基于卡方检验与SVM的多雷达抗欺骗干扰方法  

Multi-Radar Anti-Deception Jamming Method Based on Chi-Square Test and SVM

作　　者：施裕升 王晓科 周宇泰 蒋国韬 徐天洋 SHI Yusheng;WANG Xiaoke;ZHOU Yutai;JIANG Guotao;XU Tianyang(Shanghai Electro-Mechanical Engineering Institute,Shanghai 201109,China)

机构地区：[1]上海机电工程研究所,上海201109

出　　处：《空天防御》2022年第1期108-114,共7页Air & Space Defense

摘　　要：针对各雷达相对目标的角度差异较小时传统方法(卡方检验)鉴别假目标能力较差的问题,提出了卡方检验与支持向量机(support vector machine,SVM)相结合的自适应抗距离欺骗干扰方法。首先,根据满足卡方检验的组合个数判断是否需要进一步筛选;若需要进一步筛选,将航迹间的马氏距离(卡方检验量)、欧式距离、兰氏距离作为SVM的多特征输入,训练SVM;最后,将训练好的SVM用于识别真假航迹。仿真结果表明,该方法的真航迹识别率为95.5%,明显优于卡方检验以及改进的卡方检验方法。此外,该方法的训练时间短,识别时间与传统方法相当,实时性好,工程应用性强。Aimingat the problem that the traditional method(chi-square)has poor ability to identify false targets when the angle difference between the radars relative to the target is small,an adaptive anti-rangedeception jamming method combining chi-square test and support vector machine is proposed.Firstly,determine whether further screening is required according to the number of combinations that meet the chi-square test;If further screeningis required,use the Mahalanobis distance(chi-square test variable),Euclidean distance,and Randolph distance between tracks as the multi-feature input of SVM.Then,train the SVM model.Finally,use the trained SVM to identify true and false tracks.The simulation results show that the true target track recognition rate of this method is 95.5%,which is better than the chi-square test and the improved chi-square test method significantly.In addition,the training time of this method is short;the recognition time is equivalent to the traditional method;the real-time performance is good,and the engineering application is strong.

关 键 词：卡方检验 支持向量机 航迹特征 抗欺骗干扰 

分 类 号：TN974[电子电信—信号与信息处理]