Prior-Knowledge-Guided Transformer-Model-Based Synthesis for Active S-Parameter Extrapolation in Linear Antenna Arrays
- 12 February 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Antennas and Propagation
- Vol. 74 (5) , 4401-4413
Abstract
A prior-knowledge-guided transformer-model-based synthesis method is proposed for extrapolating active S-parameters and full S-parameter matrices in linear antenna arrays, accounting for mutual coupling effects. The method predicts both the active S-parameters and full S-parameter matrices of larger arrays using training dataset generated from smaller arrays. By formulating the task as a sequence-to-sequence transformation, a transformer-model-based neural network, as one type of machine learning methods, learns the mapping between excitations and reflections at each feeding port of large-scale antenna arrays. Prior knowledge−including features of the antenna arrays and mechanisms of transformer models−is incorporated to enhance model performance and physical consistency. In full-wave simulations, the proposed transformer model is trained on simulated data from linear arrays with fewer than 20 elements and then used to extrapolate the active S-parameter and full S-parameter matrix for a 30-element array. Experimental validation using fabricated printed dipole arrays further demonstrates the accuracy and robustness of the proposed method, as supported by both simulation and measurement results.Keywords
Funding Information
- Adelaide Research and Innovation, University of Adelaide
- National University of Singapore (ARIS-RP1)
- Ministry of Education and Research, Romania (MOE-000742-01/T2EP50124-0047)
This publication has 47 references indexed in Scilit:
- A Novel Mutual Coupling ANN Model for MIMO Antennas With Physical PreprocessingIEEE Antennas and Wireless Propagation Letters, 2024
- Toward Extra Large-Scale MIMO: New Channel Properties and Low-Cost DesignsIEEE Internet of Things Journal, 2023
- Efficient Radiation Pattern Prediction of Array Antennas Based on Complex-Valued Graph Neural NetworksIEEE Antennas and Wireless Propagation Letters, 2022
- A Deep Learning-Based Approach for Radiation Pattern Synthesis of an Array AntennaIEEE Access, 2020
- Simulation of Active Reflection Coefficient Phenomena of Large Antenna Array Using FEM Domain Decomposition MethodsIEEE Antennas and Wireless Propagation Letters, 2020
- An ANN-Based Synthesis Method for Nonuniform Linear Arrays Including Mutual Coupling EffectsIEEE Access, 2020
- DNNs as Applied to Electromagnetics, Antennas, and Propagation—A ReviewIEEE Antennas and Wireless Propagation Letters, 2019
- Fast Near-Field Multifocusing of Antenna Arrays Including Element Coupling Using Neural NetworksIEEE Antennas and Wireless Propagation Letters, 2018
- Prediction of large array characteristics from small array parameters2007
- Large finite array analysis using infinite array dataIEEE Transactions on Antennas and Propagation, 1994