BP神经网络在射频识别定位系统中的应用研究  

RFID localization application based on BP neural network

作　　者：徐平[1] 沙从术[1] 赵芳杰 

机构地区：[1]河南工程学院土木工程学院,河南郑州451191

出　　处：《电子技术应用》2016年第2期64-67,共4页Application of Electronic Technique

摘　　要：为了提高采用射频识别技术进行定位的精度,针对无源标签射频识别技术及采用BP神经网络对其定位精度的改善进行了研究。首先建立了基于无源标签的射频识别定位系统,之后建立了相应的BP神经网络,并通过实验进行了验证。实验结果表明,在60 cm×50 cm的区域内,通过四角布置四个天线,利用信号强度作为输入信号,采用BP神经网络可以将定位误差控制在2 cm以内,平均欧几里得误差控制在1以内。说明采用BP神经网络可以改善射频识别定位技术的精度。In order to increase the radio frequency identification（ RFID） localization accuracy, the effects of BP neural network on localization accuracy was studied based on passive RFID tag. Firstly, the RFID localization system was established based on passive RFID tag and then the corresponding BP neural network was set. Finally the effects of BP neural network on localization accuracy were validated using the experiment test bed. The results show that for the region within 60 cm × 50 cm corners arranged by four antennas, the bias is less than 2 cm and the average euclidean error is less than 1 using the BP neural network based on the signal strength as the input signal from the four antennas. It can be included that the BP neural network can improve the accuracy of RFID localization accuracy.

关 键 词：神经网络 射频识别 定位 定位精度 

分 类 号：TN98[电子电信—信息与通信工程]