多源数据融合方法研究  

Research on Multiple Source Data Fusion Method

作　　者：李洪伟[1] 刘兆东[1] 闵远胜[1] 何亮[1] 刘鎏[1] 赵文涛 Li Hongwei;Liu Zhaodong;Min Yuansheng;He Liang;Liu Liu;Zhao Wentao(Science and Technology on Reactor System Design Technology Laboratory, Nuclear Power Institute of China, Chengdu, 610213, China;Reactor Operation and Application Research Sub-Institute, Nuclear Power Institute of China, Chengdu, 610213, China)

机构地区：[1]中国核动力研究设计院核反应堆系统设计技术重点实验室,成都610213 [2]中国核动力研究设计院反应堆运行与应用研究所,成都610213

出　　处：《核动力工程》2018年第3期77-80,共4页Nuclear Power Engineering

摘　　要：选取工程应用中易于实现的数据融合方法进行分析研究,并以融合数据与数据真实值的偏差作为数据融合方法的稳定性判定依据,进行了三余度多源数据的数据融合仿真试验。试验结果表明,加权最小二乘法在数据融合时表现稳定,可替代常用的矩估计融合和中值融合,更有效地提高融合数据的精度。This paper selects the data fusion method which is easy to realize in the engineering application, and takes the deviation of the data and the real value of the data as the stability criterion of the data fusion method, and carries out the simulation test of the data fusion of the three redundancy and multiple source data. The test results show that the weighted least square method is used in the data fusion. The performance is stable, which can replace the commonly used moment estimation fusion and median fusion, and improve the accuracy of the fused data.

关 键 词：数据融合 矩估计 模糊关系 加权最小二乘法 

分 类 号：TL363[核科学技术—核技术及应用]