Statistical process control performance characterization under field conditions

Performance characterization of SPC technology is necessary in order to assess the impact of potential SPC strategies and actions.

In this research a simulation-based tool (SPClab) is defined, designed and developed that can be used to study SPC options and its performance characteristics, considering both iid and non-iid data streams with and without step shifts in the data stream. The step shifts can be in location and/or in dispersion.

The tool has three modules (1) simulation module, (2) performance module and (3) Output/report module and is developed using Borland C++ version 3.1. The number of programming lines needed to complete the tool is 20,019. The tool was tested and demonstrated in the cases of both iid and cyclical response data streams. The results from the simulation agree closely with those of theoretical values and other investigations found in the literature for the normally distributed iid case, indicating the tools validity. The tool, SPClab, was also used to demonstrate how to assess the impact of different SPC strategies and actions by considering different sampling scheme. The adverse consequences of applying SPC models inappropriately to non-iid data streams were illustrated. An appropriate physical-covariate based modeling approach is also introduced