UNIVARIATE AND MULTIVARIATE STATISTICAL PROCESS CONTROL: GENERALIZED LIKELIHOOD RATIO CONTROL CHARTS - Couverture souple

Testik, Murat Caner

 
9783838311043: UNIVARIATE AND MULTIVARIATE STATISTICAL PROCESS CONTROL: GENERALIZED LIKELIHOOD RATIO CONTROL CHARTS

Synopsis

Univariate and multivariate quality control charts are important tools for process/product monitoring and improvement. This monograph offers the developments and analyses of univariate and multivariate control charts, which are based on a generalized likelihood ratio (GLR) approach. It is commonly assumed that a process fault may shift the mean of a monitored statistic persistently to an unknown but constant value. However, there are situations such that a mean change is not constant but time varying. Incorporating a priori knowledge of a fault signature, a univariate GLR control chart is investigated for monitoring fault signatures. The GLR methodology can also be used in developing multivariate process control charts. Here, the GLR methodology is used to unify the development of various multivariate extensions to the CUSUM control charts. In addition to the GLR control charts under a normal distribution model, another GLR control chart is also proposed for monitoring a non- homogenous Markovian queuing system.

Les informations fournies dans la section « Synopsis » peuvent faire référence à une autre édition de ce titre.

Présentation de l'éditeur

Univariate and multivariate quality control charts are important tools for process/product monitoring and improvement. This monograph offers the developments and analyses of univariate and multivariate control charts, which are based on a generalized likelihood ratio (GLR) approach. It is commonly assumed that a process fault may shift the mean of a monitored statistic persistently to an unknown but constant value. However, there are situations such that a mean change is not constant but time varying. Incorporating a priori knowledge of a fault signature, a univariate GLR control chart is investigated for monitoring fault signatures. The GLR methodology can also be used in developing multivariate process control charts. Here, the GLR methodology is used to unify the development of various multivariate extensions to the CUSUM control charts. In addition to the GLR control charts under a normal distribution model, another GLR control chart is also proposed for monitoring a non- homogenous Markovian queuing system.

Biographie de l'auteur

Murat Caner Testik is currently an Associate Professor and department chair in the Industrial Engineering Department at Hacettepe University. He is also the Vice President of European Network for Business and Industrial Statistics for 2009-2011.Dr Testik has a Ph.D. in Industrial Engineering from Arizona State University.

Les informations fournies dans la section « A propos du livre » peuvent faire référence à une autre édition de ce titre.