一种线性轮廓数据的在线监控方法  

A Method of Online Monitoring Linear Profile Data

作　　者：齐德全 陈实 QI Dequan;CHEN Shi(School of Mathematics and Statistics,Changchun University of Science and Technology,Changchun 130022)

机构地区：[1]长春理工大学数学与统计学院,长春130022

出　　处：《长春理工大学学报（自然科学版）》2022年第4期129-134,共6页Journal of Changchun University of Science and Technology(Natural Science Edition)

基　　金：吉林省教育厅项目(JJKH20210809KJ)。

摘　　要：在线监控线性轮廓数据时,往往发生的漂移大小是未知的。常用的多元指数加权滑动平均控制图(MEWMA)的监控效果受到光滑参数的影响。参数大对大漂移较有效,参数小对小漂移较有效。为了解决这一问题,提出了一种自适应的MEWMA控制图,将光滑参数定义为监控时间的函数,对线性轮廓数据的在线监控方法展开了研究。该方法能针对漂移的大小,有效地选择合适的光滑参数,从而加快失控状态下的报警速度。通过蒙特卡洛模拟和案例分析对所提方法进行检验。与WLRT、MEWMA和KMW控制图进行比较,该控制图的监控性能更好。When linear profile data is monitored online,t he size of the shift is often unknown.The monitoring effect of the commonly used multivariate exponentially weighted moving average control chart(MEWMA)is affected by the smoothing parameter.Large parameters are effective for large shifts;and small parameters are effective for small shifts.In order to solve this problem,an adaptive MEWMA control chart is proposed;the smoothing parameter is defined as a function of monitoring time;and the online monitoring method of linear profile data is studied.This method can effectively select the appropriate smooth parameters according to the size of the shift,so as to accelerate the alarm speed in the out-of-control state.The proposed method is tested by Monte Carlo simulation and case analysis.Compared with WLRT,MEWMA and KMW control charts,t his control chart has better monitoring performance.

关 键 词：自适应 多元指数加权移动平均 简单线性曲线 统计过程控制 

分 类 号：O212[理学—概率论与数理统计] O213[理学—数学]