文章提出了一种基于模糊最小均方(LMS)算法的主从滤波器的设计,采用模糊推理机制,通过从滤波器输出的信噪比来调节主滤波器的步长,从而达到快速而稳定的收敛,并将其应用于噪声抵消系统中。仿真结果表明,该算法(FMS-LMS)比传统LMS算法及只有主从滤波器的算法具有更好的性能。 This paper presents a design of master-slave filter based on fuzzy least mean square (LMS) algorithm. By using fuzzy reasoning mechanism, the step size of the main filter is adjusted by the signal-to-noise ratio of the output of the filter to achieve fast and stable The convergence and its application to noise cancellation system. The simulation results show that the proposed algorithm (FMS-LMS) has better performance than the traditional LMS algorithm and the algorithm of only master-slave filter.