| 多元自相关过程的残差T2控制图 |
| |
| 引用本文： | 孙静,杨穆尔. 多元自相关过程的残差T2控制图[J]. 清华大学学报(自然科学版), 2007, 47(12): 2184-2187 |
| |
| 作者姓名： | 孙静 杨穆尔 |
| |
| 作者单位： | 清华大学经济管理学院,现代管理研究中心,教育部人文社会科学重点研究基地,北京,100084;清华大学经济管理学院,管理科学与工程系,北京,100084;清华大学经济管理学院,管理科学与工程系,北京,100084 |
| |
| 摘 要： | 为了满足传统的统计过程控制理论中统计量彼此独立的基本假设,研究了多元自相关过程的残差T2控制图的控制方法及其控制性能。针对一般多元自相关过程,在参数已知的条件下,讨论了多元自相关过程的残差T2控制图,给出多元自相关过程偏移量的定义。通过M on te C arlo模拟,得出该控制图在不同偏移量时的平均链长,在残差T2控制图的适用范围内给出平均链长与偏移量之间的经验公式。结果表明,残差T2控制图可以有效控制出现大偏移的多元自相关过程。
|
| 关 键 词： | 统计过程控制 多元自相关过程 T2控制图 |
| 文章编号： | 1000-0054(2007)12-2184-04 |
| 修稿时间： | 2006-09-18 |
Residual-based T2 control chart for monitoring multivariate auto-correlated processes |
| |
| SUN Jing,YANG Muer. Residual-based T2 control chart for monitoring multivariate auto-correlated processes[J]. Journal of Tsinghua University(Science and Technology), 2007, 47(12): 2184-2187 |
| |
| Authors: | SUN Jing YANG Muer |
| |
| Abstract: | Traditional statistical process control(SPC) techniques are based on the assumption that the statistical data are independent,but such a fundamental condition cannot be satisfied in auto-correlated and cross-correlated multivariate processes.This paper presented a residual-based T2 control chart for general multivariate auto-correlated processes with known parameters,with an expression for the mean shifts of multivariate auto-correlated processes.Average run lengths with various mean shifts were obtained using Monte Carlo simulations.The average run lengths were related to the mean shifts for a residual-based T2 control chart.The results show that the residual-based T2 control chart can effectively monitor multivariate auto-correlated processes even if the shifts are not extremely small. |
| |
| Keywords: | statistical process control multivariate auto-correlated processes T2 control chart |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
