Machine learning assisted inverse design of pixelated mmWave patch antennas

Simple item page
dc.contributor.authorRather, Nadeem Nabi
dc.contributor.authorClaussen, Holger
dc.contributor.authorHo, Lester
dc.contributor.funderTaighde Éireann - Research Ireland
dc.date.accessioned2026-07-10T11:50:02Z
dc.date.available2026-07-10T11:50:02Z
dc.date.issued2026
dc.description.abstractIn this paper, a machine learning-assisted framework for the inverse design of pixelated millimetre-wave patch antennas targeting the 22–30 GHz band is presented. The antenna surface is represented as a 19×23 binary pixel grid on a Rogers RT/duroid 5880 substrate, where each pixel is either metal or empty, with a continuous electrical path from the feed enforced by design. An initial dataset of approximately 6,000 full-wave CST simulations was collected from structured random pixel patterns, of which only around 40% achieved a resonance with |S11| ≤ −10 dB anywhere in the band, resulting in an imbalanced dataset. To improve simulation efficiency, an XGBoost binary classifier was trained on this data to distinguish resonant from non-resonant patterns before simulation. Using the classifier as a pre-simulation filter, an additional 4,000 patterns were selected and simulated, raising the overall proportion of resonant designs in the combined 10,000-sample dataset from approximately 40% to 52%. A hybrid CNN–BiLSTM forward surrogate was then trained on this augmented dataset to predict the full complex S11 response across 801 frequency points, using a physics-guided composite loss that explicitly emphasises resonance dip accuracy. Finally, an inverse design model was developed that optimises in a compact 64-dimensional latent space using gradient descent to generate pixel patterns matching a desired S11 specification. The results show good agreement between the surrogate-predicted and CST-simulated |S11| responses for the generated designs and demonstrate the feasibility of automatically designing and reconfiguring antenna structures.en
dc.description.sponsorshipResearch Ireland|13/RC/2077 P2
dc.format.extent6
dc.format.mimetypeapplication/pdfen
dc.identifier.authororcidRather, Nadeem Nabi
dc.identifier.authororcidClaussen, Holger§0000-0003-2045-2082
dc.identifier.authororcidHo, Lester
dc.identifier.citationRather, N N, Claussen, H & Ho, L 2026, 'Machine learning assisted inverse design of pixelated mmWave patch antennas', Paper presented at IEEE International Symposium on Personal, Indoor and Mobile Radio Communications 2026, Singapore, 1/09/26 - 4/09/26 pp. 1-6.
dc.identifier.endpage6
dc.identifier.startpage1
dc.identifier.urihttps://hdl.handle.net/10468/19048
dc.language.isoen
dc.rights© 2026, IEEE (Published Version). For the purpose of Open Access, the author has applied a CC BY public copyright licence to any Author Accepted Manuscript version arising from this submission.
dc.rights.accessrightsopen access
dc.rights.licensenameAttribution 4.0 International
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.statusPeer reviewed
dc.subjectMillimetre-wave antenna
dc.subjectPixelated antenna
dc.subjectInverse design
dc.subjectSurrogate model
dc.subjectXGBoost
dc.subjectCNN-BiLSTM
dc.subjectDataset augmentation
dc.subject5G
dc.subjectmmWave
dc.subject[TyndallMicroNano]
dc.subject[Tyndall]
dc.subject[ComputerScience]
dc.titleMachine learning assisted inverse design of pixelated mmWave patch antennasen
dc.typeConference item
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Machine_Learning_Assisted_Inverse_Design_of_Pixelated_mmWave_Patch_Antennas.pdf
Size:
853.02 KB
Format:
Adobe Portable Document Format
Description:
Accepted Version
Download
Collections
Tyndall MicroNano Systems