Abstract

In the case of the complex multi-factorial processes, such as electrostatic separation of granular materials, the variability of the results is often deplored by the users. Attempts have been made to independently supervise each factor by using Shewhart control charts, which proved to be not very effective in detecting small shifts in process response. The present paper aimed at demonstrating that the effectiveness of the statistic process control can be improved by using CUSUM (cumulative sum) charts. The experiments were carried out with a mixture of bronze and aluminum particles (size range: 1 to 2 mm), using a plate-type electrostatic separator. The mobile average Shewart and CUSUM charts were established, based on 20 electrostatic separation tests performed under optimal operating conditions. An out-of-control situation was simulated and the response of the process was analyzed with both types of charts. The small shift in process response was detected only on the CUSUM chart.

Full Text
Paper version not known

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call