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

Ran, Peipei; Lesselier, Dominique; Serhir, Mohammed

doi:10.3390/electronics9111750

Open AccessArticle

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

by

Peipei Ran

¹

,

Dominique Lesselier

^1,*

and

Mohammed Serhir

²

¹

CNRS, CentraleSupélec, Laboratoire des Signaux et Systèmes, Université Paris-Saclay, 91190 Gif-sur-Yvette, France

²

CNRS, CentraleSupélec, Laboratoire de Génie Electrique et Electronique de Paris, Université Paris-Saclay, 91190 Gif-sur-Yvette, France

^*

Author to whom correspondence should be addressed.

Electronics 2020, 9(11), 1750; https://doi.org/10.3390/electronics9111750

Submission received: 29 September 2020 / Revised: 13 October 2020 / Accepted: 15 October 2020 / Published: 22 October 2020

(This article belongs to the Special Issue New Trends and Future Challenges in Computational Microwave Imaging)

Download

Browse Figures

Versions Notes

Abstract

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.

Keywords: micro-structure; convolutional neural networks; recurrent neural networks; sparsity; subwavelength super-resolution probing

Share and Cite

MDPI and ACS Style

Ran, P.; Lesselier, D.; Serhir, M. Electromagnetic Micro-Structure Non-Destructive Testing: Sparsity-Constrained and Combined Convolutional Recurrent Neural Network Methods. Electronics 2020, 9, 1750. https://doi.org/10.3390/electronics9111750

AMA Style

Ran P, Lesselier D, Serhir M. Electromagnetic Micro-Structure Non-Destructive Testing: Sparsity-Constrained and Combined Convolutional Recurrent Neural Network Methods. Electronics. 2020; 9(11):1750. https://doi.org/10.3390/electronics9111750

Chicago/Turabian Style

Ran, Peipei, Dominique Lesselier, and Mohammed Serhir. 2020. "Electromagnetic Micro-Structure Non-Destructive Testing: Sparsity-Constrained and Combined Convolutional Recurrent Neural Network Methods" Electronics 9, no. 11: 1750. https://doi.org/10.3390/electronics9111750

APA Style

Ran, P., Lesselier, D., & Serhir, M. (2020). Electromagnetic Micro-Structure Non-Destructive Testing: Sparsity-Constrained and Combined Convolutional Recurrent Neural Network Methods. Electronics, 9(11), 1750. https://doi.org/10.3390/electronics9111750

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Menu

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

Abstract

Share and Cite

Article Metrics

Article Access Statistics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI