Application of a binomial cusum control chart to monitor one drinking water indicator

Abstract

The aim of this study is to analyze the use of a binomial cumulative sum chart (CUSUM) to monitor the presence of total coliforms, biological indicators of quality of water supplies in water treatment processes. The sample series were monthly taken from a water treatment plant and were analyzed from 2007 to 2009. The statistical treatment of the data was performed using GNU R, and routines were created for the approximation of the upper limit of the binomial CUSUM chart. Furthermore, a comparative study was conducted to investigate whether there is a significant difference in sensitivity between the use of CUSUM and the traditional Shewhart chart, the most commonly used chart in process monitoring. The results obtained demonstrate that this study was essential for making the right choice in selecting a chart for the statistical analysis of this process.

Keywords

• Controle estatístico de processos. CUSUM binomial. Coliformes Totais.