A general deep learning framework for history-dependent response prediction based on UA-Seq2Seq model

DOI10.1016/j.cma.2020.113357zbMath1506.74072OpenAlexW3080517163MaRDI QIDQ2020945

Chen Wang, Jian-sheng Fan, Li-yan Xu

Publication date: 26 April 2021

Published in: Computer Methods in Applied Mechanics and Engineering (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.cma.2020.113357

zbMATH Keywords

history dependencedeep learningmechanical responseattention mechanismSeq2Seq modelunrolled GRU

Mathematics Subject Classification ID

Small-strain, rate-independent theories of plasticity (including rigid-plastic and elasto-plastic materials) (74C05)

Related Items (9)

A deep learning framework for constitutive modeling based on temporal convolutional network ⋮ Data-driven spatiotemporal modeling for structural dynamics on irregular domains by stochastic dependency neural estimation ⋮ Recurrent and convolutional neural networks in structural dynamics: a modified attention steered encoder-decoder architecture versus LSTM versus GRU versus TCN topologies to predict the response of shock wave-loaded plates ⋮ A machine learning-based viscoelastic-viscoplastic model for epoxy nanocomposites with moisture content ⋮ Spiking recurrent neural networks for neuromorphic computing in nonlinear structural mechanics ⋮ Physics-based self-learning spiking neural network enhanced time-integration scheme for computing viscoplastic structural finite element response ⋮ Exact Dirichlet boundary physics-informed neural network EPINN for solid mechanics ⋮ A machine learning framework for accelerating the design process using CAE simulations: an application to finite element analysis in structural crashworthiness ⋮ Physics-based self-learning recurrent neural network enhanced time integration scheme for computing viscoplastic structural finite element response

Uses Software

• Adam
• Tensor2Tensor
• BERT

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• A constitutive model for rate dependent and rate independent inelasticity. Application to IN718
• A macroscopic 1D model for shape memory alloys including asymmetric behaviors and transformation-dependent elastic properties
• A macroscopic constitutive model for shape-memory alloys: theory and finite element simulations
• Consistent tangent operators for rate-independent elastoplasticity
• Constitutive equations for cyclic plasticity and cyclic viscoplasticity
• Integration methods for complex plastic constitutive equations
• Artificial neural network as an incremental nonlinear constitutive model for a finite element code.
• Multilayer feedforward networks are universal approximators
• Machine learning materials physics: integrable deep neural networks enable scale bridging by learning free energy functions
• Equivalent method of evaluating mechanical properties of perforated Ni-based single crystal plates using artificial neural networks
• Cyclic plasticity using Prager's translation rule and both nonlinear kinematic and isotropic hardening: theory, validation and algorithmic implementation
• Explicit finite element implementation of an improved three dimensional constitutive model for shape memory alloys
• A return mapping algorithm for cyclic viscoplastic constitutive models
• A return mapping algorithm for plane stress elastoplasticity
• Approximation by superpositions of a sigmoidal function

This page was built for publication: A general deep learning framework for history-dependent response prediction based on UA-Seq2Seq model