Abstract
ABSTRACTTwo types of control charts exist based on different quality characteristics: variable and attribute. These characteristics are commonly monitored using separate procedures. Only a few studies focused on the utilization of control charts to monitor a process with mixed characteristics. This study develops a new concept of the control chart based on a Principal Component Analysis (PCA) Mix, that is a PCA method that can jointly handle continuous and categorical data. The Kernel Density Estimation (KDE) method is used to estimate the control limit. Through simulation studies, the performance of the proposed chart is evaluated using the Average Run Length (ARL). control limits obtained from KDE produce a stable ARL0 at ~ 370 for For the shifted process, the proposed chart demonstrates excellent performance for an appropriate number of principal components used. Applications of the simulated process and real cases show that the proposed chart is sensitive to monitoring the shifted process.
Highlights
One of the most powerful tools in Statistical Process Control (SPC) is the control chart, which has been widely used in industries and services
Principal Component Analysis (PCA) mix Multivariate data analysis can be described as statistical methods to analyse data consisting of two or more quality characteristics
The proposed multivariate control chart is constructed by T2 statistics for the first k Principal Component Scores (PCs) of Ymix: The T2 statistic for PC Mix, which is denoted by T~2; is calculated as follows:
Summary
One of the most powerful tools in Statistical Process Control (SPC) is the control chart, which has been widely used in industries and services. Aslam, Khan, Aldosari, and Jun (2016) presented two mixed control charts using EWMA statistics and Hybrid Exponential Weighted Moving Average (HEWMA) statistics by assuming that the quality characteristic follows the normal distribution. The performance of these two charts was compared with that of the mixed chart. Khan, Aslam, Kim, and Jun (2017) proposed a mixed control chart for a life test by assuming that the quality characteristics follow the Weibull distribution Those studies are only for a univariate case which is decomposed into variables and attributes and simultaneously monitored using a single control chart.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have