基于相依区间值数据的EWMA FIMSE控制图  

An EWMA FIMSE control chart based on dependent interval-valued data

作　　者：王美涵 陈培乐 潘晓映 施建华 WANG Meihan;CHEN Peile;PAN Xiaoying;SHI Jianhua(College of Mathematics and Statistics,Minnan Normal University,Zhangzhou,Fujian 363000,China;Fujian Key Laboratory of Granular Computing and Applications,Zhangzhou,Fujian 363000,China;Fujian Key Laboratory of Data Science and Statistics,Zhangzhou,Fujian 363000,China;Fujian Institute of Meteorological Big Data,Zhangzhou,Fujian 363000,China)

机构地区：[1]闽南师范大学数学与统计学院,福建漳州363000 [2]福建省粒计算及其应用重点实验室,福建漳州363000 [3]福建省数据科学与统计重点实验室,福建漳州363000 [4]数字福建气象大数据研究所,福建漳州363000

出　　处：《闽南师范大学学报（自然科学版）》2021年第3期1-7,共7页Journal of Minnan Normal University：Natural Science

基　　金：国家社会科学基金西部项目(20XTJ003)。

摘　　要：对于具有相依性的数据,指数加权移动平均(EWMA)方法是控制图领域中的实用方法 .其中,指数加权移动平均均方误差(EWMA MSE)控制图对相依单一值数据的监控性能较好.随着测量技术的发展,往往会监测到相依区间值数据,传统的方法只能将其转化为单一值数据再计算,这样会造成信息丢失.为此,提出指数加权移动平均模糊区间均方误差(EWMA FIMSE)控制图,通过数值模拟和漳州市一氧化碳浓度数据的实证分析,证实它可以比传统的控制图更快地监测到过程的异常波动.For dependent data,exponentially weighted moving average(EWMA)is a practical method in the field of control charts.Many experts have carried out researches on this basis.Among them,the exponentially weighted moving mean square error(EWMA MSE)control chart has a better monitoring performance for dependent single-valued data.However,with the development of measurement technology,we often detect the dependent interval-valued data,and the traditional method can only convert it into a single value data for calculation,which will cause information loss.Therefore,this paper proposes an exponentially weighted moving average fuzzy interval mean square error(EWMA FIMSE)control chart.Through numerical simulation and empirical analysis of carbon monoxide concentration data in Zhangzhou,it is proved that the control chart can detect the abnormal fluctuation faster than the traditional control chart.

关 键 词：指数加权移动平均 模糊区间 均方误差控制图 相依区间值数据 

分 类 号：O213[理学—概率论与数理统计]