设计自适应IIR滤波器的单纯形-退火策略  

Design of Adaptive IIR Filters With Simplex-Annealing Strategy

作　　者：王凌[1] 李令莱[1] 郑大钟[1] 

机构地区：[1]清华大学自动化系,北京100084

出　　处：《系统工程与电子技术》2002年第7期99-102,共4页Systems Engineering and Electronics

基　　金：国家自然科学基金项目 ( 6 0 1740 2 2 ) ;"973"基础研究资助课题 (G19980 2 0 310 );"86 3"高技术计划资助课题 ( 2 0 0 1AA4112 2 0 )

摘　　要：作为信号处理领域的重要研究课题 ,滤波器设计本质上是一个多维参数寻优问题 ,且往往存在多极小。传统最小二乘法和单纯形法易陷入局部极小 ,而单一模拟退火算法搜索过程冗长 ,单一遗传算法易早熟收敛。结合模拟退火的随机概率突跳性搜索和单纯形法的凸多面体几何搜索 ,提出了有效设计自适应IIR滤波器的一种简单易实现的单纯形 退火策略 (simplexmethod simulatedannealing ,SMSA) ,并给出了算法操作和参数的合理设计方案。基于多个典型系统的随机数值仿真以及与最小二乘方法的比较研究 ,验证了所提方法的有效性、全局优化性和初值鲁棒性。As an important issue in signal processing field, filter design is essentially a multiple-parameter optimization problem with multiple local minima in most cases. Classical least-mean-square method and simplex method are easy to be trapped in local minimum, and the searching process of pure simulated annealing is rather long. Pure genetic algorithm is easy to be premature convergent. Combining the probabilistic jumping search ability of simulated annealing with the geometry search in convex polyhedron of simplex method, this paper proposes an effective, simple and easy-to-be-implemented simplex-annealing strategy (simplex method-simulated annealing, SMSA) for adaptive IIR filter design. Moreover, reasonable design scheme for search operators and parameters is provided. Random simulation based on some typical systems as well as comparison with least-mean-spuare method demonstrate, the effectiveness, global optimization ability and robustness on initial values of the proposed strategy.

关 键 词：ⅡR滤波器 单纯形-退火策略 模拟退火 单纯形法 信号处理 

分 类 号：TN713[电子电信—电路与系统]