Deinterleaving of radar pulse based on implicit feature

In the complex countermeasure environment,the pulse description words(PDWs)of the same type of multi-function radar emitters are similar in multiple dimensions.Therefore,it is difficult for conventional methods to deinterleave such emitters.In order to solve this problem,a pulse deinterleaving method based on implicit features is proposed in this paper.The proposed method introduces long short-term memory(LSTM)neural networks and statistical analysis to mine new features from similar PDW features,that is,the variation law(implicit features)of pulse sequences of different radiation sources over time.The multi-function radar emitter is deinterleaved based on the pulse sequence variation law.Statistical results show that the proposed method not only achieves satisfactory performance,but also has good robustness.

一种基于TOA的同型雷达同源判别方法

雷达信号合批是辐射源识别过程中的一个重要环节,它可以有效地消除虚假和重复的雷达信号。然而,传统的雷达信号合批算法在同型雷达信号的判别方面存在着严重不足,极易造成多个同型雷达被错误的归并。针对这种情况,提出了一种基于TOA的同型雷达同源判别方法,该算法首先利用同余方程的余数周期性质估计出雷达信号的精确PRI数值,然后利用该PRI计算出雷达信号之间的同源距离,从而判别各个雷达信号是否属于同一部雷达。理论推导及仿真实验表明了该算法的有效性。