An L-parallel coprime array is designed and an Off-grid sparse learning via iterative minimization (OGSLIM) algorithm is proposed in order to improve the performance of Two-dimensional direction-of-arrival (2-D DOA) estimation. The L-parallel coprime array consists of two parts, one is a parallel coprime array and the other one is a linear coprime array perpendicular to the parallel coprime array. The OGSLIM algorithm is based on sparse Bayesian framework and can learn the offi-grid parameter. Theory analysis and simulation results demonstrate that 2-D DOA estimation using OGSLIM algorithm with L-parallel coprime array can lead to higher estimation accuracy and resolution, it also fits to the underdetermined signals and correlated signals.
Constant false-alarm rate Block-sparse Bayesian learning (CFAR-BSBL) algorithm is proposed to reduce the computational complexity and improve Direction of arrival (DOA) estimation accuracy of offgrid signals with coprime array. Firstly, a signal model with normalized noise is built to avoid the learning procedure of noise parameter. Secondly, a block sparse Bayesian framework is built with the introduction of a temporary correlation matrix in order to use t he temporal structure of incident signals. Then the algorithm uses CFAR detection to detect the grids close to the real DOA and relieve the dependence on the number of signals. Finally, an off-grid process based on the closest grids is adopted to deal with the off-grid problem. The proposed CFAR-BSBL algorithm can obtain high accuracy and low complexity DOA estimation of off-grid signals with coprime array.
To address the challenge of recognizing Active Electronically Scanned Arrays (AESA) radar work modes under few labeled data, this paper proposes a semi-supervised algorithm based on multi-task contrastive learning. The method employs a dual-stage collaborative optimization framework combining self-supervised pre-training and supervised fine-tuning to effectively leverage latent feature information from unlabeled data. In the self-supervised pre-training stage, a dual-path data augmentation strategy is designed to generate mode-consistent pulse sequence samples, where an expander and a base encoder work synergistically to capture both temporal dependencies and cross-pulse deep correlation features. Additionally, three self-supervised tasks—contextual contrastive learning, pulse sequence reconstruction, and augmentation feature prediction—are introduced to optimize feature space distribution, disentangle noise interference, and enforce consistency constraints across augmented samples, respectively. During the supervised fine-tuning stage, a classifier integrates self-supervised representations with few labeled data to enhance recognition performance. Comparative experiments demonstrate that the proposed algorithm achieves significantly higher recognition accuracy on the AESA radar work mode dataset compared to other mainstream semi-supervised methods under few labeled conditions. Ablation studies validate the strengthening effect of the multi-task collaborative mechanism on model performance. Additionally, data augmentation comparison experiments identify the optimal augmentation strategy for this algorithm.