from the conferences organized by TANGER Ltd.
The paper deals with the evaluation of experimental data on samples of steel wire. The main attention is aimed at the R&R study, which was a part of the experiment for studying effects of three factors on various mechanical properties of drawn wires. The experiment was performed in the wire drawing laboratory at VŠB-Technical University of Ostrava. Samples of wire were tested for tensile, torsion and bending fatigue. Several operators took part in the experiment. Due to the destructive character of tests, a nested design was considered. The R&R study revealed that the mechanical properties along the wire length were not uniform and that the key assumption of the destructive-test analysis was not met. Since the employed scheme of assigning drawn wires to operators led to confounding of effects and made the further analysis dubious, another arrangement for this type of experiment is suggested in the paper. Apart from the R&R analysis, statistical methods of evaluation that take the real experimental pattern into account are discussed. The method based on means is applied and significant effects are identified.
Keywords: destructive tests, nested design, R&R study, ANOVA© This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.