Cargando…
A Design Method of Two-Dimensional Subwavelength Grating Filter Based on Deep Learning Series Feedback Neural Network
Subwavelength grating structure has excellent filtering characteristics, and its traditional design method needs a lot of computational costs. This work proposed a design method of two-dimensional subwavelength grating filter based on a series feedback neural network, which can realize forward simul...
Autores principales: | , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9609313/ https://www.ncbi.nlm.nih.gov/pubmed/36298109 http://dx.doi.org/10.3390/s22207758 |
_version_ | 1784818987707662336 |
---|---|
author | Guo, Jun-Hua Zhang, Ying-Li Zhang, Shuai-Shuai Cai, Chang-Long Liang, Hai-Feng |
author_facet | Guo, Jun-Hua Zhang, Ying-Li Zhang, Shuai-Shuai Cai, Chang-Long Liang, Hai-Feng |
author_sort | Guo, Jun-Hua |
collection | PubMed |
description | Subwavelength grating structure has excellent filtering characteristics, and its traditional design method needs a lot of computational costs. This work proposed a design method of two-dimensional subwavelength grating filter based on a series feedback neural network, which can realize forward simulation and backward design. It was programed in Python to study the filtering characteristics of two-dimensional subwavelength grating in the range of 0.4–0.7 µm. The shape, height, period, duty cycle, and waveguide layer height of two-dimensional subwavelength grating were taken into consideration. The dataset, containing 46,080 groups of data, was generated through numerical simulation of rigorous coupled-wave analysis (RCWA). The optimal network was five layers, 128 × 512 × 512 × 128 × 61 nodes, and 64 batch size. The loss function of the series feedback neural network is as low as 0.024. Meanwhile, it solves the problem of non-convergence of the network reverse design due to the non-uniqueness of data. The series feedback neural network can give the geometrical structure parameters of two-dimensional subwavelength grating within 1.12 s, and the correlation between the design results and the theoretical spectrum is greater than 0.65, which belongs to a strong correlation. This study provides a new method for the design of two-dimensional subwavelength grating, which is quicker and more accurate compared with the traditional method. |
format | Online Article Text |
id | pubmed-9609313 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-96093132022-10-28 A Design Method of Two-Dimensional Subwavelength Grating Filter Based on Deep Learning Series Feedback Neural Network Guo, Jun-Hua Zhang, Ying-Li Zhang, Shuai-Shuai Cai, Chang-Long Liang, Hai-Feng Sensors (Basel) Article Subwavelength grating structure has excellent filtering characteristics, and its traditional design method needs a lot of computational costs. This work proposed a design method of two-dimensional subwavelength grating filter based on a series feedback neural network, which can realize forward simulation and backward design. It was programed in Python to study the filtering characteristics of two-dimensional subwavelength grating in the range of 0.4–0.7 µm. The shape, height, period, duty cycle, and waveguide layer height of two-dimensional subwavelength grating were taken into consideration. The dataset, containing 46,080 groups of data, was generated through numerical simulation of rigorous coupled-wave analysis (RCWA). The optimal network was five layers, 128 × 512 × 512 × 128 × 61 nodes, and 64 batch size. The loss function of the series feedback neural network is as low as 0.024. Meanwhile, it solves the problem of non-convergence of the network reverse design due to the non-uniqueness of data. The series feedback neural network can give the geometrical structure parameters of two-dimensional subwavelength grating within 1.12 s, and the correlation between the design results and the theoretical spectrum is greater than 0.65, which belongs to a strong correlation. This study provides a new method for the design of two-dimensional subwavelength grating, which is quicker and more accurate compared with the traditional method. MDPI 2022-10-13 /pmc/articles/PMC9609313/ /pubmed/36298109 http://dx.doi.org/10.3390/s22207758 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Guo, Jun-Hua Zhang, Ying-Li Zhang, Shuai-Shuai Cai, Chang-Long Liang, Hai-Feng A Design Method of Two-Dimensional Subwavelength Grating Filter Based on Deep Learning Series Feedback Neural Network |
title | A Design Method of Two-Dimensional Subwavelength Grating Filter Based on Deep Learning Series Feedback Neural Network |
title_full | A Design Method of Two-Dimensional Subwavelength Grating Filter Based on Deep Learning Series Feedback Neural Network |
title_fullStr | A Design Method of Two-Dimensional Subwavelength Grating Filter Based on Deep Learning Series Feedback Neural Network |
title_full_unstemmed | A Design Method of Two-Dimensional Subwavelength Grating Filter Based on Deep Learning Series Feedback Neural Network |
title_short | A Design Method of Two-Dimensional Subwavelength Grating Filter Based on Deep Learning Series Feedback Neural Network |
title_sort | design method of two-dimensional subwavelength grating filter based on deep learning series feedback neural network |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9609313/ https://www.ncbi.nlm.nih.gov/pubmed/36298109 http://dx.doi.org/10.3390/s22207758 |
work_keys_str_mv | AT guojunhua adesignmethodoftwodimensionalsubwavelengthgratingfilterbasedondeeplearningseriesfeedbackneuralnetwork AT zhangyingli adesignmethodoftwodimensionalsubwavelengthgratingfilterbasedondeeplearningseriesfeedbackneuralnetwork AT zhangshuaishuai adesignmethodoftwodimensionalsubwavelengthgratingfilterbasedondeeplearningseriesfeedbackneuralnetwork AT caichanglong adesignmethodoftwodimensionalsubwavelengthgratingfilterbasedondeeplearningseriesfeedbackneuralnetwork AT lianghaifeng adesignmethodoftwodimensionalsubwavelengthgratingfilterbasedondeeplearningseriesfeedbackneuralnetwork AT guojunhua designmethodoftwodimensionalsubwavelengthgratingfilterbasedondeeplearningseriesfeedbackneuralnetwork AT zhangyingli designmethodoftwodimensionalsubwavelengthgratingfilterbasedondeeplearningseriesfeedbackneuralnetwork AT zhangshuaishuai designmethodoftwodimensionalsubwavelengthgratingfilterbasedondeeplearningseriesfeedbackneuralnetwork AT caichanglong designmethodoftwodimensionalsubwavelengthgratingfilterbasedondeeplearningseriesfeedbackneuralnetwork AT lianghaifeng designmethodoftwodimensionalsubwavelengthgratingfilterbasedondeeplearningseriesfeedbackneuralnetwork |