基于增量信息的分布式多周期决策融合方法  

A Multi-cycle Fusion Method of Distributed Decision Based on Increment Information

作　　者：王维 高晓利[1] WANG Wei;GAO Xiaoli(Sichuan Jiuzhou Electric Group Co.Ltd,Mianyang 621000,China)

机构地区：[1]四川九洲电器集团有限责任公司,四川绵阳621000

出　　处：《电子科技》2018年第8期69-72,85,共5页Electronic Science and Technology

基　　金：国家武器装备探索研究项目(7131326)

摘　　要：针对融合中心对单站决策级信息重复利用、信息传输失真导致"一票否决"、判决输出实时性差等问题,文中提出了基于增量信息的分布式多周期决策级融合算法及架构。该算法架构包括了单站和融合中心的处理逻辑,其中单站对单个周期内获得的传感器信息进行融合,融合结果作为单站该周期的决策增量信息,并被传输到融合中心;融合中心基于各单站的增量信息进行实时迭代融合并决策输出。理论分析及算例仿真结果表明,该方法降低了单站与融合中心的数据通信量,提高了融合中心决策的正确性和实时性。The decision information of single observer was used repeatedly by fusion center, ＂ one vote veto＂ was caused by transmission distortion,and real-time performance of decision output was poor. For all these problems above,a multi-cycle fusion method of distributed decision based on increment information was proposed. The algorithm architecture included the processing logic of single observer and fusion center. The single observer fused sensor＇s information which was received in a single cycle and the fusion results regarded as the decision increment were transferred to the fusion center where the increment information of each single observer was fused iteratively and made a decision in real time. Theoretical analysis and experimental result showed that the method reduced the amount of data communication between single observer and fusion center,and improved the correctness and real-time of fusion center decision making.

关 键 词：DS理论 多周期 分布式融合 决策级融合 增量信息 一票否决 

分 类 号：TP14[自动化与计算机技术—控制理论与控制工程]