Sparse Phased Array Optimization Using Deep Learning

Antenna arrays are widely used in wireless communication, radar systems, radio astronomy, and military defense to enhance signal strength, directivity, and interference suppression. We introduce a deep learning-based optimization approach that enhances the design of sparse phased arrays by reducing grating lobes. This approach begins by generating sparse array configurations to address the non-convex challenges and extensive degrees of freedom inherent in array design. We use neural networks to approximate the non-convex cost function that estimates the energy ratio between the main and side lobes. This differentiable approximation facilitates cost function minimization through gradient descent, optimizing the antenna elements' coordinates and leading to an improved layout. Additionally, we incorporate a tailored penalty mechanism that includes various physical and design constraints into the optimization process, enhancing its robustness and practical applicability. We demonstrate the effectiveness of our method by applying it to the ten array configurations with the lowest initial costs, achieving further cost reductions ranging from 411% to 643%, with an impressive average improvement of 552%. By significantly reducing side lobe levels in antenna arrays, this breakthrough paves the way for ultra-precise beamforming, enhanced interference mitigation, and next-generation wireless and radar systems with unprecedented efficiency and clarity.

Near-Field SAR Imaging of Moving Targets on Roads

This paper introduces a single-channel SAR algorithm designed to detect and produce high-fidelity images of moving targets in spotlight mode. The proposed fast backprojection algorithm utilizes multi-level interpolations and aggregation of coarse images produced from partial datasets. Specifically designed for near-field scenarios and assuming a circular radar trajectory, the algorithm demonstrates enhanced efficiency in detecting both moving and stationary vehicles on roads.

Phase-Only Beam Shaping for Transmitting Array Antennas in Radar Applications

Two beam broadening methods for active electronically scanned array (AESA) antennas with uniform amplitude excitation are proposed and compared: phase tapering optimization (PTO) and a novel time-varying phase tapering (TPT). The PTO is a simple and efficient approach assuming continuous polynomial phase distribution and requiring optimization of only few parameters. The TPT is valid mainly for radar applications, taking advantage of the fact that radars typically transmit pulse trains for coherent integration. By varying the array elements' phases from pulse to pulse, the TPT achieves effective amplitude tapering, thus providing a method of beam shaping, occasionally with a simple analytic form. The TPT also makes it possible to produce beam shaping with very low side lobe levels in comparison to the PTO. As a preliminary step, the dimensionality of the radiation pattern characterization for all scan directions is reduced from five to only two variables. This is crucial for efficient optimization of the radiation pattern which needs to be evaluated over a judiciously specified two-dimensional domain.