An Efficient Method for Complex Antenna Design Based on a Self Adaptive Surrogate Model Assisted Optimization Technique



Liu, B, Akinsolu, MO, Song, C, Hua, Q ORCID: 0000-0003-3125-9587, Excell, P, Xu, Q, Huang, Y ORCID: 0000-0001-7774-1024 and Imran, MA
(2021) An Efficient Method for Complex Antenna Design Based on a Self Adaptive Surrogate Model Assisted Optimization Technique. IEEE Transactions on Antennas and Propagation.

[img] Text
An Efficient Method for Complex Antenna Design - early access.pdf - Accepted Version

Download (9MB) | Preview

Abstract

Crown Surrogate models are widely used in antenna design for optimization efficiency improvement. Currently, the targeted antennas often have a small number of design variables and specifications, and the surrogate model training time is short. However, modern antennas become increasingly complex which need much more design variables and specifications, making the training time become a new bottleneck, i.e., in some cases even longer than electromagnetic (EM) simulation time. Therefore, a new method, called training cost reduced surrogate model-assisted hybrid differential evolution for complex antenna optimization (TR-SADEA) is presented in this paper. The key innovations include: (1) A self-adaptive Gaussian Process surrogate modeling method with a significantly reduced training time whilst mostly maintaining the antenna performance prediction accuracy, and (2) A new hybrid surrogate model-assisted antenna optimization framework which reduces the training time and increases the convergence speed. An indoor base station antenna with 2G to 5G cellular bands (45 design variables, 12 specifications) and a 5G outdoor base station antenna (23 design variables, 18 specifications) are used to demonstrate TR-SADEA. Experimental results show that more than 90% of the training time and about 20% iterations (simulations and surrogate modeling) are reduced compared to a state-of-the-art method while obtaining high antenna performance.

Item Type: Article
Depositing User: Symplectic Admin
Date Deposited: 05 Mar 2021 11:13
Last Modified: 06 Sep 2022 15:10
DOI: 10.1109/TAP.2021.3051034
URI: https://livrepository.liverpool.ac.uk/id/eprint/3116578