Developing A Cause Selecting Control Chart for Monitoring Two–Stage Processes with Poisson Quality Characteristic

Nowadays, most of products are the results of different dependent process steps. Due to the cascade property in most of these processes, using the traditional control charts for monitoring these processes is not suitable. To solve this problem, Cause selecting Charts (CSCs) are developed to monitor multistage processes. These control charts have usually been developed when quality characteristics follow normal distribution. However, sometimes other distributions rather than normal can characterize quality characteristics. In this paper a cause selecting control chart based on the standardized residuals of a generalized linear model is developed to monitor a two-stage process with a Poisson distributed quality characteristic in the second stage. The performance of the proposed control chart is investigated in terms of average run length criterion under two different link functions in comparison with the best method in the literature. The results show the better performance of the proposed control chart in detecting increasing shifts. Finally, the performance of the proposed method in practice is evaluated through a case and acceptable results are obtained.