Control Charts with Variable Dimension for Linear Combination of Poisson Variables

Control Charts with Variable Dimension for Linear Combination of Poisson Variables

0.00 Avg rating0 Votes
Article ID: iaor20162885
Volume: 32
Issue: 5
Start Page Number: 1741
End Page Number: 1755
Publication Date: Jul 2016
Journal: Quality and Reliability Engineering International
Authors: , ,
Keywords: control, heuristics: genetic algorithms, optimization, markov processes
Abstract:

This article analyzes the simultaneous control of several correlated Poisson variables by using the Variable Dimension Linear Combination of Poisson Variables (VDLCP) control chart, which is a variable dimension version of the LCP chart. This control chart uses as test statistic, the linear combination of correlated Poisson variables in an adaptive way, i.e. it monitors either p1 or p variables (p1 < p) depending on the last statistic value. To analyze the performance of this chart, we have developed software that finds the best parameters, optimizing the out‐of‐control average run length (ARL) for a shift that the practitioner wishes to detect as quickly as possible, restricted to a fixed value for in‐control ARL. Markov chains and genetic algorithms were used in developing this software. The results show performance improvement compared to the LCP chart.

Reviews

Required fields are marked *. Your email address will not be published.