分段聚类在雷达信号分选中的应用  

Application of Segment Clustering in Radar Signal Sorting

作　　者：国强[1] 王常虹[1] 郭立民[2] 李峥[3] 祝正威[3] 华云[3] 

机构地区：[1]哈尔滨工业大学空间控制与惯性技术研究中心,哈尔滨150001 [2]哈尔滨工程大学信息与通信工程学院,哈尔滨150001 [3]电子对抗国防科技重点实验室,成都610036

出　　处：《北京邮电大学学报》2008年第2期132-136,共5页Journal of Beijing University of Posts and Telecommunications

摘　　要：分析了雷达信号分选中的容差问题,现代电子战面临的越来越复杂密集的脉冲环境,使容差问题成为制约现有多参数信号分选体制分选效率的重要因素.根据统计学习理论的思想,提出了一种基于支持向量聚类和级联互耦的分段聚类雷达信号分选方法,该方法克服了容差问题对雷达信号分选的影响.通过仿真实验验证,对于高脉冲密度环境和复杂的信号形式,这种分选方法是有效的.The problem of tolerance of radar signal sorting is analyzed in modern electronic warfare that faces more complex and dense pulses environments. It is becoming a vital factor to improve the efficiency of sorting of the conventional multi-parameters signal sorting system. According to the idea of statistics learning theory, a segment clustering radar signal sorting method is presented based on cascade coupling and support vector clustering （SVC）. It prevents tolerance from affecting radar signal sorting. Experiments show that the sorting method presented is good for raising the efficiency to overcome the tolerance of radar signal sorting.

关 键 词：支持向量聚类 级联互耦 信号分选 容差 

分 类 号：TN974[电子电信—信号与信息处理]