RNN With High Precision and Noise Immunity: A Robust and Learning-Free Method for Beamforming
Cong Lin, Zhihui Jiang, Jingyu Cong, Lilan Zou
Abstract
Recurrent neural networks (RNNs), recognized for their high accuracy and strong robustness. However, the adoption of RNN-based solutions for array signal beamforming is still in its infancy, as RNNs are very sensitive to noise and cannot easily overcome the impact of environmental noise on the solution. To address these limitations, this study proposes the dynamic integrated enhanced neural network (DIENN) for array signal beamforming, which incorporates an error integral feedback mechanism. This mechanism enhances the robustness and noise immunity of the model, enabling it to maintain stable performance under dynamic noise environments. Compared with state-of-the-art (SOTA) methods, the proposed model has higher stability in beamforming tasks while providing excellent results under three interference conditions where the other algorithms of the comparison failed. The residual accuracy achieved in the case of time-varying disturbance was <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$10^{-15}$ </tex-math></inline-formula>. The feasibility of the model was verified by applying it to experimental data. To our knowledge, this is the first work to develop a zero-reset RNN for array signal processing.