基于深度学习的钝体断面外形气动性能高效预测方法
CSTR:
作者:
作者单位:

重庆大学 土木工程学院,重庆 400045

作者简介:

李少鹏(1986- ),男,博士,副教授,主要从事大跨度桥梁结构风特性研究,E-mail:lisp0314@cqu.edu.cn。
brief: LI Shaopeng (1986- ), PhD, associate professor, main research interest: wind characteristics of long-span bridge structure, E-mail: lisp0314@cqu.edu.cn.

通讯作者:

李珂(通信作者),男,博士,副教授, E-mail:keli-bridge@cqu.edu.cn。

中图分类号:

TU318;U441

基金项目:

国家自然科学基金(51978108);重庆市自然科学基金(cstc2020jcyj-msxmX0773)


An efficient deep learning prediction method for aerodynamic performance based on the shape of the main beam
Author:
Affiliation:

School of Civil Engineering, Chongqing University, Chongqing 400045, P. R. China

Fund Project:

National Natural Science Foundation of China (No. 51978108); Natural Science Foundation of Chongqing (No. cstc2020jcyj-msxmX0773)

  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献 [28]
  • |
  • 相似文献 [20]
  • | | |
  • 文章评论
    摘要:

    对于气动性能,钝体断面的气动外形非常重要,采用传统风洞试验及CFD模拟计算得到钝体断面气动性能需消耗大量时间,大大影响钝体断面气动外形的气动性能评估效率。通过卷积神经网络深度学习技术实现对气动性能的快速预测,深度学习模型训练完成后,输入形状信息和与形状相关的流场信息,即可输出不同几何形状下的阻力系数,进而得到钝体断面的气动性能。为寻找性能最优的深度学习模型,通过综合判定误差和参数量大小对卷积神经网络结构的深度和宽度进行优化。对深度学习模型输出阻力系数与CFD计算结果进行对比发现,误差符合预期要求,并且相较于传统方法,基于深度学习网络的预测所需时间达到数量级的提升,未来可作为钝体断面气动外形优化的关键方法。

    Abstract:

    The aerodynamic shape of the bluff body section is very important to the aerodynamic performance. However, it takes a lot of time to obtain the aerodynamic performance of the bluff body section using traditional wind tunnel tests and CFD simulation calculations, which greatly affects the aerodynamic performance evaluation efficiency of the bluff body section , s aerodynamic shape. This paper proposes to use the deep learning technology of convolutional neural networks to realize the rapid prediction of aerodynamic performance. After the deep learning model is trained, the shape information and the shape-related flow field information can be input to output the drag coefficients under different geometric shapes, then the aerodynamic performance of the bluff body section. However to find the best deep learning model, this paper optimizes the depth and width of the convolutional neural network structure through comprehensive judgment error and time performance. The output resistance coefficient of the deep learning model is compared with the CFD calculation results. It is found that the error meets the expected requirements, and the prediction time based on the deep learning network is an order of magnitude improvement compared with the calculation time required by the traditional method. It can be used as the bluff body section aerodynamic shape optimization in the future.

