Inverse Design of Ultra-Wideband Frequency Selective Surface Using a Graph based Conditional Variational Autoencoder (G-CVAE) integrated with a Physics Informed Neural Network (PINN)

This work proposes the inverse design of bandstop Frequency Selective Surface using a Graph based Conditional Variational Autoencoder (G-CVAE) integrated with a Physics-Informed Neural Network (PINN). This inverse design involves the prediction of FSS geometry that exhibits ultra-wide stopband chara...

Full description

Saved in:
Bibliographic Details
Published in:IEEE journal on multiscale and multiphysics computational techniques pp. 1 - 10
Main Authors: V, Bharathi, Ramanujam, Krishnamurthy, Ramanujam, Parthasarathy
Format: Journal Article
Language:English
Published: IEEE 2025
Subjects:
ISSN:2379-8815, 2379-8815
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract This work proposes the inverse design of bandstop Frequency Selective Surface using a Graph based Conditional Variational Autoencoder (G-CVAE) integrated with a Physics-Informed Neural Network (PINN). This inverse design involves the prediction of FSS geometry that exhibits ultra-wide stopband characteristics. Initially, the graph convolutional network precisely extracts the topological and spatial relationships within the FSS geometrical design. The features of the graph and simulation results of the FSS dataset are used to train the CVAE, which maps the FSS physical structure and its electromagnetic behavior. The trained CVAE predicts the FSS geometries with desired frequency responses, while the PINN is incorporated to ensure physical feasibility. By monitoring the average relative error values, the simulated and predicted transmission coefficients are brought closer to each other. Also, similar approach is followed to enhance the angular stability and to achieve polarization independence in both TE and TM modes. A G-CVAE-PINN is constructed and trained using various random combinations of graph attributes and simulation outcomes, achieving an average inaccuracy of 3%. Further, one of the best designs from the predicted FSS designs is chosen for experimental validation. This predicted and experimentally validated bandstop FSS exhibits wide band rejection of 20 GHz ranging from 8 GHz to 28 GHz. The fabricated design exhibits polarization independence up to 75°in both normal and oblique angles. Thus, the predicted FSS designs are ideal for radome, EMI shielding, and satellite communications, providing efficient frequency filtering for 5G and beyond 5G networks.
AbstractList This work proposes the inverse design of bandstop Frequency Selective Surface using a Graph based Conditional Variational Autoencoder (G-CVAE) integrated with a Physics-Informed Neural Network (PINN). This inverse design involves the prediction of FSS geometry that exhibits ultra-wide stopband characteristics. Initially, the graph convolutional network precisely extracts the topological and spatial relationships within the FSS geometrical design. The features of the graph and simulation results of the FSS dataset are used to train the CVAE, which maps the FSS physical structure and its electromagnetic behavior. The trained CVAE predicts the FSS geometries with desired frequency responses, while the PINN is incorporated to ensure physical feasibility. By monitoring the average relative error values, the simulated and predicted transmission coefficients are brought closer to each other. Also, similar approach is followed to enhance the angular stability and to achieve polarization independence in both TE and TM modes. A G-CVAE-PINN is constructed and trained using various random combinations of graph attributes and simulation outcomes, achieving an average inaccuracy of 3%. Further, one of the best designs from the predicted FSS designs is chosen for experimental validation. This predicted and experimentally validated bandstop FSS exhibits wide band rejection of 20 GHz ranging from 8 GHz to 28 GHz. The fabricated design exhibits polarization independence up to 75°in both normal and oblique angles. Thus, the predicted FSS designs are ideal for radome, EMI shielding, and satellite communications, providing efficient frequency filtering for 5G and beyond 5G networks.
