Premium
A Situationally Sample‐Size‐Adjusted Sampling Scheme Based on Process Yield Verification
Author(s) -
Wu ChienWei,
Shu MingHung,
Liu ShihWen
Publication year - 2017
Publication title -
quality and reliability engineering international
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.913
H-Index - 62
eISSN - 1099-1638
pISSN - 0748-8017
DOI - 10.1002/qre.1990
Subject(s) - prosperity , yield (engineering) , quality (philosophy) , sampling (signal processing) , mathematics , sample (material) , computer science , statistics , reliability engineering , operations management , engineering , law , chemistry , materials science , philosophy , epistemology , filter (signal processing) , chromatography , computer vision , political science , metallurgy
This paper is motivated by Food Safety Modernization Act, signed into law by President Obama on Jan. 4, 2011, after several outbreaks of tainted foods have cost human health and contracted food‐industry prosperity over the past decade. It develops a situationally sample‐size‐adjusted procedure, called a tightened–normal–tightened (TNT) sampling strategy, on the basis of yield‐index ( S pk ) verification of the production process, whose measurements, garnered from a key quality characteristic with bilateral specification limits, follow a normal distribution. In this paper, we firstly describe the sampling procedure of the S pk ‐ TNT( n T , n N , k ) inspection scheme whose sets of parameters include sample sizes for the tightened inspection ( nT ) and normal inspection ( n N ), and the critical value ( k ). Those parameters are determined from the joint solution of two nonlinear inequalities complying with the tolerable vendor's risk, buyer's risk, the desired acceptable quality level (AQL) and limiting quality level (LQL). Then, the proposed S pk ‐ TNT( n T , n N , k ) schemes for several inspection standards, widely utilized in practice, are delineated, and their functioning behaviors and propensities are further investigated. Moreover, we compare the S pk ‐ TNT( n T , n N , k ) strategy with two unadjusted inspection schemes, S pk ‐tightened, S pk ‐ T( n T , k ), and S pk ‐normal, S pk ‐ N( n N , k ), to illustrate its inspection flexibility and efficiency in real applications. Finally, implementing with a vendor–buyer contract agreement using the S pk ‐ TNT( n T , n N , k ) sampling plan, a company inspecting the submitted universal‐serial‐bus (USB) connectors demonstrates the applicability of our proposed methodologies. Copyright © 2016 John Wiley & Sons, Ltd.