West Virginia University
A new method for detection and classification of out-of-control signals in autocorrelated multivariate processes.
Abstract
dc:description.abstractAutocorrelation results in too many out-of-control false alarms when traditional T2 control charts are used in practice. In this research, a vector autoregressive (VAR) based T 2 control chart is built to improve the effectiveness of the traditional T2 control charts when variables are autocorrelated and cross-correlated. Datasets generated by a SAS program are used to test the performance of the proposed method. Computational results showed that the proposed method outperforms the ARIMA based residual T2 control chart with respect to identification accuracy and average run length. Also, the results showed that the proposed method with principal components analysis is capable of correctly interpreting out-of-control signals. Additionally, application of the proposed method is demonstrated by the use of a dataset taken from the literature and a spreadsheet based VBA program that was developed for this research.
Degree
thesis:*- Name thesis:degree_name
- MS
- Level thesis:degree_level
- Thesis
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Zhao, Tao
- Contributors dc:contributor
-
- Majid Jaraiedi
Identifiers
dc:identifier.*- Identifier
- https://researchrepository.wvu.edu/etd/11107