Flame development prediction of supersonic combustion flow based on lightweight cascaded convolutional neural network

被引:24
作者
Chen, Erda [1 ,2 ]
Guo, Mingming [1 ,2 ]
Tian, Ye [1 ,2 ]
Zhang, Yi [2 ]
Chen, Hao [1 ,2 ]
Le, Jialing [2 ]
Zhong, Fuyu [2 ]
Zhang, Hua [1 ]
机构
[1] Southwest Univ Sci & Technol, Mianyang 621000, Peoples R China
[2] China Aerodynam Res & Dev Ctr, Mianyang 621000, Peoples R China
关键词
JET FLAME; CAVITY; OSCILLATIONS; VELOCIMETRY;
D O I
10.1063/5.0140624
中图分类号
O3 [力学];
学科分类号
08 ; 0801 ;
摘要
The flame development prediction of a scramjet combustor forecasts the combustion state and provides valuable information for active flow control. Experiments were performed on a hydrogen-fueled scramjet at different equivalence ratios in a ground pulse combustion wind tunnel with a Mach-2.5 incoming flow. Five image datasets of the flame evolution process were constructed at different predicted periods. The memory fusion cascade network (MFCN) was developed to predict flame images after a certain span using flame image sequences of the previous periods. A complete evaluation system was constructed to compare and analyze the performances of MFCN, Kongs, and ResNet16 models in multi- and long-span conditions. Experimental results show that MFCN achieves a maximum increase of 46.16% of the peak signal-to-noise ratio index, 69.14% of the structural correlation coefficient index, and 5.72% of the correlation coefficient index in the independent test set. Moreover, the volume of the model only reaches the KB level, which has the characteristics of being lightweight. MFCN outperforms other methods in terms of the prediction accuracy and maintains stable prediction results during multi- and long-span tasks.
引用
收藏
页数:17
相关论文
共 41 条
[1]   Twenty years of particle image velocimetry [J].
Adrian, RJ .
EXPERIMENTS IN FLUIDS, 2005, 39 (02) :159-169
[2]   Flame stabilization enhancement by microjet-based virtual shock wave generators in a supersonic combustor [J].
An, Bin ;
Wang, Zhenguo ;
Sun, Mingbo .
PHYSICS OF FLUIDS, 2021, 33 (01)
[3]   Laser-Induced Plasma Ignition Experiments in a Direct-Connect Supersonic Combustor at Mach 3 [J].
Baccarella, Damiano ;
Lee, Gyu Sub ;
Liu, Qili ;
Elliott, Gregory S. ;
Freund, Jonathan B. ;
Lee, Tonghun .
JOURNAL OF PROPULSION AND POWER, 2020, 36 (05) :732-743
[4]   Closed-Loop Turbulence Control: Progress and Challenges [J].
Brunton, Steven L. ;
Noack, Bernd R. .
APPLIED MECHANICS REVIEWS, 2015, 67 (05)
[5]   Experimental and numerical investigations on propagating modes of detonations: Detonation wave/boundary layer interaction [J].
Cai, Xiaodong ;
Liang, Jianhan ;
Deiterding, Ralf ;
Mahmoudi, Yasser ;
Sun, Mingbo .
COMBUSTION AND FLAME, 2018, 190 :201-215
[6]   Ignition processes and modes excited by laser-induced plasma in a cavity based supersonic combustor [J].
Cai, Zun ;
Zhu, Jiajian ;
Sun, Mingbo ;
Wang, Zhenguo ;
Bai, Xue-Song .
APPLIED ENERGY, 2018, 228 :1777-1782
[7]   Intelligent reconstruction of the flow field in a supersonic combustor based on deep learning [J].
Chen, Hao ;
Guo, Mingming ;
Tian, Ye ;
Le, Jialing ;
Zhang, Hua ;
Zhong, Fuyu .
PHYSICS OF FLUIDS, 2022, 34 (03)
[8]   Dual-path flow field reconstruction for a scramjet combustor based on deep learning [J].
Deng, Xue ;
Guo, Mingming ;
Chen, Hao ;
Tian, Ye ;
Le, Jialing ;
Zhang, Hua .
PHYSICS OF FLUIDS, 2022, 34 (09)
[9]   Flame Propagation in Millimeter-Scale Tubes for Lean Ethylene-Oxygen Mixtures [J].
Du, Ning ;
Kong, Wenjun ;
Han, Wenhu ;
Ju, Yiguang .
AIAA JOURNAL, 2020, 58 (03) :1337-1347
[10]   Turbulence Modeling in the Age of Data [J].
Duraisamy, Karthik ;
Iaccarino, Gianluca ;
Xiao, Heng .
ANNUAL REVIEW OF FLUID MECHANICS, VOL 51, 2019, 51 :357-377