Quantitative relations between curing processes and local properties within thick composites based on simulation and machine learning

Overheating is almost inevitable during the curing of thick polymer matrix composite parts, which always induces degradation of the mechanical properties. To explore the relationship between the local process variables and the property distribution of interlaminar shear strengths and compression str...

Full description

Bibliographic Details
Main Authors: Yubo Zhou, Min Li, Qiao Cheng, Shaokai Wang, Yizhuo Gu, Xiangbao Chen
Format: Article
Language:English
Published: Elsevier 2023-02-01
Series:Materials & Design
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S0264127523001016
_version_ 1811158437550096384
author Yubo Zhou
Min Li
Qiao Cheng
Shaokai Wang
Yizhuo Gu
Xiangbao Chen
author_facet Yubo Zhou
Min Li
Qiao Cheng
Shaokai Wang
Yizhuo Gu
Xiangbao Chen
author_sort Yubo Zhou
collection DOAJ
description Overheating is almost inevitable during the curing of thick polymer matrix composite parts, which always induces degradation of the mechanical properties. To explore the relationship between the local process variables and the property distribution of interlaminar shear strengths and compression strengths inside thick composites, experiments and relative simulations were conducted herein. Based on machine learning techniques, a convolutional autoencoder (CAE) was used to evaluate the spatial distributions of temperature, cure degree, and stress during autoclave curing process of thick composites. The results demonstrate a strong linear relationship between the spatial distribution of stress with the property values of interlaminar shear strengths and compressive strengths. This indicates that the stress distribution history strongly impacts the mechanical properties of thick laminates, which is usually neglected in previous studies that only concerns the stress magnitude.
first_indexed 2024-04-10T05:24:41Z
format Article
id doaj.art-584552c6de8c4b61b10bc8245723a4b8
institution Directory Open Access Journal
issn 0264-1275
language English
last_indexed 2024-04-10T05:24:41Z
publishDate 2023-02-01
publisher Elsevier
record_format Article
series Materials & Design
spelling doaj.art-584552c6de8c4b61b10bc8245723a4b82023-03-08T04:13:52ZengElsevierMaterials & Design0264-12752023-02-01226111686Quantitative relations between curing processes and local properties within thick composites based on simulation and machine learningYubo Zhou0Min Li1Qiao Cheng2Shaokai Wang3Yizhuo Gu4Xiangbao Chen5School of Materials Science and Engineering, Beihang University, No. 37 Xueyuan Road, Haidian District, Beijing 100191, ChinaSchool of Materials Science and Engineering, Beihang University, No. 37 Xueyuan Road, Haidian District, Beijing 100191, China; Ningbo Institute of Technology, Beihang University, Beilun District, Ningbo 315800, China; Corresponding author at: School of Materials Science and Engineering, Beihang University, No. 37 Xueyuan Road, Haidian District, Beijing 100191, China.School of Materials Science and Engineering, Beihang University, No. 37 Xueyuan Road, Haidian District, Beijing 100191, ChinaSchool of Materials Science and Engineering, Beihang University, No. 37 Xueyuan Road, Haidian District, Beijing 100191, China; Ningbo Institute of Technology, Beihang University, Beilun District, Ningbo 315800, ChinaResearch Institute of Frontier Science, Beihang University, No. 37 Xueyuan Road, Haidian District, Beijing 100191, ChinaBejing Institute of Aeronautical Materials, Aero Engine Corporation of China, No.8, Hangcai Avenue, Haidian District, Beijing 100095, ChinaOverheating is almost inevitable during the curing of thick polymer matrix composite parts, which always induces degradation of the mechanical properties. To explore the relationship between the local process variables and the property distribution of interlaminar shear strengths and compression strengths inside thick composites, experiments and relative simulations were conducted herein. Based on machine learning techniques, a convolutional autoencoder (CAE) was used to evaluate the spatial distributions of temperature, cure degree, and stress during autoclave curing process of thick composites. The results demonstrate a strong linear relationship between the spatial distribution of stress with the property values of interlaminar shear strengths and compressive strengths. This indicates that the stress distribution history strongly impacts the mechanical properties of thick laminates, which is usually neglected in previous studies that only concerns the stress magnitude.http://www.sciencedirect.com/science/article/pii/S0264127523001016Machine learningAutoclave process simulationThick compositesMechanical propertiesStress distribution
spellingShingle Yubo Zhou
Min Li
Qiao Cheng
Shaokai Wang
Yizhuo Gu
Xiangbao Chen
Quantitative relations between curing processes and local properties within thick composites based on simulation and machine learning
Materials & Design
Machine learning
Autoclave process simulation
Thick composites
Mechanical properties
Stress distribution
title Quantitative relations between curing processes and local properties within thick composites based on simulation and machine learning
title_full Quantitative relations between curing processes and local properties within thick composites based on simulation and machine learning
title_fullStr Quantitative relations between curing processes and local properties within thick composites based on simulation and machine learning
title_full_unstemmed Quantitative relations between curing processes and local properties within thick composites based on simulation and machine learning
title_short Quantitative relations between curing processes and local properties within thick composites based on simulation and machine learning
title_sort quantitative relations between curing processes and local properties within thick composites based on simulation and machine learning
topic Machine learning
Autoclave process simulation
Thick composites
Mechanical properties
Stress distribution
url http://www.sciencedirect.com/science/article/pii/S0264127523001016
work_keys_str_mv AT yubozhou quantitativerelationsbetweencuringprocessesandlocalpropertieswithinthickcompositesbasedonsimulationandmachinelearning
AT minli quantitativerelationsbetweencuringprocessesandlocalpropertieswithinthickcompositesbasedonsimulationandmachinelearning
AT qiaocheng quantitativerelationsbetweencuringprocessesandlocalpropertieswithinthickcompositesbasedonsimulationandmachinelearning
AT shaokaiwang quantitativerelationsbetweencuringprocessesandlocalpropertieswithinthickcompositesbasedonsimulationandmachinelearning
AT yizhuogu quantitativerelationsbetweencuringprocessesandlocalpropertieswithinthickcompositesbasedonsimulationandmachinelearning
AT xiangbaochen quantitativerelationsbetweencuringprocessesandlocalpropertieswithinthickcompositesbasedonsimulationandmachinelearning