Binomial CUSUM chart with curtailment

被引：17

作者：

Haridy, Salah ^{[1
,2
]}

Wu, Zhang ^{[1
]}

Chen, Songlin ^{[1
]}

Knoth, Sven ^{[3
]}

机构：

[1] Nanyang Technol Univ, Sch Mech & Aerosp Engn, Singapore 639798, Singapore

[2] Northeastern Univ, Dept Mech & Ind Engn, Boston, MA 02115 USA

[3] Helmut Schmidt Univ, Dept Econ & Social Sci, Hamburg, Germany

来源：

INTERNATIONAL JOURNAL OF PRODUCTION RESEARCH | 2014年 / 52卷 / 15期

关键词：

quality control; statistical process control; control chart; CUSUM chart; curtailment; OPTIMIZATION DESIGN; ECONOMIC DESIGN; SHIFTS; PROPORTION;

D O I：

10.1080/00207543.2014.882026

中图分类号：

T [工业技术];

学科分类号：

08 ;

摘要：

The binomial cumulative sum (CUSUM) chart has been widely used to monitor the fraction nonconforming (p) of a process. It is a powerful procedure for detecting small and moderate p shifts. This article proposes a binomial CUSUM control chart using curtailment technique (Curt_CUSUM chart in short). The new chart is able to improve the overall detection effectiveness while holding the false alarm rate at a specified level. The results of the comparative studies show that, on average, the Curt_CUSUM chart is more effective than the CUSUM chart without curtailment by 30%, in terms of Average Number of Defectives, under different circumstances. The Curt_CUSUM chart can be applied to a 100% inspection as well as a general random sampling inspection.

引用

页码：4646 / 4659

页数：14

共 50 条

[1] Control charts for health care monitoring under overdispersion [J].