A Proposed Double Moving Average (DMA) Control Chart
Loading...
Date
2007-03
Authors
Wong, Voon Hee
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
Control chart techniques have been widely used in industries to monitor the
quality of manufacturing processes. Memory control charts are introduced as
alternatives to the Shewhart charts for quick detections of small sustaining
process shifts. Among the widely used memory control charts are the moving
average (MA) chart, exponentially weighted moving average (EWMA) chart and
cumulative sum (CUSUM) chart. The double exponentially weighted moving
average (DEWMA) technique has been investigated in recent years and is
found to be more efficient than the EWMA technique for detecting small shifts in
the process mean. This thesis extends the technique of performing exponential
smoothing twice on an EWMA chart, as in the case of the DEWMA chart to
computing the moving average twice on an MA chart for the process mean. The
new MA chart is known as the double moving average (DMA) chart. The
simulation study conducted shows that the proposed DMA chart improves upon
the average run length (ARL) performance of the MA chart. The DMA and
DEWMA are memory control charts that are based on two different weighted
average schemes. All of the simulation studies in this thesis are conducted
using the "Statistical Analysis System (SAS)" version 8.0 program. Two
examples are given to show how the proposed DMA chart is used in a real
situation.
Description
Keywords
Mathematical Sciences, , Control Chart