A Unified Antijamming Design in Complex Environments Based on Cross-Modal Fusion and Intelligent Decision-Making

With the rapid development of radar jamming systems, especially digital radio frequency memory (DRFM), the electromagnetic environment is increasingly complicated. In recent years, the application of neural networks in the fields of radar interference recognition and anti-jamming has proven to be highly effective, such as convolutional neural networks (CNNs). However, most existing studies solely focus on either jamming recognition or anti-jamming strategy design. In this paper, we propose a unified framework that integrates interference recognition with intelligent anti-jamming strategy selection. Specifically, time-frequency (TF) features of radar echoes are first extracted using both Short-Time Fourier Transform (STFT) and Smoothed Pseudo Wigner–Ville Distribution (SPWVD). A feature fusion method is then designed to effectively combine these two types of time-frequency representations. The fused TF features are further combined with time domain features of the radar echoes through a cross-modal fusion module based on an attention mechanism. Subsequently, a three-class classification algorithm is employed to identify the different interference types. Finally, the recognition results, in conjunction with information obtained from the passive radar, are fed into a Deep Q-Network (DQN)-based intelligent anti-jamming strategy network to select jamming suppression waveforms. The key jamming parameters obtained by the passive radar provide essential information for intelligent decision-making, enabling the generation of more effective strategies tailored to specific jamming types. The designed method demonstrates improvements in both jamming type recognition accuracy and the stability of anti-jamming strategy selection under complex environments. The experimental results demonstrate that the proposed method exhibits superior performance in comparison to Support Vector Machines (SVM), VGG-16, 2D-CNN methods, with respective improvements of 3.75%, 1.76% and 2.32% in overall accuracy under high-accuracy operating conditions. Furthermore, in comparison with the SARSA algorithm, the designed algorithm achieves faster reward convergence and more stable strategy generation.