基于二阶循环统计量的LMS算法  

A new LMS algorithm based on the second-order cyclic statistics

作　　者：陈喆[1] 王宏禹[1] 邱天爽[1] 

机构地区：[1]大连理工大学电子与信息工程学院,辽宁大连116024

出　　处：《大连理工大学学报》2002年第2期234-237,共4页Journal of Dalian University of Technology

基　　金：国家自然科学基金资助项目 (60 172 0 72 ) ;辽宁省科学技术基金资助项目 (2 0 0 110 10 5 7)

摘　　要：证明了二阶周期平稳随机信号通过线性时不变系统后 ,仍是二阶周期平稳随机信号 ,且循环频率不变 .定义了基于二阶周期自相关函数的误差准则 ,给出了新的 LMS算法 ,并讨论了新算法的性能 .仿真结果表明 ,在收敛速度和抗噪声方面 。It is proved that after a second\|order cyclostationary signal passes a time invariant system, the output signal of the system is also a second\|order cyclostationary signal, and its cyclic frequency is the same as the input signal′s. Based on the second\|order cyclic correlation, a criterion is defined, and a new LMS algorithm is presented. The performance of the new algorithm is also discussed. A few simulations indicate that the performance of the new algorithm is better than that of the classical ones in respect of convergency speed and antinoise.

关 键 词：自适应滤波 二阶周期自相关函数 经典最小均方自适应算法 二阶循环统计量 二阶周期平稳随机信号 信号处理 循环频率 

分 类 号：TN911.72[电子电信—通信与信息系统]