A DNN-based data-driven modeling employing coarse sample data for real-time flexible multibody dynamics simulations

DOI10.1016/j.cma.2020.113480zbMath1506.65097MaRDI QIDQ2020773

Hee-Sun Choi, Jin Hwan Choi, Seongji Han, Juhwan Choi, Jin-Gyun Kim

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.2020.113480

zbMATH Keywords

error correction; real-time simulations; deep neural networks; data-driven modeling; coarse sample data; flexible multibody dynamics (FMBD)

Mathematics Subject Classification ID

65L05: Numerical methods for initial value problems involving ordinary differential equations

70E55: Dynamics of multibody systems

Related Items

Multibody dynamics and control using machine learning, Multi-fidelity meta modeling using composite neural network with online adaptive basis technique

Uses Software

• Adam

Cites Work

• Unnamed Item
• Unnamed Item
• Nonlinear model order reduction for flexible multibody dynamics: a modal derivatives approach
• Accelerated subset simulation with neural networks for reliability analysis
• Reliability analysis of structures using artificial neural network based genetic algorithms
• Multibody dynamics in computational mechanics and engineering applications
• Multibody system dynamics: roots and perspectives
• Flexible multibody dynamics: Review of past and recent developments
• Structural reliability analysis of elastic-plastic structures using neural networks and Monte Carlo simulation
• Artificial neural network as an incremental nonlinear constitutive model for a finite element code.
• Detection of cracks using neural networks and computational mechanics
• Flexible multibody dynamics using coordinate reduction improved by dynamic correction
• Data-driven reduced order model with temporal convolutional neural network
• Data-driven modelling of nonlinear spatio-temporal fluid flows using a deep convolutional generative adversarial network
• Computational mechanics enhanced by deep learning
• A neural network-based surrogate model for carbon nanotubes with geometric nonlinearities
• An efficient formulation for flexible multibody dynamics using a condensation of deformation coordinates
• An enhanced Craig-Bampton method
• Computational homogenization of nonlinear elastic materials using neural networks
• Neural network constitutive modelling for non-linear characterization of anisotropic materials
• A new neural network-based model for hysteretic behavior of materials
• Numerical implementation of a neural network based material model in finite element analysis
• Learning representations by back-propagating errors
• Coupling of substructures for dynamic analyses.
• Neural-network-based realibility analysis: A comparative study