KLAPUT Pavel VŠB-Technická univerzita Ostrava

Spoluautoři PLURA Jiří

The success of companies at the market is for several decades depended on the quality of the provided products and services. This quality cannot be achieved without functioning quality management system. ISO/TS 16949 standard, which includes the requirements for quality management system in the automotive industry whose suppliers are mostly metallurgical companies in Chapter 7.6.1 requires, that statistical studies must be performed in order to analyze the variability of all types of measurement and testing systems. The acceptability of the measurement system is currently assessed on the results of combined gage repeatability and reproducibility study (GRR). The most used methods for evaluation of GRR study are average and range method (A&R) and analysis of variance (ANOVA). The results of GRR analysis can be considerably influenced by interactions between parts and appraisers. Less used ANOVA which requires using of special software and its numerical results are difficult to interpret, is able to evaluate these interactions. More used A&R method, which use is much simpler, is not capable to evaluate these interactions. The occurrence of interactions can significantly affect the results of gage repeatability and reproducibility study and therefore also acceptability of the measurement system. For this reason it is necessary the influence of these interactions correctly evaluate and recognize. The aim of this paper is to analyze the possibility of identification of these interactions using appropriate graphical tools of measurement system analysis. It will be also analyzed the ability of these graphical tools to reveal not only influence, but also the location of these interactions.

Zpět