Machine learning for polymer composites process simulation - a review

被引：65

作者：

Cassola, Stefano ^{[1
]}

Duhovic, Miro ^{[1
]}

Schmidt, Tim ^{[1
]}

May, David ^{[1
]}

机构：

[1] Tech Univ Kaiserslautern, Leibniz Inst Verbundwerkstoffe GmbH, Erwin Schrodinger Str,Geb 58, D-67663 Kaiserslautern, Germany

来源：

COMPOSITES PART B-ENGINEERING | 2022年 / 246卷

关键词：

C; Process simulation; Process modelling; Finite element analysis (FEA); D; Process monitoring; E; Resin flow; Liquid composite molding; Forming; Compression molding; ARTIFICIAL NEURAL-NETWORKS; INJECTION-MOLDING PROCESS; PROCESS PARAMETERS; DATA ASSIMILATION; OPTIMIZATION; PHYSICS; PREDICTION; PERMEABILITY; ORIENTATION; ALGORITHM;

D O I：

10.1016/j.compositesb.2022.110208

中图分类号：

T [工业技术];

学科分类号：

08 ;

摘要：

Over the last 20 years Machine Learning (ML) has been applied to a wide variety of applications in the fields of engineering and computer science. In the field of material science in particular, it has been used to help speed up predictions of structure property relationships and in general enhance the material design process. In this paper, we review the current status of ML and its specific application to polymer composites process simulation. We also review some case studies going beyond this focus, especially in the fields of computational fluid dynamics, solid mechanics and Computer Aided Engineering (CAE), to show the potential for further application in our research area. The types of ML algorithms, tools, techniques used in the various applications and their couplings with other CAE software tools are summarized and the overall result/potential of each application/method is highlighted.

引用

页数：17

共 169 条

[1]

Abadi M, 2016, PROCEEDINGS OF OSDI'16: 12TH USENIX SYMPOSIUM ON OPERATING SYSTEMS DESIGN AND IMPLEMENTATION, P265

[2] Meshless physics-informed deep learning method for three-dimensional solid mechanics [J].

Abueidda, Diab W. ;

Lu, Qiyue ;

Koric, Seid .

INTERNATIONAL JOURNAL FOR NUMERICAL METHODS IN ENGINEERING, 2021, 122 (23) :7182-7201

[3]

Advani S.G., 2011, Process Modeling in Composites Manufacturing

[4]

Al-Rfou R, 2016, arXiv preprint arXiv:1605.02688, P1

[5] Prediction of porous media fluid flow using physics informed neural networks [J].

Almajid, Muhammad M. ;

Abu-Al-Saud, Moataz O. .

JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING, 2022, 208

[6]

Bahadir SK, 2015, FIBRES TEXT EAST EUR, V23, P90

[7] Applying physics informed neural network for flow data assimilation [J].

Bai, Xiao-dong ;

Wang, Yong ;

Zhang, Wei .

JOURNAL OF HYDRODYNAMICS, 2020, 32 (06) :1050-1058

[8] Predicting the fiber orientation in glass fiber reinforced polymers using the moment of inertia and convolutional neural networks [J].

Bleiziffer, Patrick ;

Hofmann, Juergen ;

Zboray, Robert ;

Wiege, Thorsten ;

Herger, Roger .

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2021, 104

[9]

Brand R, 2020, SOLVER IN THE LOOP L, V1, DOI [10.48550/arXiv.2007.00016.arXiv, DOI 10.48550/ARXIV.2007.00016.ARXIV]

[10] Automated fiber placement: A review of history, current technologies, and future paths forward [J].

Brasington, Alex ;

Sacco, Christopher ;

Halbritter, Joshua ;

Wehbe, Roudy ;

Harik, Ramy .

COMPOSITES PART C: OPEN ACCESS, 2021, 6

← 1 2 3 4 5 6 7 8 9 10 →