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

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 geomet...

Descripción completa

Detalles Bibliográficos
Autores: Pascual García, Juan, Quesada Pereira, Fernando Daniel, Cañete Rebenaque, David, Gómez Díaz, Juan Sebastián, Melcón Álvarez, Alejandro
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2009
País:España
Institución:Universidad Politécnica de Cartagena(UPCT)
Repositorio:Repositorio Digital UPCT
OAI Identifier:oai:repositorio.upct.es:10317/8499
Acceso en línea:https://onlinelibrary.wiley.com/doi/abs/10.1002/mmce.20363
http://hdl.handle.net/10317/8499
Access Level:acceso abierto
Palabra clave:Neural Networks
Microwave filters
Microstrip fliters
Filter design techniques
Teoría de la Señal y las Comunicaciones
2202.10 Radioondas y Microondas
id ES_d029db0718e6b9514295dcd2ea3c4466
oai_identifier_str oai:repositorio.upct.es:10317/8499
network_acronym_str ES
network_name_str España
repository_id_str
spelling A new neural network technique for the design of multilayered microwave shielded bandpass filtersPascual García, JuanQuesada Pereira, Fernando DanielCañete Rebenaque, DavidGómez Díaz, Juan SebastiánMelcón Álvarez, AlejandroNeural NetworksMicrowave filtersMicrostrip flitersFilter design techniquesTeoría de la Señal y las Comunicaciones2202.10 Radioondas y MicroondasIn 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.John WileyGrupo Electromagnetismo Aplicado a las Telecomunicaciones202020202009info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfapplication/pdfhttps://onlinelibrary.wiley.com/doi/abs/10.1002/mmce.20363http://hdl.handle.net/10317/8499reponame:Repositorio Digital UPCTinstname:Universidad Politécnica de Cartagena(UPCT)InglésAtribución-CompartirIgual 3.0 España© Copyright 2008 Wiley Periodicals, Inc.http://creativecommons.org/licenses/by-sa/3.0/es/info:eu-repo/semantics/openAccessoai:repositorio.upct.es:10317/84992026-05-15T06:39:02Z
dc.title.none.fl_str_mv A new neural network technique for the design of multilayered microwave shielded bandpass filters
title A new neural network technique for the design of multilayered microwave shielded bandpass filters
spellingShingle A new neural network technique for the design of multilayered microwave shielded bandpass filters
Pascual García, Juan
Neural Networks
Microwave filters
Microstrip fliters
Filter design techniques
Teoría de la Señal y las Comunicaciones
2202.10 Radioondas y Microondas
title_short A new neural network technique for the design of multilayered microwave shielded bandpass filters
title_full A new neural network technique for the design of multilayered microwave shielded bandpass filters
title_fullStr A new neural network technique for the design of multilayered microwave shielded bandpass filters
title_full_unstemmed A new neural network technique for the design of multilayered microwave shielded bandpass filters
title_sort A new neural network technique for the design of multilayered microwave shielded bandpass filters
dc.creator.none.fl_str_mv Pascual García, Juan
Quesada Pereira, Fernando Daniel
Cañete Rebenaque, David
Gómez Díaz, Juan Sebastián
Melcón Álvarez, Alejandro
author Pascual García, Juan
author_facet Pascual García, Juan
Quesada Pereira, Fernando Daniel
Cañete Rebenaque, David
Gómez Díaz, Juan Sebastián
Melcón Álvarez, Alejandro
author_role author
author2 Quesada Pereira, Fernando Daniel
Cañete Rebenaque, David
Gómez Díaz, Juan Sebastián
Melcón Álvarez, Alejandro
author2_role author
author
author
author
dc.contributor.none.fl_str_mv Grupo Electromagnetismo Aplicado a las Telecomunicaciones
dc.subject.none.fl_str_mv Neural Networks
Microwave filters
Microstrip fliters
Filter design techniques
Teoría de la Señal y las Comunicaciones
2202.10 Radioondas y Microondas
topic Neural Networks
Microwave filters
Microstrip fliters
Filter design techniques
Teoría de la Señal y las Comunicaciones
2202.10 Radioondas y Microondas
description 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.
publishDate 2009
dc.date.none.fl_str_mv 2009
2020
2020
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv https://onlinelibrary.wiley.com/doi/abs/10.1002/mmce.20363
http://hdl.handle.net/10317/8499
url https://onlinelibrary.wiley.com/doi/abs/10.1002/mmce.20363
http://hdl.handle.net/10317/8499
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.rights.none.fl_str_mv Atribución-CompartirIgual 3.0 España
© Copyright 2008 Wiley Periodicals, Inc.
http://creativecommons.org/licenses/by-sa/3.0/es/
info:eu-repo/semantics/openAccess
rights_invalid_str_mv Atribución-CompartirIgual 3.0 España
© Copyright 2008 Wiley Periodicals, Inc.
http://creativecommons.org/licenses/by-sa/3.0/es/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv John Wiley
publisher.none.fl_str_mv John Wiley
dc.source.none.fl_str_mv reponame:Repositorio Digital UPCT
instname:Universidad Politécnica de Cartagena(UPCT)
instname_str Universidad Politécnica de Cartagena(UPCT)
reponame_str Repositorio Digital UPCT
collection Repositorio Digital UPCT
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869420149281390592
score 15,300719

Similares en LA Referencia