使用深度残差网络的乘波体气动性能预测

陈冰雁; 刘传振; 白鹏; 乔宇

doi:10.7638/kqdlxxb-2019.0027

欢迎来到能源电力期刊网！

English Version 期刊登录

您当前的位置：

首页 >

文章列表页 >

使用深度残差网络的乘波体气动性能预测

专栏——智能空气动力学研究探索 | 更新时间：2026-05-28

- 使用深度残差网络的乘波体气动性能预测
- Aerodynamic prediction for waveriders using deep residual learning
- 空气动力学学报 2019年37卷第3期页码：505-509
- 作者机构：
  
  1. 中国航天空气动力技术研究院,北京,100074
  2. 中国科学院深圳先进技术研究院,深圳,518000
- 作者简介：
  
  陈冰雁(1977-), 广东省惠州人, 男, 研究员, 主要从事飞行器气动设计研究.E-mail:chen_bingyan@hotmail.com
  刘传振(1989-), 山东省德州人, 男, 博士, 工程师, 主要从事气动外形设计研究.E-mail:chuanzhenliu@126.com
- 基金信息：
  
  国家自然科学基金（11672281）
- DOI：10.7638/kqdlxxb-2019.0027
  中图分类号： TP18;V211
- 纸质出版：2019
- 稿件说明：
移动端阅览
陈冰雁, 刘传振, 白鹏, 乔宇. 使用深度残差网络的乘波体气动性能预测[J]. 空气动力学学报, 2019, 37(3): 505-509.

CHEN Bingyan, LIU Chuanzhen, BAI Peng, et al. Aerodynamic prediction for waveriders using deep residual learning[J]. 2019, 37(3): 505-509.
陈冰雁, 刘传振, 白鹏, 乔宇. 使用深度残差网络的乘波体气动性能预测[J]. 空气动力学学报, 2019, 37(3): 505-509. DOI： 10.7638/kqdlxxb-2019.0027.

CHEN Bingyan, LIU Chuanzhen, BAI Peng, et al. Aerodynamic prediction for waveriders using deep residual learning[J]. 2019, 37(3): 505-509. DOI： 10.7638/kqdlxxb-2019.0027.

摘要

本文探究深度学习人工智能技术在飞行器气动外形预测中的应用。以激波装配法乘波体设计为背景，建立气动数据快速生成工具，使用拉丁超立方采样得到海量样本数据。使用深度残差神经网络构建气动外形参数到气动性能数据的代理模型，并与随机森林和双隐层神经网络等普通机器学习模型对比；同时将数据转换为图片，研究基于图片识别的深度学习模型搭建，省略飞行器外形的参数化表达。测试结果说明，深度残差网络作为数据代理模型的精度是随机森林和双隐层神经网络的3倍以上，而基于图片识别的代理模型精度提高有限。研究表明，深度残差网络在乘波体等易于生成大量数据的气动外形的性能预测中效果明显，为深度学习技术在气动外形设计中的应用奠定了基础。

Abstract

The applications of deep learning in aerodynamic predictions are explored in the article. A big data set is generated from 3D waverider design using the Latin Hypercube Sampling. The deep residual neural network (ResNet) is applied to construct a surrogate model for aerodynamic shape parameters and aerodynamic performances. Compared with the Random Forests and two-hidden-layer Neural Network

the high efficiency of ResNet is studied. In addition

the idea of surrogate models based on the image recognition is proposed with the image set. The aerodynamic performance prediction omits the shape parameterization

and the surrogate model is easy to be implemented. The efficiency of the ResNet surrogate model is over 3 times higher than that of the common machine learning methods

such as Random Forests and two-hidden-layer Neural Network. However

the efficiency of the ResNet image recognition model is not improved. The results suggest that the feasibility of the deep learning in aerodynamic shape design is confirmed

especially in some simple configurations

such as waverider.

关键词

Keywords

references

GAO Z H, WANG C. Aerodynamic shape design method for aircraft:status and trends[J]. Acta Aerodynamica Sinica, 2017, 35(4):516-528. (in Chinese)

HILTON G E. OSINDERO S, THE Y W. A fast learning algorithm for deep belief nets[J]. Neural Computation, 2006, 18(7): 1527-1554.

KRIZHEVSKY A, SUTSKEVER I, HINTON G E. Imagenet classification with deep convolutional neural networks[C]//Proceedings of Advances in Neural Information Processing System. South lake Tahoe, USA: Curran Associates Press, 2012: 1097-1105.

SILVER D, HUANG A, MADDISON C, et al. Mastering the game of Go with deep neural networks and tree search[J]. Nature, 2016, 529(7587):484-489.

HOYLE N, BRESSLOFF N W, KEANE A J. Design optimization of a two-dimensional subsonic engine air intake[J]. AIAA Journal, 2006, 44:2672-2681.

PATNAIK S N, CORONEOS R M. A subsonic aircraft design optimization with neural network and regression approximators[R]. AIAA 2004-4606, 2004.

CHEN H, QIAN W Q, HE L. Aerodynamic coefficient prediction of airfoils based on deep learning[J]. Acta Aerodynamica Sinica, 2018, 36(2):294-299. (in Chinese)

CHEN B Y, LIU C Z, JI C Q. Waverider design and analysis based on shock-fitting method[J]. Acta Aerodynamica Sinica, 2017, 35(3):421-428. (in Chinese)

LES PIEGL, WAYNE TILLER. The NURBS book (second edition)[M]. USA:Springer-Verlag, 1995:32-84.

KRIZHEVSKY ALEX, SUTSKEVER I, HINTON G. Image-Net classification with deep convolutional neural networks[J]. Communications of the ACM, 2017, 6(6):84-90.

SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large scale image recognition[C]//International Conference on Learning Representations. San Diego, USA, 2015.

CHRISTIAN S, LIU W, JIA Y, et al. Going deeper with convolutions[C]//IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Boston, USA, 2015.

HE K M, ZHANG X, REN S Q, et al. Deep residual learning for image recognition[R]//IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Boston, USA, 2015.

JIA Y Q, SHELHAMER E, DONALHUE J, et al. Caffe: convolutional architecture for fast feature embedding[C]//Proceedings of the ACM International Conference on Multimedia. Glasgow, UK, 2014.

HE K M, ZHANG X, KOMODAKIS N. Delving deep into rectifiers: surpassing human-level performance on imagenet classification[C]//IEEE International Conference on Computer Vision. Santiago, Chile, 2015.

BREIMAN L. Bagging predictors[J]. Machine Learning, 1996, 24(2):123-140.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于U-Net的磁浮飞行风洞气动力干扰剥离算法

基于神经网络与遗传算法的热气防冰结构优化

基于条件扩散模型的火箭气动外形快速设计方法

基于NURBS曲线的任意圆心角度叶型前尾缘构造

定常来流下钝体二维组合断面气动特性与流场的智能预测方法