Designing High-Quality-Factor Electrospun Nanofiber Air Filters with Physics-Informed Machine Learning
Nanotechnology · 17.11.2026
DOI: 10.1088/1361-6528/aec2fa ↗Kurz gefasst
Fachartikel in der Zeitschrift Nanotechnology, online erschienen am 17.11.2026. Verfasst von Dharshini Sankaralingam und 5 weiteren Autor:innen. Beteiligte Einrichtung: Centre for Nanotechnology Research, Vellore Institute of Technology, 343A Advanced Computational Lab, Techonology Tower, VIT Vellore-632014, Vellore,….
Abstract (Originalsprache)
High filtration efficiency ($\eta$) and low pressure drop ($\Delta P$) are desirable performance parameters for an air filter, and the quality factor \rev{(QF)} is the standard figure-of-merit that
balances particle capture against breathability. 
In this work, we present a physics-informed machine-learning
framework that predicts efficiency, pressure drop, and the derived quality factor
for electrospun fibrous filters.
Two physics-informed neural networks \rev{(PINNs), formulated as physics-constrained networks in which the filtration laws are imposed as hard constraints rather than as differential-equation residual penalties,} are constructed: a pressure-drop network constrained by Darcy’s law and an efficiency network constrained by the classical exponential log-penetration relation. By embedding these filtration laws as differentiable constraints, the framework learns effective permeability and single-fiber efficiency, enabling physically consistent prediction and optimization of the quality factor.
 
A dataset spanning multiple polymers, fiber diameters, packing fractions, membrane thicknesses, face
velocities, and filtration particle sizes is compiled from published
experimental studies. The pressure-drop PINN attains
$R^2=0.982$, outperforming all five purely data-driven
regressors, while the efficiency PINN attains $R^2=0.984$. Systematic variation of the input parameters identifies fiber diameter as the dominant lever for improving QF, shows that the optimal QF depends on particle size, and confirms the weak dependence of QF on membrane thickness. These results indicate that physics-guided learning offers a generalizable and physically consistent route to the predictive design of high-performance, energy-efficient electrospun filters.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Centre for Nanotechnology Research, Vellore Institute of Technology, 343A Advanced Computational Lab, Techonology Tower, VIT Vellore-632014, Vellore, Vellore, Tamil Nadu, 632014, India.
- Vellore Institute of Technology, 343A Advanced Computational Lab, Techonology Tower, Vit, Vellore, Vellore, Tamilnadu, 632014, India.
- Centre for Nanotechnology Research, Vellore Institute of Technology, TT343A Technology Tower, VELLORE, VELLORE, TAMIL NADU, 632014, India.
ORCID-Profile: Athira S, Amrutha R Menon, Rohit Nimje, Ashutosh Mahajan
Zitieren
APA
Sankaralingam, D., S, V., S, A., Menon, A. R., Nimje, R., & Mahajan, A. (2026). Designing High-Quality-Factor Electrospun Nanofiber Air Filters with Physics-Informed Machine Learning. Nanotechnology. https://doi.org/10.1088/1361-6528/aec2fa
Vancouver
Sankaralingam D, S V, S A, Menon AR, Nimje R, Mahajan A. Designing High-Quality-Factor Electrospun Nanofiber Air Filters with Physics-Informed Machine Learning. Nanotechnology. 2026. doi:10.1088/1361-6528/aec2fa
BibTeX
@article{Sankaralingam2026,
author = {Sankaralingam, Dharshini and S, Vignesh and S, Athira and Menon, Amrutha R and Nimje, Rohit and Mahajan, Ashutosh},
title = {Designing High-Quality-Factor Electrospun Nanofiber Air Filters with Physics-Informed Machine Learning},
journal = {Nanotechnology},
year = {2026},
doi = {10.1088/1361-6528/aec2fa}
}
EUVIMED