探雷声纳目标的概率分类技术  

Probability Classification Method for Mine Detection Sonar Targets

作　　者：马爱民[1] 

机构地区：[1]海军大连舰艇学院,辽宁大连116018

出　　处：《指挥控制与仿真》2017年第3期1-4,共4页Command Control & Simulation

基　　金：国防预研基金(3020604010302)

摘　　要：探雷声纳搜索海底时发现目标数量多,重合点少,现有方法难以快速有效识别水雷。对此提出一种基于概率特征的目标分类技术,通过多次搜索获得小目标发现率,根据错判概率最小准则确定分类判据,对概率差异明显的目标实现有效分类。对以往的实际搜索数据分析结果证明,该方法能有效剔除大部分低概率小目标,减小待处理目标数量,显著提高探雷声纳的综合搜索效能。The targets which found by mine detection sonar whi le searching sea bed are large quantity and can9t be found a-gain easily. The current measures are di fficult to classify the mines from the sonar targets. Now a new method has been devel-oped to do this efficiently,which based on the difference between the targets9 detecting probabilities acquired from mult iple searches. The method has been approved effective when it applies on some practical examples. The results express that a large percentage of lower probability targets are rejected, the numbers of reserved targets are reduced obviously and the com-prehensive effectiveness of the mine-detection sonar is raised remarkably.

关 键 词：探雷声纳 概率特征 分类判据 综合效能 

分 类 号：TJ617[兵器科学与技术—武器系统与运用工程] E917[军事]