Skip to content
Conference Open access

Digital Twin-Oriented Physics-Informed Neural Networks for Airfoil Aerodynamics Analysis

Maryam Mohammed Elbanna Mahmoud Yousef S. El-Bahloul Wael Seddik Moustafa
Jul 2026 · Journal of Physics, Conference Series · Vol 3289, pp. 012004 · 0 citations · 21 references
Physics

TL;DR

This study presents a systematic implementation and validation of PINNs for predicting lift and drag coefficients across NACA airfoil geometries under varying Reynolds numbers and angles of attack, and highlights the feasibility of combining CFD, physics-informed AI, and Digital Twin technologies to accelerate and enhance aerodynamic workflows.

Abstract

Aerodynamic analysis, a core aspect of studying physical phenomena, relies on governing equations traditionally solved via computational fluid dynamics (CFD). While CFD enables high-fidelity simulations of complex flows, including the Navier–Stokes equations, it often requires simplifying assumptions and substantial computational resources, limiting real-time analysis. Physics-Informed Neural Networks (PINNs) offer a promising alternative by embedding physical laws into the training process, ensuring predictions remain consistent with aerodynamic principles. This study presents a systematic implementation and validation of PINNs for predicting lift (Cl) and drag (Cd) coefficients across NACA airfoil geometries under varying Reynolds numbers and angles of attack. The methodology leverages CFD-generated data for training and incorporates physics-based loss functions enforcing linear lift theory, symmetry, positive drag, and drag–lift relationships. The trained PINN is integrated into an interactive Digital Twin environment, enabling real-time aerodynamic analysis, design exploration, and optimization. Results demonstrate rapid convergence, with total loss decreasing four orders of magnitude and mean absolute errors of 0.049 for Cl and 0.0019 for Cd, corresponding to 2.4% and 12.5% relative errors, respectively. Lift predictions show excellent agreement with CFD (R² = 0.993), while drag predictions capture trends with moderate scatter (R² = 0.738). Case studies of symmetric, low-camber, and high-camber airfoils confirm accurate reproduction of expected aerodynamic behavior. This work highlights the feasibility of combining CFD, physics-informed AI, and Digital Twin technologies to accelerate and enhance aerodynamic workflows.

Read PDF

Similar papers

Sep 2026

Computational Fluid Dynamics and Machine Learning for B-2 Spirit Flying-Wing Aerodynamic Prediction

The study includes a hybrid of high-fidelity computational fluid dynamics (CFD) and artificial neural networks (ANNs) for the investigation and prediction of the aerodynamic performance of the B-2 Spirit stealth flying-wing aircraft. The analysis of the three-dimensional geometry was performed by reconstructing it and...

Mamoon Aamir, Aqsa Zafar Abbasi, Nermeen Abdullah et al. · 0 citations
Open access Oct 2026

Optimized Hermite Interpolation for Geometrically and Aerodynamically Consistent Airfoil Reconstruction in Computational Fluid Dynamics

Airfoil profiles form the foundation of flight performance by determining the balance between lift and drag forces. Computational Fluid Dynamics (CFD) analyses enable a detailed examination of the velocity and pressure distributions around these profiles. Interpolation methods enhance the accuracy of simulations by all...

Mehmet Arslan, C. Özek, Bihter Daş · 1 citation
Oct 2026

Artificial intelligence-driven airfoil aerodynamic design via deep surrogate modeling and evolutionary algorithm

Airfoil aerodynamic design relies on computationally expensive flow solvers, while aerodynamic performance optimization and target pressure distribution inverse design are treated separately. This study develops a framework combining low-dimensional geometric representation, deep surrogate modeling, and evolutionary se...

Ming-Rui Li, Jing-Ying Wang, Ke Sun et al. · 0 citations

Airfoil2Vec: Spectral Geometry-Conditioned Neural Surrogate Models for Airfoil Aerodynamics and a Downforce-Generating CFD Dataset

We introduce a dataset of approximately 10,000 Reynolds-Averaged Navier-Stokes (RANS) simulations of steady, incompressible, two-dimensional subsonic flow around downforce-generating NACA 4-digit airfoils, targeting aerodynamic regimes relevant to automotive and motorsport applications (openly available on https://hugg...

Haitz Sáez de Ocáriz Borde, Flavio Savarino, A. C. Popescu et al. · 0 citations
Jan 2027

Unsteady Aerodynamic Prediction of a Variable-Sweep Morphing Wing via Steady–Unsteady Data Fusion

Variable-sweep wing aircraft demonstrate pronounced unsteady aerodynamic characteristics throughout the wing morphing process. Accurate prediction of unsteady aerodynamics remains a critical challenge due to complex flow physics and high computational cost. Traditional computational fluid dynamics (CFD) methods are p...

Yu-Qi Lei, Xiao-Min An, Yue-Tong Wang et al. · 0 citations

Unsteady Aerodynamic Modeling for Coflow Jet Airfoils

This study develops an improved state-space model for coflow jet (CFJ) airfoils by incorporating the jet momentum coefficient into the internal state-variable equation. The key contributions are summarized as follows. First, to quantitatively characterize flow separation characteristics of CFJ airfoils, steady and...

Y. Zhao, Bai-Gang Mi, Xuan Bai · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.