.png){kind=icon}
.png){kind=icon}
Return
A Multiobjective Antenna Optimization Method Based on the Surrogate Model-Assisted Deep Reinforcement Learning
.png){kind=icon}
PRE
AI
DOI：10.1109/LAWP.2026.3653465.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
A novel multiobjective antenna optimization method based on the surrogate model-assisted deep reinforcement learning (SADRL) is proposed. The method is divided into three stages: coarse topology optimization, surrogate model construction, and fine topology optimization. First, the adaptive variable fidelity electromagnetic model is used to assist the improved binary particle swarm optimization algorithm for coarse optimization of antenna topology. This stage provides an initial database for surrogate-model training and a high-quality initial solution for subsequent deep reinforcement learning (DRL) algorithm. Second, the Bayesian convolutional neural networks is employed as an online surrogate model, aiming to provide a low-cost interactive environment for the DRL. Finally, the deep Q-network is used to perform fine optimization of antenna topology. To validate the proposed method, a multiobjective optimization of a monopole antenna is conducted with objectives of omnidirectionality, operating bandwidth, and in-band gain flatness. The optimized design provides an operating band that covers 3.3 GHz to 3.8 GHz and 5.75 GHz to 5.85 GHz, while maintaining realized gains of 1.89 ± 0.23 dBi and 1.35 ± 0.11 dBi across the target bands, the azimuthal gain ripple is less than 2.86 dBi. Compared with other optimization methods, the proposed SADRL achieves the target design with fewer electromagnetic simulations.
Keywords:
Deep Q-network
deep reinforcement learning
multiobjective
surrogate model
topology optimization
Journal
IF:
4.8
Papers:
1.0W
Citations:
2.8W