A Transformation Technique in Designing Multi-Attributes C Control Charts

In a production process, when the quality of a product depends on more than one characteristic, multivariate quality control techniques are used. Although multivariate statistical process control is receiving increased attention in the literature, little work has been done to deal with multi-attribute processes. In this paper, we develop a new methodology to monitor multi-attribute processes in which the defects counts are important and different types of defects are dependent random variables. In order to do this, based on the symmetric square root transformation concept, first we transform multi-attribute data such that the correlation between variables either vanishes or becomes very small. Then, by simulation and bisection method, we find the symmetric control limits and form a symmetric rectangular region for control. In simulation studies, we present some numerical examples to illustrate the proposed method and to evaluate and compare its performance to the ones of the existing method.
Key words
Multivariate C control charts, process monitoring, optimal control limits, symmetric control charts, symmetric square root