A FAST ROBUST LMS ALGORITHM UTILIZING THE DYNAMICS OF A DAMPED PENDULUM

in this paper, a new fast LMS-based adaptive algorithm is proposed. It is derived by incorporating a clamping force in the LMS update recurs ion similar to the force acting upon a damped planar pendulum. An expr ession for evolution and the steady-state behavior for the mean weight vector is developed This expression provides a mathematical bound whi ch constrains the parameter that controls the maximum contribution of the introduced damping force. Furthermore, an expression for the mean square error is developed to examine algorithm behavior in the mean sq uare sense. Simulation results show an improved robust performance for the new algorithm as compared with the conventional LMS and Momentum LMS (MLMS) algorithms in smoothly tracking the optimal solution in sta tionary, correlated and nonstationary noisy environments. Moreover, si mulation examples include system identification with varying power env ironments. (C) 1997 The Franklin Institute. Published by Elsevier Scie nce Ltd.