基于粒子群算法的自适应LMS滤波器设计及可重构硬件实现  

Design of Adaptive LMS Filter Based on Particle Swarm Optimization and Implementation on Reconfigurable Hardware

作　　者：黄媛媛[1] 王友仁[1] 崔江[1] 张砦[1] 杨玲[1] 

机构地区：[1]南京航空航天大学自动化学院,江苏南京210016

出　　处：《佳木斯大学学报（自然科学版）》2010年第1期1-4,共4页Journal of Jiamusi University：Natural Science Edition

基　　金：航空科学基金资助项目(2009ZD52045)

摘　　要：自适应滤波器设计是典型的多参数组合优化问题,利用一种改进的粒子群优化算法(MPSO)来优化设计自适应LMS滤波器.将滤波器设计问题转化为滤波器参数优化的问题,利用改进的粒子群算法MPSO搜索整个参数空间,从而获得全局优化的系数.设计的滤波器应用于系统的跟踪响应中,并在基于可重构硬件的平台上实现自适应滤波器.从收敛和失调性能指标评价所设计的LMS滤波器,实验结果表明设计的LMS滤波器具有较好的性能,证明了这种方法的有效性和优越性.The optimum design of adaptive filter is a representative issue of multi - parameters combination optimization. An efficient technique of designing the adaptive LMS （Least Mean Square） filter using a modified Particle Swarm Optimization （MPSO） is presented in this paper. The design of adaptive filter is converted into the optimization of the parameters of adaptive filter. The MPSO can search the whole parameters space effectively and globally to optimize parameters. The adaptive filter structure is implemented on the reconfigurable hardware and employed in the application for tracking response. It is shown that the designed LMS has good performance both in convergence and small maladjustment. At the same time, the effectiveness and superiority of the introduced method are demonstrated by experimental results.

关 键 词：自适应滤波器 LMS算法 滤波器优化设计 粒子群算法 可重构硬件 

分 类 号：N301.6[自然科学总论]