Enhancement of measurement capability for precision manufacturing processes using an attribute gauge system

Abstract

This research discusses precision manufacturing processes that have near-zero-defect manufacturing environments with occasional non-conformities in some samples when random shocks arise. Repeatability variance and reproducibility variance are commonly used to assess measurement precision, but they may fail to estimate measurement parameters in precision manufacturing processes. This paper proposes a novel attribute gauge system that consists of five modules. The measurement parameters estimation module derives equations for the random shock probability and measurement parameters using the Expectation–Maximization algorithm and zero-inflated Poisson model. The variance between measurement systems module derives the equation of variance within operators and gauges from the laboratory component of the bias. The repeatability variance module derives a repeatability measurement equation and the reproducibility variance module derives the reproducibility measurement equation using the ASTM E691 standard. Finally, the measurement system acceptability criteria module derives a measurement capability index and assesses measurement precision based on the ASTM F1469 standard. A thin-film transistor liquid crystal display manufacturing case study is used to illustrate the process and potential of the proposed system. Findings can be used as a reference for evaluating measurement systems with attribute data. Analytical results are also useful to quality practitioners attempting to improve measurement system effectiveness.