基于不确定性度量和证据距离的导弹系统参数融合  

Missles System Data Fusion Based on the Uncertainty Measurement and Evidence Distance

作　　者：张平峰 孟蕾[2] 李玲玲[3] 

机构地区：[1]海军驻上海地区航天系统军事代表室,上海200000 [2]海军航空工程学院飞行工程系,烟台264000 [3]海军出版社,天津300450

出　　处：《舰船电子工程》2016年第7期41-43,133,共4页Ship Electronic Engineering

摘　　要：证据理论是一项重要的工具在信息融合领域。然而Dempster组合规则不能有效地处理高冲突现象因为它能产生反直观结果。针对这个问题,提出了一种新的证据组合方法。该方法同时利用证据总不确定度和证据距离来生成新的权重进而修正组合证据,并取得合理的组合结果。通过实验应用到导弹系统自动驾驶仪中,结果表明论文方法具有更好的收敛速度,能有效处理高冲突证据组合问题。Dempster-Shafer evidence theory is an important tool in the fields of information fusion.However Dempster’s rule of combination cannot efficiently handle highly conflictring evidence combination for it can arouse counter-intuitive behaviors.To deal with such a problem,a novel weighted average evidence combination approach is proposed.Not only the distance of evidence but also the uncertainty measure is utilized to determine the wights of the bodies of evidengce.Based on the weighted averaged BOE and Dempster’s rule of combination,the rational combinatiuon results can be obtained.It’s applied in missles system autopilot through experiment.The experimental results show that the method proposed can effectively handle conflicting evidence combination with better convergence.

关 键 词：证据理论 证据体 融合 距离函数 不确定度 

分 类 号：R730.58[医药卫生—肿瘤]