Optimal design of pre-control plans

Abstract

[EN] Pre-control is a quality tool for quick set-up approvals, especially used in short-run processes. It is based on specifications instead of on the natural variability of the process and uses cumulative counts in order to yield a conclusion. Its main drawbacks are a high false alarm rate and a low power to detect process deviations, under certain circumstances. These issues can be addressed by making the technique more flexible, as shown in previous works. In this paper, we introduce a Mathematical Programming approach in order to optimally determine the value of the pre-control parameters, so that it can meet the user s requirements while minimizing the sample size of the technique as much as possible. We propose and develop a mathematical model for optimal pre-control and perform some numerical experiments in order to show its effectiveness.