A machine learning framework for accelerating the design process using CAE simulations: an application to finite element analysis in structural crashworthiness

DOI10.1016/J.CMA.2021.114008MaRDI QIDQ2237726zbMATH OpenOpenAlexFDO

Authors Christopher P. Kohar, Lars Greve, Tom K. Eller, Daniel S. Connolly, Kaan Inal

Publication date 28 October 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.2021.114008

zbMATH Keywords

machine learningautoencoderfinite element simulationcrashworthinessCNN modelLSTM model

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Computer science aspects of computer-aided design (68U07) Finite element, Rayleigh-Ritz and Galerkin methods for boundary value problems involving PDEs (65N30)

Recommendations

• FEA-Net: a physics-guided data-driven model for efficient mechanical response prediction
• Machine learning for topology optimization: physics-based learning through an independent training strategy
• Universal machine learning for topology optimization
• Smart finite elements: a novel machine learning application
• Data-driven simulation for general-purpose multibody dynamics using deep neural networks

Cites work

• scientific article; zbMATH DE number 1218049 (Why is no real title available?)
• A Comparison of Three Methods for Selecting Values of Input Variables in the Analysis of Output from a Computer Code
• A general deep learning framework for history-dependent response prediction based on UA-Seq2Seq model
• A method for the solution of certain non-linear problems in least squares
• An Algorithm for Least-Squares Estimation of Nonlinear Parameters
• Deep learned finite elements
• Deep learning
• Deep learning acceleration of total Lagrangian explicit dynamics for soft tissue mechanics
• Fundamentals of artificial intelligence
• Hierarchical deep learning neural network (HiDeNN): an artificial intelligence (AI) framework for computational science and engineering
• Learning representations by back-propagating errors
• Neural networks for computing in fracture mechanics. Methods and prospects of applications
• Nonlinear finite elements for continua and structures
• Reducing the Dimensionality of Data with Neural Networks
• Smart sampling and incremental function learning for very large high dimensional data

Cited in

(5)

• A generative learning and graph-based framework for computing field variables in finite element simulations
• Learned Gaussian quadrature for enriched solid finite elements
• Efficient AMG reduction-based preconditioners for structural mechanics
• A general framework of high-performance machine learning algorithms: application in structural mechanics
• Machine learning regression approaches for predicting the ultimate buckling load of variable-stiffness composite cylinders

Describes a project that uses

Uses Software

• Adam
• StanfordCoreNLP
• TensorFlow
• darch
• LS-DYNA
• Matlab

This page was built for publication: A machine learning framework for accelerating the design process using CAE simulations: an application to finite element analysis in structural crashworthiness

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2237726)