Publication result detail

A Low-Cost ANN Surrogate-Based Multi-Objective Optimization Method for Designing UWB Antennas

BEDNARSKÝ, V.; KADLEC, P.; SHEN, M.

Original Title

A Low-Cost ANN Surrogate-Based Multi-Objective Optimization Method for Designing UWB Antennas

English Title

A Low-Cost ANN Surrogate-Based Multi-Objective Optimization Method for Designing UWB Antennas

Type

Paper in proceedings (conference paper)

Original Abstract

The design of antennas is a complex challenge that requires the simultaneous optimization of multiple performance metrics. Engineers must make tradeoffs between technical specifications, cost constraints, and practical implementation. This study investigates the application of multi-objective optimization techniques for the automated design and synthesis of ultra-wideband (UWB) monopole antenna systems. Specifically, it explores the balance between impedance matching and antenna miniaturization, ensuring optimal performance while minimizing physical footprint. The research leverages computational methods, incorporating Artificial Neural Network (ANN) surrogates trained on high-fidelity electromagnetic simulations to accelerate optimization. By integrating ANN-based surrogate modeling with evolutionary algorithms, this approach enhances computational efficiency and facilitates the rapid exploration of Pareto-optimal solutions.

English abstract

The design of antennas is a complex challenge that requires the simultaneous optimization of multiple performance metrics. Engineers must make tradeoffs between technical specifications, cost constraints, and practical implementation. This study investigates the application of multi-objective optimization techniques for the automated design and synthesis of ultra-wideband (UWB) monopole antenna systems. Specifically, it explores the balance between impedance matching and antenna miniaturization, ensuring optimal performance while minimizing physical footprint. The research leverages computational methods, incorporating Artificial Neural Network (ANN) surrogates trained on high-fidelity electromagnetic simulations to accelerate optimization. By integrating ANN-based surrogate modeling with evolutionary algorithms, this approach enhances computational efficiency and facilitates the rapid exploration of Pareto-optimal solutions.

Keywords

Antennas, UWB, Optimization, Multi-Objective, MATLAB, CST MWS

Key words in English

Antennas, UWB, Optimization, Multi-Objective, MATLAB, CST MWS

Authors

BEDNARSKÝ, V.; KADLEC, P.; SHEN, M.

Released

24.05.2025

Publisher

IEEE

Location

Hnanice, Czech republic

ISBN

979-8-3315-4447-8

Book

Proceeding of the 35th International Conference Radioelektronika (RADIOELEKTRONIKA)

Pages from

1

Pages to

6

Pages count

6

URL

https://ieeexplore.ieee.org/document/11008382a

BibTex

@inproceedings{BUT198004,
  author="Vojtěch {Bednarský} and Petr {Kadlec} and Ming {Shen}",
  title="A Low-Cost ANN Surrogate-Based Multi-Objective Optimization Method for Designing UWB Antennas",
  booktitle="Proceeding of the 35th International Conference Radioelektronika (RADIOELEKTRONIKA)",
  year="2025",
  pages="1--6",
  publisher="IEEE",
  address="Hnanice, Czech republic",
  doi="10.1109/RADIOELEKTRONIKA65656.2025.11008382",
  isbn="979-8-3315-4447-8",
  url="https://ieeexplore.ieee.org/document/11008382a"
}