[논문]Prediction of composite microstructure stress-strain curves using convolutional neural networks

Yang, Charles; Kim, Youngsoo; Ryu, Seunghwa; Gu, Grace X.

doi:10.1016/j.matdes.2020.108509

[해외논문] Prediction of composite microstructure stress-strain curves using convolutional neural networks 원문보기

Materials & Design, v.189, 2020년, pp.108509 -

Yang, Charles (Department of Mechanical Engineering, University of California) , Kim, Youngsoo (Department of Mechanical Engineering & KI for the NanoCentury, Korea Advanced Institute of Science and Technology) , Ryu, Seunghwa (Department of Mechanical Engineering & KI for the NanoCentury, Korea Advanced Institute of Science and Technology) , Gu, Grace X. (Department of Mechanical Engineering, University of California)

Abstract ▼ AI-Helper

Abstract Stress-strain curves are an important representation of a material's mechanical properties, from which important properties such as elastic modulus, strength, and toughness, are defined. However, generating stress-strain curves from numerical methods such as finite element method (FEM) is computationally intensive, especially when considering the entire failure path for a material. As a result, it is difficult to perform high throughput computational design of materials with large design spaces, especially when considering mechanical responses beyond the elastic limit. In this work, a combination of principal component analysis (PCA) and convolutional neural networks (CNN) are used to predict the entire stress-strain behavior of binary composites evaluated over the entire failure path, motivated by the significantly faster inference speed of empirical models. We show that PCA transforms the stress-strain curves into an effective latent space by visualizing the eigenbasis of PCA. Despite having a dataset of only 10-27% of possible microstructure configurations, the mean absolute error of the prediction is <10% of the range of values in the dataset, when measuring model performance based on derived material descriptors, such as modulus, strength, and toughness. Our study demonstrates the potential to use machine learning to accelerate material design, characterization, and optimization. Highlights Used convolutional neural networks to predict the entire stress-strain curve of binary composites with excellent accuracy Demonstrated the ability to compress stress-strain curves with negligible loss in information Established novel custom loss function for neural networks predicting compressed stressstrain curves Formulated interpretable evaluation metric of a machine learning model’s ability to predict stress-strain curves Graphical abstract [DISPLAY OMISSION]

Keyword

참고문헌 (37)

Compos. Struct. Ghazlan 153 278 2016 10.1016/j.compstruct.2016.06.020 Three-dimensional Voronoi model of a nacre-mimetic composite structure under impulsive loading

상세보기
Compos. Struct. Kim 189 27 2018 10.1016/j.compstruct.2018.01.038 An extended analytic model for the elastic properties of platelet-staggered composites and its application to 3D printed structures

상세보기
Nat. Commun. Sakhavand 6 6523 2015 10.1038/ncomms7523 Universal composition-structure-property maps for natural and biomimetic platelet-matrix composites and stacked heterostructures

상세보기
Compos. Part B Eng. Tran 108 210 2017 10.1016/j.compositesb.2016.09.083 Bimaterial 3D printing and numerical analysis of bio-inspired composite structures under in-plane and transverse loadings

상세보기
J. Mech. Phys. Solids Zhang 83 285 2015 10.1016/j.jmps.2015.06.015 Biomimetic staggered composites with highly enhanced energy dissipation: modeling, 3D printing, and testing

상세보기
Int. J. Smart Nano Mater. Zhang 00 1 2019 Developments in 4D-printing: a review on current smart materials, technologies, and applications
Adv. Mater. Compton 26 5930 2014 10.1002/adma.201401804 3D-printing of lightweight cellular composites

상세보기
MRS Bull. Das 41 729 2016 10.1557/mrs.2016.217 Metallic materials for 3D printing

상세보기
Scr. Mater. Jared 135 141 2017 10.1016/j.scriptamat.2017.02.029 Additive manufacturing: toward holistic design

상세보기
Makiewicz 2012 ASM Proc. Int. Conf. Trends Weld. Res Microstructure evolution during laser additive manufacturing of Ti6Al4V alloys
Eur. J. Mech. A. Solids Lee 72 79 2018 10.1016/j.euromechsol.2018.02.008 Theoretical study of the effective modulus of a composite considering the orientation distribution of the fillers and the interfacial damage

상세보기
Front. Mater. Ryu 6 21 2019 10.3389/fmats.2019.00021 Micromechanics-based homogenization of the effective physical properties of composites with an anisotropic matrix and interfacial imperfections

상세보기
RSC Adv. Sun 2 7617 2012 10.1039/c2ra20218b Hierarchical structure and mechanical properties of nacre: a review

상세보기
Comput. Mech. Ambati 55 383 2015 10.1007/s00466-014-1109-y A review on phase-field models of brittle fracture and a new fast hybrid formulation

상세보기
Comput. Mater. Sci. Jeong 155 483 2018 10.1016/j.commatsci.2018.09.021 Phase field modeling of crack propagation under combined shear and tensile loading with hybrid formulation

상세보기
Compos. Struct. Kim 220 769 2019 10.1016/j.compstruct.2019.04.017 A three-dimensional fracture pattern diagram of staggered platelet structures

상세보기
Comput. Mater. Sci. Liu 121 35 2016 10.1016/j.commatsci.2016.04.009 Abaqus implementation of monolithic and staggered schemes for quasi-static and dynamic fracture phase-field model

상세보기
Comput. Methods Appl. Mech. Eng. Miehe 199 2765 2010 10.1016/j.cma.2010.04.011 A phase field model for rate-independent crack propagation: robust algorithmic implementation based on operator splits

상세보기
Int. J. Numer. Methods Eng. Miehe 83 1273 2010 10.1002/nme.2861 Thermodynamically consistent phase-field models of fracture: variational principles and multi-field FE implementations

