This paper presents a system based on artificial neural network (ANN) that predicts ground plane design for desired radiation properties of a monopole antenna with operation band of 4.8 to 5 GHz. The operating frequency can be adapted to any other frequency regimes. Initially, a 180 × 180 mm2 ground plane, which is composed of a copper layer, is designed and integrated to a radiative pole that creates monopole antenna configuration. The ground plane is divided into 18 rows and 18 columns as 18 × 18 matrix so that each unit cell has a square shape having 10 mm side length. Moreover, 152 different ground plane configurations are created by using logic 1 s and 0 s. Multi-layered feed forward ANN is used along with Scale Conjugate Gradient learning algorithm to design ground plane of the monopole antenna. Simulated 152 random ground plane arrays and obtained radiation patterns are used to train ANN for the ground plane design. If a user wants to manipulate radiation, artificial neural network gives the optimum ground plane design for the desired radiation direction and gain with 91.03% accuracy. Finally, one test antenna is fabricated and experimentally measured to support the results of the simulated one. The proposed ANN model approach can be easily used for antenna applications in the antenna industry.

中文翻译：

---

使用人工神经网络对 4.9 GHz 可重构单极天线的地平面设计配置估计以获得所需的辐射特征

本文介绍了一种基于人工神经网络 (ANN) 的系统，该系统可预测接地平面设计，以实现工作频段为 4.8 至 5 GHz 的单极天线的所需辐射特性。工作频率可以适应任何其他频率范围。最初，设计了一个由铜层组成的 180 × 180 mm2 接地平面并将其集成到辐射极上，从而形成单极天线配置。地平面被划分为 18 行和 18 列作为 18 × 18 矩阵，以便每个单元具有边长为 10 毫米的正方形形状。此外，通过使用逻辑 1 和 0 可以创建 152 种不同的接地平面配置。多层前馈人工神经网络与尺度共轭梯度学习算法一起用于设计单极天线的地平面。模拟的 152 个随机地平面阵列和获得的辐射方向图用于训练用于地平面设计的 ANN。如果用户想要操纵辐射，人工神经网络会为所需的辐射方向和增益提供最佳地平面设计，准确度为 91.03%。最后，制造了一个测试天线并进行了实验测量，以支持模拟天线的结果。建议的 ANN 模型方法可以很容易地用于天线行业的天线应用。制造了一个测试天线并进行了实验测量，以支持模拟天线的结果。建议的 ANN 模型方法可以很容易地用于天线行业的天线应用。制造了一个测试天线并进行了实验测量，以支持模拟天线的结果。建议的 ANN 模型方法可以很容易地用于天线行业的天线应用。