摘要
结合随机过程均值偏移的概率分布和田口质量损失函数,研究了非正态EWMA控制图的优化设计问题。利用Burr分布近似各种非正态分布,使田口质量损失函数的总平均值最小进而确定参数的最优值,对比研究表明该方法设计的非正态EWMA(ML-EWMA)控制图明显优于统计方法设计的非正态EWMA控制图,具有较小的质量损失。
The optimization design of Exponential Weighted Moving Average (EWMA) control chart for non-normal data is addressed. A method that combines Taguchi's loss function and the probability distribution of the random process mean shift is proposed. By using the Burr distribution to approximate various non-normal distributions, the parameter of the EWMA control chart for non-normal data is determined through minimizing the overall mean value (ML) of Taguchi's loss function. Comparative studies show that the proposed ML-EWMA control chart for non-normal data is significantly superior to the statistical EWMA control chart for non-normal data in terms of the overall loss of ML.
出处
《工业工程》
北大核心
2011年第5期75-78,共4页
Industrial Engineering Journal
基金
国家自然科学基金资助项目(70771102
71002073)
航空科学基金资助项目(2009ZG55019
2008ZG55019)
河南省高校科技创新人才支持计划项目(2010HASTIT024)
关键词
EWMA控制图
非正态分布
田口质量损失函数
随机过程均值偏移
Exponential Weighted Moving Average (EWMA) control chart
non-normal distribution
Taguchi's loss function
random process mean shift