基于BP神经网络的分形DGS微带天线设计

Fractal DGS Microstrip Design Based on BP Neural Network

微带天线易于产生谐波辐射,造成功率的损耗。加入DGS的微带天线可以抑制谐波,但是普通DGS会增加天线的背向功率漏射,且接地板利用率较低,分形DGS可以很好地克服这些缺点。为了缩短DGS的设计周期,采用BP神经网络对DGS进行进建模,在此基础上分析设计了一种分形DGS微带天线,并对制作的实物进行了测量,测量结果与仿真结果吻合较好,证明了该神经网络模型的正确性和分形DGS在微带天线谐波抑制中的有效性。

The microstrip patch antenna is easier to produce harmonic radiation which waste the power. Harmonic power can be supressed by the microstrip patch antenna, but the back radiation power would be enforced. Now these problems would be overcome by the fractal DGS. The BP neural net- work of DGS is built to cut off the time used in DGS designing period. Based on the BP neural net- work model, a fractal DGS microstrip patch antenna is designed and measured, the measured results are in good agreement with the simulation ones, which prove the accuracy of the BP neural network model and the effectiveness of the fractal DGS in harmonic suppress of the microstrip patch antenna.