D-S证据理论可以有效的处理不确定信息,是有效的信息融合方法之一。但在证据高度冲突时,因其归一化过程会产生有悖常理的结果。基于此,提出了一种新的证据合成方法。首先采用加性策略对命题进行排序,找出证据支持最大的几个命题,然后对其进行冲突检验及修正,再利用PCR5规则实现信息融合。与其它方法相比,新方法在系统提供的证据高度冲突时仍然能够有效快速的识别出目标。

D-S evidence theory is a useful method of processing uncertain information. It is widely used in information fusion systems. However, it involves counter-intuitive results when the highly conflicting evidences exist. In order to solve this problem, a new fusion method of conflicting evidence checkout and correction associated with PCR5 rule was proposed. Firstly, compositor of all propositions by using adding strategy was introduced. Then, several propositions highly supported by evidences were picked out to check and correct the conflict evidence. Finally, PCR5 rule was used to realize information fusion. Compared with other existing methods, the proposed approach is more efficient in combining conflict evidence.