Adaptive array beam forming using a combined RLS-LMS algorithm
Jalal Abdulsayed Srar, Kah-Seng Chung · eSpace (Curtin University) · 2008
A new adaptive algorithm, called RLMS, which combines the use of recursive least square (RLS) and least mean square (LMS), is proposed for array beam forming. The convergence of the RLMS algorithm is analyzed, in terms of mean square error, in the presence of additive white Gaussian noise. Computer simulation results show that the convergence performance of RLMS is superior to either RLS or LMS operating on its own. Furthermore, the convergence of RLMS is quite insensitive to changes in either signal-to-noise ratio, or the initial value of the input correlation matrix for the RLS section, or the step size adopted for the LMS section.