Nonlinear Regression Operating on Microstructures Described from Topological Data Analysis for the Real-Time Prediction of Effective Properties

Nonlinear Regression Operating on Microstructures Described from Topological Data Analysis for the Real-Time Prediction of Effective Properties

Real-time decision making needs evaluating quantities of interest (QoI) in almost real time. When these QoI are related to models based on physics, the use of Model Order Reduction techniques allows speeding-up calculations, enabling fast and accurate evaluations. To accommodate real-time constraint...

Full description

Bibliographic Details
Main Authors: Minyoung Yun, Clara Argerich, Elias Cueto, Jean Louis Duval, Francisco Chinesta
Format: Article
Language:English
Published: MDPI AG 2020-05-01
Series:Materials
Subjects:
machine learning
data-driven mechanics
TDA
<i>Code2Vect</i>
nonlinear regression
effective properties
Online Access:https://www.mdpi.com/1996-1944/13/10/2335
id doaj-80d7e6573bb643a881d9154dafefca95
record_format Article
spelling doaj-80d7e6573bb643a881d9154dafefca952020-11-25T02:04:04ZengMDPI AGMaterials1996-19442020-05-01132335233510.3390/ma13102335Nonlinear Regression Operating on Microstructures Described from Topological Data Analysis for the Real-Time Prediction of Effective PropertiesMinyoung Yun0Clara Argerich1Elias Cueto2Jean Louis Duval3Francisco Chinesta4PIMM Laboratory & ESI Group Chair, Arts et Métiers Institute of Technology, CNRS, Cnam, HESAM Université, 151 boulevard de l’Hôpital, 75013 Paris, FrancePIMM Laboratory & ESI Group Chair, Arts et Métiers Institute of Technology, CNRS, Cnam, HESAM Université, 151 boulevard de l’Hôpital, 75013 Paris, FranceAragon Institute of Engineering Research, Universidad de Zaragoza, 50009 Zaragoza, SpainESI Group, Bâtiment Seville, 3bis rue Saarinen, 50468 Rungis, FrancePIMM Laboratory & ESI Group Chair, Arts et Métiers Institute of Technology, CNRS, Cnam, HESAM Université, 151 boulevard de l’Hôpital, 75013 Paris, FranceReal-time decision making needs evaluating quantities of interest (QoI) in almost real time. When these QoI are related to models based on physics, the use of Model Order Reduction techniques allows speeding-up calculations, enabling fast and accurate evaluations. To accommodate real-time constraints, a valuable route consists of computing parametric solutions—the so-called computational vademecums—that constructed off-line, can be inspected on-line. However, when dealing with shapes and topologies (complex or rich microstructures) their parametric description constitutes a major difficulty. In this paper, we propose using Topological Data Analysis for describing those rich topologies and morphologies in a concise way, and then using the associated topological descriptions for generating accurate supervised classification and nonlinear regression, enabling an almost real-time evaluation of QoI and the associated decision making.https://www.mdpi.com/1996-1944/13/10/2335machine learningdata-driven mechanicsTDA<i>Code2Vect</i>nonlinear regressioneffective properties
collection DOAJ
language English
format Article
sources DOAJ
author Minyoung Yun
Clara Argerich
Elias Cueto
Jean Louis Duval
Francisco Chinesta
spellingShingle Minyoung Yun
Clara Argerich
Elias Cueto
Jean Louis Duval
Francisco Chinesta
Nonlinear Regression Operating on Microstructures Described from Topological Data Analysis for the Real-Time Prediction of Effective Properties
Materials
machine learning
data-driven mechanics
TDA
<i>Code2Vect</i>
nonlinear regression
effective properties
author_facet Minyoung Yun
Clara Argerich
Elias Cueto
Jean Louis Duval
Francisco Chinesta
author_sort Minyoung Yun
title Nonlinear Regression Operating on Microstructures Described from Topological Data Analysis for the Real-Time Prediction of Effective Properties
title_short Nonlinear Regression Operating on Microstructures Described from Topological Data Analysis for the Real-Time Prediction of Effective Properties
title_full Nonlinear Regression Operating on Microstructures Described from Topological Data Analysis for the Real-Time Prediction of Effective Properties
title_fullStr Nonlinear Regression Operating on Microstructures Described from Topological Data Analysis for the Real-Time Prediction of Effective Properties
title_full_unstemmed Nonlinear Regression Operating on Microstructures Described from Topological Data Analysis for the Real-Time Prediction of Effective Properties
title_sort nonlinear regression operating on microstructures described from topological data analysis for the real-time prediction of effective properties
publisher MDPI AG
series Materials
issn 1996-1944
publishDate 2020-05-01
description Real-time decision making needs evaluating quantities of interest (QoI) in almost real time. When these QoI are related to models based on physics, the use of Model Order Reduction techniques allows speeding-up calculations, enabling fast and accurate evaluations. To accommodate real-time constraints, a valuable route consists of computing parametric solutions—the so-called computational vademecums—that constructed off-line, can be inspected on-line. However, when dealing with shapes and topologies (complex or rich microstructures) their parametric description constitutes a major difficulty. In this paper, we propose using Topological Data Analysis for describing those rich topologies and morphologies in a concise way, and then using the associated topological descriptions for generating accurate supervised classification and nonlinear regression, enabling an almost real-time evaluation of QoI and the associated decision making.
topic machine learning
data-driven mechanics
TDA
<i>Code2Vect</i>
nonlinear regression
effective properties
url https://www.mdpi.com/1996-1944/13/10/2335
work_keys_str_mv AT minyoungyun nonlinearregressionoperatingonmicrostructuresdescribedfromtopologicaldataanalysisfortherealtimepredictionofeffectiveproperties
AT claraargerich nonlinearregressionoperatingonmicrostructuresdescribedfromtopologicaldataanalysisfortherealtimepredictionofeffectiveproperties
AT eliascueto nonlinearregressionoperatingonmicrostructuresdescribedfromtopologicaldataanalysisfortherealtimepredictionofeffectiveproperties
AT jeanlouisduval nonlinearregressionoperatingonmicrostructuresdescribedfromtopologicaldataanalysisfortherealtimepredictionofeffectiveproperties
AT franciscochinesta nonlinearregressionoperatingonmicrostructuresdescribedfromtopologicaldataanalysisfortherealtimepredictionofeffectiveproperties
_version_ 1724944811098636288

Similar Items