Automatically Inverse Design of FSSs by Conditional Variational Autoencoder and Equivalent Circuit Models With Large Language Models

Recently, deep learning has attracted intensive attentions in electromagnetic society, especially for inverse problems. In this work, we propose two language-guided automatic design frameworks for frequency selective surfaces (FSSs), where both of them are assisted by large language models (LLMs). O...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on antennas and propagation Vol. 73; no. 11; pp. 8922 - 8932
Main Authors: Shen, Jiajun, Liu, Jianfa, Qu, Changhao, Wang, Bao, Wang, Qian, Wei, Zhun
Format: Journal Article
Language:English
Published: New York IEEE 01.11.2025
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
Autoencoders
Band-pass filters
Bandwidth
Conditional variational autoencoder (CVAE)
Data mining
Design
Equivalent circuits
Feature extraction
frequency selective surface (FSS)
Frequency selective surfaces
Inverse design
Inverse problems
Language
large language model (LLM)
Large language models
Load modeling
Machine learning
Parameters
Scattering parameters
Silicon
Training
ISSN:0018-926X, 1558-2221
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Recently, deep learning has attracted intensive attentions in electromagnetic society, especially for inverse problems. In this work, we propose two language-guided automatic design frameworks for frequency selective surfaces (FSSs), where both of them are assisted by large language models (LLMs). On the one hand, the LLM is used to extract key desired features from language, which is then followed with a conditional variational autoencoder (CVAE) to generate S-parameters from the extracted features. With the generative S-parameters, an inverse surrogate model is designed to predict the geometry sizes of FSSs followed by LLM to output designed specifications in language. On the other hand, an inverse-design framework is further introduced to build the mapping from equivalent-circuit model to geometry sizes of FSS, where the loss is further constrained by a forward surrogate to alleviate nonunique problems in inverse design. The proposed framework is validated by designing numerous FSSs including high-pass, low-pass, bandpass, and band-stop types, where a representative structure is further fabricated and tested to verify the proposed methods.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0018-926X
1558-2221
DOI:10.1109/TAP.2025.3596796