.png){kind=icon}
返回
Augmenting mesh-based data-driven models with physics gradients
.png){kind=icon}
OA
AI
DOI：10.1016/j.ast.2025.110037.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Deep learning technologies are increasingly used in various applications, with significant potential in aerospace for reduced-order modelling due to their ability to handle nonlinear systems. The effectiveness of data-driven methods relies on the adequacy and volume of training data, which poses a challenge in a design environment. To address this, physics-informed machine learning, which integrates physics knowledge into data-driven frameworks, has emerged as a promising solution. Directly applying physics terms to aircraft surfaces is complex, so this study utilizes solution gradients to effectively capture flow features. We introduce a hybrid framework that combines geometric deep learning with gradient terms, building on a previous data-driven approach for aerodynamic modelling on large-scale, three-dimensional unstructured grids. We evaluated various hybrid schemes to enhance prediction accuracy. Two gradient-enhanced approaches were found to outperform the purely data-driven model: the first integrates output differentiation into the training loss, achieving the highest accuracy at an increased training cost; the second employs a masking technique to weight regions with large gradients, providing a reasonable accuracy improvement at a lower training cost. This study focuses on predicting distributed aerodynamic loads around the NASA Common Research Model wing/body configuration under various transonic flight conditions. Our findings show that incorporating gradient information into deep learning models significantly improves the accuracy of the predictions and can compensate for a smaller dataset without compromising accuracy. Furthermore, the approaches proposed herein are directly applicable to any problem with discretised spatial domain.
Keyword:
Geometric deep learning
Physics informed
Gradient guided
Computational fluid dynamics
Transonic aerodynamics
Graph convolutional network
Multi mesh
Autoencoder
Hybrid approach
Common research model
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
5.8
论文数:
1.0W
被引数:
3.0W
机构
引用论文
Estimating model inadequacy in ordinary differential equations with physics-informed neural networks用物理信息神经网络估计常微分方程中的模型不足
PREAI
分享收藏A 60-Year-Old Woman with Primary Biliary Cholangitis and Crohn’s Ileitis Following the Suspension of Ursodeoxycholic Acid一位60岁女性，在停止熊去氧胆酸治疗后出现原发性胆汁性胆管炎和克罗恩病回肠炎
OAAI
OAAI分享收藏Seeing Emotion with Your Ears: Emotional Prosody Implicitly Guides Visual Attention to Faces.png)
PLoS ONEOAAI
PLoS ONEIF0
OAAI分享收藏Integrating Scientific Knowledge with Machine Learning for Engineering and Environmental Systems将科学知识与机器学习相结合，用于工程和环境系统OAAI
OAAI分享收藏Two-dimensional bricklayer arrangements of tolans using halogen bonding interactions使用卤素键相互作用的tolans的二维瓦工层布置
PREAI
分享收藏
查看更多内容