Author V, Bharathi
Ramanujam, Krishnamurthy
Ramanujam, Parthasarathy
Author_xml – sequence: 1
  givenname: Bharathi
  surname: V
  fullname: V, Bharathi
  email: bharathiv@iiitt.ac.in
– sequence: 2
  givenname: Krishnamurthy
  surname: Ramanujam
  fullname: Ramanujam, Krishnamurthy
  email: Ramanujam,rkrishnamurthy@iiitt.ac.in
– sequence: 3
  givenname: Parthasarathy
  surname: Ramanujam
  fullname: Ramanujam, Parthasarathy
  email: parthasarathy@nitt.edu
BookMark eNpNkMtOwzAQRS0EEs8fQCy8hEWKH0mcLKtQSlEpSFBYRk48bg3FLrYL6o_xfQSoBKu5Gulc6Z59tG2dBYSOKelRSsrz65ub6qHHCMt6PGdlWZAttMe4KJOioNn2v7yLjkJ4JoRQwRghbA99juw7-AD4AoKZWew0ni6il8mTUdBIq_Clh7cV2HaN72EBbTTvgO9XXssW8DQYO8MSD71cznEjAyhcOatMNM7KBX6U3shN7q-i62qcAo9Ph0n12B-cYWMjzLyMHfdh4ryrupuvg2kDHlnt_Gv3n8DKd_gE4ofzL_j0bjSZnB2iHS0XAY429wBNLwcP1VUyvh2Oqv44aSnPY8IyKbVQIDIKTSnyRog0axrZ8jwHwouUqSZXTGdMU-gW8YJxrTRLuUpZKSg_QOy3t_UuBA-6XnrzKv26pqT-ll__yK-_5dcb-R108gsZAPgDKOMkEyn_Au0vhOc
CODEN IJMMOP
ContentType Journal Article
DBID 97E
RIA
RIE
AAYXX
CITATION
DOI 10.1109/JMMCT.2025.3629980
DatabaseName IEEE All-Society Periodicals Package (ASPP) 2005–Present
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE Electronic Library (IEL)
CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Xplore
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Applied Sciences
EISSN 2379-8815
EndPage 10
ExternalDocumentID 10_1109_JMMCT_2025_3629980
11230574
Genre orig-research
GroupedDBID 0R~
97E
AAJGR
AASAJ
AAWTH
ABAZT
ABJNI
ABQJQ
ABVLG
ACGFS
AGQYO
AHBIQ
AKJIK
AKQYR
ALMA_UNASSIGNED_HOLDINGS
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
EBS
IFIPE
JAVBF
OCL
RIA
RIE
AAYXX
AGSQL
CITATION
EJD
ID FETCH-LOGICAL-c136t-25aaf7de751eb976b7745bbac366e03842db6d2f52f1efac3823fdf243d429713
IEDL.DBID RIE
ISSN 2379-8815
IngestDate Sat Nov 29 06:52:38 EST 2025
Wed Nov 19 08:26:45 EST 2025
IsPeerReviewed true
IsScholarly true
Language English
License https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
https://doi.org/10.15223/policy-029
https://doi.org/10.15223/policy-037
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c136t-25aaf7de751eb976b7745bbac366e03842db6d2f52f1efac3823fdf243d429713
PageCount 10
ParticipantIDs ieee_primary_11230574
crossref_primary_10_1109_JMMCT_2025_3629980
PublicationCentury 2000
PublicationDate 2025-00-00
PublicationDateYYYYMMDD 2025-01-01
PublicationDate_xml – year: 2025
  text: 2025-00-00
PublicationDecade 2020
PublicationTitle IEEE journal on multiscale and multiphysics computational techniques
PublicationTitleAbbrev JMMCT
PublicationYear 2025
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0001722002
Score 2.2785897
Snippet This work proposes the inverse design of bandstop Frequency Selective Surface using a Graph based Conditional Variational Autoencoder (G-CVAE) integrated with...
