Scholarlink

During the design of multi-objective antennas, optimizing efficiency and computing expenses are key considerations. In this essay, a rapid antenna optimization strategy that combines the BP neural network with the non-dominated sorting genetic algorithm II is proposed. Firstly, to enhance the global optimization capability, we improve the whale optimization algorithm by improving population initialization, incorporating a nonlinear convergence factor, and introducing adaptive inertia weights. Then, using the IWOA, we optimize the BPNN’s initial weights and thresholds to improve model accuracy. Finally, we present a Pareto-optimal three-band antenna optimization, demonstrating that the proposed method can effectively optimize antenna performance while significantly reducing computational cost.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Multi-objective Optimization of Antenna Based on Improved WOA-BP Neural Network

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Huawei Zhuang,
  • Fangzhen Sun,
  • Gaoqi Li,
  • Jianzhao Liu

摘要

During the design of multi-objective antennas, optimizing efficiency and computing expenses are key considerations. In this essay, a rapid antenna optimization strategy that combines the BP neural network with the non-dominated sorting genetic algorithm II is proposed. Firstly, to enhance the global optimization capability, we improve the whale optimization algorithm by improving population initialization, incorporating a nonlinear convergence factor, and introducing adaptive inertia weights. Then, using the IWOA, we optimize the BPNN’s initial weights and thresholds to improve model accuracy. Finally, we present a Pareto-optimal three-band antenna optimization, demonstrating that the proposed method can effectively optimize antenna performance while significantly reducing computational cost.