Measurement System Analysis Applied to AISI 12L14 Steel Turning  
Author R.S. Peruchi


Co-Author(s) P.P. Balestrassi; A.P. Paiva; R. Sawhney; E.M. Anda; S.A. Niknam


Abstract The aim of this paper is to explore how measurement systems having correlated characteristics are analyzed through studies of gage repeatability and reproducibility (GR&R). Moreover, to increase the reliability of the results, the multivariate evaluation index was estimated using four weighting strategies based on arithmetic and geometric means. This GR&R study considered 12 parts, 3 operators, 4 replicates, and 5 responses (Ra, Ry, Rz, Rq and Rt). The data set has a correlation structure that determines 84.5% of explanation for the first pair of eigenvalues extracted from total variation matrix. The weighted indexes are compared with univariate and multivariate indexes in the literature. One of the more significant findings to emerge from this study is that the univariate approach is unable to provide a single assessment to the multivariate measurement system. It was also shown that the weighted strategies in this paper were more accurate in estimating the evaluation index for multivariate GR&R studies.


Keywords measurement system analysis, repeatability and reproducibility, multivariate analysis of variance, roughness
    Article #:  19213
Proceedings of the 19th ISSAT International Conference on Reliability and Quality in Design
August 5-7, 2013 - Honolulu, Hawaii, U.S.A.