Dependent Mixed and Mixed Repetitive Sampling Plans for Linear Profiles

Fu Kwun Wang*, Yeneneh Tamirat, Shih Che Lo, Muhammad Aslam

*此作品的通信作者

研究成果: 期刊稿件文章同行評審

12 引文 斯高帕斯(Scopus)

摘要

In this paper, we present two new dependent mixed sampling plans and a mixed repetitive sampling plan based on the process yield index for linear profiles. A mixed sampling plan includes two stages; the first stage is a combined test by variables and by attributes, and the second stage is tested by attributes only. The first plan is based on the traditional mixed sampling scheme without marginal quality, and the second plan is based on the modified mixed sampling scheme with marginal quality. If a lot is very bad, the probability it can be rejected with the small initial sample is higher for dependent mixed sampling with marginal quality. We compare dependent mixed plans with other types of double sampling plans; the former outperforms the others with respect to average sample number. Additionally, the number of profiles required in the first stage is much smaller than in the second stage. When the inspection is costly and destructive, a mixed repetitive sampling plan includes one stage that combines the inspection by attributes and by variables and allows resampling in some conditions. We compare the mixed repetitive sampling plan with the repetitive sampling plans by attributes and by variables. The probability of acceptance using the mixed repetitive sampling plan performs better than the repetitive sampling plans by attributes and by variables. Three examples are used to illustrate the proposed methods.

原文英語
頁(從 - 到)1669-1683
頁數15
期刊Quality and Reliability Engineering International
33
發行號8
DOIs
出版狀態已出版 - 12 2017
對外發佈

文獻附註

Publisher Copyright:
Copyright © 2017 John Wiley & Sons, Ltd.

指紋

深入研究「Dependent Mixed and Mixed Repetitive Sampling Plans for Linear Profiles」主題。共同形成了獨特的指紋。

引用此