采用SRM准则对RLS-FIR滤波器的改进  

Improved RLS Filters Based on Structural Risk Minimum Principle

作　　者：毛忠阳[1] 王红星[1] 王洪利 宋恒[1] 

机构地区：[1]海军航空工程学院电子信息工程系,山东烟台264001

出　　处：《电讯技术》2011年第2期40-45,共6页Telecommunication Engineering

基　　金：国家自然科学基金资助项目(60772056);中国博士后科学基金资助项目(20070421094)~~

摘　　要：针对自适应FIR滤波器在非平稳条件下跟踪性能差的问题,提出采用结构风险最小化(SRM)准则来改进FIR滤波器的方法,并进行了分析和仿真实验。仿真结果表明:在平稳条件下,采用SRM准则的FIR滤波器收敛于Wiener最优解;在非平稳条件下,采用SRM准则的FIR滤波器跟踪性能大幅提高,优于自适应递推最小二乘(RLS-FIR)滤波器。To solve the problem that the tracking performance of adaptive FIR filter is poor under nonstationary condition, the method to improve FIR filter based on structural risk minimum （SRM） principle is presented in this paper. Simulation results show that on condition of stationary signals, SRM-based filter converges to Wiener optimal solution, and on condition of nonstationary signals, SRM-based filter significantly improves the tracking performance and is better than adaptive recursive least squares FIR（RLS- FIR） filter.

关 键 词：无线通信 自适应滤波器 非平稳条件 结构风险最小化 跟踪性能 

分 类 号：TN911[电子电信—通信与信息系统]