Anti-chaff Jamming Method of Radar Based on Real Dataset and Residual Attention Model

As a typical and widely used passive jamming method, chaff cloud has a strong jamming ability on radar, and still can not be well resolved. It is exceedingly necessary to improve the anti-chaff jamming ability of the radar. In this paper, we address this challenge by proposing an effective residual attention network named RA-Net. Specifically, we introduce the attention mechanism to enable the network to focus on the most informative and stable hierarchical features of the high resolution range profile (HRRP) data, effectively improving the model’s feature extraction capability and overall performance. In addition, we address the limitation of insufficient measured chaff cloud echo data by establishing a remarkably rich and diverse dataset of chaff cloud HRRP data through extensive field experiments, providing a valuable resource and critical foundation for advancing HRRP recognition research in this domain. Experimental results on measured HRRP data demonstrate that RA-Net achieves superior recognition accuracy 97.10% and outstanding generalization performance compared to traditional methods, establishing a new benchmark for chaff cloud HRRP recognition.