摘要
本文将以AR(2)过程为例,将CUSUM和EWMA控制图的统计量相整合,提出改进MEC和MCE两种控制图,以平均运行链长(ARL)和额外平方损失(EQL)做为评价效率的重要指标。通过仿真分析去验证,新的控制图对于自相关模型发生均值漂移具有较好的检测效率.
In this paper,the AR(2) process is taken as an example,the statistics of CUSUM and EWMA control charts are integrated,and two control charts,MEC and MCE,are proposed.The average run length(ARL) and extra quadratic loss(EQL) are used as important index to evaluate the efficiency.Through the simulation analysis to verify,the new control chart has a good detection efficiency for the mean shift of the autocorrelation model.
作者
魏兴龙
宋向东
WEI Xing-long;SONG Xiang-dong(Science College, Yanshan University, Qinhuangdao 066004, Chin)
出处
《价值工程》
2018年第3期192-195,共4页
Value Engineering
关键词
残差
平均运行链长
自相关
漂移
MEC
MCE
统计过程控制
residual
average run length(ARL)
autoregressive
shift
Mixed EWMA-CUSUM
Mixed CUSUM-EWMA
statistical process control