改进的NLMS算法及其在自适应预测中的应用  

Improved Variable Step Size LMS Algorithm and Its Application in Adaptive Prediction

作　　者：孙娟[1] 王俊[1] 刘斌[1] 

机构地区：[1]西安电子科技大学雷达信号处理国家重点实验室,西安710071

出　　处：《中国电子科学研究院学报》2007年第5期507-512,共6页Journal of China Academy of Electronics and Information Technology

基　　金：自然科学基金资助项目(No.60472087)

摘　　要：通过分析NLMS[1]和VSSLMS[7]两种算法控制时变步长的思想及这两种算法的优缺点,文章提出了一种改进的归一化变步长算法,它同时使用输入信号积累和瞬时误差来控制步长更新。该算法的优越性在于收敛速度快,尤其在系统跳变时也能快速收敛,可很好地应用于自适应预测系统中。理论分析与计算机仿真结果都表明该算法收敛速度快、失调量小、稳定性好,且在低信噪比的环境中比其他同类算法有更好的性能。First, the paper introduces the principle of NLMS and VSSLMS algorithms to control the new variable step size, and their advantages and disadvantages. Based on that, an improved variable step size LMS adaptive filtering algorithm is presented, which makes use of the accumulation of the input signal and temporal error signal to control the new variable step size. The superiority of this algorithm lies in its faster convergence rate, especially in the time varying system; thus, it can be applied perfectly to the adaptive predicted system. Computer simulation results confirm the theoretical analyses and show that this algorithm has faster convergence rate, smaller misadjustment and a better stability, and can achieve better performance in lower SNR situation.

关 键 词：自适应滤波 变步长自适应滤波算法 失调 自适应预测 

分 类 号：TN957.51[电子电信—信号与信息处理]