Identification of out of control quality characteristics in a multivariate manufacturing environment

Multivariate statistical process control charts: an overview

“…The main idea of the method proposed by Doganaksoy et al 185 is the univariate t ranking procedure using the test statistic…”

A boosting approach for understanding out-of-control signals in multivariate control charts

“…This example was firstly used at the beginning of the nineties by Doganaksoy et al (1991). It works with four variables connected with ballistic missile testing.…”

“…The problem with this method is that the decomposition of the T 2 statistic into p independent T 2 components is not unique. Therefore, this situation has generated a number of different articles, the most outstanding of which were published by Mason et al (1996Mason et al ( , 1997, Doganaksoy et al (1991), Timm (1996) and Runger et al (1996).…”

Pattern Recognition of Process Mean Shift using Combined ANN Recognizer

“…[13,14] proposed the decomposition of T 2 statistic and showed that the interpretation of a signal from a T 2 statistic is greatly aided if the corresponding value is partitioned into independent parts. [5] It must be stated that limited research work was reported on the combined recognizer approach for pattern recognition as most of the existing ANN model for pattern recognition are mainly generalized-based where only a single classifier was applied in the diagnosis of abnormal pattern. However, it is recognized that in general, the use of combined classifiers instead of a single classifier leads to an increase in the overall recognition accuracy [17,21].Therefore further research on the combined recognizer towards pattern recognition is encouraged.…”