Assessing Process Capability: A Case Study

Abstract

Research efforts in the area of process capability have largely been devoted to finding a better process capability index (PCI) and to a lesser extent on the stochastic behavior of the estimated PCIs [1], [2]. Much of this development has gone unused for many reasons including a) a plethora of indices, b) interpretation, c) software support, d) standards and e) dissemination. The addition of the indices appears to have had little impact on the practitioners. Cp and Cpk (including Cpl and Cpu) [3] continue to be the most heavily used indices with Cpm [4] and Cpmk [5] occurring occasionally. The addition of stochastic assessments for estimated PCIs is a positive development, however statistical developments have frequently lacked background knowledge and implementation ease, hindering use by practitioners. A case study from the printing industry will be used to draw attention to areas impacting the practical use of PCIs. Concepts including a) establishing effective tolerance limits, b) the ongoing assessment and interpretation of PCIs and c) ongoing improvement will be presented. We will use the case to a) illustrate a strategy followed by practitioners using PCIs as a quality management tool, b) to draw attention to gaps that exist in the practical use of PCIs, c) to illustrate how some of these difficulties were overcome and d) to highlight research areas in the practical use of PCIs. A variety of quality tools including flowcharts/process documentation, control charts, process capability indices and experimental design are illustrated throughout the manuscript. Data used in the analyses has been included where permitted. Although drawn from the printing industry, the tools used, lessons learned and generic achievements are applicable to the wider area of product design and manufacturing, particularly where customers have unique requirements for a common product.