TY - JOUR
T1 - A thermodynamically consistent physics-informed deep learning material model for short fiber/polymer nanocomposites
AU - Bahtiri, Betim
AU - Arash, Behrouz
AU - Scheffler, Sven
AU - Jux, Maximilian
AU - Rolfes, Raimund
N1 - Publisher Copyright:
© 2024 The Author(s)
PY - 2024/7/1
Y1 - 2024/7/1
N2 - This work proposes a physics-informed deep learning (PIDL)-based constitutive model for investigating the viscoelastic–viscoplastic behavior of short fiber-reinforced nanoparticle-filled epoxies under various ambient conditions. The deep-learning model is trained to enforce thermodynamic principles, leading to a thermodynamically consistent constitutive model. To accomplish this, a long short-term memory network is combined with a feed-forward neural network to predict internal variables required for characterizing the internal dissipation of the nanocomposite materials. In addition, another feed-forward neural network is used to indicate the free-energy function, which enables defining the thermodynamic state of the entire system. The PIDL model is initially developed for the three-dimensional case by generating synthetic data from a classical constitutive model. The model is then trained by extracting the data directly from cyclic loading–unloading experimental tests. Numerical examples show that the PIDL model can accurately predict the mechanical behavior of epoxy-based nanocomposites for different volume fractions of fibers and nanoparticles under various hygrothermal conditions.
AB - This work proposes a physics-informed deep learning (PIDL)-based constitutive model for investigating the viscoelastic–viscoplastic behavior of short fiber-reinforced nanoparticle-filled epoxies under various ambient conditions. The deep-learning model is trained to enforce thermodynamic principles, leading to a thermodynamically consistent constitutive model. To accomplish this, a long short-term memory network is combined with a feed-forward neural network to predict internal variables required for characterizing the internal dissipation of the nanocomposite materials. In addition, another feed-forward neural network is used to indicate the free-energy function, which enables defining the thermodynamic state of the entire system. The PIDL model is initially developed for the three-dimensional case by generating synthetic data from a classical constitutive model. The model is then trained by extracting the data directly from cyclic loading–unloading experimental tests. Numerical examples show that the PIDL model can accurately predict the mechanical behavior of epoxy-based nanocomposites for different volume fractions of fibers and nanoparticles under various hygrothermal conditions.
KW - Finite deformation
KW - Physics-informed neural networks
KW - Recurrent neural network
KW - Short fiber/epoxy nanocomposites
KW - Thermodynamic consistent modeling
UR - http://www.scopus.com/inward/record.url?scp=85192974637&partnerID=8YFLogxK
U2 - 10.1016/j.cma.2024.117038
DO - 10.1016/j.cma.2024.117038
M3 - Article
AN - SCOPUS:85192974637
VL - 427
JO - Computer Methods in Applied Mechanics and Engineering
JF - Computer Methods in Applied Mechanics and Engineering
SN - 0045-7825
M1 - 117038
ER -