Optimal design of microwave absorber using novel variational autoencoder from a latent space search strategy
This paper introduces a new objective-driven design method based on deep learning for meta-structure absorber for X-band (8–12 GHz) application. The method consists of three steps; at Step 1, developing a simulator to predict a spectrum of microwave from a conductive layer of absorber as an image in...
Guardado en:
Autores principales: | , , , , , |
---|---|
Formato: | article |
Lenguaje: | EN |
Publicado: |
Elsevier
2021
|
Materias: | |
Acceso en línea: | https://doaj.org/article/ceb41be6506b488bb10628a411516ceb |
Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
id |
oai:doaj.org-article:ceb41be6506b488bb10628a411516ceb |
---|---|
record_format |
dspace |
spelling |
oai:doaj.org-article:ceb41be6506b488bb10628a411516ceb2021-11-28T04:27:44ZOptimal design of microwave absorber using novel variational autoencoder from a latent space search strategy0264-127510.1016/j.matdes.2021.110266https://doaj.org/article/ceb41be6506b488bb10628a411516ceb2021-12-01T00:00:00Zhttp://www.sciencedirect.com/science/article/pii/S0264127521008212https://doaj.org/toc/0264-1275This paper introduces a new objective-driven design method based on deep learning for meta-structure absorber for X-band (8–12 GHz) application. The method consists of three steps; at Step 1, developing a simulator to predict a spectrum of microwave from a conductive layer of absorber as an image input, at Step 2, designing an autoencoder network to take the patterns as input and outputs the same pattern, at Step 3, making an inverse design method for a new pattern under a given goal (spectrum). The proposed method was verified by comparing with the reflectance spectrum calculated by FDTD on the designed absorber with an optimal conductive pattern layer. For the effective training of a general random-like pixel patterns, the variational autoencoder (VAE) that uses a new adaptive annealing loss and a symmetricity layer block in VAE decoder is suggested to improve the training performance. The covariance Matrix Adaptation Evolution Strategy (CMA-ES) which searches the optimal pattern in the VAE latent space is used for suggesting the candidates of the optimal pattern. The proposed method can find an optimal absorber with minimum −16 dB reflectance in X-band that exceed the best absorption among all the training samples obtained by FDTD.Han-Ik OnLeekyo JeongMinseok JungDong-Joong KangJun-Hyub ParkHak-Joo LeeElsevierarticleMicrowave absorberFDTDDeep learningVAECMA-ESBalancing lossMaterials of engineering and construction. Mechanics of materialsTA401-492ENMaterials & Design, Vol 212, Iss , Pp 110266- (2021) |
institution |
DOAJ |
collection |
DOAJ |
language |
EN |
topic |
Microwave absorber FDTD Deep learning VAE CMA-ES Balancing loss Materials of engineering and construction. Mechanics of materials TA401-492 |
spellingShingle |
Microwave absorber FDTD Deep learning VAE CMA-ES Balancing loss Materials of engineering and construction. Mechanics of materials TA401-492 Han-Ik On Leekyo Jeong Minseok Jung Dong-Joong Kang Jun-Hyub Park Hak-Joo Lee Optimal design of microwave absorber using novel variational autoencoder from a latent space search strategy |
description |
This paper introduces a new objective-driven design method based on deep learning for meta-structure absorber for X-band (8–12 GHz) application. The method consists of three steps; at Step 1, developing a simulator to predict a spectrum of microwave from a conductive layer of absorber as an image input, at Step 2, designing an autoencoder network to take the patterns as input and outputs the same pattern, at Step 3, making an inverse design method for a new pattern under a given goal (spectrum). The proposed method was verified by comparing with the reflectance spectrum calculated by FDTD on the designed absorber with an optimal conductive pattern layer. For the effective training of a general random-like pixel patterns, the variational autoencoder (VAE) that uses a new adaptive annealing loss and a symmetricity layer block in VAE decoder is suggested to improve the training performance. The covariance Matrix Adaptation Evolution Strategy (CMA-ES) which searches the optimal pattern in the VAE latent space is used for suggesting the candidates of the optimal pattern. The proposed method can find an optimal absorber with minimum −16 dB reflectance in X-band that exceed the best absorption among all the training samples obtained by FDTD. |
format |
article |
author |
Han-Ik On Leekyo Jeong Minseok Jung Dong-Joong Kang Jun-Hyub Park Hak-Joo Lee |
author_facet |
Han-Ik On Leekyo Jeong Minseok Jung Dong-Joong Kang Jun-Hyub Park Hak-Joo Lee |
author_sort |
Han-Ik On |
title |
Optimal design of microwave absorber using novel variational autoencoder from a latent space search strategy |
title_short |
Optimal design of microwave absorber using novel variational autoencoder from a latent space search strategy |
title_full |
Optimal design of microwave absorber using novel variational autoencoder from a latent space search strategy |
title_fullStr |
Optimal design of microwave absorber using novel variational autoencoder from a latent space search strategy |
title_full_unstemmed |
Optimal design of microwave absorber using novel variational autoencoder from a latent space search strategy |
title_sort |
optimal design of microwave absorber using novel variational autoencoder from a latent space search strategy |
publisher |
Elsevier |
publishDate |
2021 |
url |
https://doaj.org/article/ceb41be6506b488bb10628a411516ceb |
work_keys_str_mv |
AT hanikon optimaldesignofmicrowaveabsorberusingnovelvariationalautoencoderfromalatentspacesearchstrategy AT leekyojeong optimaldesignofmicrowaveabsorberusingnovelvariationalautoencoderfromalatentspacesearchstrategy AT minseokjung optimaldesignofmicrowaveabsorberusingnovelvariationalautoencoderfromalatentspacesearchstrategy AT dongjoongkang optimaldesignofmicrowaveabsorberusingnovelvariationalautoencoderfromalatentspacesearchstrategy AT junhyubpark optimaldesignofmicrowaveabsorberusingnovelvariationalautoencoderfromalatentspacesearchstrategy AT hakjoolee optimaldesignofmicrowaveabsorberusingnovelvariationalautoencoderfromalatentspacesearchstrategy |
_version_ |
1718408408206409728 |