A new neural network technique for the design of multilayered microwave shielded bandpass filters

Juan Pascual García, Fernando Quesada Pereira, David Cañete Rebenaque, Juan Sebastian Gomez Diaz, Alejandro Álvarez Melcón

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

In this work, we propose a novel technique based on neural networks, for the design of microwave filters in shielded printed technology. The technique uses radial basis function neural networks to represent the non linear relations between the quality factors and coupling coefficients, with the geometrical dimensions of the resonators. The radial basis function neural networks are employed for the first time in the design task of shielded printed filters, and permit a fast and precise operation with only a limited set of training data. Thanks to a new cascade configuration, a set of two neural networks provide the dimensions of the complete filter in a fast and accurate way. To improve the calculation of the geometrical dimensions, the neural networks can take as inputs both electrical parameters and physical dimensions computed by other neural networks. The neural network technique is combined with gradient based optimization methods to further improve the response of the filters. Results are presented to demonstrate the usefulness of the proposed technique for the design of practical microwave printed coupled line and hairpin filters.

Original languageEnglish (US)
Pages (from-to)405-415
Number of pages11
JournalInternational Journal of RF and Microwave Computer-Aided Engineering
Volume19
Issue number3
DOIs
StatePublished - May 1 2009
Externally publishedYes

Fingerprint

Microwave filters
Bandpass filters
Neural networks
Resonators
Microwaves

Keywords

  • Filter design
  • Microwave filters
  • Multilayered shielded structures
  • Neural networks

ASJC Scopus subject areas

  • Computer Science Applications
  • Computer Graphics and Computer-Aided Design
  • Electrical and Electronic Engineering

Cite this

A new neural network technique for the design of multilayered microwave shielded bandpass filters. / García, Juan Pascual; Pereira, Fernando Quesada; Rebenaque, David Cañete; Gomez Diaz, Juan Sebastian; Melcón, Alejandro Álvarez.

In: International Journal of RF and Microwave Computer-Aided Engineering, Vol. 19, No. 3, 01.05.2009, p. 405-415.

Research output: Contribution to journalArticle

García, Juan Pascual ; Pereira, Fernando Quesada ; Rebenaque, David Cañete ; Gomez Diaz, Juan Sebastian ; Melcón, Alejandro Álvarez. / A new neural network technique for the design of multilayered microwave shielded bandpass filters. In: International Journal of RF and Microwave Computer-Aided Engineering. 2009 ; Vol. 19, No. 3. pp. 405-415.
@article{fafbf7d3860c46738c2678ef0a32c613,
title = "A new neural network technique for the design of multilayered microwave shielded bandpass filters",
abstract = "In this work, we propose a novel technique based on neural networks, for the design of microwave filters in shielded printed technology. The technique uses radial basis function neural networks to represent the non linear relations between the quality factors and coupling coefficients, with the geometrical dimensions of the resonators. The radial basis function neural networks are employed for the first time in the design task of shielded printed filters, and permit a fast and precise operation with only a limited set of training data. Thanks to a new cascade configuration, a set of two neural networks provide the dimensions of the complete filter in a fast and accurate way. To improve the calculation of the geometrical dimensions, the neural networks can take as inputs both electrical parameters and physical dimensions computed by other neural networks. The neural network technique is combined with gradient based optimization methods to further improve the response of the filters. Results are presented to demonstrate the usefulness of the proposed technique for the design of practical microwave printed coupled line and hairpin filters.",
keywords = "Filter design, Microwave filters, Multilayered shielded structures, Neural networks",
author = "Garc{\'i}a, {Juan Pascual} and Pereira, {Fernando Quesada} and Rebenaque, {David Ca{\~n}ete} and {Gomez Diaz}, {Juan Sebastian} and Melc{\'o}n, {Alejandro {\'A}lvarez}",
year = "2009",
month = "5",
day = "1",
doi = "10.1002/mmce.20363",
language = "English (US)",
volume = "19",
pages = "405--415",
journal = "International Journal of RF and Microwave Computer-Aided Engineering",
issn = "1096-4290",
publisher = "John Wiley and Sons Inc.",
number = "3",

}

TY - JOUR

T1 - A new neural network technique for the design of multilayered microwave shielded bandpass filters

AU - García, Juan Pascual

AU - Pereira, Fernando Quesada

AU - Rebenaque, David Cañete

AU - Gomez Diaz, Juan Sebastian

AU - Melcón, Alejandro Álvarez

PY - 2009/5/1

Y1 - 2009/5/1

N2 - In this work, we propose a novel technique based on neural networks, for the design of microwave filters in shielded printed technology. The technique uses radial basis function neural networks to represent the non linear relations between the quality factors and coupling coefficients, with the geometrical dimensions of the resonators. The radial basis function neural networks are employed for the first time in the design task of shielded printed filters, and permit a fast and precise operation with only a limited set of training data. Thanks to a new cascade configuration, a set of two neural networks provide the dimensions of the complete filter in a fast and accurate way. To improve the calculation of the geometrical dimensions, the neural networks can take as inputs both electrical parameters and physical dimensions computed by other neural networks. The neural network technique is combined with gradient based optimization methods to further improve the response of the filters. Results are presented to demonstrate the usefulness of the proposed technique for the design of practical microwave printed coupled line and hairpin filters.

AB - In this work, we propose a novel technique based on neural networks, for the design of microwave filters in shielded printed technology. The technique uses radial basis function neural networks to represent the non linear relations between the quality factors and coupling coefficients, with the geometrical dimensions of the resonators. The radial basis function neural networks are employed for the first time in the design task of shielded printed filters, and permit a fast and precise operation with only a limited set of training data. Thanks to a new cascade configuration, a set of two neural networks provide the dimensions of the complete filter in a fast and accurate way. To improve the calculation of the geometrical dimensions, the neural networks can take as inputs both electrical parameters and physical dimensions computed by other neural networks. The neural network technique is combined with gradient based optimization methods to further improve the response of the filters. Results are presented to demonstrate the usefulness of the proposed technique for the design of practical microwave printed coupled line and hairpin filters.

KW - Filter design

KW - Microwave filters

KW - Multilayered shielded structures

KW - Neural networks

UR - http://www.scopus.com/inward/record.url?scp=65649111173&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=65649111173&partnerID=8YFLogxK

U2 - 10.1002/mmce.20363

DO - 10.1002/mmce.20363

M3 - Article

VL - 19

SP - 405

EP - 415

JO - International Journal of RF and Microwave Computer-Aided Engineering

JF - International Journal of RF and Microwave Computer-Aided Engineering

SN - 1096-4290

IS - 3

ER -