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

doi:10.3390/polym14153229

CORC > 力学研究所 > 中国科学院力学研究所 > 流固耦合系统力学重点实验室(2012-)

	Accelerating the Layup Sequences Design of Composite Laminates via Theory-Guided Machine Learning Models
	Liao, Zhenhao 6; Qiu, Cheng 4,5; Yang, Jun 3; Yang, Jinglei 1,2,4; Yang, Lei 6
刊名	POLYMERS
	2022-08-01
卷号	14 期号:15 页码:14
关键词	composite laminate mechanical property layup design finite element simulation neural network
DOI	10.3390/polym14153229
通讯作者	Yang, Lei(yanglei@szu.edu.cn)
英文摘要	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.
资助项目	University Stability Support Program Project of the Shenzhen Natural Science Foundation[20200814105851001] ; National Key R&D Program of China[2018YFB2100901] ; Induction of Entrepreneurship Talents Program - Foshan-HKUST Projects[FSUST20-ETP06] ; Project of Hetao Shenzhen-Hong Kong Science and Technology Innovation Cooperation Zone[HZQB-KCZYB-2020083]
WOS关键词	OPTIMIZATION
WOS研究方向	Polymer Science
语种	英语
WOS记录号	WOS:000838958200001
资助机构	University Stability Support Program Project of the Shenzhen Natural Science Foundation ; National Key R&D Program of China ; Induction of Entrepreneurship Talents Program - Foshan-HKUST Projects ; Project of Hetao Shenzhen-Hong Kong Science and Technology Innovation Cooperation Zone
内容类型	期刊论文
源URL	[http://dspace.imech.ac.cn/handle/311007/89946]
专题	力学研究所_流固耦合系统力学重点实验室(2012-)
通讯作者	Yang, Lei
作者单位	1.Foshan SMN Mat Tech Co Ltd, Foshan 528200, Peoples R China 2.HKUST Shenzhen Hong Kong Collaborat Innovat Res I, Shenzhen 518031, Peoples R China 3.China Railway 5th Bur Construct Engn Co Ltd, Guiyang 550081, Guizhou, Peoples R China 4.Hong Kong Univ Sci & Technol, Dept Mech & Aerosp Engn, Hong Kong 999077, Peoples R China 5.Chinese Acad Sci, Inst Mech, Beijing 100190, Peoples R China 6.Shenzhen Univ, Coll Civil & Transportat Engn, Dept Civil Engn, Shenzhen 518060, Peoples R China
推荐引用方式 GB/T 7714	Liao, Zhenhao,Qiu, Cheng,Yang, Jun,et al. Accelerating the Layup Sequences Design of Composite Laminates via Theory-Guided Machine Learning Models[J]. POLYMERS,2022,14(15):14.
APA	Liao, Zhenhao,Qiu, Cheng,Yang, Jun,Yang, Jinglei,&Yang, Lei.(2022).Accelerating the Layup Sequences Design of Composite Laminates via Theory-Guided Machine Learning Models.POLYMERS,14(15),14.
MLA	Liao, Zhenhao,et al."Accelerating the Layup Sequences Design of Composite Laminates via Theory-Guided Machine Learning Models".POLYMERS 14.15(2022):14.