Cargando…

Capturing functional relations in fluid–structure interaction via machine learning

While fluid–structure interaction (FSI) problems are ubiquitous in various applications from cell biology to aerodynamics, they involve huge computational overhead. In this paper, we adopt a machine learning (ML)-based strategy to bypass the detailed FSI analysis that requires cumbersome simulations...

Descripción completa

Detalles Bibliográficos
Autores principales: Soni, Tejas, Sharma, Ashwani, Dutta, Rajdeep, Dutta, Annwesha, Jayavelu, Senthilnath, Sarkar, Saikat
Formato: Online Artículo Texto
Lenguaje:English
Publicado: The Royal Society 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8984386/
https://www.ncbi.nlm.nih.gov/pubmed/35401993
http://dx.doi.org/10.1098/rsos.220097
_version_ 1784682175381110784
author Soni, Tejas
Sharma, Ashwani
Dutta, Rajdeep
Dutta, Annwesha
Jayavelu, Senthilnath
Sarkar, Saikat
author_facet Soni, Tejas
Sharma, Ashwani
Dutta, Rajdeep
Dutta, Annwesha
Jayavelu, Senthilnath
Sarkar, Saikat
author_sort Soni, Tejas
collection PubMed
description While fluid–structure interaction (FSI) problems are ubiquitous in various applications from cell biology to aerodynamics, they involve huge computational overhead. In this paper, we adopt a machine learning (ML)-based strategy to bypass the detailed FSI analysis that requires cumbersome simulations in solving the Navier–Stokes equations. To mimic the effect of fluid on an immersed beam, we have introduced dissipation into the beam model with time-varying forces acting on it. The forces in a discretized set-up have been decoupled via an appropriate linear algebraic operation, which generates the ground truth force/moment data for the ML analysis. The adopted ML technique, symbolic regression, generates computationally tractable functional forms to represent the force/moment with respect to space and time. These estimates are fed into the dissipative beam model to generate the immersed beam’s deflections over time, which are in conformity with the detailed FSI solutions. Numerical results demonstrate that the ML-estimated continuous force and moment functions are able to accurately predict the beam deflections under different discretizations.
format Online
Article
Text
id pubmed-8984386
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher The Royal Society
record_format MEDLINE/PubMed
spelling pubmed-89843862022-04-08 Capturing functional relations in fluid–structure interaction via machine learning Soni, Tejas Sharma, Ashwani Dutta, Rajdeep Dutta, Annwesha Jayavelu, Senthilnath Sarkar, Saikat R Soc Open Sci Engineering While fluid–structure interaction (FSI) problems are ubiquitous in various applications from cell biology to aerodynamics, they involve huge computational overhead. In this paper, we adopt a machine learning (ML)-based strategy to bypass the detailed FSI analysis that requires cumbersome simulations in solving the Navier–Stokes equations. To mimic the effect of fluid on an immersed beam, we have introduced dissipation into the beam model with time-varying forces acting on it. The forces in a discretized set-up have been decoupled via an appropriate linear algebraic operation, which generates the ground truth force/moment data for the ML analysis. The adopted ML technique, symbolic regression, generates computationally tractable functional forms to represent the force/moment with respect to space and time. These estimates are fed into the dissipative beam model to generate the immersed beam’s deflections over time, which are in conformity with the detailed FSI solutions. Numerical results demonstrate that the ML-estimated continuous force and moment functions are able to accurately predict the beam deflections under different discretizations. The Royal Society 2022-04-06 /pmc/articles/PMC8984386/ /pubmed/35401993 http://dx.doi.org/10.1098/rsos.220097 Text en © 2022 The Authors. https://creativecommons.org/licenses/by/4.0/Published by the Royal Society under the terms of the Creative Commons Attribution License http://creativecommons.org/licenses/by/4.0/ (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, provided the original author and source are credited.
spellingShingle Engineering
Soni, Tejas
Sharma, Ashwani
Dutta, Rajdeep
Dutta, Annwesha
Jayavelu, Senthilnath
Sarkar, Saikat
Capturing functional relations in fluid–structure interaction via machine learning
title Capturing functional relations in fluid–structure interaction via machine learning
title_full Capturing functional relations in fluid–structure interaction via machine learning
title_fullStr Capturing functional relations in fluid–structure interaction via machine learning
title_full_unstemmed Capturing functional relations in fluid–structure interaction via machine learning
title_short Capturing functional relations in fluid–structure interaction via machine learning
title_sort capturing functional relations in fluid–structure interaction via machine learning
topic Engineering
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8984386/
https://www.ncbi.nlm.nih.gov/pubmed/35401993
http://dx.doi.org/10.1098/rsos.220097
work_keys_str_mv AT sonitejas capturingfunctionalrelationsinfluidstructureinteractionviamachinelearning
AT sharmaashwani capturingfunctionalrelationsinfluidstructureinteractionviamachinelearning
AT duttarajdeep capturingfunctionalrelationsinfluidstructureinteractionviamachinelearning
AT duttaannwesha capturingfunctionalrelationsinfluidstructureinteractionviamachinelearning
AT jayavelusenthilnath capturingfunctionalrelationsinfluidstructureinteractionviamachinelearning
AT sarkarsaikat capturingfunctionalrelationsinfluidstructureinteractionviamachinelearning