A double generally weighted moving average control chart for monitoring the process variability

Area of Science:

• Industrial Engineering
• Statistical Quality Control
• Operations Research

Background:

• Traditional control charts struggle with detecting small process variability shifts.
• Memory-type control charts offer improved sensitivity but require further optimization.
• Accurate monitoring of process variability is crucial for maintaining product quality and operational efficiency.

Purpose of the Study:

• To propose a novel double generally weighted moving average (DGWMA) control chart for process variability monitoring.
• To evaluate the run-length performance of the proposed $$-DGWMA chart using Monte Carlo simulations.
• To compare the efficiency of the $$-DGWMA chart against existing memory-type control charts.

Main Methods:

• Development of a double generally weighted moving average (DGWMA) control chart utilizing a three-parameter logarithmic transformation.
• Application of Monte Carlo simulations to assess the run-length performance of the proposed $$-DGWMA chart.
• Comparative analysis of the $$-DGWMA chart against established memory-type control charts.

Main Results:

• The proposed $$-DGWMA chart demonstrates enhanced efficiency in detecting small shifts in process variability.
• The $$-DGWMA chart exhibits increased sensitivity in identifying upward shifts in process variability.
• A practical implementation example showcases the effectiveness of the new $$-DGWMA chart with real-world data.

Conclusions:

• The $$-DGWMA control chart offers a statistically superior method for monitoring process variability.
• This new chart provides a valuable tool for quality control professionals seeking to improve process monitoring capabilities.
• The findings suggest the $$-DGWMA chart is a promising advancement in statistical process control.