| 多变异源过程控制与指数加权移动平均控制图的应用研究 |
| |
| 引用本文： | 何桢,董延峰,张敏.多变异源过程控制与指数加权移动平均控制图的应用研究[J].机械科学与技术(西安),2008,27(11). |
| |
| 作者姓名： | 何桢 董延峰 张敏 |
| |
| 作者单位： | 天津大学管理学院,天津300072 |
| |
| 摘 要： | 改进休哈特控制图能够解决多变异源过程控制虚发警报错误过高的问题,但是对均值偏移的检出力过低。本文研究的目的是将指数加权移动平均(EWMA)控制图用于多变异源过程控制,提高控制图对均值偏移的检出力。通过对多个变异源的方差分析,基于对部分方差估计,给出指数加权移动平均控制图在多变异源过程控制的应用方法。通过计算指数加权移动平均控制图的平均运行长度,并与改进的休哈特控制图作比较,证明指数加权移动平均控制图在检测多变异源过程均值偏移时检出力有较大提高,应用实例的结果表明当偏移量小于1σ时,检出力能提高10倍以上。
|
| 关 键 词： | 方差分析 方差估计 控制图 指数加权移动平均:检出力 |
On Process Control for Multiple Sources of Variation Using Exponentially Weighted Moving Average Control Charts |
| |
| Abstract: | Improved Shewhart control charts can reduce the false alarm probability for process that exhibit multiple sources of variation,but its power is not satisfactory for the shift of process average.In this paper,we use exponentially weighted moving average(EWMA) control charts for process control of multiple sources of variation to improve the power to detect changes in the process average.Based on the statistical analysis of variance and variance components estimate for each source of variation,we present process control methods with EWMA control charts.Comparison of the average run length of the improved Shewhart control charts with that of the EWMA control charts shows that the power of EWMA control charts is more sensitive than the improved Shewhart control charts.In the example,the power of EWMA control charts achieves 10 times more than the improved Shewhart control charts when the shift of process average is less than 1σ. |
| |
| Keywords: | analysis of variance variance component estimate control chart EWMA power |
| 本文献已被 维普 等数据库收录！ |
|
