自适应动量项BP神经网络盲均衡算法  

Modified blind equalization algorithm based on back-propagation neural networks with adaptive momentum factor

作　　者：王华[1] 程海青[2] 

机构地区：[1]太原理工大学计算机软件学院,山西太原030024 [2]太原理工大学信息工程学院,山西太原030024

出　　处：《计算机工程与设计》2010年第6期1297-1300,共4页Computer Engineering and Design

摘　　要：为了消除数字信号在传输过程中产生的码间串扰,使得接收端能够正确解调,对信道畸变进行有效补偿,在基于动量项BP神经网络盲均衡算法的基础上,提出一种能够自适应调节BP神经网络动量项的盲均衡算法。该算法根据盲均衡过程中误差函数的变化情况,自适应调节BP神经网络的动量项,充分发挥动量项在避免网络训练陷于较浅的局部极小点的优势。仿真实验结果表明,该算法在稳定性及收敛性能上均优于固定动量BP神经网络盲均衡算法。To infer the transmitted signal from the received signal and to eliminate the InterSymbol interference of the signal, an adaptive momentum factor is introduced for blind equalization based on BP neural network with momentum factor.The momentum factor is modified adaptively according to the values of mean square error.Stimulation shows that this new algorithm is superior to that using constant momentum only, in such aspects as the convergence speed, the steady residual error and the bit-error-rate.

关 键 词：盲均衡 误差反传算法 神经网络 自适应算法 动量项 

分 类 号：TN911.5[电子电信—通信与信息系统]