基于BP神经网络的直扩信号扩频码盲识别  

DSSS Signal Spread Spectrum Codes Blind Identification Based on BP Neural Network

作　　者：赵德芳[1] 张天骐[1] 金翔[1] 杜晓华[1] 

机构地区：[1]重庆邮电大学信号与信息处理重庆市重点实验室,重庆400065

出　　处：《电讯技术》2010年第10期28-35,共8页Telecommunication Engineering

基　　金：国家自然科学基金资助项目(61071196);国家自然科学基金-中物院NSAF联合基金资助项目(10776040);教育部新世纪优秀人才支持计划(NCET-10-0927);信号与信息处理重庆市市级重点实验室建设项目(CSTC2009CA2003);重庆市科委自然科学基金资助项目(CSTC2009BB2287)~~

摘　　要：针对微弱直扩信号的盲检测与估计问题,在接收方未知发送方扩频序列的前提下,提出了一种恢复直接序列扩频(DSSS)信号扩频码的方法。该方法基于反向传播(BP)神经网络,它的输入是接收到的信号,而其期望输出是和输入相同的信号,根据误差反向传播来有监督地调节神经网络,网络达到收敛时根据第二层权值的符号函数值即可盲估计出扩频码序列。实验结果表明,即使是在负信噪比情况下,该方法也能得到一个很好的估计效果。In view of blind detection and estimation problems for weak DS signals, a method is presented to recover the spread spectrum code of direct sequence spread spectrum（DSSS） signal, whereas the receiver has no knowledge of the transmitter＇ s spreading sequence. The method is based on back propagation （BP） neural network, whose input is the received signal, and the expected output is the same as the input signal. It is supervised to adjust the neural network according to the error back - propagation, and then it can perform blind estimation of the spread spectrum code sequences according to the symbol function value of the second layer weights when adjusting the network to reach convergence. Experimental results show that the method provides a good estimation, even when the signal power is below the noise power.

关 键 词：直接序列扩频 BP神经网络 改进BP算法 伪码序列 盲识别 

分 类 号：TN911[电子电信—通信与信息系统]