A multivariate GR&R approach to variability evaluation of measuring instruments in resistance spot welding process

The resistance spot welding is a promising and widely used method for joining mechanical structures, being applicable in various industrial sectors and constantly improved in order to guarantee a product with high reliability and mechanical quality. This paper aims to verify the variability attributed to different measuring instruments for this process, considering the multivariate nature of its critical-to-quality characteristics. In order to verify the degree of reliability of the results in this process, the multivariate repeatability and reproducibility study based on the weighted principal components method was used, considering two different responses. Design of experiments methodology was used for collecting the data, in order to obtain a real representation of the process amplitude. The measurements were evaluated by image analyzer and conventional metrology mechanical instruments. The results showed a better precision of the metrics performed by the image analyzer, where the measurements presented lower variability, while the mechanical instruments showed greater uncertainties for the measured values.