Data-driven discovery of the design rules for considering the curing deformation and the application on double-double composites

The process-induced deformation (PID) of composite laminates has been one of the critical problems for engineering structures. While lots of design rules has been proposed for standardize the laminate design, there is a lack of specific rule to follow when controlling PID is a necessity due to the n...

Full description

Saved in:
Bibliographic Details
Main Authors: Yizhuo Gui, Hongwei Song, Jinglei Yang, Cheng Qiu
Format: Article
Language:English
Published: Elsevier 2025-07-01
Series:Composites Part C: Open Access
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2666682025000556
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849718896470261760
author Yizhuo Gui
Hongwei Song
Jinglei Yang
Cheng Qiu
author_facet Yizhuo Gui
Hongwei Song
Jinglei Yang
Cheng Qiu
author_sort Yizhuo Gui
collection DOAJ
description The process-induced deformation (PID) of composite laminates has been one of the critical problems for engineering structures. While lots of design rules has been proposed for standardize the laminate design, there is a lack of specific rule to follow when controlling PID is a necessity due to the numerous affecting parameters. In this regard, a data-driven framework was proposed in this paper to determine the layup rules to follow for minimizing PID. Two specific machine learning (ML) models were built. One is combined model of convolutional neural networks (CNN) and principle component analysis (PCA) technique for connecting the layup sequences and their corresponding PID. Another one is the symbolic regression model, as an explainable ML technique, to quantitatively evaluate this connection. With the training data generated from the robust numerical simulation, it is found that a proper asymmetry is the key intrinsic factor that makes a smaller PID as it will counteract with the contributions of other extrinsic mechanisms. More importantly, a formula for easy evaluation of the asymmetry is provided to assist in guiding the layup design considering PID constraints. The formula is applied on the design problem of double-double (DD) composites. With the proper asymmetry added onto the original DD layup, the DD composites show a clear improvement on controlling the PID.
format Article
id doaj-art-a077a3783a554178935a3b4db4523dea
institution DOAJ
issn 2666-6820
language English
publishDate 2025-07-01
publisher Elsevier
record_format Article
series Composites Part C: Open Access
spelling doaj-art-a077a3783a554178935a3b4db4523dea2025-08-20T03:12:15ZengElsevierComposites Part C: Open Access2666-68202025-07-011710061210.1016/j.jcomc.2025.100612Data-driven discovery of the design rules for considering the curing deformation and the application on double-double compositesYizhuo Gui0Hongwei Song1Jinglei Yang2Cheng Qiu3Institute of Mechanics, Chinese Academy of Sciences, Beijing, PR China; University of Chinese Academy of Sciences, Beijing, PR ChinaInstitute of Mechanics, Chinese Academy of Sciences, Beijing, PR ChinaDepartment of Mechanical and Aerospace Engineering, Hong Kong University of Science and Technology, Hong Kong, PR China; HKUST Shenzhen-Hong Kong Collaborative Innovation Research Institute, Shenzhen, PR ChinaInstitute of Mechanics, Chinese Academy of Sciences, Beijing, PR China; Corresponding author.The process-induced deformation (PID) of composite laminates has been one of the critical problems for engineering structures. While lots of design rules has been proposed for standardize the laminate design, there is a lack of specific rule to follow when controlling PID is a necessity due to the numerous affecting parameters. In this regard, a data-driven framework was proposed in this paper to determine the layup rules to follow for minimizing PID. Two specific machine learning (ML) models were built. One is combined model of convolutional neural networks (CNN) and principle component analysis (PCA) technique for connecting the layup sequences and their corresponding PID. Another one is the symbolic regression model, as an explainable ML technique, to quantitatively evaluate this connection. With the training data generated from the robust numerical simulation, it is found that a proper asymmetry is the key intrinsic factor that makes a smaller PID as it will counteract with the contributions of other extrinsic mechanisms. More importantly, a formula for easy evaluation of the asymmetry is provided to assist in guiding the layup design considering PID constraints. The formula is applied on the design problem of double-double (DD) composites. With the proper asymmetry added onto the original DD layup, the DD composites show a clear improvement on controlling the PID.http://www.sciencedirect.com/science/article/pii/S2666682025000556Process-Induced Deformation (PID)Finite Element ModelingMachine LearningLayup Sequences
spellingShingle Yizhuo Gui
Hongwei Song
Jinglei Yang
Cheng Qiu
Data-driven discovery of the design rules for considering the curing deformation and the application on double-double composites
Composites Part C: Open Access
Process-Induced Deformation (PID)
Finite Element Modeling
Machine Learning
Layup Sequences
title Data-driven discovery of the design rules for considering the curing deformation and the application on double-double composites
title_full Data-driven discovery of the design rules for considering the curing deformation and the application on double-double composites
title_fullStr Data-driven discovery of the design rules for considering the curing deformation and the application on double-double composites
title_full_unstemmed Data-driven discovery of the design rules for considering the curing deformation and the application on double-double composites
title_short Data-driven discovery of the design rules for considering the curing deformation and the application on double-double composites
title_sort data driven discovery of the design rules for considering the curing deformation and the application on double double composites
topic Process-Induced Deformation (PID)
Finite Element Modeling
Machine Learning
Layup Sequences
url http://www.sciencedirect.com/science/article/pii/S2666682025000556
work_keys_str_mv AT yizhuogui datadrivendiscoveryofthedesignrulesforconsideringthecuringdeformationandtheapplicationondoubledoublecomposites
AT hongweisong datadrivendiscoveryofthedesignrulesforconsideringthecuringdeformationandtheapplicationondoubledoublecomposites
AT jingleiyang datadrivendiscoveryofthedesignrulesforconsideringthecuringdeformationandtheapplicationondoubledoublecomposites
AT chengqiu datadrivendiscoveryofthedesignrulesforconsideringthecuringdeformationandtheapplicationondoubledoublecomposites