Reducing sampling costs in multivariate SPC with a double-dimension T 2 control chart

Abstract:

In some real situations there is the need of controlling p variables of a multivariate process, where p<inf>1</inf> out of these p variables are easy and inexpensive to monitor, while the p<inf>2</inf>=p-p<inf>1</inf> remaining variables are difficult and/or expensive to measure. However, this set of p <inf>2</inf> variables is important to quickly detect the process shifts. This paper develops a control chart based on the T² statistic where normally only the set of p<inf>1</inf> variables is monitored, and only when the T² value falls in a warning area the rest of variables (p <inf>2</inf>) are measured and combined with the sample values from the p <inf>1</inf> variables, in order to obtain a new T² statistic. This new chart is the double dimension T² (DDT²) control chart. The ARL of the DDT² chart is obtained and the chart's parameters are optimized using genetic algorithms with the aim of maximizing the performance in detecting a given process shift. The optimized DDT² chart is compared against the standard T² chart when all the variables are monitored. The results show that the DDT² clearly outperforms T ² chart in terms of cost, and in some cases even detects process shifts faster than the latter. In addition, friendly software has been developed with the objective of promoting the real application of this new control chart. © 2013 Elsevier B.V. All rights reserved.

Año de publicación:

2013

Keywords:

• Double sampling
• Cost sampling
• T control chart 2
• T2 control chart

Fuente:

scopus

google