SourceID crossref
ieee
SourceType Index Database
Publisher
StartPage 1
SubjectTerms 5G and beyond 5G applications
Accuracy
Autoencoders
Computer architecture
Conditional Variational Autoencoder
Feature extraction
Frequency Selective Surface
Geometry
Inverse design
Microprocessors
Optimization
Physics-Informed Neural Network
Shielding Effectiveness
Training
Vectors
Title Inverse Design of Ultra-Wideband Frequency Selective Surface Using a Graph based Conditional Variational Autoencoder (G-CVAE) integrated with a Physics Informed Neural Network (PINN)
URI https://ieeexplore.ieee.org/document/11230574
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVIEE
  databaseName: IEEE Xplore
  customDbUrl:
  eissn: 2379-8815
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001722002
  issn: 2379-8815
  databaseCode: RIE
  dateStart: 20160101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1JS8QwFA4qHry4izvv4EGRaJt0y3EYnVHBIrjeStK8gCBT6XQE_5i_zyTtuBw8eCuhKQlfmrd97z1CDmKWuXgmp1mkAmr1W6RCoaaZMIInJSZolG82keZ59vQkbrpkdZ8Lg4iefIYn7tHH8nVVTpyr7NTqBvZ4ptEsmU3TpE3W-naopMwRDqaJMYE4vbq-7t9ZE5DFJ_aatnZF8Ev4_Oim4oXJYOmfy1gmi53WCL0W5hUyg6NVstRpkND9n-M18uHKZtRjhDNPzIDKwP1LU0v6-KxRyZGGQd1yp9_h1nfAsZcd3E5qI0sETx8ACUNXxBqcfNPQr1xM2_sL4cHa1Z3vEHqTpnI1MDXWcDik_Yfe-RF81Z7Q4Py79lOeYFqOoc16suOuGIidnrfsczi8uczzo3VyPzi_61_QrjMDLUOeNJTFUppUYxqHqKxCo6wSGSslS54kGPAsYlolmpmYmRDtDlyw0WjDIq6t_LN28QaZG1Uj3CQglRSoueJcY6SFksgDGcZlliqRSBZukeMpZMVrW4Cj8IZLIAoPcOEALjqAt8i6w-v7zQ6q7T_Gd8iCm976VHbJXFNPcI_Ml2_N87je9wfsEwES0mk
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3JTuQwELXYJLgMMMMIhq0OcwAhQ2Jn87HV0KwdIdEw3CI7LktIow5Kp5Hmx-b7sJ2wHThwi6zEsvUc1_aqipDfMctcPJPTLFIBtfotUqFQ00wYwZMSEzTKN5tI8zy7vxfXXbK6z4VBRE8-w0P36GP5uiqnzlV2ZHUDezzTaJbMx1HEgjZd682lkjJHOXhJjQnE0cVw2B9ZI5DFh_aitpZF8EH8vOun4sXJYPmLC1kh3zq9EXot0KtkBsffyXKnQ0L3h05-kP-ucEY9QTj21AyoDNz-bWpJ_zxoVHKsYVC37Ol_cON74NjrDm6mtZElgicQgIRTV8YanITT0K9cVNt7DOHOWtad9xB606ZyVTA11rB3Svt3vZN9eK0-ocF5eO1UnmJaTqDNe7LjrhyI_Txv-eewd32e5_tr5HZwMuqf0a43Ay1DnjSUxVKaVGMah6isSqOsGhkrJUueJBjwLGJaJZqZmJkQ7Q5cuNFowyKurQS0lvFPMjeuxrhOQCopUHPFucZICyWRBzKMyyxVIpEs3CAHL5AVj20JjsKbLoEoPMCFA7joAN4gaw6vtzc7qH59Mr5LFs9Gw6vi6jy_3CRLbqrWw7JF5pp6ittkoXxqHib1jj9szxZQ1bA
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Inverse+Design+of+Ultra-Wideband+Frequency+Selective+Surface+Using+a+Graph+based+Conditional+Variational+Autoencoder+%28G-CVAE%29+integrated+with+a+Physics+Informed+Neural+Network+%28PINN%29&rft.jtitle=IEEE+journal+on+multiscale+and+multiphysics+computational+techniques&rft.au=V%2C+Bharathi&rft.au=Ramanujam%2C+Krishnamurthy&rft.au=Ramanujam%2C+Parthasarathy&rft.date=2025&rft.pub=IEEE&rft.eissn=2379-8815&rft.spage=1&rft.epage=10&rft_id=info:doi/10.1109%2FJMMCT.2025.3629980&rft.externalDocID=11230574
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2379-8815&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2379-8815&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2379-8815&client=summon