基于加权似然比检验的自适应EWMA控制图设计  

Design of Adaptive EWMA Control Chart Based on Weighted Likelihood Ratio Test

作　　者：贡平邺 郑冰静 郭宝才[1,2] GONG Pingye;ZHENG Bingjing;GUO Baocai(School of Statistics and Mathematics,Zhejiang Gongshang University,Hangzhou 310018;Collaborative Innovation Center of Statistical Data Engineering Technology and Application,Zhejiang Gongshang University,Hangzhou 310018)

机构地区：[1]浙江工商大学统计与数学学院,杭州310018 [2]浙江工商大学统计数据工程技术与应用协同创新中心,杭州310018

出　　处：《系统科学与数学》2023年第6期1587-1611,共25页Journal of Systems Science and Mathematical Sciences

基　　金：国家社会科学基金(18BTJ037)资助课题。

摘　　要：自适应控制图设计是统计过程控制研究领域中的一个热点问题,也受到实际从业人员的广泛关注.文章首先将加权似然比检验的思想引入自适应指数加权移动平均(AEWMA)控制图的设计中,提出了一种联合监控过程均值和方差的AEWMA控制图(称为AWLRT控制图),并基于链长的均值和标准差研究了光滑参数对AWLRT控制图的影响.随后,在监控过程均值或(和)方差上,对所提AWLRT控制图与已有控制图进行了性能比较.结果显示,所提AWLRT控制图的表现一致最优.最后通过一个实例来说明所提AWLRT控制图在实际中的应用.Adaptive control charts are a hot research topic in Statistical Process Control,and widely concerned by practitioners.This paper first introduces the idea of the weighted likelihood ratio test into the design of adaptive exponentially weighted moving average(AEWMA) control charts and develops an AEWMA chart for joint monitoring the process mean and variance(denoted by the AWLRT chart).The effect of the smoothing parameter on the proposed AWLRT chart is investigated in terms of the mean and standard deviation of run length.Subsequently,the out-of-control performances of the AWLRT and other existing control charts for monitoring the process mean or(and) variance are compared.The results show that the proposed AWLRT chart has consistently optimal performances.Finally,the application of the proposed AWLRT chart is illustrated by a real example.

关 键 词：自适应控制图 加权似然比检验 联合监控 权重函数 

分 类 号：O213[理学—概率论与数理统计]