摘要
针对自适应IIR滤波器潜在的不稳定性和性能指标函数容易陷入局部极小点而导致性能下降等问题,用一种新的优化算法-微粒群算法来对自适应IIR滤波器进行优化设计,它不依赖于梯度信息,能够有效地实现自适应IIR滤波器参数的全局寻优,仿真结果表明用微粒群算法进行参数寻优优于遗传算法,不仅解决了自适应滤波器性能指标函数容易陷入局部极小点的问题,也解决了稳定性问题。
Adaptive ⅡR filtering suffers from potential instability and converges to a local minimum of the objective function. According to these problems, a new method -particle swarm optimization is presented for optimizing the design of AIIRF structures. It doesn't depend on grads information. Experimental result shows that AIIRF based on particle swarm optimization reach the global optimization of objective function and quickly converges, and is better than genetic algorithm, Particle swarm optimization for AIIRF problems also provide filter stability.
出处
《计算机工程与设计》
CSCD
北大核心
2006年第11期2049-2050,2076,共3页
Computer Engineering and Design
关键词
自适应ⅡR滤波
微粒群算法
遗传算法
参数优化
adaptive IIR filtering
particle swarm algorithm
genetic algorithm
parameter optimization