基于改进GA-BP算法的RFID天线参数优化方法  

RFID Antenna Paramter Optimization Method Based on Improved GA-BP Algorithm

作　　者：杨文冬 杨建一 孙浩强 南敬昌[1] YANG Wendong;YANG Jianyi;SUN Haoqiang;NAN Jingchang(School of Electronic and Information Engineering,Liaoning Technical University,Huludao 125105,China)

机构地区：[1]辽宁工程技术大学电子与信息工程学院,葫芦岛125105

出　　处：《微波学报》2024年第3期22-28,45,共8页Journal of Microwaves

摘　　要：为了提高算法对天线参数的预测精度,提出了一种基于Adagrad优化器的改进遗传算法-反向传播(GA-BP)算法。通过在迭代过程中引入Adagrad优化器与阈值策略,对发生退化的种群最优个体的位置信息进行重新引导,解决了GA-BP算法局部寻优能力不足等问题,大幅度减小了误差损失并且加快了收敛速度。利用该方法对射频识别(RFID)标签天线的印刷品质和电磁参数进行了建模与分析。结果表明,改进GA-BP算法在稳步搜索极值的同时可以避免陷入局部极值陷阱,在误差和收敛效率方面均优于传统的反向传播(BP)算法与GA-BP算法,能够得到较高的预测精度,实现了RFID标签天线印刷品质的优化控制以及S_(11)特征曲线的预测。相比于BP算法与GA-BP算法,改进GA-BP算法在用于优化RFID标签天线的印刷品质时,平均绝对误差分别降低了91.92%和85.64%。在电磁参数预测应用时,分别降低了13.77%和13.19%。In order to improve the prediction accuracy of the algorithm for antenna parameters,an improved genetic algorithm-back propagation(GA-BP)algorithm based on Adagrad optimizer is proposed.By introducing the Adagrad optimizer and threshold strategy in the iterative process,the position information of the optimal individual in the degenerated population is redirected,solving the problem of insufficient local optimization ability of the GA-BP algorithm,significantly reducing the error loss and accelerating the convergence speed.Based on this method,the printing quality and electromagnetic parameters of the radio frequency identification(RFID)tag antenna are modeled and analyzed.The results show that the improved GA-BP algorithm can search for extremes steadily while avoiding the local extremum trap,and outperforms the traditional BP algorithm and GA-BP algorithm in terms of error and convergence efficiency,and can achieve higher prediction accuracy for the optimal control of RFID tag antenna print quality and S_(11)characteristic curve prediction.Compared with the BP and GA-BP algorithms,the improved GA-BP algorithm can reduce the average absolute error in the application of printing quality of RFID tag antennas by 91.92%and 85.64%,respectively.The reductions are 13.77%and 13.19%,respectively,when the improved GA-BP algorithm is applied to electromagnetic parameter prediction.

关 键 词：通信技术 射频识别标签天线 改进遗传算法-反向传播算法 Adagrad优化器 

分 类 号：TN92[电子电信—通信与信息系统] TN828[电子电信—信息与通信工程]