Adaptive Beamforming via Desired Signal Robust Removal for Interference-Plus-Noise Covariance Matrix Reconstruction

Abstract

To tackle the problem of the desired signal (DS) steering vector mismatch, especially in the situation of direction-of-arrival error and array perturbations, a robust interference-plus-noise covariance matrix (INCM) reconstruction method based upon DS removal is presented. Unlike previous studies, this paper proposes to remove the DS component from the training data by building a blocking matrix, which is computed as the inverse of the DS-plus-noise covariance matrix (DSNCM). More specifically, to increase the robustness against arbitrary mismatches, the DS steering vector estimated as the prime eigenvector of the DS matrix, which is attained through integrating the Capon spectrum estimator over the annulus uncertainty sets of the mainlobe region in advance, is adopted to give a faithful blocking matrix. After that, utilizing the obtained blocking matrix to process the training data, the quasi INCM is computed indeed. Finally, a precise INCM is reconstructed by projecting the principal components of the quasi INCM onto the aforesaid DSNCM. Numerical simulations have illustrated that the proposed adaptive beamformer can outperform the existing ones and gain almost optimal performance under different scenarios.