상세보기
Finite Elem. Anal. Des. Molnar 130 27 2017 10.1016/j.finel.2017.03.002 2D and 3D Abaqus implementation of a robust staggered phase-field solution for modeling brittle fracture

상세보기
Eng. Fract. Mech. Nguyen 139 18 2015 10.1016/j.engfracmech.2015.03.045 A phase field method to simulate crack nucleation and propagation in strongly heterogeneous materials from direct imaging of their microstructure

상세보기
Phys. Rev. Lett. Hanakata 121 2018 10.1103/PhysRevLett.121.255304 Accelerated search and design of stretchable graphene kirigami using machine learning

상세보기
Appl. Phys. Lett. Teske 114 2019 10.1063/1.5088412 A machine learning approach for automated fine-tuning of semiconductor spin qubits

상세보기
Appl. Phys. Lett. Woolley 98 2011 10.1063/1.3600662 Automated probe microscopy via evolutionary optimization at the atomic scale

상세보기
Adv. Funct. Mater. Du 21 772 2011 10.1002/adfm.201001397 Structural origin of the strain-hardening of spider silk

상세보기
Mater. Horizons Gu 5 939 2018 10.1039/C8MH00653A Bioinspired hierarchical composite design using machine learning: simulation, additive manufacturing, and experiment

상세보기
New J. Phys. Montavon 15 2013 10.1088/1367-2630/15/9/095003 Machine learning of molecular electronic properties in chemical compound space

상세보기
Sci. Rep. Pilania 3 2810 2013 10.1038/srep02810 Accelerating materials property predictions using machine learning

상세보기
MRS Commun. Chen 9 556 2019 10.1557/mrc.2019.32 Machine learning for composite materials

상세보기
MRS Commun. Yang 9 609 2019 10.1557/mrc.2019.49 Using convolutional neural networks to predict composite properties beyond the elastic limit

상세보기
J. Comput. Chem. Goh 38 1291 2017 10.1002/jcc.24764 Deep learning for computational chemistry

상세보기
Nature Lecun 521 436 2015 10.1038/nature14539 Deep learning

상세보기
Sci. Adv. Li 4 2018 10.1126/sciadv.aap8672 Machine learning-enabled identification of material phase transitions based on experimental data: exploring collective dynamics in ferroelectric relaxors

상세보기
ACS Appl. Mater. Interfaces Neumayer 10 42674 2018 10.1021/acsami.8b15872 Decoupling mesoscale functional response in PLZT across the ferroelectric-relaxor phase transition with contact kelvin probe force microscopy and machine learning

상세보기
J. Mach. Learn. Res. Pedregosa 12 2825 2011 Scikit-learn: machine learning in Python

상세보기
Chollet
CoRR. Abs/1412 Kingma 6 2015 Adam: a method for stochastic optimization

LOADING...

활용도 분석정보

상세보기

다운로드

내보내기

활용도 Top5 논문

해당 논문의 주제분야에서 활용도가 높은 상위 5개 콘텐츠를 보여줍니다.
더보기 버튼을 클릭하시면 더 많은 관련자료를 살펴볼 수 있습니다.

내보내기 구분	파일저장 인쇄 메일전송
구성항목	기본정보 상세정보 관리번호, 논문명, 저널/프로시딩명, 저자 , 발행년, 권, 호, 시작페이지, 끝페이지, 발행기관 관리번호, 논문명, 대등논문명, 저자 , 저널/프로시딩명, 발행기관, 발행년, 발행언어, 권, 호, 시작페이지, 끝페이지, ISBN, ISSN, 주제분야, 키워드, 초록(한글), 초록(영문), 저자(소속기관)
저장형식	Text(ASCII format) Excel format RefWorks Direct Export RIS format (for Reference Manager, ProCite, EndNote), Scholar's Aids, Mendeley
메일정보	받는사람 (필수) @ 보내는사람 (선택) @ 제목 내용 KISTI 검색결과 이메일 서비스
안내	총 건의 자료가 검색되었습니다. 다운받으실 자료의 인덱스를 입력하세요. (1-10,000) 검색결과의 순서대로 최대 10,000건 까지 다운로드가 가능합니다. 데이타가 많을 경우 속도가 느려질 수 있습니다.(최대 2~3분 소요) 다운로드 파일은 UTF-8 형태로 저장됩니다. 파일의 내용이 제대로 보이지 않을실 때는 웹브라우저 상단의 보기 -> 인코딩 -> 자동선택 여부를 확인하십시오. ~ Text(ASCII format) Excel format

연합인증

[해외논문] Prediction of composite microstructure stress-strain curves using convolutional neural networks 원문보기

Abstract ▼ AI-Helper

Keyword

참고문헌 (37)

이 논문을 인용한 문헌

연구과제 타임라인

활용도 분석정보

활용도 Top5 논문

관련 콘텐츠

원문 보기

원문 URL 링크

오픈액세스(OA) 유형

연관된 기능

AI-Helper ※ AI-Helper는 오픈소스 모델을 사용합니다.

선택된 텍스트

연합인증

[해외논문] Prediction of composite microstructure stress-strain curves using convolutional neural networks 원문보기

Abstract ▼ AI-Helper

Keyword

참고문헌 (37)

이 논문을 인용한 문헌

연구과제 타임라인

전체(0) 논문(0) 특허(0) 보고서(0)

전체(0) 논문(0) 특허(0) 보고서(0)

활용도 분석정보

활용도 Top5 논문 더보기

관련 콘텐츠

원문 보기

원문 URL 링크

오픈액세스(OA) 유형

연관된 기능

AI-Helper ※ AI-Helper는 오픈소스 모델을 사용합니다.

선택된 텍스트

활용도 Top5 논문