17–18 May 2021
Online
Europe/London timezone

High-purity processes GLR control charts for composite change-point scenarios

18 May 2021, 10:40
20m
Online

Online

Data Science in Process Industries Process modelling

Speaker

Caterina Rizzo (Dow Inc.)

Description

Generalized Likelihood Ratio (GLR)-based control charts for monitoring count processes have been proposed considering a variety of underlying dis- tributions and they are known to outperform the traditional control charts in effectively detecting a wide range of parameters’ shifts, while being relatively easy to design. In this study, generalized likelihood ratio tests for monitoring high-purity processes with composite null and alternative hypotheses for geo- metric and exponential distributions are designed and their performances are evaluated via simulations. Moreover, composite change-point scenarios relevant for testing more practical and realistic out-of-control scenarios in the chemical industry are considered, extending the traditional cases in which means shifts or linear trends are detected to more complex scenarios.

Primary author

Caterina Rizzo (Dow Inc.)

Presentation materials