    参考文献
    [1] 陈政清. 桥梁风工程[M]. 北京: 人民交通出版社, 2005.CHEN Z Q. Bridge wind engineering [M]. Beijing: China Communications Press, 2005. (in Chinese)
    [2] 欧阳克俭, 陈政清, 李红利, 等. 空间主缆悬索桥非线性静风稳定分析[J]. 土木建筑与环境工程, 2010, 32(3): 83-87.OUYANG K J, CHEN Z Q, LI H L, et al. Nonlinear aerostatic stability of suspension bridge with spatial main cables [J]. Journal of Civil, Architectural & Environmental Engineering, 2010, 32(3): 83-87. (in Chinese)
    [3] 廖海黎, 李明水, 马存明, 等. 桥梁风工程2019年度研究进展[J]. 土木与环境工程学报(中英文), 2020, 42(5): 56-66.LIAO H L, LI M S, MA C M, et al. State-of-the-art review of bridge wind engineering in 2019 [J]. Journal of Civil and Environmental Engineering, 2020, 42(5): 56-66. (in Chinese)
    [4] 高亮. 桥梁断面三分力系数试验研究[D]. 西安: 长安大学, 2010.GAO L. Investigation into three-component force coefficients of bridge deck section [D]. Xi,an: Chang,an University, 2010. (in Chinese)
    [5] 张丹. 流线型桥梁断面三分力系数及表面压力系数雷诺数效应[D]. 西安: 长安大学, 2013.ZHANG D. Reynolds number effect of streamline-like bridge deck section static coeffcient and surface pressure [D]. Xi,an: Chang,an University, 2013. (in Chinese)
    [6] 刘昊苏, 雷俊卿. 大跨度双层桁架主梁三分力系数识别[J]. 浙江大学学报(工学版), 2019, 53(6): 1092-1100.LIU H S, LEI J Q. Identification of three-component coefficients of double deck truss girder for long-span bridge [J]. Journal of Zhejiang University (Engineering Science), 2019, 53(6): 1092-1100. (in Chinese)
    [7] 宋锦忠, 徐建英. 桥梁节段模型风洞试验技术研讨[C]//2004全国结构风工程实验技术研讨会论文集. 长沙, 2004: 68-70.SONG J Z. XU J Y. Discussion on wind tunnel test technology of bridge segment model [C]//Proceedings of the 2004 National Symposium on Structural Wind Engineering Experimental Technology. Changsha, 2004: 68-70. (in Chinese)
    [8] 晏致涛, 李正良, 祁仁俊. 大跨度中承式拱桥节段模型风洞试验[J]. 重庆建筑大学学报, 2006, 28(6): 55-57, 98.YAN Z T, LI Z L, QI R J. Wind tunnel tests of long span half-through arch bridge section model [J]. Journal of Chongqing Jianzhu University, 2006, 28(6): 55-57, 98. (in Chinese)
    [9] 王锋, 赖笑. 基于CFD桥梁典型断面三分力系数差异研究[J]. 建筑技术开发, 2017, 44(1): 131-132.WANG F, LAI X. Study on difference of typical section of three component coefficients based on CFD bridge [J]. Building Technology Development, 2017, 44(1): 131-132. (in Chinese)
    [10] 刘婷婷, 张文首. CFD方法的大跨度桥梁抖振荷载[J]. 土木建筑与环境工程, 2011, 33(6): 59-63.LIU T T, ZHANG W S. Load analysis of butteting bridges by CFD [J]. Journal of Civil, Architectural & Environmental Engineering, 2011, 33(6): 59-63. (in Chinese)
    [11] 勾红叶, 杨彪, 华辉, 等. 桥梁信息化及智能桥梁2019年度研究进展[J]. 土木与环境工程学报(中英文), 2020, 42(5): 14-27.GOU H Y, YANG B, HUA H, et al. State-of-the-art review of bridge informatization and intelligent bridge in 2019 [J]. Journal of Civil and Environmental Engineering, 2020, 42(5): 14-27. (in Chinese)
    [12] 李乔, 杨兴旺. 桥梁主梁断面空气力学特性分析的人工神经网络方法[J]. 中南公路工程, 2000, 25(3): 56-59.LI Q, YANG X W. ANN method for analysis of aerodynamic characteristics of bridge girder section [J]. Central South Highway Engineering, 2000, 25(3): 56-59. (in Chinese)
    [13] 杨兴旺. 人工神经网络在桥梁主梁断面空气力学特性分析中的应用[D]. 成都: 西南交通大学, 2000.YANG X W. Application of artificial neural network in analysis of aerodynamic characteristics of bridge main girder section [D]. Chengdu: Southwest Jiaotong University, 2000. (in Chinese)
    [14] 黄继鸿, 苏红莲, 赵新华. 基于BP神经网络的翼型空气动力系数预测[J]. 航空工程进展, 2010, 1(1): 36-39.HUANG J H, SU H L, ZHAO X H. Aerodynamic coefficient prediction of airfoil using BP neural network [J]. Advances in Aeronautical Science and Engineering, 2010, 1(1): 36-39. (in Chinese)
