论文部分内容阅读
对敌方雷达信号调制类型的识别是电子对抗的一个重要方面。采用了一种基于人工免疫聚类和进化规划的混合算法设计径向基函数(RBF)网络,并将其应用于雷达信号调制类型的自动识别。该算法首先利用一种实现数据聚类的人工免疫机制,根据输入数据集合自适应地确定RBF网络初始中心的数量和位置,之后采用进化规划训练RBF网络。仿真实验表明,采用这种方法设计的RBF网络对各种模拟调制信号的调制类型达到了较高的识别精度。
Identification of enemy radar signal modulation types is an important aspect of electronic warfare. A hybrid algorithm based on artificial immune clustering and evolutionary programming is used to design a radial basis function (RBF) network, which is applied to the automatic recognition of radar signal modulation types. Firstly, the algorithm uses an artificial immune mechanism to implement data clustering. Based on the input data set, the algorithm initially determines the number and location of the initial centers of the RBF network, and then uses the evolution programming to train the RBF network. The simulation results show that the RBF network designed by this method achieves high recognition accuracy for the modulation types of various analog modulation signals.