Accurate microwave filter design based on particle swarm optimization and one‐dimensional convolution autoencoders

This paper proposes a one‐dimensional convolutional autoencoders (1D‐CAE) surrogate‐based electromagnetic (EM) optimization technique exploiting particle swarm optimization (PSO) algorithm for microwave filter design. The 1D‐CAE is a flexible neural network structure that can be used as surrogate mo...

Full description

Saved in:
Bibliographic Details
Published in:International journal of RF and microwave computer-aided engineering Vol. 32; no. 4
Main Authors: Wang, Yanxing, Zhang, Zhuowei, Yi, Yaxin, Zhang, Yongliang
Format: Journal Article
Language:English
Published: Hoboken, USA John Wiley & Sons, Inc 01.04.2022
Subjects:
Algorithms
CAD
Computer aided design
Design optimization
Filter design (mathematics)
Inverse problems
Mathematical models
microwave filter design
Microwave filters
Modelling
Neural networks
one‐dimensional convolutional autoencoders
Optimization techniques
Parameters
Particle swarm optimization
surrogate model
ISSN:1096-4290, 1099-047X
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper proposes a one‐dimensional convolutional autoencoders (1D‐CAE) surrogate‐based electromagnetic (EM) optimization technique exploiting particle swarm optimization (PSO) algorithm for microwave filter design. The 1D‐CAE is a flexible neural network structure that can be used as surrogate model to handle forward modeling problems as well as solving inverse problems, such as extracting the coupling matrix from S‐parameters. In this paper, the 1D‐CAE is proposed to handle forward modeling problem. On the one hand, the 1D‐CAE model is adopted to as the surrogate model to the EM simulation solver to speed up the PSO algorithm optimization process. On the other hand, the 1D‐CAE model can update the data set and network parameters online to continuously improve the prediction accuracy of the surrogate model during the PSO algorithm iterations. Compared with other neural network structures, the 1D‐CAE model proposed in this paper requires less data and converges faster in the same test environment. To demonstrate the validity of the proposed method, it was used to design a sixth‐order and an eighth‐order cross‐coupled filter. The design results shown that the proposed method is valid.
Bibliography:Funding information
This work was supported by the National Natural Science Foundation of China (NSFC) (Project Nos. 61761032 and 62161032) and Nature Science Foundation of Inner Mongolia (Contract No. 2019MS06006).
ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1096-4290
1099-047X
DOI:10.1002/mmce.23034