Embedding finite-volume HLLC flux conservation into CNN training cuts airfoil drag prediction error substantially versus pure pixel MAE, especially in low-data regimes.
Prediction of aerodynamic flow fields using convolutional neural networks
4 Pith papers cite this work, alongside 526 external citations. Polarity classification is still indexing.
4
Pith papers citing it
526
external citations · Crossref
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
A deep-learning plus manifold-learning reduced-order model predicts transonic airfoil pressure fields and shock positions with about 3.5% error, outperforming POD and ISOMAP baselines when enough training data is available.
An attention-based physics-guided CNN surrogate is trained to predict long-time microstructural evolution under the Cahn-Hilliard equation for both critical and off-critical mixtures while preserving composition and matching Lifshitz-Slyozov domain growth.
μ-FlowNet applies an attention U-Net to map flow fields in irregular microchannels, reporting dice score 0.9317 and IoU 0.8731 on test data while outperforming standard U-Net and T-Net.
citing papers explorer
-
CoFINN: Conservation Flux Informed Neural Networks for Physics Problems Governed by Conservation Laws
Embedding finite-volume HLLC flux conservation into CNN training cuts airfoil drag prediction error substantially versus pure pixel MAE, especially in low-data regimes.
-
Nonlinear Reduced-Order Modeling of Compressible Flow Fields Using Deep Learning and Manifold Learning
A deep-learning plus manifold-learning reduced-order model predicts transonic airfoil pressure fields and shock positions with about 3.5% error, outperforming POD and ISOMAP baselines when enough training data is available.
-
Physics-guided Convolutional Neural Network for Domain Growth Prediction in Systems with Conserved Kinetics
An attention-based physics-guided CNN surrogate is trained to predict long-time microstructural evolution under the Cahn-Hilliard equation for both critical and off-critical mixtures while preserving composition and matching Lifshitz-Slyozov domain growth.
-
$\mu$-FlowNet: A Deep Learning Approach for Mapping Flow Fields in Irregular Microchannels Using an Attention-based U-Net Encoder-Decoder Architecture
μ-FlowNet applies an attention U-Net to map flow fields in irregular microchannels, reporting dice score 0.9317 and IoU 0.8731 on test data while outperforming standard U-Net and T-Net.