An improved algorithm for radar adaptive beamforming based on machine learning

In the field of radar digital signal processing, adaptive beamforming is a widely used technique for suppressing interference and noise. The Least Mean Square Algorithm (LMS) is a simple and easy algorithm for adaptive digital beamforming. However, it has the disadvantage of not achieving a balance between convergence speed and stability. In order to improve the performance of adaptive beamforming, this paper firstly reviews the classical LMS algorithm and then the machine learning optimization algorithm. Improvement effects of the three machine learning methods on the LMS algorithm are analyzed. The results show that the improved LMS algorithm based on AdaGrad exhibits the best performance. The algorithm can independently adjust the adaptive learning rate of different parameter components, making the iterative process of the adaptive beamforming more stable, efficient, and suitable for both theoretical research and engineering practice.