Problems of application of measurement system analysis (MSA) in metallurgical production

P. Klaput, D. Vykydal, F. Tošenovský, J. Plura, P. Halfarová, VŠB – Technical University of Ostrava, Faculty of Metallurgy and Materials Engineering, Ostrava, Czech Republic This paper lists the most fundamental problems related to the application of measurement system analysis (MSA) in metallurgical production and outlines ways of solving them. Based on the real measurements it was found, that the width of the confidence interval constructed for the value of combined gage repeatability and reproducibility (GRR) can be reduced (and thus the reliability of the GRR value can be increased) more by raising the number of trials than by increasing the number of samples. The basic assumption for the use of analysis of variance (constant variance and the occurrence of outliers) can be verified by using the proposed multiple box and whisker plot.