Low-Cost and Highly Accurate Behavioral Modeling of Antenna Structures by Means of Knowledge-Based Domain-Constrained Deep Learning Surrogates
- 26 October 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Antennas and Propagation
- Vol. 71 (1) , 105-118
Abstract
The awareness and practical benefits of behavioral modeling methods have been steadily growing in the antenna engineering community over the last decade or so. Undoubtedly, the most important advantage thereof is a possibility of a dramatic reduction of computational expenses associated with computer-aided design procedures, especially those relying on full-wave electromagnetic (EM) simulations. In particular, the employment of fast replacement models (surrogates) allows for repetitive evaluations of the antenna structure at negligible cost, thereby accelerating processes such as parametric optimization, multi-criterial design, or uncertainty quantification. Notwithstanding, a construction of reliable data-driven surrogates is seriously hindered by the curse of dimensionality and the need for covering broad ranges of geometry/material parameters, which is imperative from the perspective of design utility. A recently proposed constrained modeling approach with knowledge-based stochastic determination of the model domain addresses this issue to a large extent and has been demonstrated to enable quasi-global modeling capability while maintaining a low setup cost. This work introduces a novel technique that capitalizes on the domain confinement paradigm and incorporates deep-learning-based regression modeling to facilitate handling of highly-nonlinear antenna characteristics. The presented framework is demonstrated using three microstrip antennas and favorably compared to several state-of-the-art techniques. The predictive power of our models reaches remarkable two percent of a relative RMS error (averaged over the considered antenna structures), which is a significant improvement over all benchmark methods.Keywords
Funding Information
- Icelandic Centre for Research (217771)
- Narodowe Centrum Nauki (2020/37/B/ST7/01448)
This publication has 79 references indexed in Scilit:
- Characterisation by Gaussian processes of finite substrate size effects on gain patterns of microstrip antennasIET Microwaves, Antennas & Propagation, 2016
- Low-Cost Data-Driven Surrogate Modeling of Antenna Structures by Constrained SamplingIEEE Antennas and Wireless Propagation Letters, 2016
- Bayesian Model Fusion: Large-Scale Performance Modeling of Analog and Mixed-Signal Circuits by Reusing Early-Stage DataIEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2015
- Space mapping optimization of handset antennas considering EM effects of mobile phone components and human bodyInternational Journal of RF and Microwave Computer-Aided Engineering, 2015
- Cognition-Driven Formulation of Space Mapping for Equal-Ripple Optimization of Microwave FiltersIEEE Transactions on Microwave Theory and Techniques, 2015
- Going deeper with convolutions2015
- An ME-PC Enhanced HDMR Method for Efficient Statistical Analysis of Multiconductor Transmission Line NetworksIEEE Transactions on Components, Packaging and Manufacturing Technology, 2015
- Physics-based Multi-fidelity Surrogate Modeling with Entropy-based Availability Methods2014
- WASP-NET®: Recent advances in fast full 3D EM CAD of waveguide feeds and aperture antennas2011
- Space Mapping: The State of the ArtIEEE Transactions on Microwave Theory and Techniques, 2004