摘要
本文研究多变量自相关过程协方差矩阵的质量监控问题.针对服从VAR(1)模型的多变量自相关过程,基于残差分析思想,将多变量指数加权移动平均(MEWMA)控制图用于对过程的监控.首先对残差MEWMA控制图统计量进行了推导,其次采用MonteCarlo仿真的方法,以平均运行链长为评价准则对残差MEWMA控制图的监控效果进行了分析.仿真结果表明,残差MEWMA控制图具有较好的监控效果.
In this paper, the quality control problem for monitoring covariance matrix of multivariate auto correlated processes is discussed. Based on the residual-analyzing theory, it applies multivariate exponen- tially weighted moving average （MEWMA） control chart to monitor the VAR（1） multivariate auto correlated processes. Firstly, statistics of residual-based MEWMA control chart are deduced. Then, average run length analysis of control charts is presented by Monte Carlo simulation. From the simulation analysis, it can be concluded that an excellent performance in detecting shifts in the covariance matrix with different degrees in different directions can be obtained by the residual-based MEWMA control chart.
出处
《系统工程学报》
CSCD
北大核心
2012年第2期279-286,共8页
Journal of Systems Engineering
基金
国家自然科学基金重点资助项目(70931002)
南京理工大学自主科研资助项目(AE88831)
中国博士后科学基金资助项目(2011M500928)
