基于BP神经网络矩形微带天线谐振频率预测  

Prediction of rectangular microstrip antenna's resonant frequency based on BP neural network

作　　者：李向阳[1] 曾文波[1] 

机构地区：[1]广西科技大学电子信息与控制工程学院,广西柳州545006

出　　处：《广西科技大学学报》2014年第3期26-31,共6页Journal of Guangxi University of Science and Technology

基　　金：广西高等学校科研资助项目(200103YB107)资助

摘　　要：谐振频率是微带天线的重要技术指标,建立合适的数学模型以获得微带天线精确的谐振频率,在微带天线的设计中至关重要,通过BP神经网络建模的方法对天线谐振频率进行预测.以一款谐振频率为2.4 GHz的矩形微带天线为分析算例,通过HFSS软件的仿真计算,获取了大量的天线样本,在此基础上建立了矩形微带天线的BP神经网络模型,并预测出不同结构参数下5个矩形微带天线的谐振频率.再将这5个天线的结构参数输入HFSS软件,用HFSS软件对这些天线进行仿真得到其谐振频率,比较结果证明采用BP神经网模型预测得到的天线谐振频率与HFSS仿真结果间误差很小,说明神经网络预测得到的天线谐振频率有效,本文的设计方法可行,效果良好.Resonant frequency is an important technical indicator of microstrip antenna, and obtaining the resonant frequency of microstrip antenna by establishing an appropriate mathematical model is crucial in the design of microstrip antenna. In this paper predicting the resonant frequency of microstrip antenna by establishing model based on BP neural network is the main content. Taking a rectangular microstrip antenna whose resonant frequency is 2.4 GHz as an example of analysis study, and using simulation software HFSS to get a lot of antenna samples, on the basis of those samples we establish a BP neural network model of rectangular microstrip antenna and predict the resonant frequency rectangular of five microstrip antennas with different structure parameters by using the model. Then we put the five antennas＇s structural parameters into the HFSS software and use HFSS simulation software to get resonant frequencies of these antennas. The comparison results prove the error between the resonant frequency of the antenna predicted by using BP neural network model and HFSS simulation results is small. The test results indicate that the antenna＇s resonant frequency getting by using design approach is feasible with good results. neural network prediction was valid, and this article

关 键 词：矩形微带天线 BP神经网络 HFSS天线仿真软件 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]