Mechanics of Materials · 2024 · 16 citations · 31 references
EngineeringMaterials EngineeringMaterials ScienceComputational Materials ScienceComputational MechanicsSolid MechanicsConstitutive ModelingMultiscale Materials ModelingMultiscale MechanicsNeural NetworksStress-strain BehaviorViscoplastic BehaviorComposite Constitutive ModelingContinuum Mechanics ModelsHeterogeneous Material ModelingMicromechanicsMicromechanics Of CompositesNeural Network ModelingRate-dependent Constitutive ModelsStrain-rate Dependence
In this work, a hybrid physics-based data-driven surrogate model for the microscale analysis of heterogeneous material is investigated. The proposed model benefits from the physics-based knowledge contained in the constitutive models used in the full-order micromodel by embedding the material models in a neural network. Following previous developments, this paper extends the applicability of the physically recurrent neural network (PRNN) by introducing an architecture suitable for rate-dependent materials in a finite strain framework. In this model, the homogenized deformation gradient of the micromodel is encoded into a set of deformation gradients serving as input to the embedded constitutive models. These constitutive models compute stresses, which are combined in a decoder to predict the homogenized stress, such that the internal variables of the history-dependent constitutive models naturally provide physics-based memory for the network. To demonstrate the capabilities of the surrogate model, we consider a unidirectional composite micromodel with transversely isotropic elastic fibers and elasto-viscoplastic matrix material. The extrapolation properties of the surrogate model trained to replace such micromodel are tested on loading scenarios unseen during training, ranging from different strain-rates to cyclic loading and relaxation. Speed-ups of three orders of magnitude with respect to the runtime of the original micromodel are obtained. • Extension of the Physically Recurrent Neural Network (PRNN) for 3D anisotropic materials under finite strains. • Physics-based constitutive models are embedded within the network. • The PRNN memory is based on the internal variables evolution of the embedded material models. • The network successfully reproduces strain rate dependency and unloading without being trained for it. • Speed-ups of three orders of magnitude compared to original micromodel.
31
Adam: A Method for Stochastic Optimization
Diederik P. Kingma, Jimmy Ba · UvA-DARE (University of Amsterdam) · 2014 · 84.8K citations · Full text
Advances in Neural Information Processing Systems 29
Onur Teymur, Kostas Zygalakis, Ben Calderhead · 2016 · 13.5K citations