Research on asymmetric flame reconstruction based on prior regularization and its intelligent improvement

Abstract In this paper, a priori regularized-based total variation algebraic iteration (ARTTV) reconstruction algorithm for asymmetric flame is studied in detail. The impact of convergence characteristics, noise immunity, relative error, projection angle dependence to the algorithm are analyzed. In order to further improve the inversion accuracy, stability and computational efficiency of algorithm, the ARTTV is optimized in two aspects. First, the learning factor adaptive particle swarm optimization (PSO) algorithm is proposed for solving the regularization parameter, and this makes the iterative results more stable. Second, we propose to use the nonlinear fitting ability of Extreme learning machine (ELM) neural network to approximate the ARTTV-PSO algorithm to obtain nearly the same reconstruction performance. The results show that the ELM-optimized reconstruction algorithm can reduce the inversion time by about 300 times with only about 0.54% accuracy loss.

[1]  Hongsheng Guo,et al.  Numerical modelling of soot formation and oxidation in laminar coflow non-smoking and smoking ethylene diffusion flames , 2003 .

[2]  Lin Li,et al.  An extreme learning machine combined with Landweber iteration algorithm for the inverse problem of electrical capacitance tomography , 2015 .

[3]  Fan Jiang,et al.  Tomographic measurement of temperature in non-axisymmetric arc plasma by single camera multi-view imaging system. , 2018, Optics express.

[4]  Guang-Bin Huang,et al.  Extreme learning machine: a new learning scheme of feedforward neural networks , 2004, 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541).

[5]  Xin Jin,et al.  A limited-angle CT reconstruction method based on anisotropic TV minimization , 2013, Physics in medicine and biology.

[6]  G. Herman,et al.  Algebraic reconstruction techniques (ART) for three-dimensional electron microscopy and x-ray photography. , 1970, Journal of theoretical biology.

[7]  Zhang Cao,et al.  Development of a fan-beam TDLAS-based tomographic sensor for rapid imaging of temperature and gas concentration. , 2015, Optics express.

[8]  Kefa Cen,et al.  On the treatment of non-optimal regularization parameter influence on temperature distribution reconstruction accuracy in participating medium , 2012 .

[9]  Xuesong Li,et al.  Practical aspects of implementing three-dimensional tomography inversion for volumetric flame imaging. , 2013, Applied optics.

[10]  Bin Yan,et al.  Efficient TpV minimization for circular, cone-beam computed tomography reconstruction via non-convex optimization , 2015, Comput. Medical Imaging Graph..

[11]  Kyle J Daun,et al.  Parameter selection methods for axisymmetric flame tomography through Tikhonov regularization. , 2008, Applied optics.

[12]  E. Sidky,et al.  Image reconstruction in circular cone-beam computed tomography by constrained, total-variation minimization , 2008, Physics in medicine and biology.

[13]  Liwu Liu,et al.  Reconstruction of time-averaged temperature of non-axisymmetric turbulent unconfined sooting flame by inverse radiation analysis , 2003 .

[14]  James Paul Holloway,et al.  A reconstruction algorithm for a spatially resolved plasma optical emission spectroscopy sensor , 2001 .

[15]  Xiangyu Zhang,et al.  An improved colorimetric method for visualization of 2-D, inhomogeneous temperature distribution in a gas fired industrial furnace by radiation image processing , 2011 .

[16]  Prabhat Munshi,et al.  A ROBUST MART ALGORITHM FOR TOMOGRAPHIC APPLICATIONS , 1999 .

[17]  Chuanlong Xu,et al.  Optical Sectioning Tomographic Reconstruction of Three-Dimensional Flame Temperature Distribution Using Single Light Field Camera , 2018, IEEE Sensors Journal.

[18]  C. Kaminski,et al.  Tomographic absorption spectroscopy for the study of gas dynamics and reactive flows , 2017 .

[19]  Lihui Peng,et al.  Image reconstruction algorithms for electrical capacitance tomography , 2003 .

[20]  Zhu He,et al.  Integrated research of a multi-wavelength method in anisotropic scattering flame on soot temperature and radiative coefficient reconstruction. , 2018, Applied optics.

[21]  Bin Zhang,et al.  Flame four-dimensional deflection tomography with compressed-sensing-revision reconstruction , 2016 .

[22]  Roger Fletcher,et al.  A Rapidly Convergent Descent Method for Minimization , 1963, Comput. J..

[23]  Yojiro Ishino,et al.  Three-Dimensional Computerized Tomographic Reconstruction of Instantaneous Distribution of Chemiluminescence of a Turbulent Premixed Flame , 2005 .

[24]  R. Eberhart,et al.  Empirical study of particle swarm optimization , 1999, Proceedings of the 1999 Congress on Evolutionary Computation-CEC99 (Cat. No. 99TH8406).

[25]  Erkki Oja,et al.  GPU-accelerated and parallelized ELM ensembles for large-scale regression , 2011, Neurocomputing.

[26]  Kefa Cen,et al.  Experimental reconstructions of flame temperature distributions in laboratory-scale and large-scale pulverized-coal fired furnaces by inverse radiation analysis , 2012 .

[27]  Huaichun Zhou,et al.  Experiments investigation on 2D distribution of soot temperature and volume fraction by image processing of visible radiation , 2017 .

[28]  Huai-Chun Zhou,et al.  Experimental investigations on visualization of three-dimensional temperature distributions in a large-scale pulverized-coal-fired boiler furnace , 2005 .

[29]  Chuanlong Xu,et al.  Liquid lens-based optical sectioning tomography for three-dimensional flame temperature measurement , 2017 .

[30]  Kefa Cen,et al.  On the treatment of scattering for three-dimensional temperature distribution reconstruction accuracy in participating medium , 2011 .

[31]  Anding Wang,et al.  Solving linearly constrained matrix least squares problem by LSQR , 2014, Appl. Math. Comput..

[32]  He-Ping Tan,et al.  Light field imaging analysis of flame radiative properties based on Monte Carlo method , 2018 .

[33]  Lin Ma,et al.  Determination of the optimal regularization parameters in hyperspectral tomography. , 2008, Applied optics.

[34]  Zhu He,et al.  Research on the Effect of Soot Self-Absorption on Flame Multispectral Radiation Reconstruction , 2019, Journal of Thermophysics and Heat Transfer.

[35]  L. Rudin,et al.  Nonlinear total variation based noise removal algorithms , 1992 .

[36]  Xizi Song,et al.  A spatially adaptive total variation regularization method for electrical resistance tomography , 2015 .

[37]  Xiangyu Zhang,et al.  Simultaneous Measurement of Three-Dimensional Temperature Distributions and Radiative Properties Based on Radiation Image Processing Technology in a Gas-Fired Pilot Tubular Furnace , 2014 .

[38]  A. Kak,et al.  Simultaneous Algebraic Reconstruction Technique (SART): A Superior Implementation of the Art Algorithm , 1984, Ultrasonic imaging.

[39]  Chuguang Zheng,et al.  Visualization of three-dimensional temperature distributions in a large-scale furnace via regularized reconstruction from radiative energy images: numerical studies , 2002 .

[40]  Yingzheng Liu,et al.  Rapid tomographic reconstruction based on machine learning for time-resolved combustion diagnostics. , 2018, The Review of scientific instruments.