Prediction model of flow field in an isolator over various operating conditions

Abstract The flow characteristics in a scramjet isolator are quite complicated, so it is difficult to achieve precise operating state detection on a scramjet isolator by wall pressure only. Flow field prediction using deep learning is a promising method to provide a rich source of information for isolator operating state detection. A data-driven model is proposed for the prediction of the flow field in an isolator by fusion convolutional neural networks using measurements of the pressure on the isolator. Numerical simulations of flow in an isolator at various Mach numbers and backpressures are carried out to establish the dataset. A convolutional neural network architecture composed of a fusion of paths is designed. The convolutional neural network is trained using the computational fluid dynamics dataset to establish the mapping relationship between the wall pressure on the isolator and the flow field in the isolator, including the Mach number field, the pressure field, and the temperature field. The trained model is then tested over various Mach numbers and backpressures. The relative error of the prediction results in most areas does not exceed 5%, and the correlation coefficients between prediction results and computational fluid dynamic results are all over 0.99 in the whole testing set. The predictions of this model are found to agree well with the computational fluid dynamics results, i.e., the data-driven model successfully learns the relationship between internal flow field and pressure experienced on the wall of an isolator.

[1]  Prabhat,et al.  Application of Deep Convolutional Neural Networks for Detecting Extreme Weather in Climate Datasets , 2016, ArXiv.

[2]  Daren Yu,et al.  Mathematical Model of Shock-Train Path with Complex Background Waves , 2017 .

[3]  J. Wagner,et al.  Experimental Investigation of Unstart in an Inlet/Isolator Model in Mach 5 Flow , 2009 .

[4]  He-xia Huang,et al.  Behavior of Shock Train in Curved Isolators with Complex Background Waves , 2018 .

[5]  Inversion and reconstruction of supersonic cascade passage flow field based on a model comprising transposed network and residual network , 2019 .

[6]  Daren Yu,et al.  Low-frequency unsteadiness of shock-wave/boundary-layer interaction in an isolator with background waves , 2020 .

[7]  He-xia Huang,et al.  Behavior of shock trains in a hypersonic inlet/isolator model with complex background waves , 2012 .

[8]  Daren Yu,et al.  Optimal Classification Criterions of Hypersonic Inlet Start/Unstart , 2007 .

[9]  Jun-tao Chang,et al.  Path dependence characteristic of shock train in a 2D hypersonic inlet with variable background waves , 2019, Aerospace Science and Technology.

[10]  G. Barakos,et al.  Flow physics and sensitivity to RANS modelling assumptions of a multiple shock wave/turbulent boundary layer interaction , 2020 .

[11]  Daren Yu,et al.  Mechanism and Prediction for Occurrence of Shock-Train Sharp Forward Movement , 2016 .

[13]  Birgit Reinartz,et al.  Aerodynamic Performance Analysis of a Hypersonic Inlet Isolator Using Computation and Experiment , 2003 .

[14]  Yufeng Yao,et al.  Numerical investigation on shock train control and applications in a scramjet engine , 2017 .

[15]  Daren Yu,et al.  Backpressure unstart detection for a scramjet inlet based on information fusion , 2014 .

[16]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[17]  J. Swithenbank.  Hypersonic air-breathing propulsion , 1967 .

[18]  Nan Li,et al.  Recent research progress on unstart mechanism, detection and control of hypersonic inlet , 2017 .

[19]  Izhar Wallach,et al.  AtomNet: A Deep Convolutional Neural Network for Bioactivity Prediction in Structure-based Drug Discovery , 2015, ArXiv.

[20]  J. Templeton,et al.  Reynolds averaged turbulence modelling using deep neural networks with embedded invariance , 2016, Journal of Fluid Mechanics.

[21]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[22]  H. Ren,et al.  Experimental and numerical investigation of isolator in three-dimensional inward turning inlet , 2019 .

[23]  W. Bao,et al.  Behavior and flow mechanism of shock train self-excited oscillation influenced by background waves , 2020 .

[24]  Nitish Srivastava,et al.  Improving neural networks by preventing co-adaptation of feature detectors , 2012, ArXiv.

[25]  Wei Li,et al.  Convolutional Neural Networks for Steady Flow Approximation , 2016, KDD.

[26]  Wubingyi Shen,et al.  Characteristics of reaction zone in a dual-mode scramjet combustor during mode transitions , 2020 .

[27]  Hui Li,et al.  Prediction model of velocity field around circular cylinder over various Reynolds numbers by fusion convolutional neural networks based on pressure on the cylinder , 2018 .

[28]  T. P. Miyanawala,et al.  An Efficient Deep Learning Technique for the Navier-Stokes Equations: Application to Unsteady Wake Flow Dynamics , 2017, 1710.09099.

[29]  F. Billig,et al.  Structure of Shock Waves in Cylindrical Ducts , 1973 .

[30]  Wolfgang Koschel,et al.  Experimental Investigation of the Internal Compression Inside a Hypersonic Intake , 2002 .

[31]  A. Roudakov,et al.  CIAM/NASA Mach 6.5 Scramjet Flight and Ground Test , 1999 .

[32]  Shihe Yi,et al.  Investigation on flows in a supersonic isolator with an adjustable cowl convergence angle , 2014 .

[33]  Corin Segal,et al.  The Scramjet Engine: Processes and Characteristics , 2009 .

[34]  Jiming Yang,et al.  Unsteady Behaviors of a Hypersonic Inlet Caused by Throttling in Shock Tunnel , 2013 .

[35]  Chi-Keung Tang,et al.  Fast image/video upsampling , 2008, SIGGRAPH Asia '08.

[36]  Wei Yu,et al.  On learning optimized reaction diffusion processes for effective image restoration , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[37]  Jun-tao Chang,et al.  Unstart Margin Characterization Method of Scramjet Considering Isolator–Combustor Interactions , 2015 .

[38]  Juntao Chang,et al.  Flow field reconstruction and prediction of the supersonic cascade channel based on a symmetry neural network under complex and variable conditions , 2020, AIP Advances.

[39]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[40]  Keming Cheng,et al.  Unsteady behavior of oblique shock train and boundary layer interactions , 2018, Aerospace Science and Technology.

[41]  V. Raman,et al.  Large-eddy simulation of a supersonic inlet-isolator , 2012 .

[42]  Ziao Wang,et al.  Numerical investigation on the forced oscillation of shock train in hypersonic inlet with translating cowl , 2019, Aerospace Science and Technology.

[43]  Daren Yu,et al.  Real-time unstart prediction and detection of hypersonic inlet based on recursive Fourier transform , 2015 .

[44]  Ye Tian,et al.  Experimental study on flame development and stabilization in a kerosene fueled supersonic combustor , 2019, Aerospace Science and Technology.

[45]  Daren Yu,et al.  Research progress on strut-equipped supersonic combustors for scramjet application , 2018, Progress in Aerospace Sciences.

[46]  Daren Yu,et al.  Operation pattern classification of hypersonic inlets , 2009 .

[47]  Yang Yu.  Over-expanded separation transitions of single expansion ramp nozzle in the accelerating and decelerating processes , 2020 .

[48]  Pierre Sagaut,et al.  Time-Frequency Analysis and Detection of Supersonic Inlet Buzz , 2007 .