Machine-Learning-Based Reconstruction of Flame Temperature and CO2 Concentration Fields

Yicheng Zhang; Yongkang Han; Ya Zhou; Tao Ren; Xunchen Liu

doi:10.3788/AOS202040.2312003

[1] Chen X, Kan R F, Yang C G et al. Concentration measurements of NO2 and NH3 based on wavelength-modulation frequency-division-multiplexing spectroscopic technique[J]. Acta Optica Sinica, 38, 0512004(2018).

[2] Qu D S, Fan H J, Liu L W et al. Measurement of gas parameters in supersonic combustion field based on near-infrared spectroscopy[J]. Acta Optica Sinica, 40, 0330001(2020).

[3] Zhang F C, Sun B J, Sun X G. Multispectral true temperature inversion based on multi-objective minimization optimization method[J]. Acta Optica Sinica, 39, 0212008(2019).

[4] Huang Y, Zhang G Y, Liu X C et al. Temperature distribution of axisymmetric diffusion flame measured by mid-infrared laser[J]. Journal of Engineering Thermophysics, 38, 1447-1453(2017).

[5] Liu C, Xu L J, Cao Z. Measurement of nonuniform temperature and concentration distributions by combining line-of-sight tunable diode laser absorption spectroscopy with regularization methods[J]. Applied Optics, 52, 4827-4842(2013).

[6] Wang F, Cen K, Li N et al. Two-dimensional tomography for gas concentration and temperature distributions based on tunable diode laser absorption spectroscopy[J]. Measurement Science and Technology, 21, 045301(2010).

[7] Zhang G Y, Wang G Q, Huang Y et al. Reconstruction and simulation of temperature and CO2 concentration in an axisymmetric flame based on TDLAS[J]. Optik, 170, 166-177(2018).

[8] Liu X C, Zhang G Y, Huang Y et al. Two-dimensional temperature and carbon dioxide concentration profiles in atmospheric laminar diffusion flames measured by mid-infrared direct absorption spectroscopy at 4.2 μm[J]. Applied Physics B, 124, 1-10(2018).

[9] Zhang H D. Reconstruction of flame temperature field and soot concentration field based on hyperspectral imaging system[D]. Hangzhou: Zhejiang University(2016).

[10] Michalski R S, Carbonell J G, Mitchell T M. Machine learning[M]. Berlin, Heidelberg: Springer Berlin Heidelberg(1983).

[11] Chen N F Y, Kasim M F, Ceurvorst L et al. Machine learning applied to proton radiography of high-energy-density plasmas[J]. Physical Review E, 95, 043305(2017).

[12] Rodrigues É O. Pinheiro V H A, Liatsis P, et al. Machine learning in the prediction of cardiac epicardial and mediastinal fat volumes[J]. Computers in Biology and Medicine, 89, 520-529(2017).

[13] Huang J Q, Liu H C, Cai W W. Online in situ prediction of 3-D flame evolution from its history 2-D projections via deep learning[J]. Journal of Fluid Mechanics, 875, R2(2019).

[14] Jin Y, Zhang W Q, Song Y et al. Three-dimensional rapid flame chemiluminescence tomography via deep learning[J]. Optics Express, 27, 27308-27334(2019).

[15] Johns J M, Burkes D. Development of multilayer perceptron networks for isothermal time temperature transformation prediction of U-Mo-X alloys[J]. Journal of Nuclear Materials, 490, 155-166(2017).

[16] Ren T, Modest M F, Fateev A et al. Machine learning applied to retrieval of temperature and concentration distributions from infrared emission measurements[J]. Applied Energy, 252, 113448(2019).

[17] Taglialatela Scafati F, Lavorgna M, Mancaruso E et al[M]. Artificial intelligence for modeling and control of nonlinear phenomena in internal combustion engines, 1-19(2017).

[18] Nutkiewicz A, Yang Z, Jain R K. Data-driven Urban Energy Simulation (DUE-S): a framework for integrating engineering simulation and machine learning methods in a multi-scale urban energy modeling workflow[J]. Applied Energy, 225, 1176-1189(2018).

[19] Rothman L S, Gordon I E, Barber R J et al. HITEMP, the high-temperature molecular spectroscopic database[J]. Journal of Quantitative Spectroscopy and Radiative Transfer, 111, 2139-2150(2010).

[20] Smooke M D. McEnally C S, Pfefferle L D, et al. Computational and experimental study of soot formation in a coflow, laminar diffusion flame[J]. Combustion and Flame, 117, 117-139(1999).

[21] Cuoci A, Frassoldati A, Faravelli T et al. Numerical modeling of laminar flames with detailed kinetics based on the operator-splitting method[J]. Energy & Fuels, 27, 7730-7753(2013).

[22] Cuoci A, Frassoldati A, Faravelli T et al. A computational tool for the detailed kinetic modeling of laminar flames: application to C2H4/CH4 coflow flames[J]. Combustion and Flame, 160, 870-886(2013).

[23] Cuoci A, Frassoldati A, Faravelli T et al. OpenSMOKE++: an object-oriented framework for the numerical modeling of reactive systems with detailed kinetic mechanisms[J]. Computer Physics Communications, 192, 237-264(2015).

[24] Kramer O[M]. Machine learning for evolution strategies(2016).

[25] Kingma D P. arXiv:1412[2020-07-16]. 6980 https:∥arxiv., org/abs/1412, 6980(2014).