Jan 2027· Journal of Aerospace Engineering· 0 citations· 35 references
Abstract
Deep learning models show great promise for rapid computational fluid dynamics (CFD), yet the comparative effectiveness of data-driven and physics-informed approaches for complex high-speed flows has been unclear. We conducted a rigorous comparative analysis of purely data-driven and physics-constrained neural network models for predicting flow fields in confined channels across a wide Mach number range. The analysis systematically evaluated the model’s performance in interpolating and extrapolating flow conditions. The overall error level remained around 0.1%. The results demonstrate that the introduction of physics-based loss functions is critical for enhancing the physical consistency of predictions. Although purely data-driven models may achieve fewer local errors in certain regions, the physics-constrained approach ensures solutions that are globally consistent with governing physical principles, even near strong discontinuities like shock waves. This comes with the added benefit of significantly improved training efficiency. For these reasons, our work demonstrates that physics constraints are indispensable for generating physically plausible results in complex flow regimes. The developed model achieves rapid flow field prediction in under 1 s, offering a robust and efficient tool for the rapid iteration of supersonic flow designs.
A reduced-order physics-constrained deep learning framework, SupersonicNet, is developed for the rapid prediction of two-dimensional supersonic flow fields (Ma 2.5–5.0) in confined channels with variable forward-facing step geometries. The framework is built upon a modified U-Net architecture. The continuity equation a...
Yu-De Yan, Jian Dai· The Physics of Fluids· 0 citations
Ultra-deep gas wellbores (length-to-diameter ratio > 60 000) lack a computationally efficient and physically consistent one-dimensional flow model that integrates both data-driven learning and conservation-law priors. This paper introduces a deep Euler-moment model leveraging a hybrid Physics-Informed Neural Network ar...
Xing-Yu Li, Hui Zhang, Kun-Hong Lv et al.· The Physics of Fluids· 0 citations
This study presents a comparative investigation of Physics-Informed Neural Networks (PINNs) and data-driven Deep Operator Networks (DeepONets) for predicting the evolution of plane Newtonian Couette flow with dynamic wall slip. First, a PINN framework is employed to solve flow for selected physical parameters. Subseque...
G. Foutsitzi, Nikolaos Antoniadis, Georgios C. Georgiou· Fluids· 0 citations
Irregular borehole enlargement alters annular flow structures and can create low-velocity regions that impair hole cleaning. However, conventional computational fluid dynamics (CFD) requires repeated geometric reconstruction and numerical simulations for each wellbore configuration, while existing physics-informed mode...
Zhi-Chao Xie, Jian Yang, Chi Zhao et al.· Processes· 0 citations
Physics-Informed Neural Networks (PINNs) offer a physically driven alternative to conventional computational fluid dynamics, yet their application to sloshing remains largely unexplored. This paper establishes a self-consistent PINN paradigm for two-dimensional linear sloshing that trains exclusively on physical residu...
Yan Qi, Shi-Kun Chen, Zhan-Xue Cao et al.· The Physics of Fluids· 0 citations
Thermal design and monitoring of compact heat exchangers require fields across changing operating conditions, and increasingly from a few embedded sensors, yet each new Reynolds number is a new mesh-based simulation. A physics-informed neural network (PINN) framework is presented for the coupled prediction and inverse...
Gaston Haidak, Jian-Long Kou, Dong-Yun Wang· The Physics of Fluids· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.