    [15] 陈讷郁, 葛耀君. 基于人工神经网络的典型桥梁断面气动参数识别[J]. 土木工程学报, 2019, 52(8): 91-97, 128.CHEN N Y, GE Y J. Aerodynamic parameter identification of typical bridge sections based on artificial neural network [J]. China Civil Engineering Journal, 2019, 52(8): 91-97, 128. (in Chinese)
    [16] LIAO H L, MEI H Y, HU G, et al. Machine learning strategy for predicting flutter performance of streamlined box girders [J]. Journal of Wind Engineering and Industrial Aerodynamics, 2021, 209: 104493.
    [17] HU G, KWOK K C S. Predicting wind pressures around circular cylinders using machine learning techniques [J]. Journal of Wind Engineering and Industrial Aerodynamics, 2020, 198: 104099.
    [18] HU G, LIU L B, TAO D C, et al. Deep learning-based investigation of wind pressures on tall building under interference effects [J]. Journal of Wind Engineering and Industrial Aerodynamics, 2020, 201: 104138.
    [19] CHEN D L, GAO X, XU C F, et al. FlowGAN: A conditional generative adversarial network for flow prediction in various conditions [C]//2020 IEEE 32nd International Conference on Tools with Artificial Intelligence. November 9-11, 2020, Baltimore, MD, USA. IEEE, 2020: 315-322.
    [20] MIYANAWALA T P, JAIMAN R K. A novel deep learning method for the predictions of current forces on bluff bodies [C]//Proceedings of ASME 2018 37th International Conference on Ocean, Offshore and Arctic Engineering, June 17-22, 2018, Madrid, Spain. 2018.
    [21] 陈海, 钱炜祺, 何磊. 基于深度学习的翼型气动系数预测[J]. 空气动力学学报, 2018, 36(2): 294-299.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)
    [22] 廖鹏, 姚磊江, 白国栋, 等. 基于深度学习的混合翼型前缘压力分布预测[J]. 航空动力学报, 2019, 34(8): 1751-1758.LIAO P, YAO L J, BAI G D, et al. Prediction of hybrid airfoil leading edge pressure distribution based on deep learning [J]. Journal of Aerospace Power, 2019, 34(8): 1751-1758. (in Chinese)
    [23] KHAN A, SOHAIL A, ZAHOORA U, et al. A survey of the recent architectures of deep convolutional neural networks [J]. Artificial Intelligence Review, 2020, 53(8): 5455-5516.
    [24] SZEGEDY C, VANHOUCKE V, IOFFE S, et al. Rethinking the inception architecture for computer vision [C]//2016 IEEE Conference on Computer Vision and Pattern Recognition. June 27-30, 2016, Las Vegas, NV, USA. IEEE, 2016: 2818-2826.
    [25] 尹宝才, 王文通, 王立春. 深度学习研究综述[J]. 北京工业大学学报, 2015, 41(1): 48-59.YIN B C, WANG W T, WANG L C. Review of deep learning [J]. Journal of Beijing University of Technology, 2015, 41(1): 48-59. (in Chinese)
    [26] ELDAN R, SHAMIR O. The power of depth for feedforward neural networks [C]//Conference on Learning Theory, 2016: ArXiv:1512.03965.
    [27] LU Z, PU H, WANG F, et al. The expressive power of neural networks: a view from the width[C]//Neural Information Processing Systems, 2017: 6232-6240.
    [28] 廖星宇. 深度学习入门之PyTorch[M]. 北京: 电子工业出版社, 2017.LIAO X Y. PyTorch for getting started with deep learning [M]. Beijing: Publishing House of Electronics industry, 2017. (in Chinese)
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

李少鹏,李海,李珂.基于深度学习的钝体断面外形气动性能高效预测方法[J].土木与环境工程学报(中英文),2024,46(1):122-129. LI Shaopeng, LI Hai, LI Ke. An efficient deep learning prediction method for aerodynamic performance based on the shape of the main beam[J]. JOURNAL OF CIVIL AND ENVIRONMENTAL ENGINEERING,2024,46(1):122-129.10.11835/j. issn.2096-6717.2022.025

复制
分享
文章指标
  • 点击次数:471
  • 下载次数: 571
  • HTML阅读次数: 84
  • 引用次数: 0
历史
  • 收稿日期:2020-11-01
  • 在线发布日期: 2023-12-05
文章二维码