Accelerating multiscale finite element simulations of history-dependent materials using a recurrent neural network

FE² multiscale simulations of history-dependent materials are accelerated by means of a recurrent neural network (RNN) surrogate for the history-dependent micro level response. We propose a simple strategy to efficiently collect stress–strain data from the micro model, and we modify the RNN model such that it resembles a nonlinear...

Viscoplasticity for instabilities due to strain softening and strain-rate softening

Discretization influence in strain-softening problems

Fundamental issues in finite element analyses of localization of deformation

A generalisation of J2-flow theory for polar continua

A non-linear finite element approach for the analysis of mode-I free edge delamination in composites

Wave propagation, localization and dispersion in a gradient-dependent medium

On the Role of Dispersive Waves in Strain-Softening Media

Localisation in a Cosserat continuum under static and dynamic loading conditions

Nonlinear analysis of propagation of delamination near free edges

A comparison of different crack models applied to plain and reinforced concrete

Numerical simulation of free edge delamination in graphite-epoxy laminates under uniaxial tension

Analysis of concrete fracture in "direct" tension

Analysis of Mixed-Mode Fracture in Concrete

Computation of post-bifurcation and post-failure behavior of strain-softening solids