一种约束稳定性最小均方噪声对消算法

A Constrained Stability Least Mean Square Noise Cancellation Algorithm

研究了最小均方误差(LMS)算法、归一化的最小均方(NLMS)算法及变步长NLMS算法在自适应噪声干扰抵消器中的应用,针对目前这些算法在噪声对消器应用中的缺点,将约束稳定性最小均方(CS-LMS)算法应用到噪声处理中,并进一步结合变步长的思想提出来一种新的变步长CSLMS算法。通过MATLAB进行仿真分析,结果证实提出的算法与其他算法相比,能很好地滤除掉噪声从而得到期望信号,明显的降低了稳态误差,并拥有好的收敛速度。

The least mean square error （LMS） algorithm, normalized least mean square （NLMS） algorithm and variable step NLMS algorithm in adaptive noise canceller are studied, and aiming at the shortcomings of these algorithms in applications, the constrained stability least mean square （CS-LMS） algorithm is applied to dealing with noise, and further combined with the thought of variable step size, a new variable step size CS-LMS algorithm is proposed. Simulation with MATLAB indicates that this proposed algorithm, as compared with other algorithms, could fairly filter out the noise so as to acquire the desired signal, significantly reduce the steady-state error, and has excellent convergence speed.