基于小波变换的变步长LMS自适应滤波算法  

Based on the Wavelet Transform of the Variable step LMS Adaptive Filtering Algorithm

作　　者：卢炳乾[1] 冯存前[1] 龙戈农[1] 

机构地区：[1]空军工程大学防空反导学院,西安710051

出　　处：《中国电子科学研究院学报》2013年第5期512-515,共4页Journal of China Academy of Electronics and Information Technology

基　　金：陕西省自然科学基金资助项目(2010JQ8007)

摘　　要：变步长LMS自适应滤波算法通过构造合适的步长因子有效的解决了传统LMS算法收敛速度和稳态误差相矛盾的问题。变换域LMS自适应滤波算法通过正交变换降低了输入信号矩阵的相关性,提高了算法的收敛速度。将这两种算法相结合,提出了一种新的基于小波变换的变步长LMS自适应滤波算法。仿真结果表明,该算法无论是收敛速度还是稳态误差都有了很大的提高。The problem that it is difficult for the traditional LMS adaptive filtering algorithm to ease the conflict between convergence and steady-state error is solved by variable step-size LMS adaptive filtering algorithm solved. Transform domain LMS adaptive filtering algorithm can reduce the relativity of input sig- nals effectively through orthogonal transforms, so the convergence rate will be improved. Combining this two algorithms and a new variable step-size LMS algorithm based on wavelet transform can be presented. The computer simulation results indicate that the new algorithm improved both the convergence rate and the steady-state error.

关 键 词：变步长LMS算法 变换域LMS算法 收敛速度 稳态误差 

分 类 号：TN971[电子电信—信号与信息处理]