参数寻优LSSVM算法在机载火控雷达工作模式判定中的应用  

A Parameter-Optimized LSSVM Method for Operation Modes Recognition of Airborne Fire Control Radar

作　　者：王玉冰[1] 程嗣怡[1] 周一鹏[1] 呙鹏程 

机构地区：[1]空军工程大学航空航天工程学院,西安710038

出　　处：《空军工程大学学报（自然科学版）》2017年第3期49-53,共5页Journal of Air Force Engineering University(Natural Science Edition)

基　　金：航空科学基金(20145596025;20152096019)

摘　　要：针对机载火控雷达工作模式判定问题,应用一种基于网格搜索和交叉验证的参数寻优最小二乘支持向量机(LSSVM)算法,实现对4种典型空空工作模式的自学习判定。首先,从非合作雷达信号中提取特征参数并构建雷达信号特征库作为训练样本;然后通过网格搜索进行参数寻优模型训练,实现样本范围不确定条件下的模型调整;最后应用K-fold交叉验证方法进行训练性能评价,减小样本随机性导致的模型误差,提高泛化能力。仿真结果表明,该方法对速度搜索模式、边搜索边测距模式、边扫描边跟踪模式和单目标跟踪模式的判定准确率达97%。In the light of realizing the self-learning operation mode recognition of air borne fire control ra- dar, an optimized LSSVM algorithm based on grid search and K-fold verification is proposed. First, This paper extracts feature parameters from non-cooperative radar signal and establishes library base of radar signal as training sample in LSSVM model. Next, the paper applies grid search method in parameter optimization to realize model adjustment under the circumstance of uncertain sample range. In the sequel, The paper utilizes K-fold cross validation for realizeing performance evaluation and reduceing model error caused by sample randomness improv generalization ability. Simulation results show that recognition accuracy of VS/RWS/TWS/STT modes reaches 97 %, thus having a good recognition performance and practi- cal value of proposed method.

关 键 词：机载火控雷达 工作模式判定 LSSVM 网格搜索 K—fold交叉验证 

分 类 号：TN97[电子电信—信号与信息处理]