A CUSUM CONTROL SCHEME FOR CLUSTERED DEFECTS

ABSTRACT

Control charts are widely used in statistical process control. A c-chart is often used to monitor product defects. Most applications of the c chart assume that Poisson distribution is the correct probability model underlying the process. When defects tend to occur in clusters, then it is likely that the Poisson model is inappropriate. In this paper, we propose a CUSUM control procedure to monitor the product defects modeled by the Neyman's type-A distribution. A numerical example is given to illustrate the operation of the proposed method. An extensive comparison shows that the proposed method can perform better than traditional c chart.

Keywords:

• clustered defects
• CUSUM control chart
• average run length
• statistical process control