Work mode identification of airborne phased array radar based on the combination of multi-level modeling and deep learning

摘要

According to the change law of pulse signal in airborne phased array radar under different modes, a new method based on multi-level modeling combined with deep learning is proposed to recognize airborne phased array radar under different modes. Firstly parameters-jointing modeling is proposed to model the emitters at pulse level, pulse group level and the work mode level. Then stacked denoising auto-encoder is introduced to extract features from pulse signal under the work mode level unsupervised. Finally the parameters of the network are optimized by the back propagation algorithm in order to recognize airborne phased array radar under different modes. Qualitative experiments show that compared with the original algorithm based on knowledge base, the new method are able to extract essential characteristics of the input, reduce the dependence on prior knowledge, and achieve a good performance.