Constitutive relation remains one of the most important, yet fundamental challenges in study granular materials. Instead using closed-form phenomenological models or numerical multiscale modelling, machine learning has emerged as an alternative paradigm to revolutionise constitutive modelling However, deep neural networks (DNNs) require massive training data and often fail make credible extrapo...

The present work is focused on the computational simulation of granular media on different scales. On the mircoscopic level, we suggest a discrete element method to evaluate inter-particle contact forces. On the macroscopic level, we utilize the finite element method to determine stress distributions in a continuum sense. To bridge the gap between both scales, we apply the concept of a represen...

In this paper, a novel multiscale hierarchical model based on finite element analysis and neural network computation was developed to link mesoscopic and macroscopic scales to simulate bone remodeling process. The finite element calculation is performed at macroscopic level and trained neural networks are employed as numerical devices for substituting the finite element computation needed for t...

The recent development of retrieval techniques and advances in 3D shape representation has induced a large amount of research. This paper presents a methodology with three options to retrieve shapes in 3D data bases, based on mapping shapes in 1D using representative sequences, which are matched using Fast Dynamic Time Warping distance. The three options are compared through a performance measu...

in this work we simulated the representative volume element (rve) of carbon nanotube (cnt) which is surrounded by high temperature superconductor (ybco) by using ansys finite element software. first we considered perfect model (for ybco and cnt) and investigated the effect of radius, length, and the number of nanotube in young’s modulus of the ybco by applying force on rve. then, a third region...