Design of experiments for the calibration of history-dependent models via deep reinforcement learning and an enhanced Kalman filter

DOI10.1007/s00466-023-02335-6arXiv2209.13126MaRDI QIDQ6159325

Sharlotte L. B. Kramer, Ruben Villarreal, Nhon N. Phan, Nikolaos N. Vlassis, Tommie A. Catanach, WaiChing Sun, Nathaniel Trask, Reese E. Jones

Publication date: 1 June 2023

Published in: Computational Mechanics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2209.13126

zbMATH Keywords

elastoplasticityexperimental designdeep reinforcement learningenhanced Kalman filter

Mathematics Subject Classification ID

Mechanics of deformable solids (74-XX)

Related Items

A neural kernel method for capturing multiscale high-dimensional micromorphic plasticity of materials with internal structures

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• A thermo-mechanically coupled theory for large deformations of amorphous polymers. II: Applications
• Reinforcement learning in the brain
• Bayesian experimental design: A review
• Kernel-based reinforcement learning
• Meta-modeling game for deriving theory-consistent, microstructure-based traction-separation laws via deep reinforcement learning
• A non-cooperative meta-modeling game for automated third-party calibrating, validating and falsifying constitutive laws with parallelized adversarial attacks
• Novel sparseness-inducing dual Kalman filter and its application to tracking time-varying spatially-sparse structural stiffness changes and inputs
• A return mapping algorithm for isotropic and anisotropic plasticity models using a line search method
• \(\mathrm{SO}(3)\)-invariance of informed-graph-based deep neural network for anisotropic elastoplastic materials
• Model Calibration and Parameter Estimation
• Deep Reinforcement Learning
• Optimal Design of Experiments
• A Review of Modern Computational Algorithms for Bayesian Optimal Design