Abstract The present study applies two different machine learning (ML) algorithms to predict the stress-strain mapping for the non-linear behaviour of thermoplastic materials: a Long Short-Term Memory (LSTM) algorithm and a Feed-Forward Neural Network (FFNN). The approach of this work requires the generation of the stress-strain curve for specific material parameters. The training data are obtained from the von Mises material law and the Ramberg-Osgood equation. The four combinations of ML algorithms with constitutive laws are evaluated and show a good agreement with numerical data.
%0 Journal Article
%1 https://doi.org/10.1002/pamm.202100225
%A Pi Savall, Berta
%A Mielke, André
%A Ricken, Tim
%D 2021
%J PAMM
%K ffnn lstm machine-learning plasticity rg-expmech-enveng stress-strain-curve
%N 1
%P e202100225
%R https://doi.org/10.1002/pamm.202100225
%T Data-Driven Stress Prediction for Thermoplastic Materials
%U https://onlinelibrary.wiley.com/doi/abs/10.1002/pamm.202100225
%V 21
%X Abstract The present study applies two different machine learning (ML) algorithms to predict the stress-strain mapping for the non-linear behaviour of thermoplastic materials: a Long Short-Term Memory (LSTM) algorithm and a Feed-Forward Neural Network (FFNN). The approach of this work requires the generation of the stress-strain curve for specific material parameters. The training data are obtained from the von Mises material law and the Ramberg-Osgood equation. The four combinations of ML algorithms with constitutive laws are evaluated and show a good agreement with numerical data.
@article{https://doi.org/10.1002/pamm.202100225,
abstract = {Abstract The present study applies two different machine learning (ML) algorithms to predict the stress-strain mapping for the non-linear behaviour of thermoplastic materials: a Long Short-Term Memory (LSTM) algorithm and a Feed-Forward Neural Network (FFNN). The approach of this work requires the generation of the stress-strain curve for specific material parameters. The training data are obtained from the von Mises material law and the Ramberg-Osgood equation. The four combinations of ML algorithms with constitutive laws are evaluated and show a good agreement with numerical data.},
added-at = {2024-05-13T22:55:55.000+0200},
author = {Pi Savall, Berta and Mielke, André and Ricken, Tim},
biburl = {https://puma.ub.uni-stuttgart.de/bibtex/245f5f89ee91731c1d5157d570b8b46b9/isd},
doi = {https://doi.org/10.1002/pamm.202100225},
eprint = {https://onlinelibrary.wiley.com/doi/pdf/10.1002/pamm.202100225},
interhash = {2341f824a173435e1b3f360d80f507c2},
intrahash = {45f5f89ee91731c1d5157d570b8b46b9},
journal = {PAMM},
keywords = {ffnn lstm machine-learning plasticity rg-expmech-enveng stress-strain-curve},
number = 1,
pages = {e202100225},
timestamp = {2024-05-14T16:40:06.000+0200},
title = {Data-Driven Stress Prediction for Thermoplastic Materials},
url = {https://onlinelibrary.wiley.com/doi/abs/10.1002/pamm.202100225},
volume = 21,
year = 2021
}
