Near-Field-Based 5G Sub-6 GHz Array Antenna Diagnosis Using Transfer Learning

In this paper, we propose a method for near-field-based 5G sub 6-GHz array antenna diagnosis using transfer learning. A classification network was implemented for normal/abnormal operation of the array antenna and the failure of a specific port. Furthermore, a regression network that could predict t...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Hong Jun Lim, Dong Hwan Lee, Hark Byeong Park, Keum Cheol Hwang
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	near-field measurement machine learning transfer learning array antenna diagnosis 5G sub 6-GHz Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999
Acceso en línea:	https://doaj.org/article/88a58fa3ff924a7684e5fdd37d5c8c7d
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:88a58fa3ff924a7684e5fdd37d5c8c7d
record_format	dspace
spelling	oai:doaj.org-article:88a58fa3ff924a7684e5fdd37d5c8c7d2021-11-11T15:13:42ZNear-Field-Based 5G Sub-6 GHz Array Antenna Diagnosis Using Transfer Learning10.3390/app1121101642076-3417https://doaj.org/article/88a58fa3ff924a7684e5fdd37d5c8c7d2021-10-01T00:00:00Zhttps://www.mdpi.com/2076-3417/11/21/10164https://doaj.org/toc/2076-3417In this paper, we propose a method for near-field-based 5G sub 6-GHz array antenna diagnosis using transfer learning. A classification network was implemented for normal/abnormal operation of the array antenna and the failure of a specific port. Furthermore, a regression network that could predict the amplitude and phase of the excitation signal of the array antenna was employed. Additionally, to accelerate the array antenna diagnosis, several near-field lines were sampled and reflected in the regression network. The proposed method was verified by measuring a fabricated 5G sub-6 GHz band 4<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mspace width="0.166667em"></mspace><mo>×</mo><mspace width="0.166667em"></mspace></mrow></semantics></math></inline-formula>4 array antenna in various scenarios using a divider and coaxial cables. The tests showed that the trained network accurately diagnosed 29 of 30 measurement results.Hong Jun LimDong Hwan LeeHark Byeong ParkKeum Cheol HwangMDPI AGarticlenear-field measurementmachine learningtransfer learningarray antenna diagnosis5G sub 6-GHzTechnologyTEngineering (General). Civil engineering (General)TA1-2040Biology (General)QH301-705.5PhysicsQC1-999ChemistryQD1-999ENApplied Sciences, Vol 11, Iss 10164, p 10164 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	near-field measurement machine learning transfer learning array antenna diagnosis 5G sub 6-GHz Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999
spellingShingle	near-field measurement machine learning transfer learning array antenna diagnosis 5G sub 6-GHz Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999 Hong Jun Lim Dong Hwan Lee Hark Byeong Park Keum Cheol Hwang Near-Field-Based 5G Sub-6 GHz Array Antenna Diagnosis Using Transfer Learning
description	In this paper, we propose a method for near-field-based 5G sub 6-GHz array antenna diagnosis using transfer learning. A classification network was implemented for normal/abnormal operation of the array antenna and the failure of a specific port. Furthermore, a regression network that could predict the amplitude and phase of the excitation signal of the array antenna was employed. Additionally, to accelerate the array antenna diagnosis, several near-field lines were sampled and reflected in the regression network. The proposed method was verified by measuring a fabricated 5G sub-6 GHz band 4<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mspace width="0.166667em"></mspace><mo>×</mo><mspace width="0.166667em"></mspace></mrow></semantics></math></inline-formula>4 array antenna in various scenarios using a divider and coaxial cables. The tests showed that the trained network accurately diagnosed 29 of 30 measurement results.
format	article
author	Hong Jun Lim Dong Hwan Lee Hark Byeong Park Keum Cheol Hwang
author_facet	Hong Jun Lim Dong Hwan Lee Hark Byeong Park Keum Cheol Hwang
author_sort	Hong Jun Lim
title	Near-Field-Based 5G Sub-6 GHz Array Antenna Diagnosis Using Transfer Learning
title_short	Near-Field-Based 5G Sub-6 GHz Array Antenna Diagnosis Using Transfer Learning
title_full	Near-Field-Based 5G Sub-6 GHz Array Antenna Diagnosis Using Transfer Learning
title_fullStr	Near-Field-Based 5G Sub-6 GHz Array Antenna Diagnosis Using Transfer Learning
title_full_unstemmed	Near-Field-Based 5G Sub-6 GHz Array Antenna Diagnosis Using Transfer Learning
title_sort	near-field-based 5g sub-6 ghz array antenna diagnosis using transfer learning
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/88a58fa3ff924a7684e5fdd37d5c8c7d
work_keys_str_mv	AT hongjunlim nearfieldbased5gsub6ghzarrayantennadiagnosisusingtransferlearning AT donghwanlee nearfieldbased5gsub6ghzarrayantennadiagnosisusingtransferlearning AT harkbyeongpark nearfieldbased5gsub6ghzarrayantennadiagnosisusingtransferlearning AT keumcheolhwang nearfieldbased5gsub6ghzarrayantennadiagnosisusingtransferlearning
_version_	1718436390602014720

Near-Field-Based 5G Sub-6 GHz Array Antenna Diagnosis Using Transfer Learning

Ejemplares similares