Since their inception, computational homogenization methods based on the fast Fourier
transform (FFT) have grown in popularity, establishing themselves as a powerful tool …

In this work, a unified AI-framework named Hierarchical Deep Learning Neural Network
(HiDeNN) is proposed to solve challenging computational science and engineering …

Recurrent neural networks (RNNs) have demonstrated very impressive performances in
learning sequential data, such as in language translation and music generation. Here, we …

Dielectric elastomers (DEs) are a sort of electroactive polymers with large and fast
responses, light masses and high energy densities. Hence, they are regarded as one of the …

Nanoparticle-filled rubber under tensile deformation was observed in situ by transmission
electron microscopy (TEM), and the spatial distributions of the local maximum and minimum …

Concurrent analysis of composite materials can provide the interaction among scales for
better composite design, analysis, and performance prediction. A data-driven concurrent n …

In order to explain or predict the macroscopic mechanical properties of polymer composites
with complex nanostructures, atomic force microscopy (AFM)-based nanomechanics is one …

In this study, we propose a mixed Fast Fourier Transform (FFT)-based homogenization
approach to analyze finite deformations of heterogeneous solids with different …

Although fracture resistance is critical for rubber materials, the fracture mechanisms are
poorly understood from a microscopic perspective. In this study, a crack propagation process …

Thermal residual stress is identified as one of the major reasons of stress concentration in
material's microstructures which initiates failure in the microstructure. Considering the details …