IMPROVED LMS ALGORITHM FOR ADAPTIVE BEAMFORMING

The constrained least mean square (LMS) algorithm as applied to array beamforming requires an estimate of the gradient to update the array weights. There are a number of schemes to estimate the required gradient. These gradient estimation methods do not utilize the array samples available previous to the current iteration cycle. In this paper two adaptive algorithms are proposed and studied which make use of all the available samples to estimate the required gradient. One algorithm, referred to as the recursive LMS algorithm, is applicable for an array of arbitrary geometry whereas the second algorithm, referred to as the improved LMS algorithm, is useful for a line array of equispaced elements. © 1990 IEEE