Application of supervised machine learning as a method for identifying DEM contact law parameters

Calibration of Discrete Element Method (DEM) models is an iterative process of adjusting input parameters such that the macroscopic results of simulations and experiments are similar. Therefore, selecting appropriate input parameters of a model effectively is crucial for the efficient use of the met...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autor principal:	Piotr Klejment
Formato:	article
Lenguaje:	EN
Publicado:	AIMS Press 2021
Materias:	discrete element method supervised machine learning uniaxial compression strength test numerical model calibration Biotechnology TP248.13-248.65 Mathematics QA1-939
Acceso en línea:	https://doaj.org/article/b3810644237b4d258a753edb0674cfb5
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:b3810644237b4d258a753edb0674cfb5
record_format	dspace
spelling	oai:doaj.org-article:b3810644237b4d258a753edb0674cfb52021-11-23T02:15:23ZApplication of supervised machine learning as a method for identifying DEM contact law parameters10.3934/mbe.20213701551-0018https://doaj.org/article/b3810644237b4d258a753edb0674cfb52021-09-01T00:00:00Zhttps://www.aimspress.com/article/doi/10.3934/mbe.2021370?viewType=HTMLhttps://doaj.org/toc/1551-0018Calibration of Discrete Element Method (DEM) models is an iterative process of adjusting input parameters such that the macroscopic results of simulations and experiments are similar. Therefore, selecting appropriate input parameters of a model effectively is crucial for the efficient use of the method. Despite the growing popularity of DEM, there is still an ongoing need for an efficient method for identifying contact law parameters. Commonly used trial and error procedures are very time-consuming and unpractical, especially in the case of models with many parameters to calibrate. It seems that machine learning may offer a new approach to that problem. This research aims to apply supervised machine learning to figure out the dependencies between specific microscopic and macroscopic parameters. More than 6000 DEM simulations of uniaxial compression tests gathered the data for two algorithms - Multiple Linear Regression and Random Forest. Promising results with an accuracy of over 99% give good hope for finding a universal relation between input and output parameters (for a specific DEM implementation) and reducing the number of simulations required for the calibration procedure. Another pertinent question concerns the size of the DEM models used during calibration based on the uniaxial compression test. It has been proven that calibration of certain parameters can be done on smaller samples, where the critical threshold is around 30% of the radius of the original model.Piotr KlejmentAIMS Pressarticlediscrete element methodsupervised machine learninguniaxial compression strength testnumerical model calibrationBiotechnologyTP248.13-248.65MathematicsQA1-939ENMathematical Biosciences and Engineering, Vol 18, Iss 6, Pp 7490-7505 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	discrete element method supervised machine learning uniaxial compression strength test numerical model calibration Biotechnology TP248.13-248.65 Mathematics QA1-939
spellingShingle	discrete element method supervised machine learning uniaxial compression strength test numerical model calibration Biotechnology TP248.13-248.65 Mathematics QA1-939 Piotr Klejment Application of supervised machine learning as a method for identifying DEM contact law parameters
description	Calibration of Discrete Element Method (DEM) models is an iterative process of adjusting input parameters such that the macroscopic results of simulations and experiments are similar. Therefore, selecting appropriate input parameters of a model effectively is crucial for the efficient use of the method. Despite the growing popularity of DEM, there is still an ongoing need for an efficient method for identifying contact law parameters. Commonly used trial and error procedures are very time-consuming and unpractical, especially in the case of models with many parameters to calibrate. It seems that machine learning may offer a new approach to that problem. This research aims to apply supervised machine learning to figure out the dependencies between specific microscopic and macroscopic parameters. More than 6000 DEM simulations of uniaxial compression tests gathered the data for two algorithms - Multiple Linear Regression and Random Forest. Promising results with an accuracy of over 99% give good hope for finding a universal relation between input and output parameters (for a specific DEM implementation) and reducing the number of simulations required for the calibration procedure. Another pertinent question concerns the size of the DEM models used during calibration based on the uniaxial compression test. It has been proven that calibration of certain parameters can be done on smaller samples, where the critical threshold is around 30% of the radius of the original model.
format	article
author	Piotr Klejment
author_facet	Piotr Klejment
author_sort	Piotr Klejment
title	Application of supervised machine learning as a method for identifying DEM contact law parameters
title_short	Application of supervised machine learning as a method for identifying DEM contact law parameters
title_full	Application of supervised machine learning as a method for identifying DEM contact law parameters
title_fullStr	Application of supervised machine learning as a method for identifying DEM contact law parameters
title_full_unstemmed	Application of supervised machine learning as a method for identifying DEM contact law parameters
title_sort	application of supervised machine learning as a method for identifying dem contact law parameters
publisher	AIMS Press
publishDate	2021
url	https://doaj.org/article/b3810644237b4d258a753edb0674cfb5
work_keys_str_mv	AT piotrklejment applicationofsupervisedmachinelearningasamethodforidentifyingdemcontactlawparameters
_version_	1718417396923891712

Application of supervised machine learning as a method for identifying DEM contact law parameters

Ejemplares similares