An Effective Method to Handle Measurement Uncertainty in Conformance Testing Procedures

摘要

This paper deals with a new design criterion aimed at keeping the decisional risks associated to conformance testing procedures below given target values. The proposed approach is based on two closed-form analytical expressions describing the dependence of both the Consumer''s Risk (CR) and the Producer''s Risk (PR) on three essential parameters for conformance testing, i.e. the process capability index (Cp), the Test Uncertainty Ratio (TUR) and the Gauging to Tolerance interval Ratio (GTR). Such approximate expressions are not only very accurate, but also much less computationally demanding than the implicit, integration-based expressions of CR and PR. This assures faster results and less numerical problems when the values of TUR and GTR meeting the wanted CR and PR requirements are determined.