A deep learning based prediction model for effective elastic properties of porous materials

Abstract With the development of the economy and society, porous materials have been widely used in various fields due to their unique structure and function. Therefore, it is of great significance to analyze the mechanical properties of porous materials. In traditional analysis methods, experimenta...

Full description

Saved in:
Bibliographic Details
Main Authors: Chang Liu, Ran Guo, Yangming Su
Format: Article
Language:English
Published: Nature Portfolio 2025-02-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-90016-0
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850185392111747072
author Chang Liu
Ran Guo
Yangming Su
author_facet Chang Liu
Ran Guo
Yangming Su
author_sort Chang Liu
collection DOAJ
description Abstract With the development of the economy and society, porous materials have been widely used in various fields due to their unique structure and function. Therefore, it is of great significance to analyze the mechanical properties of porous materials. In traditional analysis methods, experimental and numerical simulation methods are mainly used. When conducting finite element numerical simulation analysis on porous materials, a large number of fine grids need to be divided, and the calculation process is time-consuming and laborious. This article randomly generates porous microstructure models through algorithms and uses efficient quadtree algorithms to calculate their mechanical properties, thereby obtaining a large amount of machine-learning sample data. Furthermore, a neural network-based machine learning algorithm is established to predict the mechanical properties of porous materials. By using microstructure images as the input layer of the model, the mechanical properties under corresponding conditions can be directly predicted. This study provides a new method for predicting mechanical properties based on microstructure images. It has been verified that the mechanical properties directly predicted by the network are similar to the actual ones, with high accuracy and computational efficiency.
format Article
id doaj-art-ba2516587dcf47c2b25bc08f7fe20cf9
institution OA Journals
issn 2045-2322
language English
publishDate 2025-02-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-ba2516587dcf47c2b25bc08f7fe20cf92025-08-20T02:16:45ZengNature PortfolioScientific Reports2045-23222025-02-0115111410.1038/s41598-025-90016-0A deep learning based prediction model for effective elastic properties of porous materialsChang Liu0Ran Guo1Yangming Su2Faculty of Civil Engineering and Mechanics, Kunming University of Science and TechnologyFaculty of Civil Engineering and Mechanics, Kunming University of Science and TechnologyFaculty of Civil Engineering and Mechanics, Kunming University of Science and TechnologyAbstract With the development of the economy and society, porous materials have been widely used in various fields due to their unique structure and function. Therefore, it is of great significance to analyze the mechanical properties of porous materials. In traditional analysis methods, experimental and numerical simulation methods are mainly used. When conducting finite element numerical simulation analysis on porous materials, a large number of fine grids need to be divided, and the calculation process is time-consuming and laborious. This article randomly generates porous microstructure models through algorithms and uses efficient quadtree algorithms to calculate their mechanical properties, thereby obtaining a large amount of machine-learning sample data. Furthermore, a neural network-based machine learning algorithm is established to predict the mechanical properties of porous materials. By using microstructure images as the input layer of the model, the mechanical properties under corresponding conditions can be directly predicted. This study provides a new method for predicting mechanical properties based on microstructure images. It has been verified that the mechanical properties directly predicted by the network are similar to the actual ones, with high accuracy and computational efficiency.https://doi.org/10.1038/s41598-025-90016-0Deep learningPorous materialsQuadtree algorithmConvolutional neural network (CNN)
spellingShingle Chang Liu
Ran Guo
Yangming Su
A deep learning based prediction model for effective elastic properties of porous materials
Scientific Reports
Deep learning
Porous materials
Quadtree algorithm
Convolutional neural network (CNN)
title A deep learning based prediction model for effective elastic properties of porous materials
title_full A deep learning based prediction model for effective elastic properties of porous materials
title_fullStr A deep learning based prediction model for effective elastic properties of porous materials
title_full_unstemmed A deep learning based prediction model for effective elastic properties of porous materials
title_short A deep learning based prediction model for effective elastic properties of porous materials
title_sort deep learning based prediction model for effective elastic properties of porous materials
topic Deep learning
Porous materials
Quadtree algorithm
Convolutional neural network (CNN)
url https://doi.org/10.1038/s41598-025-90016-0
work_keys_str_mv AT changliu adeeplearningbasedpredictionmodelforeffectiveelasticpropertiesofporousmaterials
AT ranguo adeeplearningbasedpredictionmodelforeffectiveelasticpropertiesofporousmaterials
AT yangmingsu adeeplearningbasedpredictionmodelforeffectiveelasticpropertiesofporousmaterials
AT changliu deeplearningbasedpredictionmodelforeffectiveelasticpropertiesofporousmaterials
AT ranguo deeplearningbasedpredictionmodelforeffectiveelasticpropertiesofporousmaterials
AT yangmingsu deeplearningbasedpredictionmodelforeffectiveelasticpropertiesofporousmaterials