Physics-informed data-driven closure relation for dilute short fiber suspensions

Abstract Tensor based formulations for modeling fiber orientation require the use of a closure approximation to solve the macro-descriptor evolution equation. This originates from the hydrodynamic component of motion and has received some attention in literature. In this work, we use the concept of...

Full description

Saved in:
Bibliographic Details
Main Authors: Bruno Ramoa, Chady Ghnatios, João Miguel Nóbrega, Francisco Chinesta
Format: Article
Language:English
Published: SpringerOpen 2025-03-01
Series:Advanced Modeling and Simulation in Engineering Sciences
Subjects:
Online Access:https://doi.org/10.1186/s40323-025-00290-w
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849392396749504512
author Bruno Ramoa
Chady Ghnatios
João Miguel Nóbrega
Francisco Chinesta
author_facet Bruno Ramoa
Chady Ghnatios
João Miguel Nóbrega
Francisco Chinesta
author_sort Bruno Ramoa
collection DOAJ
description Abstract Tensor based formulations for modeling fiber orientation require the use of a closure approximation to solve the macro-descriptor evolution equation. This originates from the hydrodynamic component of motion and has received some attention in literature. In this work, we use the concept of universal ordinary differential equations to infer a data-driven closure for fibers in the diluted regime using simple homogeneous flows. The closure can be understood as an orthogonal correction to the linear closure in eigenspace. To simplify and accelerate the training process, empirically determined bounds are used to restrain the machine learning output to physically admissible values. Three sets of tests are used to assess the performance of the model with simple homogeneous flows not included in the training pool, sequential combination of simple flows, and a non-homogeneous flow in a center gated disk. The results show that the trained model is able to adequately replicate the true dynamics of orientation, even for unseen flow regimes.
format Article
id doaj-art-46ef0ca0a84346e8aff7c81582bc65fd
institution Kabale University
issn 2213-7467
language English
publishDate 2025-03-01
publisher SpringerOpen
record_format Article
series Advanced Modeling and Simulation in Engineering Sciences
spelling doaj-art-46ef0ca0a84346e8aff7c81582bc65fd2025-08-20T03:40:47ZengSpringerOpenAdvanced Modeling and Simulation in Engineering Sciences2213-74672025-03-0112112210.1186/s40323-025-00290-wPhysics-informed data-driven closure relation for dilute short fiber suspensionsBruno Ramoa0Chady Ghnatios1João Miguel Nóbrega2Francisco Chinesta3Institute for Polymers and Composites, University of MinhoDepartment of Mechanical engineering, University of North FloridaInstitute for Polymers and Composites, University of MinhoPIMM Lab & ESI Chair, CNRS@CREATE, Arts et Metiers Institute of TechnologyAbstract Tensor based formulations for modeling fiber orientation require the use of a closure approximation to solve the macro-descriptor evolution equation. This originates from the hydrodynamic component of motion and has received some attention in literature. In this work, we use the concept of universal ordinary differential equations to infer a data-driven closure for fibers in the diluted regime using simple homogeneous flows. The closure can be understood as an orthogonal correction to the linear closure in eigenspace. To simplify and accelerate the training process, empirically determined bounds are used to restrain the machine learning output to physically admissible values. Three sets of tests are used to assess the performance of the model with simple homogeneous flows not included in the training pool, sequential combination of simple flows, and a non-homogeneous flow in a center gated disk. The results show that the trained model is able to adequately replicate the true dynamics of orientation, even for unseen flow regimes.https://doi.org/10.1186/s40323-025-00290-wMachine learningPhysics informed machine learningFiber orientation modeling
spellingShingle Bruno Ramoa
Chady Ghnatios
João Miguel Nóbrega
Francisco Chinesta
Physics-informed data-driven closure relation for dilute short fiber suspensions
Advanced Modeling and Simulation in Engineering Sciences
Machine learning
Physics informed machine learning
Fiber orientation modeling
title Physics-informed data-driven closure relation for dilute short fiber suspensions
title_full Physics-informed data-driven closure relation for dilute short fiber suspensions
title_fullStr Physics-informed data-driven closure relation for dilute short fiber suspensions
title_full_unstemmed Physics-informed data-driven closure relation for dilute short fiber suspensions
title_short Physics-informed data-driven closure relation for dilute short fiber suspensions
title_sort physics informed data driven closure relation for dilute short fiber suspensions
topic Machine learning
Physics informed machine learning
Fiber orientation modeling
url https://doi.org/10.1186/s40323-025-00290-w
work_keys_str_mv AT brunoramoa physicsinformeddatadrivenclosurerelationfordiluteshortfibersuspensions
AT chadyghnatios physicsinformeddatadrivenclosurerelationfordiluteshortfibersuspensions
AT joaomiguelnobrega physicsinformeddatadrivenclosurerelationfordiluteshortfibersuspensions
AT franciscochinesta physicsinformeddatadrivenclosurerelationfordiluteshortfibersuspensions