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.

中文翻译：

---

用于短纤维/聚合物纳米复合材料的热力学一致的物理信息深度学习材料模型

这项工作提出了一种基于物理信息深度学习（PIDL）的本构模型，用于研究短纤维增强纳米颗粒填充环氧树脂在各种环境条件下的粘弹性-粘塑性行为。深度学习模型经过训练以执行热力学原理，从而形成热力学一致的本构模型。为了实现这一目标，将长短期记忆网络与前馈神经网络相结合，以预测表征纳米复合材料内部耗散所需的内部变量。此外，另一个前馈神经网络用于指示自由能函数，这使得能够定义整个系统的热力学状态。 PIDL 模型最初是通过从经典本构模型生成合成数据来针对三维情况开发的。然后通过直接从循环加载-卸载实验测试中提取数据来训练模型。数值算例表明，PIDL模型可以准确预测不同体积分数的纤维和纳米粒子在各种湿热条件下的环氧基纳米复合材料的力学行为。