Novel DeepONet architecture to predict stresses in elastoplastic structures with variable complex geometries and loads

DOI10.1016/j.cma.2023.116277arXiv2306.03645MaRDI QIDQ6096499

Shashank Kushwaha, Iwona Jasiuk, Diab W. Abueidda, Junyan He, Seid Koric, Jaewan Park

Publication date: 12 September 2023

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

Full work available at URL: https://arxiv.org/abs/2306.03645

zbMATH Keywords

plastic deformationparametric geometrystress predictionmachine/deep learning

Mathematics Subject Classification ID

Mechanics of deformable solids (74-XX) Biology and other natural sciences (92-XX)

Related Items (1)

StressD: 2D stress estimation using denoising diffusion model

Cites Work

• Unnamed Item
• Efficient topology optimization in MATLAB using 88 lines of code
• Multilayer feedforward networks are universal approximators
• Physics-informed graph neural Galerkin networks: a unified framework for solving PDE-governed forward and inverse problems
• Neural operator prediction of linear instability waves in high-speed boundary layers
• Improved architectures and training algorithms for deep operator networks
• A physics-informed variational DeepONet for predicting crack path in quasi-brittle materials
• A deep learning energy method for hyperelasticity and viscoelasticity
• Interfacing finite elements with deep neural operators for fast multiscale modeling of mechanics problems
• On the influence of over-parameterization in manifold based surrogates and deep neural operators
• Deep energy method in topology optimization applications
• MIONet: Learning Multiple-Input Operators via Tensor Product
• DeepXDE: A Deep Learning Library for Solving Differential Equations

This page was built for publication: Novel DeepONet architecture to predict stresses in elastoplastic structures with variable complex geometries and loads