A combination of large eddy simulation and physics-informed machine learning to predict pore-scale flow behaviours in fibrous porous media: A case study of transient flow passing through a surgical mask

Mesgarpour, M., Habib, R., Shadloo, M. S. and Karimi, N. (2023) A combination of large eddy simulation and physics-informed machine learning to predict pore-scale flow behaviours in fibrous porous media: A case study of transient flow passing through a surgical mask. Engineering Analysis with Boundary Elements, 149, pp. 52-70. (doi: 10.1016/j.enganabound.2023.01.010)

Abstract

A predictive method using physics-informed machine learning (PIML) and large eddy simulation (LES) is developed to capture the transient flow field through microscale porous media (PSPM). An image processing technique extracts the 3D geometry of the internal layers of the mask from 2D microscopy images, and then the fluid flow is first simulated numerically. The subsequently developed PIML method successfully predicts the transient flow patterns inside the porous medium. For the first time, 3D maps of time-dependent pressure, velocity, and vorticity are predicted across the fibrous porous medium. The results show that, compared to conventional computational fluid dynamics, the PIML method can reduce the computational cost by over 20 times. Further, the LES model can replicate the fine fluctuations caused by the flow passage through the porous medium. Therefore, the developed methodology allows for transient flow predictions in highly complex configurations at a substantially reduced cost. The results indicate that the PIML method can reduce the total computational time (including training and prediction) by 22.5 and 20.7 times over the standard numerical simulation, based on speeds of 0.1 and 0.5 m/s, respectively. Several factors including the inherent differences between CPUs and GPUs, algorithms and software, appear to influence this improvement.

• Item Type: Articles
• Additional Information: N. Karimi acknowledges the financial support by the Engineering and Physical Science Research Council, UK; through the grant number EP/V036777/1 Risk Evaluation Fast Intelligent Tool (RELIANT) for COVID 19. M. S. Shadloo acknowledge the access to French HPC resources provided by the French regional computing center of Normandy (CRIANN) (Grants No. 2017002).
• Status: Published
• Refereed: Yes
• Glasgow Author(s) Enlighten ID: Habib, Dr Rabeeah and Karimi, Dr Nader
• Authors: Mesgarpour, M., Habib, R., Shadloo, M. S., and Karimi, N.
• College/School: College of Science and Engineering > School of Engineering; College of Science and Engineering > School of Engineering > Systems Power and Energy
• Journal Name: Engineering Analysis with Boundary Elements
• Publisher: Elsevier
• ISSN: 0955-7997
• ISSN (Online): 1873-197X
• Published Online: 16 January 2023
• Copyright Holders: Copyright © 2023 The Authors
• First Published: First published in Engineering Analysis with Boundary Elements 149:52-70
• Publisher Policy: Reproduced under a Creative Commons License

Project Code	Award No	Project Name	Principal Investigator	Funder's Name	Funder Ref	Lead Dept
311655		Risk EvaLuatIon fAst iNtelligent Tool (RELIANT) for COVID19	Andrea Cammarano	Engineering and Physical Sciences Research Council (EPSRC)	EP/V036777/1	ENG - Autonomous Systems & Connectivity