Improving product quality by multiple inspections: Prior and posterior planning of serial inspection procedures

Abstract

In many practical situations, a complex product is inspected more than once in a sequential manner to further improve its quality. In this paper, the problem of designing the multiple inspection plan via a Bayesian method is considered. As a prior distribution in the Bayesian model, a negative binomial distribution that has many desirable properties is used. Two types of design problem are considered. In prior planning of a serial inspection procedure, the number of inspections necessary to achieve a desired level of quality must be determined prior to starting the inspection process. In posterior planning, the inspection process can be terminated if the product meets a given level of quality. In both cases, the improved level of quality is measured in this paper either by the expected number of undetected errors still remaining in the product or by the probability of no undetected errors in the product.

Keywords:

• Inspection error
• quality control
• screening
• Bayesian model

Acknowledgements

The research was partially funded by a two-year grant from the Research Competitiveness Subprogram of the Board of Regents Support Fund and by the James C. and Cherie H. Flores University Professorship of MBA Studies at Louisiana State University.

[Supplementary materials are available for this article. Go to the publisher's online edition of IIE Transactions for the following free supplemental resource: Appendix]