Electromagnetic Micro-Structure Non-Destructive Testing: Sparsity-Constrained and Combined Convolutional Recurrent Neural Network Methods

被引:4
作者
Ran, Peipei [1 ]
Lesselier, Dominique [1 ]
Serhir, Mohammed [2 ]
机构
[1] Univ Paris Saclay, Lab Signaux & Syst, Cent Supelec, CNRS, F-91190 Gif Sur Yvette, France
[2] Univ Paris Saclay, Lab Genie Elect & Elect Paris, Cent Supelec, CNRS, F-91190 Gif Sur Yvette, France
关键词
micro-structure; convolutional neural networks; recurrent neural networks; sparsity; subwavelength super-resolution probing; SCATTERING; SET;
D O I
10.3390/electronics9111750
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
How to locate missing rods within a micro-structure composed of a grid-like, finite set of infinitely long circular cylindrical dielectric rods under the sub-wavelength condition is investigated. Sub-wavelength distances between adjacent rods and sub-wavelength rod diameters require super-resolution, beyond the Rayleigh criterion. Two different methods are proposed to achieve this: One builds upon the multiple scattering expansion method (MSM), and it enforces strong sparsity-prior information. The other is a data-driven method that combines convolutional neural networks (CNN) and recurrent neural networks (RNN), and it can be applied in effect with little knowledge of the wavefield interactions involved, in much contrast with the previous one. Comprehensive numerical simulations are proposed in terms of the missing rod number, shape, the frequency of observation, and the configuration of the tested structures. Both methods are shown to achieve suitable detection, yet under more or less stringent conditions as discussed.
引用
收藏
页码:1 / 16
页数:16
相关论文
共 30 条
[1]   A Mathematical Theory of Super-Resolution by Using a System of Sub-Wavelength Helmholtz Resonators [J].
Ammari, Habib ;
Zhang, Hai .
COMMUNICATIONS IN MATHEMATICAL PHYSICS, 2015, 337 (01) :379-428
[2]   Formulation for electromagnetic scattering and propagation through grating stacks of metallic and dielectric cylinders for photonic crystal calculations. Part I. Method [J].
Botten, LC ;
Nicorovici, NAP ;
Asatryan, AA ;
McPhedran, RC ;
de Sterke, CM ;
Robinson, PA .
JOURNAL OF THE OPTICAL SOCIETY OF AMERICA A-OPTICS IMAGE SCIENCE AND VISION, 2000, 17 (12) :2165-2176
[3]   Fault detection in dielectric grid scatterers [J].
Brancaccio, Adriana ;
Solimene, Raffaele .
OPTICS EXPRESS, 2015, 23 (07) :8200-8215
[4]  
Cho K., 2014, P EMPIRICAL METHODS, P1724, DOI DOI 10.3115/V1/D14-1179
[5]  
Chung J., 2014, ARXIV14123555, DOI DOI 10.48550/ARXIV.1412.3555
[6]   A Modified Efficient KNN Method for Antenna Optimization and Design [J].
Cui, Liangze ;
Zhang, Yao ;
Zhang, Runren ;
Liu, Qing Huo .
IEEE TRANSACTIONS ON ANTENNAS AND PROPAGATION, 2020, 68 (10) :6858-6866
[7]  
Duchi J, 2011, J MACH LEARN RES, V12, P2121
[8]   Acoustic response of a rigid-frame porous medium plate with a periodic set of inclusions [J].
Groby, J. -P. ;
Wirgin, A. ;
De Ryck, L. ;
Lauriks, W. ;
Gilbert, R. P. ;
Xu, Y. S. .
JOURNAL OF THE ACOUSTICAL SOCIETY OF AMERICA, 2009, 126 (02) :685-693
[9]   Localization and characterization of simple defects in finite-sized photonic crystals [J].
Groby, Jean-Philippe ;
Lesselier, Dominique .
JOURNAL OF THE OPTICAL SOCIETY OF AMERICA A-OPTICS IMAGE SCIENCE AND VISION, 2008, 25 (01) :146-152
[10]   Wave physics as an analog recurrent neural network [J].
Hughes, Tyler W. ;
Williamson, Ian A. D. ;
Minkov, Momchil ;
Fan, Shanhui .
SCIENCE ADVANCES, 2019, 5 (12)