神经网络在微带DGS结构设计中的应用

采用神经网络并结合逆向方法训练网络对微带DGS(Defected Ground Structure)结构进行建模分析。通过文中实例可以看出,人工神经网络产生的结果与数值仿真的结果吻合良好,证明该方法结合FDTD分析方法,作为电路设计辅助工具,具有缩短设计时间、降低设计成本的优点。为微带DGS结构分析和设计提供了一个新途径。

Application of Neural Network to Design of Microstrip DGS

In this paper, a neural network model of the defected ground structure is established, and the ANN is trained with the converse method. The ANN results are in good agreement with the calculated results, which shows that the approach used in this paper is valid. The developed design model can be used to take the place of the FDTD method of the DGS structure, being a kind of aid tool of circuit design. As the ANN is used in the design of DGS structure, the design time is shortened and the design cost reduced.