A deep learning approach for the velocity field prediction in a scramjet isolator

被引:65
作者
Kong, Chen [1 ]
Chang, Juntao [1 ]
Li, Yunfei [1 ]
Wang, Ziao [1 ]
机构
[1] Harbin Inst Technol, Harbin 150001, Heilongjiang, Peoples R China
基金
中国国家自然科学基金;
关键词
DIODE-LASER ABSORPTION; SUPERRESOLUTION RECONSTRUCTION; NEURAL-NETWORKS; SHOCK; MODEL; SPECTROSCOPY; VELOCIMETRY; FLOWS;
D O I
10.1063/5.0039537
中图分类号
O3 [力学];
学科分类号
08 ; 0801 ;
摘要
The accurate parameter prediction of a flow field is of practical significance to promote the development of hypersonic flight. Velocity field prediction using deep learning is a promising method to provide an accurate velocity field in a scramjet isolator. A new approach for the velocity field prediction in a scramjet isolator is developed in this study. A data-driven model is proposed for the prediction of the velocity field in a scramjet isolator by convolutional neural networks (CNNs) using measurements of the pressure on the isolator. Numerical simulations of flow in a three-dimensional scramjet isolator at various Mach numbers and backpressures are carried out to establish the dataset capturing the flow mechanism over various operating conditions. A CNN architecture composed of multiple reconstruction modules and feature extraction modules is designed. The CNN is trained using the computational fluid dynamics dataset to establish the mapping relationship between the wall pressure on the isolator and the velocity field in the isolator. The trained model is then tested over various Mach numbers and backpressures. The data-driven model successfully learns the relationship between the velocity field and pressure experienced on the wall of the isolator, i.e., the trained CNN model successfully reconstructed the velocity field based on the wall pressure on the isolator with high accuracy.
引用
收藏
页数:18
相关论文
共 43 条
  • [1] Twenty years of particle image velocimetry
    Adrian, RJ
    [J]. EXPERIMENTS IN FLUIDS, 2005, 39 (02) : 159 - 169
  • [2] Deep learning
    LeCun, Yann
    Bengio, Yoshua
    Hinton, Geoffrey
    [J]. NATURE, 2015, 521 (7553) : 436 - 444
  • [3] [Anonymous], 2010, INT C PATT REC
  • [4] Measurements of parameters of transient gas flows by a diode laser absorption spectroscopy at elevated pressures and temperatures
    Bolshov, M. A.
    Kuritsyn, Yu. A.
    Liger, V. V.
    Mironenko, V. R.
    Kolesnikov, O. M.
    [J]. OPTICS AND SPECTROSCOPY, 2017, 122 (05) : 705 - 714
  • [5] Closed-Loop Turbulence Control: Progress and Challenges
    Brunton, Steven L.
    Noack, Bernd R.
    [J]. APPLIED MECHANICS REVIEWS, 2015, 67 (05)
  • [6] Supersonic Mass-Flux Measurements via Tunable Diode Laser Absorption and Nonuniform Flow Modeling
    Chang, Leyen S.
    Strand, Christopher L.
    Jeffries, Jay B.
    Hanson, Ronald K.
    Diskin, Glenn S.
    Gaffney, Richard L.
    Capriotti, Diego P.
    [J]. AIAA JOURNAL, 2011, 49 (12) : 2783 - 2791
  • [7] Super-resolution reconstruction of turbulent velocity fields using a generative adversarial network-based artificial intelligence framework
    Deng, Zhiwen
    He, Chuangxin
    Liu, Yingzheng
    Kim, Kyung Chun
    [J]. PHYSICS OF FLUIDS, 2019, 31 (12)
  • [8] Learning a Deep Convolutional Network for Image Super-Resolution
    Dong, Chao
    Loy, Chen Change
    He, Kaiming
    Tang, Xiaoou
    [J]. COMPUTER VISION - ECCV 2014, PT IV, 2014, 8692 : 184 - 199
  • [9] Super-resolution reconstruction of turbulent flows with machine learning
    Fukami, Kai
    Fukagata, Koji
    Taira, Kunihiko
    [J]. JOURNAL OF FLUID MECHANICS, 2019, 870 : 106 - 120
  • [10] Diode laser absorption spectroscopy of water vapor in a scramjet combustor
    Griffiths, AD
    Houwing, AFP
    [J]. APPLIED OPTICS, 2005, 44 (31) : 6653 - 6659