Cargando…

Accelerating the Layup Sequences Design of Composite Laminates via Theory-Guided Machine Learning Models

Experimental and numerical investigations are presented for a theory-guided machine learning (ML) model that combines the Hashin failure theory (HFT) and the classical lamination theory (CLT) to optimize and accelerate the design of composite laminates. A finite element simulation with the incorpora...

Descripción completa

Detalles Bibliográficos
Autores principales: Liao, Zhenhao, Qiu, Cheng, Yang, Jun, Yang, Jinglei, Yang, Lei
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9371008/
https://www.ncbi.nlm.nih.gov/pubmed/35956742
http://dx.doi.org/10.3390/polym14153229
_version_ 1784766998832480256
author Liao, Zhenhao
Qiu, Cheng
Yang, Jun
Yang, Jinglei
Yang, Lei
author_facet Liao, Zhenhao
Qiu, Cheng
Yang, Jun
Yang, Jinglei
Yang, Lei
author_sort Liao, Zhenhao
collection PubMed
description Experimental and numerical investigations are presented for a theory-guided machine learning (ML) model that combines the Hashin failure theory (HFT) and the classical lamination theory (CLT) to optimize and accelerate the design of composite laminates. A finite element simulation with the incorporation of the HFT and CLT were used to generate the training dataset. Instead of directly mapping the relationship between the ply angles of the laminate and its strength and stiffness, a multi-layer interconnected neural network (NN) system was built following the logical sequence of composite theories. With the forward prediction by the NN system and the inverse optimization by genetic algorithm (GA), a benchmark case of designing a composite tube subjected to the combined loads of bending and torsion was studied. The ML models successfully provided the optimal layup sequences and the required fiber modulus according to the preset design targets. Additionally, it shows that the machine learning models, with the guidance of composite theories, realize a faster optimization process and requires less training data than models with direct simple NNs. Such results imply the importance of domain knowledge in helping improve the ML applications in engineering problems.
format Online
Article
Text
id pubmed-9371008
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-93710082022-08-12 Accelerating the Layup Sequences Design of Composite Laminates via Theory-Guided Machine Learning Models Liao, Zhenhao Qiu, Cheng Yang, Jun Yang, Jinglei Yang, Lei Polymers (Basel) Article Experimental and numerical investigations are presented for a theory-guided machine learning (ML) model that combines the Hashin failure theory (HFT) and the classical lamination theory (CLT) to optimize and accelerate the design of composite laminates. A finite element simulation with the incorporation of the HFT and CLT were used to generate the training dataset. Instead of directly mapping the relationship between the ply angles of the laminate and its strength and stiffness, a multi-layer interconnected neural network (NN) system was built following the logical sequence of composite theories. With the forward prediction by the NN system and the inverse optimization by genetic algorithm (GA), a benchmark case of designing a composite tube subjected to the combined loads of bending and torsion was studied. The ML models successfully provided the optimal layup sequences and the required fiber modulus according to the preset design targets. Additionally, it shows that the machine learning models, with the guidance of composite theories, realize a faster optimization process and requires less training data than models with direct simple NNs. Such results imply the importance of domain knowledge in helping improve the ML applications in engineering problems. MDPI 2022-08-08 /pmc/articles/PMC9371008/ /pubmed/35956742 http://dx.doi.org/10.3390/polym14153229 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Liao, Zhenhao
Qiu, Cheng
Yang, Jun
Yang, Jinglei
Yang, Lei
Accelerating the Layup Sequences Design of Composite Laminates via Theory-Guided Machine Learning Models
title Accelerating the Layup Sequences Design of Composite Laminates via Theory-Guided Machine Learning Models
title_full Accelerating the Layup Sequences Design of Composite Laminates via Theory-Guided Machine Learning Models
title_fullStr Accelerating the Layup Sequences Design of Composite Laminates via Theory-Guided Machine Learning Models
title_full_unstemmed Accelerating the Layup Sequences Design of Composite Laminates via Theory-Guided Machine Learning Models
title_short Accelerating the Layup Sequences Design of Composite Laminates via Theory-Guided Machine Learning Models
title_sort accelerating the layup sequences design of composite laminates via theory-guided machine learning models
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9371008/
https://www.ncbi.nlm.nih.gov/pubmed/35956742
http://dx.doi.org/10.3390/polym14153229
work_keys_str_mv AT liaozhenhao acceleratingthelayupsequencesdesignofcompositelaminatesviatheoryguidedmachinelearningmodels
AT qiucheng acceleratingthelayupsequencesdesignofcompositelaminatesviatheoryguidedmachinelearningmodels
AT yangjun acceleratingthelayupsequencesdesignofcompositelaminatesviatheoryguidedmachinelearningmodels
AT yangjinglei acceleratingthelayupsequencesdesignofcompositelaminatesviatheoryguidedmachinelearningmodels
AT yanglei acceleratingthelayupsequencesdesignofcompositelaminatesviatheoryguidedmachinelearningmodels