关键词: 变步长, 最小均方误差（LMS）算法, 收敛速率, 稳态误差

Abstract: LMS（Least Mean Square） algorithm is widely used due to its simple and stable performance.But there is an inherent conflict between the convergence rate and steady-state misadjustment，which can be overcome through the adjustment of size factor.A new improved LMS algorithm is presented according to the analysis of some variable step size algorithms.The computer simulation results are consistent with the theoretic analysis，which show that the algorithm not only has a faster convergence rate，but also has a smaller steady-state error.

Key words: variable step-size, Least Mean Square（LMS） algorithm, convergence rate, steady-state error