Theory-inspired machine learning for stress-strain curve prediction of short fiber-reinforced composites with unseen design space

被引:6
作者
Tsai, Meng-Lin [1 ]
Huang, Chang-Wei [2 ,3 ]
Chang, Shu-Wei [1 ,4 ]
机构
[1] Natl Taiwan Univ, Coll Engn, Dept Civil Engn, Roosevelt Rd 1,Sect 4, Taipei 10617, Taiwan
[2] Chung Yuan Christian Univ, Dept Civil Engn, Taoyuan City 320314, Taiwan
[3] Chung Yuan Christian Univ, R&D Ctr Membrane Technol, Taoyuan City 320314, Taiwan
[4] Natl Taiwan Univ, Coll Engn, Dept Biomed Engn, Roosevelt Rd 1,Sect 4, Taipei 10617, Taiwan
关键词
Machine learning; Deep neural network; Short fiber reinforced composite; Theory guide machine learning; Two-phase learning; MEAN-FIELD HOMOGENIZATION; MECHANICAL-PROPERTIES; ELASTIC PROPERTIES; NUMERICAL-SIMULATION; MATRIX COMPOSITES; FRAMEWORK; BEHAVIOR; MICROSTRUCTURE; PERFORMANCE; FABRICATION;
D O I
10.1016/j.eml.2023.102097
中图分类号
TH [机械、仪表工业];
学科分类号
0802 ;
摘要
Computational analysis of composites is well established; however, the process is time-consuming, owing to the disparate length scales and nonlinearities involved. Therefore, the use of machine learning models to predict the mechanical properties of short fiber-reinforced composites (SFRCs) is promising when large amounts of data are lacking. However, predicting data for an unseen design space remains challenging. The use of existing theoretical models for training is a viable solution to address this issue. This paper proposes a theory-guided machine learning (TGML) framework through training deep neural networks, based on the finite element analysis dataset that considers the cohesive effect of the interface, to predict the nonlinear mechanical responses of SFRCs. Our results demonstrate that incorporating the Halpin-Tsai theory with machine learning improves the predictive performance of the model in an unseen design space. Moreover, inspired by this theory, we propose a theoryinspired two-phase machine learning (TPML) approach to further improve predictive performance. Our results indicate that TGML and TPML capture more information from the data and thus enhance predictive performance. The proposed method can be adapted to the analyses of other composites with nonlinear mechanical behaviors.
引用
收藏
页数:9
相关论文
共 64 条
  • [1] ABAQUS Documentation, 2020, about us
  • [2] Evaluation of interfacial strength between fiber and matrix based on cohesive zone modeling
    Budiman, Bentang Arief
    Takahashi, Kosuke
    Inaba, Kazuaki
    Kishimoto, Kikuo
    [J]. COMPOSITES PART A-APPLIED SCIENCE AND MANUFACTURING, 2016, 90 : 211 - 217
  • [3] Mechanical behavior of high dosage short carbon fiber reinforced epoxy composites
    Capela, C.
    Oliveira, S. E.
    Ferreira, J. A. M.
    [J]. FIBERS AND POLYMERS, 2017, 18 (06) : 1200 - 1207
  • [4] Structure and mechanical properties of selected biological materials
    Chen, P. -Y
    Lin, A. Y. M.
    Lin, Y-S.
    Seki, Y.
    Stokes, A. G.
    Peyras, J.
    Olevsky, E. A.
    Meyers, M. A.
    McKittrick, J.
    [J]. JOURNAL OF THE MECHANICAL BEHAVIOR OF BIOMEDICAL MATERIALS, 2008, 1 (03) : 208 - 226
  • [5] Geometrically toughening mechanism of cellular composites inspired by Fibonacci lattice in Liquidambar formosana
    Chiang, Yuan
    Tung, Cheng-Che
    Lin, Xiang-Di
    Chen, Po-Yu
    Chen, Chuin-Shan
    Chang, Shu-Wei
    [J]. COMPOSITE STRUCTURES, 2021, 262
  • [6] ASYMPTOTIC MODULUS RESULTS FOR COMPOSITES CONTAINING RANDOMLY ORIENTED FIBERS
    CHRISTENSEN, RM
    [J]. INTERNATIONAL JOURNAL OF SOLIDS AND STRUCTURES, 1976, 12 (07) : 537 - 544
  • [7] The Effects of Strain Rates on Mechanical Properties and Failure Behavior of Long Glass Fiber Reinforced Thermoplastic Composites
    Cui, Junjia
    Wang, Shaoluo
    Wang, Shuhao
    Li, Guangyao
    Wang, Peilin
    Liang, Chengsong
    [J]. POLYMERS, 2019, 11 (12)
  • [8] Daw A, 2017, Physics-guided neural networks (pgnn): An application in lake temperature modeling
  • [9] A second-moment incremental formulation for the mean-field homogenization of elasto-plastic composites
    Doghri, I.
    Brassart, L.
    Adam, L.
    Gerard, J. -S.
    [J]. INTERNATIONAL JOURNAL OF PLASTICITY, 2011, 27 (03) : 352 - 371
  • [10] El Zoghbi B., 2019, Cell, V100, P16, DOI [10.5923/j.cmaterials.20190901.03, DOI 10.5923/J.CMATERIALS.20190901.03]