| 注册
首页|期刊导航|航空学报|基于多任务学习的翼型结冰与气动特性预测

基于多任务学习的翼型结冰与气动特性预测

辛惠竹 李晨 桑为民 侯靓

航空学报2026,Vol.47Issue(16):90-104,15.
✕
航空学报2026,Vol.47Issue(16):90-104,15.DOI:10.7527/S1000-6893.2025.32983

基于多任务学习的翼型结冰与气动特性预测

Airfoil icing and aerodynamic characteristics prediction based on multi-task learning

辛惠竹 1李晨 2桑为民 1侯靓1

作者信息

  • 1. 西北工业大学 航空学院,西安 710072||飞行器基础布局全国重点实验室,西安 710072
  • 2. 上海卫星工程研究所,上海 201109
  • 折叠

摘要

Abstract

To address the problem of limited accuracy in single-task learning for airfoil icing prediction and the difficulty in simultane-ously obtaining icing morphology and aerodynamic characteristics,a multi-task learning based airfoil icing prediction framework called MTAF(Multi-Task Airfoil Former)is proposed.The framework employs an encoder-decoder architecture that extracts deep representations of airfoil geometry and flight conditions through a shared fea-ture encoder,realizes feature fusion and task interaction via a task correlation module,and accomplishes icing predic-tion and aerodynamic coefficient prediction respectively through dedicated prediction heads.The performance of Transformer and ConvNeXt backbone net-works within this framework is comparatively studied.Based on training and testing with 625 NACA 2412 airfoil samples,results demonstrate that the Transformer architecture achieves pixel accu-racy of 99.79%and coefficient of determination for 0.990 6 in icing prediction tasks,significantly outperforming 99.50%and 0.977 2 of ConvNeXt.For aerodynamic coefficient prediction,Transformer achieves coefficient of deter-mination values of 0.975 4 for lift coefficient and 0.987 4 for drag coefficient,which are comparable to 0.973 3 and 0.990 1 of ConvNeXt,respectively,with each architecture showing distinct advantages.The MTAF framework main-tains stable prediction performance across different icing types and various flight conditions,providing a high-precision prediction tool for airfoil icing engineering applications.

关键词

飞机结冰/图像预测/气动特性/Transformer/卷积神经网络

Key words

aircraft icing/image prediction/aerodynamic characteristics/Transformer/convolutional neural network

分类

航空航天

引用本文复制引用

辛惠竹,李晨,桑为民,侯靓..基于多任务学习的翼型结冰与气动特性预测[J].航空学报,2026,47(16):90-104,15.

基金项目

结冰与防除冰重点实验室开放课题(IADL20230302) (IADL20230302)

国家自然科学基金(12572270) (12572270)

西北工业大学"1-0"重大工程科学问题项目(G2024KY0613) Open Fund of Key Laboratory of Icing and Anti/De-icing(IADL20230302) (G2024KY0613)

National Natural Science Foundation of China(12572270) (12572270)

The"1-0"Major Engineering Science Problem Project of Northwestern Polytechnical University(G2024KY0613) (G2024KY0613)

航空学报

1000-6893

访问量0
|
下载量0
段落导航相关论文