Active Noise Control System using Least Mean Square Algorithm

An active noise control system is one of the best methods used to reduce noise effectively. The Least Mean Square (LMS) algorithm is a key parameter is the step size. As is well known if the step size is large, the convergence rate is rapid, but the steady-state Means Square Error (MSE) is increased. On the other hand if the step size is small, the steady state error is small, but the convergence is slow. Thus, the step size provides tradeoff between the convergence rate and steady-state MSE of LMS algorithm. The filtered-X least mean square algorithm has the good convergence speed, low steady state mean square error and low computational complexity features. The Active Noise Control (ANC) uses a primary input containing the corrupted signal and a reference input containing noise correlated in some unknown way with primary noise. ANC system noise reduction rate and convergence rate are improved dynamically than the FxLMS fixed step size methods. In this paper LMS algorithm use to reduce a noise level in noise source with novel convergence speed using fixed step size. A simulation carried out for noise reduction using MATLAB.