learning Approach to Mechanical Property Prediction of Single-Network Hydrogel

Hydrogel has a complex network structure with inhomogeneous and random distribution of polymer chains. Much effort has been paid to fully understand the relationship between mesoscopic network structure and macroscopic mechanical properties of hydrogels. In this paper, we develop a deep learning app...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Jing-Ang Zhu, Yetong Jia, Jincheng Lei, Zishun Liu
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	deep learning hydrogel network mechanical property convolutional neural network self-avoiding walk Mathematics QA1-939
Acceso en línea:	https://doaj.org/article/45f51acdab934d4abd0d001bd3104004
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:45f51acdab934d4abd0d001bd3104004
record_format	dspace
spelling	oai:doaj.org-article:45f51acdab934d4abd0d001bd31040042021-11-11T18:20:17ZDeep Learning Approach to Mechanical Property Prediction of Single-Network Hydrogel10.3390/math92128042227-7390https://doaj.org/article/45f51acdab934d4abd0d001bd31040042021-11-01T00:00:00Zhttps://www.mdpi.com/2227-7390/9/21/2804https://doaj.org/toc/2227-7390Hydrogel has a complex network structure with inhomogeneous and random distribution of polymer chains. Much effort has been paid to fully understand the relationship between mesoscopic network structure and macroscopic mechanical properties of hydrogels. In this paper, we develop a deep learning approach to predict the mechanical properties of hydrogels from polymer network structures. First, network structural models of hydrogels are constructed from mesoscopic scale using self-avoiding walk method. The constructed model is similar to the real hydrogel network. Then, two deep learning models are proposed to capture the nonlinear mapping from mesoscopic hydrogel network structural model to its macroscale mechanical property. A deep neural network and a 3D convolutional neural network containing the physical information of the network structural model are implemented to predict the nominal stress–stretch curves of hydrogels under uniaxial tension. Our results show that the end-to-end deep learning framework can effectively predict the nominal stress–stretch curves of hydrogel within a wide range of mesoscopic network structures, which demonstrates that the deep learning models are able to capture the internal relationship between complex network structures and mechanical properties. We hope this approach can provide guidance to structural design and material property design of different soft materials.Jing-Ang ZhuYetong JiaJincheng LeiZishun LiuMDPI AGarticledeep learninghydrogel networkmechanical propertyconvolutional neural networkself-avoiding walkMathematicsQA1-939ENMathematics, Vol 9, Iss 2804, p 2804 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	deep learning hydrogel network mechanical property convolutional neural network self-avoiding walk Mathematics QA1-939
spellingShingle	deep learning hydrogel network mechanical property convolutional neural network self-avoiding walk Mathematics QA1-939 Jing-Ang Zhu Yetong Jia Jincheng Lei Zishun Liu Deep Learning Approach to Mechanical Property Prediction of Single-Network Hydrogel
description	Hydrogel has a complex network structure with inhomogeneous and random distribution of polymer chains. Much effort has been paid to fully understand the relationship between mesoscopic network structure and macroscopic mechanical properties of hydrogels. In this paper, we develop a deep learning approach to predict the mechanical properties of hydrogels from polymer network structures. First, network structural models of hydrogels are constructed from mesoscopic scale using self-avoiding walk method. The constructed model is similar to the real hydrogel network. Then, two deep learning models are proposed to capture the nonlinear mapping from mesoscopic hydrogel network structural model to its macroscale mechanical property. A deep neural network and a 3D convolutional neural network containing the physical information of the network structural model are implemented to predict the nominal stress–stretch curves of hydrogels under uniaxial tension. Our results show that the end-to-end deep learning framework can effectively predict the nominal stress–stretch curves of hydrogel within a wide range of mesoscopic network structures, which demonstrates that the deep learning models are able to capture the internal relationship between complex network structures and mechanical properties. We hope this approach can provide guidance to structural design and material property design of different soft materials.
format	article
author	Jing-Ang Zhu Yetong Jia Jincheng Lei Zishun Liu
author_facet	Jing-Ang Zhu Yetong Jia Jincheng Lei Zishun Liu
author_sort	Jing-Ang Zhu
title	Deep Learning Approach to Mechanical Property Prediction of Single-Network Hydrogel
title_short	Deep Learning Approach to Mechanical Property Prediction of Single-Network Hydrogel
title_full	Deep Learning Approach to Mechanical Property Prediction of Single-Network Hydrogel
title_fullStr	Deep Learning Approach to Mechanical Property Prediction of Single-Network Hydrogel
title_full_unstemmed	Deep Learning Approach to Mechanical Property Prediction of Single-Network Hydrogel
title_sort	deep learning approach to mechanical property prediction of single-network hydrogel
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/45f51acdab934d4abd0d001bd3104004
work_keys_str_mv	AT jingangzhu deeplearningapproachtomechanicalpropertypredictionofsinglenetworkhydrogel AT yetongjia deeplearningapproachtomechanicalpropertypredictionofsinglenetworkhydrogel AT jinchenglei deeplearningapproachtomechanicalpropertypredictionofsinglenetworkhydrogel AT zishunliu deeplearningapproachtomechanicalpropertypredictionofsinglenetworkhydrogel
_version_	1718431880591704064

Deep Learning Approach to Mechanical Property Prediction of Single-Network Hydrogel

Ejemplares similares