Design of Optimal Exponential CUSUM Control Charts
作者:
GanF. F.,
期刊:
Journal of Quality Technology
(Taylor Available online 1994)
卷期:
Volume 26,
issue 2
页码: 109-124
ISSN:0022-4065
年代: 1994
DOI:10.1080/00224065.1994.11979511
出版商: Taylor&Francis
关键词: Average Run Length;Cumulative Sum Control Charts;Exponential Distribution;Poisson Process
数据来源: Taylor
摘要:
Control charts are needed in many manufacturing processes for monitoring the rate of occurrences of events such as nonconforming items. This rate can usually be modeled by the interarrival times for a homogeneous Poisson process, which are independent and identically distributed exponential random variables. The monitoring of the exponential mean provides an alternative method for monitoring the rate of occurrences of events. An extensive numerical study indicates that the reference valuekobtained from the sequential probability ratio test is the optimal chart parameterkfor the exponential CUSUM chart. Graphs of chart parameters are given and these graphs can be used to easily obtain the chart parameters of an optimal exponential CUSUM chart. The relative performance of exponential CUSUM and Poisson CUSUM charts for monitoring the rate of occurrences of events is also assessed.
点击下载:
PDF (1052KB)
返 回