Reconstructing cellular surface of gaseous detonation based on artificial neural network and proper orthogonal decomposition

Abstract Gaseous detonation has complicated cellular surface, whose comprehensive investigation is critical not only to the detonation physics but also the detonation engine development. Because measuring the high-resolution dynamic surface is beyond the present experimental technical skills, we propose a reconstruction method of detonation wave surface based on post-surface flow field. This method combines two technologies, the proper orthogonal decomposition (POD) in fluid research and the artificial neural network (ANN) in machine learning research. POD is employed to extract the main features of flow fields, and the pre-trained ANN builds up the connection between the reduced coefficients of full flow fields and post-surface flow fields. The reconstruction is tested through the numerical results from one-step irreversible heat release model, displaying a good performance in both cellular normal detonations and unstable oblique detonations. The method may provide a universal frame for the detonation research, and has the potential to be employed in other numerical and experimental results.

[1]  M. Radulescu,et al.  Statistical analysis of cellular detonation dynamics from numerical simulations: one-step chemistry , 2011 .

[2]  Hong Liu,et al.  Effect of acoustically absorbing wall tubes on the near-limit detonation propagation behaviors in a methane–oxygen mixture , 2019, Fuel.

[3]  Joshua R. Codoni,et al.  Investigation of the structure of detonation waves in a non-premixed hydrogen–air rotating detonation engine using mid-infrared imaging , 2019, Proceedings of the Combustion Institute.

[4]  A. A. Borisov,et al.  Pulse detonation propulsion : challenges, current status, and future perspective , 2004 .

[5]  L. Sirovich.  Turbulence and the dynamics of coherent structures. I. Coherent structures , 1987 .

[6]  Frank K. Lu,et al.  Airbreathing rotating detonation wave engine cycle analysis , 2010 .

[7]  Hong Liu,et al.  The effect of instability of detonation on the propagation modes near the limits in typical combustible mixtures , 2019, Fuel.

[8]  Bernard Widrow,et al.  Improving the learning speed of 2-layer neural networks by choosing initial values of the adaptive weights , 1990, 1990 IJCNN International Joint Conference on Neural Networks.

[9]  Hong Liu,et al.  Theoretical prediction model and experimental investigation of detonation limits in combustible gaseous mixtures , 2019 .

[10]  B. A. P. Reif,et al.  Large-eddy simulations of dense-gas dispersion within a high-Reynolds number turbulent boundary layer , 2017 .

[11]  P. Schmid,et al.  Dynamic mode decomposition of numerical and experimental data , 2008, Journal of Fluid Mechanics.

[12]  Yuejin Zhu,et al.  Fabrication of a helical detonation channel: Effect of initial pressure on the detonation propagation modes of ethylene/oxygen mixtures , 2018, Combustion and Flame.

[13]  John H. S. Lee.  The Detonation Phenomenon , 2008 .

[14]  H. Teng,et al.  Evolution of cellular structures on oblique detonation surfaces , 2015 .

[15]  Zhenhua Pan,et al.  Wavelet pattern and self-sustained mechanism of gaseous detonation rotating in a coaxial cylinder , 2011 .

[16]  E. Oran.  Understanding explosions – From catastrophic accidents to creation of the universe , 2015 .

[17]  Elaine S. Oran,et al.  Formation and evolution of two-dimensional cellular detonations , 1999 .

[18]  Linyang Zhu,et al.  Machine learning methods for turbulence modeling in subsonic flows around airfoils , 2018, Physics of Fluids.

[19]  Hong Liu,et al.  Velocity behavior downstream of perforated plates with large blockage ratio for unstable and stable detonations , 2019, Aerospace Science and Technology.

[20]  U. Rist,et al.  Proper orthogonal decomposition reconstruction of a transitional boundary layer with and without control , 2004 .

[21]  Nathan E. Murray,et al.  Properties of subsonic open cavity flow fields , 2009 .

[22]  Jian Yu,et al.  Flowfield Reconstruction Method Using Artificial Neural Network , 2019, AIAA Journal.

[23]  Robert T. Fievisohn,et al.  Steady-State Analysis of Rotating Detonation Engine Flowfields with the Method of Characteristics , 2017 .

[24]  Bo Zhang,et al.  The effects of large scale perturbation-generating obstacles on the propagation of detonation filled with methane–oxygen mixture , 2017 .

[25]  Joseph E. Shepherd,et al.  Detonation in gases , 2009 .

[26]  F. Sharpe,et al.  Two-dimensional numerical simulations of idealized detonations , 1999, Proceedings of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences.

[27]  E. Toro.  Riemann Solvers and Numerical Methods for Fluid Dynamics , 1997 .

[28]  Vassilios Theofilis,et al.  Modal Analysis of Fluid Flows: An Overview , 2017, 1702.01453.

[29]  Hong Liu,et al.  Investigation on the detonation propagation limit criterion for methane-oxygen mixtures in tubes with different scales , 2019, Fuel.

[30]  Andrzej Teodorczyk,et al.  Detonation cell size model based on deep neural network for hydrogen, methane and propane mixtures with air and oxygen , 2019, Nuclear Engineering and Technology.

[31]  H. Ng,et al.  Numerical study on unstable surfaces of oblique detonations , 2014, Journal of Fluid Mechanics.

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

[33]  Antonio J. Torregrosa,et al.  Modal decomposition of the unsteady flow field in compression-ignited combustion chambers , 2018 .

[34]  Simona Silvia Merola,et al.  POD-based analysis of combustion images in optically accessible engines , 2010 .

[35]  Hecong Liu,et al.  Toward real-time volumetric tomography for combustion diagnostics via dimension reduction. , 2018, Optics letters.

[36]  Martin Fodslette Møller,et al.  A scaled conjugate gradient algorithm for fast supervised learning , 1993, Neural Networks.

[37]  Akiko Matsuo,et al.  Numerical investigation on detonation velocity in rotating detonation engine chamber , 2017 .

[38]  V. V. Tyurenkova,et al.  Three-dimensional modeling of rotating detonation in a ramjet engine , 2019, Acta Astronautica.

[39]  Scott T. M. Dawson,et al.  Model Reduction for Flow Analysis and Control , 2017 .

[40]  Weiwei Cai,et al.  Online in situ prediction of 3-D flame evolution from its history 2-D projections via deep learning , 2019, Journal of Fluid Mechanics.

[41]  Jianqing Huang,et al.  Compressing convolutional neural networks using POD for the reconstruction of nonlinear tomographic absorption spectroscopy , 2019, Comput. Phys. Commun..

[42]  John Hoke,et al.  Chemiluminescence imaging of an optically accessible non-premixed rotating detonation engine , 2017 .

[43]  H. D. Ng.  Effects of activation energy on the instability of oblique detonation surfaces with a one-step chemistry model , 2018, Physics of Fluids.